Compare commits

..

262 Commits

Author SHA1 Message Date
Asias He
f19fbc3058 gossip: Fix tokens assignment in assassinate_endpoint
The tokens vector is defined a few lines above and is needed outsie the
if block.

Do not redefine it again in the if block, otherwise the tokens will be empty.

Found by code inspection.

Fixes #3551.

Message-Id: <c7a06375c65c950e94236571127f533e5a60cbfd.1530002177.git.asias@scylladb.com>
(cherry picked from commit c3b5a2ecd5)
2018-06-27 12:01:19 +03:00
Vlad Zolotarov
8eddb28954 locator::ec2_multi_region_snitch: don't call for ec2_snitch::gossiper_starting()
ec2_snitch::gossiper_starting() calls for the base class (default) method
that sets _gossip_started to TRUE and thereby prevents to following
reconnectable_snitch_helper registration.

Fixes #3454

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
Message-Id: <1528208520-28046-1-git-send-email-vladz@scylladb.com>
(cherry picked from commit 2dde372ae6)
2018-06-12 19:02:48 +03:00
Avi Kivity
5aaa8031a2 Update seastar submodule
* seastar f5162dc...da2e1af (1):
  > net/tls: Wait for output to be sent when shutting down

Fixes #3459.
2018-05-24 12:02:15 +03:00
Avi Kivity
3d50e7077a Merge "Backport fixes for streaming segfault with bogus dst_cpu_id for 2.0" from Asias
"
The minimum changes that makes the backport of "streaming: Do send failed
message for uninitialized session" without backport conflits.

Fixes simliar issue we saw:

  https://github.com/scylladb/scylla/issues/3115
"

* tag 'asias/backport_issue_3115_for_2.0/v1' of github.com:scylladb/seastar-dev:
  streaming: Do send failed message for uninitialized session
  streaming: Introduce streaming::abort()
  streaming: Log peer address in on_error
  streaming: Check if _stream_result is valid
  streaming: Introduce received_failed_complete_message
2018-05-24 11:14:20 +03:00
Avi Kivity
4063e92f57 dist: redhat: get rid of raid0.devices_discard_performance
This parameter is not available on recent Red Hat kernels or on
non-Red Hat kernels (it was removed on 3.10.0-772.el7,
RHBZ 1455932). The presence of the parameter on kernels that don't
support it cause the module load to fail, with the result that the
storage is not available.

Fix by removing the parameter. For someone running an older Red Hat
kernel the effect will be that discard is disabled, but they can fix
that by updating the kernel. For someone running a newer kernel, the
effect will be that they can access their data.

Fixes #3437.
Message-Id: <20180516134913.6540-1-avi@scylladb.com>

(cherry picked from commit 3b8118d4e5)
2018-05-24 11:08:13 +03:00
Asias He
b6de30bb87 streaming: Do send failed message for uninitialized session
The uninitialized session has no peer associated with it yet. There is
no point sending the failed message when abort the session. Sending the
failed message in this case will send to a peer with uninitialized
dst_cpu_id which will casue the receiver to pass a bogus shard id to
smp::submit_to which cases segfault.

In addition, to be safe, initialize the dst_cpu_id to zero. So that
uninitialized session will send message to shard zero instead of random
bogus shard id.

Fixes the segfault issue found by
repair_additional_test.py:RepairAdditionalTest.repair_abort_test

Fixes #3115
Message-Id: <9f0f7b44c7d6d8f5c60d6293ab2435dadc3496a9.1515380325.git.asias@scylladb.com>

(cherry picked from commit 774307b3a7)
2018-05-24 15:24:29 +08:00
Asias He
c23e3a1eda streaming: Introduce streaming::abort()
It will be used soon by stream_plan::abort() to abort a stream session.

(cherry picked from commit fad34801bf)
2018-05-24 15:21:54 +08:00
Asias He
2732b6cf1d streaming: Log peer address in on_error
(cherry picked from commit 8a3f6acdd2)
2018-05-24 15:20:43 +08:00
Asias He
49722e74da streaming: Check if _stream_result is valid
If on_error() was called before init() was executed, the
_stream_result can be invalid.

(cherry picked from commit be573bcafb)
2018-05-24 15:20:02 +08:00
Asias He
ba7623ac55 streaming: Introduce received_failed_complete_message
It is the handler for the failed complete message. Add a flag to
remember if we received a such message from peer, if so, do not send
back the failed complete message back to the peer when running
close_session with failed status.

(cherry picked from commit eace5fc6e8)
2018-05-24 15:19:26 +08:00
Avi Kivity
9db2ff36f2 dist: redhat: fix binutils dependency on alternatives
Since /sbin is a symlink, file dependencies on /sbin/alternatives
don't work.

Change to /usr/bin to fix.
2018-04-26 12:00:42 +03:00
Avi Kivity
378029b8da schema_tables: discard [[nodiscard]] attribute
Note supported on gcc 5.3, which is used to build this branch.
2018-04-25 18:37:17 +03:00
Mika Eloranta' via ScyllaDB development
2b7644dc36 build: fix rpm build script --jobs N handling
Fixes argument misquoting at $SRPM_OPTS expansion for the mock commands
and makes the --jobs argument work as supposed.

Signed-off-by: Mika Eloranta <mel@aiven.io>
Message-Id: <20180113212904.85907-1-mel@aiven.io>
(cherry picked from commit 7266446227)
2018-04-25 17:47:09 +03:00
Duarte Nunes
4bd931ba59 db/schema_tables: Only drop UDTs after merging tables
Dropping a user type requires that all tables using that type also be
dropped. However, a type may appear to be dropped at the same time as
a table, for instance due to the order in which a node receives schema
notifications, or when dropping a keyspace.

When dropping a table, if we build a schema in a shard through a
global_schema_pointer, then we'll check for the existence of any user
type the schema employs. We thus need to ensure types are only dropped
after tables, similarly to how it's done for keyspaces.

Fixes #3068

Tests: unit-tests (release)

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20180129114137.85149-1-duarte@scylladb.com>
(cherry picked from commit 1e3fae5bef)
2018-04-25 01:15:45 +03:00
Avi Kivity
78eebe74c7 loading_cache: adjust code for older compilers
Need this-> qualifier in a generic lambda, and static_assert()s need
a message.
2018-04-23 16:12:25 +03:00
Avi Kivity
30e21afb13 streaming: adjust code for older compilers
Need this-> qualifier in a generic lambda.
2018-04-23 16:12:25 +03:00
Shlomi Livne
e8616b10e5 release: prepare for 2.0.4
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2018-04-23 09:11:35 +03:00
Avi Kivity
0cb842dde1 Update seastar submodule
* seastar e7facd4...f5162dc (1):
  > tls: Ensure we always pass through semaphores on shutdown

Fixes #3358.
2018-04-14 20:52:57 +03:00
Gleb Natapov
7945f5edda cql_server: fix a race between closing of a connection and notifier registration
There is a race between cql connection closure and notifier
registration. If a connection is closed before notification registration
is complete stale pointer to the connection will remain in notification
list since attempt to unregister the connection will happen to early.
The fix is to move notifier unregisteration after connection's gate
is closed which will ensure that there is no outstanding registration
request. But this means that now a connection with closed gate can be in
notifier list, so with_gate() may throw and abort a notifier loop. Fix
that by replacing with_gate() by call to is_closed();

Fixes: #3355
Tests: unit(release)

Message-Id: <20180412134744.GB22593@scylladb.com>
(cherry picked from commit 1a9aaece3e)
2018-04-12 16:57:30 +03:00
Asias He
9c2a328000 gossip: Relax generation max difference check
start node 1 2 3
shutdown node2
shutdown node1 and node3
start node1 and node3
nodetool removenode node2
clean up all scylla data on node2
bootstrap node2 as a new node

I saw node2 could not bootstrap stuck at waiting for schema information to compelte for ever:

On node1, node3

    [shard 0] gossip - received an invalid gossip generation for peer 127.0.0.2; local generation = 2, received generation = 1521779704

On node2

    [shard 0] storage_service - JOINING: waiting for schema information to complete

This is becasue in nodetool removenode operation, the generation of node1 was increased from 0 to 2.

   gossiper::advertise_removing () calls eps.get_heart_beat_state().force_newer_generation_unsafe();
   gossiper::advertise_token_removed() calls eps.get_heart_beat_state().force_newer_generation_unsafe();

Each force_newer_generation_unsafe increases the generation by 1.

Here is an example,

Before nodetool removenode:
```
curl -X GET --header "Accept: application/json" "http://127.0.0.1:10000/failure_detector/endpoints/" | python -mjson.tool
   {
   "addrs": "127.0.0.2",
   "generation": 0,
   "is_alive": false,
   "update_time": 1521778757334,
   "version": 0
   },
```

After nodetool revmoenode:
```
curl -X GET --header "Accept: application/json" "http://127.0.0.1:10000/failure_detector/endpoints/" | python -mjson.tool
 {
     "addrs": "127.0.0.2",
     "application_state": [
         {
             "application_state": 0,
             "value": "removed,146b52d5-dc94-4e35-b7d4-4f64be0d2672,1522038476246",
             "version": 214
         },
         {
             "application_state": 6,
             "value": "REMOVER,14ecc9b0-4b88-4ff3-9c96-38505fb4968a",
             "version": 153
            }
     ],
     "generation": 2,
     "is_alive": false,
     "update_time": 1521779276246,
     "version": 0
 },
```

In gossiper::apply_state_locally, we have this check:

```
if (local_generation != 0 && remote_generation > local_generation + MAX_GENERATION_DIFFERENCE) {
    // assume some peer has corrupted memory and is broadcasting an unbelievable generation about another peer (or itself)
  logger.warn("received an invalid gossip generation for peer {}; local generation = {}, received generation = {}",ep, local_generation, remote_generation);

}
```
to skip the gossip update.

To fix, we relax generation max difference check to allow the generation
of a removed node.

After this patch, the removed node bootstraps successfully.

Tests: dtest:update_cluster_layout_tests.py
Fixes #3331

Message-Id: <678fb60f6b370d3ca050c768f705a8f2fd4b1287.1522289822.git.asias@scylladb.com>
(cherry picked from commit f539e993d3)
2018-03-29 12:10:37 +03:00
Tomasz Grabiec
98498c679b test.py: set BOOST_TEST_CATCH_SYSTEM_ERRORS=no
This will make boost UTF abort execution on SIGABRT rather than trying
to continue running other test cases. This doesn't work well with
seastar integration, the suite will hang.
Message-Id: <1516205469-16378-1-git-send-email-tgrabiec@scylladb.com>

(cherry picked from commit ab6ec571cb)
2018-03-27 22:42:00 +03:00
Duarte Nunes
b147b5854b view_schema_test: Retry failed queries
Due to the asynchronous nature of view update propagation, results
might still be absent from views when we query them. To be able to
deterministically assert on view rows, this patch retries a query a
bounded number of times until it succeeds.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170718212646.2958-1-duarte@scylladb.com>
(cherry picked from commit ab72132cb1)
2018-03-27 22:42:00 +03:00
Duarte Nunes
226095f4db types: Implement hash() for collections
This patch provides a rather trivial implementation of hash() for
collection types.

It is needed for view building, where we hold mutations in a map
indexed by partition keys (and frozen collection types can be part of
the key).

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170718192107.13746-1-duarte@scylladb.com>
(cherry picked from commit 3bfcf47cc6)
2018-03-27 22:42:00 +03:00
Avi Kivity
3dd1f68590 tests: fix view_schema_test with clang
Clang is happy to create a vector<data_value> from a {}, a {1, 2}, but not a {1}.
No doubt it is correct, but sheesh.

Make the data_value explicit to humor it.
Message-Id: <20170713074315.9857-1-avi@scylladb.com>

(cherry picked from commit 162d9aa85d)
2018-03-27 22:25:17 +03:00
Avi Kivity
e08e4c75d7 Merge "Fix abort during counter table read-on-delete" from Tomasz
"
This fixes an abort in an sstable reader when querying a partition with no
clustering ranges (happens on counter table mutation with no live rows) which
also doesn't have any static columns. In such case, the
sstable_mutation_reader will setup the data_consume_context such that it only
covers the static row of the partition, knowing that there is no need to read
any clustered rows. See partition.cc::advance_to_upper_bound(). Later when
the reader is done with the range for the static row, it will try to skip to
the first clustering range (missing in this case). If clustering_ranges_walker
tells us to skip to after_all_clustering_rows(), we will hit an assert inside
continuous_data_consumer::fast_forward_to() due to attempt to skip past the
original data file range. If clustering_ranges_walker returns
before_all_clustering_rows() instead, all is fine because we're still at the
same data file position.

Fixes #3304.
"

* 'tgrabiec/fix-counter-read-no-static-columns' of github.com:scylladb/seastar-dev:
  tests: mutation_source_test: Test reads with no clustering ranges and no static columns
  tests: simple_schema: Allow creating schema with no static column
  clustering_ranges_walker: Stop after static row in case no clustering ranges

(cherry picked from commit 054854839a)
2018-03-22 18:16:37 +02:00
Vlad Zolotarov
8bcb4e7439 test.py: limit the tests to run on 2 shards with 4GB of memory
Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
(cherry picked from commit 57a6ed5aaa)
2018-03-22 12:47:12 +02:00
Avi Kivity
97369adb1c Merge "streaming backport for 2.0 branch" from Asias
"
Backport streaming improvements and bug fixes from 2.1 branch. With this
series, it is more robust to add node, decommission node, because the single
and big stream plan is split into multiple and smaller stream plans. In
addition, the failed stream plans will be retried automatically.
"

Fixes #3285, Fixes #3310, Fixes #3065, Fixes #1743, Fixes #3311.

* 'asias/ticket-352' of github.com:scylladb/seastar-dev:
  range_streamer: Stream 10% of ranges instead of 10 ranges per time
  Revert "streaming: Do not abort session too early in idle detection"
  dht: Fix log in range_streamer
  streaming: One cf per time on sender
  messaging_service: Get rid of timeout and retry logic for streaming verb
  storage_service: Remove rpc client on all shards in on_dead
  Merge "streaming error handling improvement" from Asias
  streaming: Fix streaming not streaming all ranges
  Merge "Use range_streamer everywhere" from Asias
2018-03-22 10:39:08 +02:00
Duarte Nunes
c89ead5e55 gms/gossiper: Synchronize endpoint state destruction
In gossiper::handle_major_state_change() we set the endpoint_state for
a particular endpoint and replicate the changes to other cores.

This is totally unsynchronized with the execution of
gossiper::evict_from_membership(), which can happen concurrently, and
can remove the very same endpoint from the map  (in all cores).

Replicating the changes to other cores in handle_major_state_change()
can interleave with replicating the changes to other cores in
evict_from_membership(), and result in an undefined final state.

Another issue happened in debug mode dtests, where a fiber executes
handle_major_state_change(), calls into the subscribers, of which
storage_service is one, and ultimately lands on
storage_service::update_peer_info(), which iterates over the
endpoint's application state with deferring points in between (to
update a system table). gossiper::evict_from_membership() was executed
concurrently by another fiber, which freed the state the first one is
iterating over.

Fixes #3299.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20180318123211.3366-1-duarte@scylladb.com>
(cherry picked from commit 810db425a5)
2018-03-18 14:55:50 +02:00
Asias He
46fd96d877 range_streamer: Stream 10% of ranges instead of 10 ranges per time
If there are a lot of ranges, e.g., num_tokens=2048, 10 ranges per
stream plan will cause tons of stream plan to be created to stream data,
each having very few data. This cause each stream plan has low transfer
bandwidth, so that the total time to complete the streaming increases.

It makes more sense to send a percentage of the total ranges per stream
plan than a fixed ranges.

Here is an example to stream a keyspace with 513 ranges in
total, 10 ranges v.s. 10% ranges:

Before:
[shard 0] range_streamer - Bootstrap with 127.0.0.1 for
keyspace=system_traces, 510 out of 513 ranges: ranges = 51
[shard 0] range_streamer - Bootstrap with ks for keyspace=127.0.0.1
succeeded, took 107 seconds

After:
[shard 0] range_streamer - Bootstrap with 127.0.0.1 for
keyspace=system_traces, 510 out of 513 ranges: ranges = 10
[shard 0] range_streamer - Bootstrap with ks for keyspace=127.0.0.1
succeeded, took 22 seconds

Message-Id: <a890b84fbac0f3c3cc4021e30dbf4cdf135b93ea.1520992228.git.asias@scylladb.com>
(cherry picked from commit 9b5585ebd5)
2018-03-15 10:11:08 +08:00
Asias He
19806fc056 Revert "streaming: Do not abort session too early in idle detection"
This reverts commit f792c78c96.

With the "Use range_streamer everywhere" (7217b7ab36) series,
all the user of streaming now do streaming with relative small ranges
and can retry streaming at higher level.

Reduce the time-to-recover from 5 hours to 10 minutes per stream session.

Even if the 10 minutes idle detection might cause higher false positive,
it is fine, since we can retry the "small" stream session anyway. In the
long term, we should replace the whole idle detection logic with
whenever the stream initiator goes away, the stream slave goes away.

Message-Id: <75f308baf25a520d42d884c7ef36f1aecb8a64b0.1520992219.git.asias@scylladb.com>
(cherry picked from commit ad7b132188)
2018-03-15 10:10:58 +08:00
Asias He
0b314a745f dht: Fix log in range_streamer
The address and keyspace should be swapped.

Before:
  range_streamer - Bootstrap with ks3 for keyspace=127.0.0.1 succeeded,
  took 56 seconds

After:
  range_streamer - Bootstrap with 127.0.0.1 for keyspace=ks3 succeeded,
  took 56 seconds

Message-Id: <5c49646f1fbe45e3a1e7545b8470e04b166922c4.1520416042.git.asias@scylladb.com>
(cherry picked from commit 73d8e2743f)
2018-03-13 15:07:13 +08:00
Asias He
73870751d9 streaming: One cf per time on sender
In the case there are large number of column families, the sender will
send all the column families in parallel. We allow 20% of shard memory
for streaming on the receiver, so each column family will have 1/N, N is
the number of in-flight column families, memory for memtable. Large N
causes a lot of small sstables to be generated.

It is possible there are multiple senders to a single receiver, e.g.,
when a new node joins the cluster, the maximum in-flight column families
is number of peer node. The column families are sent in the order of
cf_id. It is not guaranteed that all peers has the same speed so they
are sending the same cf_id at the same time, though. We still have
chance some of the peers are sending the same cf_id.

Fixes #3065

Message-Id: <46961463c2a5e4f1faff232294dc485ac4f1a04e.1513159678.git.asias@scylladb.com>
(cherry picked from commit a9dab60b6c)
2018-03-13 12:20:41 +08:00
Asias He
c8983034c0 messaging_service: Get rid of timeout and retry logic for streaming verb
With the "Use range_streamer everywhere" (7217b7ab36) seires, all
the user of streaming now do streaming with relative small ranges and
can retry streaming at higher level.

There are problems with timeout and retry at RPC verb level in streaming:
1) Timeout can be false negative.
2) We can not cancel the send operations which are already called. When
user aborts the streaming, the retry logic keeps running for a long
time.

This patch removes all the timeout and retry logic for streaming verbs.
After this, the timeout is the job of TCP, the retry is the job of the
upper layer.

Message-Id: <df20303c1fa728dcfdf06430417cf2bd7a843b00.1503994267.git.asias@scylladb.com>
(cherry picked from commit 8fa35d6ddf)
2018-03-13 12:20:41 +08:00
Asias He
77d14a6256 storage_service: Remove rpc client on all shards in on_dead
We should close connections to nodes that are down on all shards instead
of the shard which runs the on_dead gossip callback.

Found by Gleb.
Message-Id: <527a14105a07218066e9f1da943693d9de6993e5.1505894260.git.asias@scylladb.com>

(cherry picked from commit 173cba67ba)
2018-03-13 12:20:41 +08:00
Avi Kivity
21259bcfb3 Merge "streaming error handling improvement" from Asias
"This series improves the streaming error handling so that when one side of the
streaming failed, it will propagate the error to the other side and the peer
will close the failed session accordingly. This removes the unnecessary wait and
timeout time for the peer to discover the failed session and fail eventually.

Fix it by:

- Use the complete message to notify peer node local session is failed
- Listen on shutdown gossip callback so that we can detect the peer is shutdown
  can close the session with the peer

Fixes #1743"

* tag 'asias/streaming/error_handling_v2' of github.com:cloudius-systems/seastar-dev:
  streaming: Listen on shutdown gossip callback
  gms: Add is_shutdown helper for endpoint_state class
  streaming: Send complete message with failed flag when session is failed
  streaming: Handle failed flag in complete message
  streaming: Do not fail the session when failed to send complete message
  streaming: Introduce send_failed_complete_message
  streaming: Do not send complete message when session is successful
  streaming: Introduce the failed parameter for complete message
  streaming: Remove unused session_failed function
  streaming: Less verbose in logging
  streaming: Better stats

(cherry picked from commit d5aba779d4)
2018-03-13 12:20:41 +08:00
Tomasz Grabiec
9f02b44537 streaming: Fix streaming not streaming all ranges
It skipped one sub-range in each of the 10 range batch, and
tried to access the range vector using end() iterator.

Fixes sporadic failures of
update_cluster_layout_tests.py:TestUpdateClusterLayout.simple_add_node_1_test.

Message-Id: <1505848902-16734-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 741ec61269)
2018-03-13 10:36:19 +08:00
Avi Kivity
9dc7a63014 Merge "Use range_streamer everywhere" from Asias
"With this series, all the following cluster operations:

- bootstrap
- rebuild
- decommission
- removenode

will use the same code to do the streaming.

The range_streamer is now extended to support both fetch from and push
to peer node. Another big change is now the range_streamer will stream
less ranges at a time, so less data, per stream_plan and range_streamer
will remember which ranges are failed to stream and can retry later.

The retry policy is very simple at the moment it retries at most 5 times
and sleep 1 minutes, 1.5^2 minutes, 1.5^3 minutes ....

Later, we can introduce api for user to decide when to stop retrying and
the retry interval.

The benefits:

 - All the cluster operation shares the same code to stream
 - We can know the operation progress, e.g., we can know total number of
   ranges need to be streamed and number of ranges finished in
   bootstrap, decommission and etc.
 - All the cluster operation can survive peer node down during the
   operation which usually takes long time to complete, e.g., when adding
   a new node, currently if any of the existing node which streams data to
   the new node had issue sending data to the new node, the whole bootstrap
   process will fail. After this patch, we can fix the problematic node
   and restart it, the joining node will retry streaming from the node
   again.
 - We can fail streaming early and timeout early and retry less because
   all the operations use stream can survive failure of a single
   stream_plan. It is not that important for now to have to make a single
   stream_plan successful. Note, another user of streaming, repair, is now
   using small stream_plan as well and can rerun the repair for the
   failed ranges too.

This is one step closer to supporting the resumable add/remove node
opeartions."

* tag 'asias/use_range_streamer_everywhere_v4' of github.com:cloudius-systems/seastar-dev:
  storage_service: Use the new range_streamer interface for removenode
  storage_service: Use the new range_streamer interface for decommission
  storage_service: Use the new range_streamer interface for rebuild
  storage_service: Use the new range_streamer interface for bootstrap
  dht: Extend range_streamer interface

(cherry picked from commit 7217b7ab36)
2018-03-13 10:34:10 +08:00
Asias He
5dcef25f6f storage_service: Add missing return in pieces empty check
If pieces.empty is empty, it is bogus to access pieces[0]:

   sstring move_name = pieces[0];

Fix by adding the missing return.

Spotted by Vlad Zolotarov <vladz@scylladb.com>

Fixes #3258
Message-Id: <bcb446f34f953bc51c3704d06630b53fda82e8d2.1520297558.git.asias@scylladb.com>

(cherry picked from commit 8900e830a3)
2018-03-06 09:58:39 +02:00
Duarte Nunes
f763bf7f0d Merge 'backport of the "loading_shared_values and size limited and evicting prepared statements cache" series' from Vlad
This backport includes changes from the "loading_shared_values and size limited and evicting prepared statements cache" series,
"missing bits from loading_shared_values series" series and the "cql_transport::cql_server: fix the distributed prepared statements cache population"
patch (the last one is squashed inside the "cql3::query_processor: implement CQL and Thrift prepared statements caches using cql3::prepared_statements_cache"
patch in order to avoid the bisect breakage).

* 'branch-2-0-backport-prepared-cache-fixes-v1' of https://github.com/vladzcloudius/scylla:
  tests: loading_cache_test: initial commit
  utils + cql3: use a functor class instead of std::function
  cql3::query_processor: implement CQL and Thrift prepared statements caches using cql3::prepared_statements_cache
  transport::server::process_prepare() don't ignore errors on other shards
  cql3: prepared statements cache on top of loading_cache
  utils::loading_cache: make the size limitation more strict
  utils::loading_cache: added static_asserts for checking the callbacks signatures
  utils::loading_cache: add a bunch of standard synchronous methods
  utils::loading_cache: add the ability to create a cache that would not reload the values
  utils::loading_cache: add the ability to work with not-copy-constructable values
  utils::loading_cache: add EntrySize template parameter
  utils::loading_cache: rework on top of utils::loading_shared_values
  sstables::shared_index_list: use utils::loading_shared_values
  utils::loading_cache: arm the timer with a period equal to min(_expire, _update)
2018-02-22 10:04:41 +00:00
Tomasz Grabiec
9af9ca0d60 tests: mutation_source_tests: Fix use-after-scope on partition range
Message-Id: <1506096881-3076-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit d11d696072)
2018-02-19 14:30:47 +00:00
Avi Kivity
fbc30221b5 row_cache_test: remove unused overload populate_range()
Breaks the build.
2018-02-11 17:01:31 +02:00
Shlomi Livne
d17aa3cd1c release: prepare for 2.0.3
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2018-02-08 18:11:35 +02:00
Vlad Zolotarov
f7e79322f1 tests: loading_cache_test: initial commit
Test utils::loading_shared_values and utils::loading_cache.

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
2018-02-02 15:28:45 -05:00
Vlad Zolotarov
e31331bdb2 utils + cql3: use a functor class instead of std::function
Define value_extractor_fn as a functor class instead of std::function.

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
2018-02-02 15:28:45 -05:00
Vlad Zolotarov
6873e26060 cql3::query_processor: implement CQL and Thrift prepared statements caches using cql3::prepared_statements_cache
- Transition the prepared statements caches for both CQL and Trhift to the cql3::prepared_statements_cache class.
   - Add the corresponding metrics to the query_processor:
      - Evictions count.
      - Current entries count.
      - Current memory footprint.

Fixes #2474

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
2018-02-02 15:28:35 -05:00
Vlad Zolotarov
24bee2c887 transport::server::process_prepare() don't ignore errors on other shards
If storing of the statement fails on any shard we should fail the whole PREPARE
request.

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
Message-Id: <1502325392-31169-13-git-send-email-vladz@scylladb.com>
2018-02-02 13:27:34 -05:00
Vlad Zolotarov
8bba15a709 cql3: prepared statements cache on top of loading_cache
This is a template class that implements caching of prepared statements for a given ID type:
   - Each cache instance is given 1/256 of the total shard memory. If the new entry is going to overflow
     this memory limit - the less recently used entries are going to be evicted so that the new entry could
     be added.
   - The memory consumption of a single prepared statement is defined by a cql3::prepared_cache_entry_size
     functor class that returns a number of bytes for a given prepared statement (currently returns 10000
     bytes for any statement).
   - The cache entry is going to be evicted if not used for 60 minutes or more.

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
2018-02-02 12:37:00 -05:00
Vlad Zolotarov
ad68d3ecfd utils::loading_cache: make the size limitation more strict
Ensure that the size of the cache is never bigger than the "max_size".

Before this patch the size of the cache could have been indefinitely bigger than
the requested value during the refresh time period which is clearly an undesirable
behaviour.

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
2018-02-02 12:36:56 -05:00
Vlad Zolotarov
707ac9242e utils::loading_cache: added static_asserts for checking the callbacks signatures
Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
2018-02-02 12:36:53 -05:00
Vlad Zolotarov
dae0563ff8 utils::loading_cache: add a bunch of standard synchronous methods
Add a few standard synchronous methods to the cache, e.g. find(), remove_if(), etc.

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
2018-02-02 12:36:43 -05:00
Vlad Zolotarov
7ba50b87f1 utils::loading_cache: add the ability to create a cache that would not reload the values
Sometimes we don't want the cached values to be periodically reloaded.
This patch adds the ability to control this using a ReloadEnabled template parameter.

In case the reloading is not needed the "loading" function is not given to the constructor
but rather to the get_ptr(key, loader) method (currently it's the only method that is used, we may add
the corresponding get(key, loader) method in the future when needed).

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
2018-02-02 12:35:25 -05:00
Vlad Zolotarov
1da277c78e utils::loading_cache: add the ability to work with not-copy-constructable values
Current get(...) interface restricts the cache to work only with copy-constructable
values (it returns future<Tp>).
To make it able to work with non-copyable value we need to introduce an interface that would
return something like a reference to the cached value (like regular containers do).

We can't return future<Tp&> since the caller would have to ensure somehow that the underlying
value is still alive. The much more safe and easy-to-use way would be to return a shared_ptr-like
pointer to that value.

"Luckily" to us we value we actually store in a cache is already wrapped into the lw_shared_ptr
and we may simply return an object that impersonates itself as a smart_pointer<Tp> value while
it keeps a "reference" to an object stored in the cache.

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
2018-02-02 12:35:21 -05:00
Vlad Zolotarov
36dfd4b990 utils::loading_cache: add EntrySize template parameter
Allow a variable entry size parameter.
Provide an EntrySize functor that would return a size for a
specific entry.

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
2018-02-02 12:35:19 -05:00
Vlad Zolotarov
c5ce2765dc utils::loading_cache: rework on top of utils::loading_shared_values
Get rid of the "proprietary" solution for asynchronous values on-demand loading.
Use utils::loading_shared_values instead.

We would still need to maintain intrusive set and list for efficient shrink and invalidate
operations but their entry is not going to contain the actual key and value anymore
but rather a loading_shared_values::entry_ptr which is essentially a shared pointer to a key-value
pair value.

In general, we added another level of dereferencing in order to get the key value but since
we use the bi::store_hash<true> in the hook and the bi::compare_hash<true> in the bi::unordered_set
this should not translate into an additional set lookup latency.

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
2018-02-02 12:35:15 -05:00
Vlad Zolotarov
25ffdf527b sstables::shared_index_list: use utils::loading_shared_values
Since utils::loading_shared_values API is based on the original shared_index_list
this change is mostly a drop-in replacement of the corresponding parts.

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
2018-02-02 12:33:34 -05:00
Vlad Zolotarov
dbc6d9fe01 utils::loading_cache: arm the timer with a period equal to min(_expire, _update)
Arm the timer with a period that is not greater than either the permissions_validity_in_ms
or the permissions_update_interval_in_ms in order to ensure that we are not stuck with
the values older than permissions_validity_in_ms.

Fixes #2590

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
2018-02-02 12:17:41 -05:00
Asias He
915683bddd locator: Get rid of assert in token_metadata
In commit 69c81bcc87 (repair: Do not allow repair until node is in
NORMAL status), we saw a coredump due to an assert in
token_metadata::first_token_index.

Throw an exception instead of abort the whole scylla process.
Message-Id: <c110645cee1ee3897e30a3ae1b7ab3f49c97412c.1504752890.git.asias@scylladb.com>

(cherry picked from commit 0ec574610d)
2018-01-29 15:28:44 +02:00
Avi Kivity
7ca8988d0e Update seastar submodule
* seastar d37cf28...e7facd4 (11):
  > tls_test: Fix echo test not setting server trust store
  > tls: Actually verify client certificate if requested
  > tls: Do not restrict re-handshake to client
  > Work around GCC 5 bug: scylladb/seastar#338, scylladb/seastar#339
  > tls: Make put/push mechanism operate "opportunisticly"
  > tls: Move handshake logic outside connect/accept
  > tls: Make sure handshake exceptions are futurized
  > tls: Guard non-established sockets in sesrefs + more explicit close + states
  > tls: Make vec_push fully exception safe
  > net/tls: explicitly ignore ready future during shutdown
  > tls: remove unneeded lambda captures

Fixes #3072
2018-01-28 14:46:06 +02:00
Paweł Dziepak
383d7e6c91 Update scylla-ami submodule
* scylla-ami be90a3f...fa2461d (1):
  > Update Amazon kernel packages release stream to 2017.09
2018-01-24 13:31:04 +00:00
Avi Kivity
7bef696ee5 Update seastar submodule
* seastar 66eb33f...d37cf28 (1):
  > Update dpdk submodule

Fixes build with glibc 2.25 (see scylladb/dpdk#3).
2018-01-18 13:52:39 +02:00
Avi Kivity
a603111a85 Merge "Fix memory leak on zone reclaim" from Tomek
"_free_segments_in_zones is not adjusted by
segment_pool::reclaim_segments() for empty zones on reclaim under some
conditions. For instance when some zone becomes empty due to regular
free() and then reclaiming is called from the std allocator, and it is
satisfied from a zone after the one which is empty. This would result
in free memory in such zone to appear as being leaked due to corrupted
free segment count, which may cause a later reclaim to fail. This
could result in bad_allocs.

The fix is to always collect such zones.

Fixes #3129
Refs #3119
Refs #3120"

* 'tgrabiec/fix-free_segments_in_zones-leak' of github.com:scylladb/seastar-dev:
  tests: lsa: Test _free_segments_in_zones is kept correct on reclaim
  lsa: Expose max_zone_segments for tests
  lsa: Expose tracker::non_lsa_used_space()
  lsa: Fix memory leak on zone reclaim

(cherry picked from commit 4ad212dc01)
2018-01-16 15:54:54 +02:00
Asias He
d5884d3c7c storage_service: Do not wait for restore_replica_count in handle_state_removing
The call chain is:

storage_service::on_change() -> storage_service::handle_state_removing()
-> storage_service::restore_replica_count() -> streamer->stream_async()

Listeners run as part of gossip message processing, which is serialized.
This means we won't be processing any gossip messages until streaming
completes.

In fact, there is no need to wait for restore_replica_count to complete
which can take a long time, since when it completes, this node will send
notification to tell the removal_coordinator that the restore process is
finished on this node. This node will be removed from _replicating_nodes
on the removal_coordinator.

Tested with update_cluster_layout_tests.py

Fixes #2886

Message-Id: <8b4fe637dfea6c56167ddde3ca86fefb8438ce96.1516088237.git.asias@scylladb.com>
(cherry picked from commit 5107b6ad16)
2018-01-16 11:38:08 +02:00
Tomasz Grabiec
e6cb685178 range_tombstone_list: Fix insert_from()
end_bound was not updated in one of the cases in which end and
end_kind was changed, as a result later merging decision using
end_bound were incorrect. end_bound was using the new key, but the old
end_kind.

Fixes #3083.
Message-Id: <1513772083-5257-1-git-send-email-tgrabiec@scylladb.com>

(cherry picked from commit dfe48bbbc7)
2017-12-21 09:29:59 +01:00
Vlad Zolotarov
cd19e5885a messaging_service: fix a mutli-NIC support
Don't enforce the outgoing connections from the 'listen_address'
interface only.

If 'local_address' is given to connect() it will enforce it to use a
particular interface to connect from, even if the destination address
should be accessed from a different interface. If we don't specify the
'local_address' the source interface will be chosen according to the
routing configuration.

Fixes #3066

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
Message-Id: <1513372688-21595-1-git-send-email-vladz@scylladb.com>
(cherry picked from commit be6f8be9cb)
2017-12-17 10:52:19 +02:00
Takuya ASADA
f367031016 dist/common/systemd: specify correct repo file path for housekeeping service on Ubuntu/Debian
Currently scylla-housekeeping-daily.service/-restart.service hardcoded
"--repo-files '/etc/yum.repos.d/scylla*.repo'" to specify CentOS .repo file,
but we use same .service for Ubuntu/Debian.
It doesn't work correctly, we need to specify .list file for Debian variants.

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1513385159-15736-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit c2e87f4677)
2017-12-16 22:05:19 +02:00
Glauber Costa
7ae67331ad database: delete created SSTables if streaming writes fail
We have had an issue recently where failed SSTable writes left the
generated SSTables dangling in a potentially invalid state. If the write
had, for instance, started and generated tmp TOCs but not finished,
those files would be left for dead.

We had fixed this in commit b7e1575ad4,
but streaming memtables still have the same isse.

Note that we can't fix this in the common function
write_memtable_to_sstable because different flushers have different
retry policies.

Fixes #3062

Signed-off-by: Glauber Costa <glauber@scylladb.com>
Message-Id: <20171213011741.8156-1-glauber@scylladb.com>
(cherry picked from commit 1aabbc75ab)
2017-12-13 10:12:35 +02:00
Jesse Haber-Kucharsky
0e6561169b cql3: Add missing return
Since `return` is missing, the "else" branch is also taken and this
results a user being created from scratch.

Fixes #3058.

Signed-off-by: Jesse Haber-Kucharsky <jhaberku@scylladb.com>
Message-Id: <bf3ca5907b046586d9bfe00f3b61b3ac695ba9c5.1512951084.git.jhaberku@scylladb.com>
(cherry picked from commit 7e3a344460)
2017-12-11 09:55:46 +02:00
Paweł Dziepak
5b3aa8e90d Merge "Fix range tombstone emitting which led to skipping over data" from Tomasz
"Fixes cache reader to not skip over data in some cases involving overlapping
range tombstones in different partition versions and discontinuous cache.

Introduced in 2.0

Fixes #3053."

* tag 'tgrabiec/fix-range-tombstone-slicing-v2' of github.com:scylladb/seastar-dev:
  tests: row_cache: Add reproducer for issue #3053
  tests: mvcc: Add test for partition_snapshot::range_tombstones()
  mvcc: Optimize partition_snapshot::range_tombstones() for single version case
  mvcc: Fix partition_snapshot::range_tombstones()
  tests: random_mutation_generator: Do not emit dummy entries at clustering row positions

(cherry picked from commit 051cbbc9af)
(cherry picked from commit be5127388d)

[tgrabiec: dropped mvcc_test change, because the file does not exist here]
2017-12-08 14:38:24 +01:00
Tomasz Grabiec
db9d502f82 tests: simple_schema: Add new_tombstone() helper
(cherry picked from commit 204ec9c673)
2017-12-08 14:18:42 +01:00
Amos Kong
cde39bffd0 dist/debian: add scylla-tools-core to depends list
Signed-off-by: Amos Kong <amos@scylladb.com>
Message-Id: <db39cbda0e08e501633556ab238d816e357ad327.1512646123.git.amos@scylladb.com>
(cherry picked from commit 8fd5d27508)
2017-12-07 13:42:24 +02:00
Amos Kong
0fbcc852a5 dist/redhat: add scylla-tools-core to requires list
Fixes #3051

Signed-off-by: Amos Kong <amos@scylladb.com>
Message-Id: <f7013a4fbc241bb4429d855671fee4b845b255cd.1512646123.git.amos@scylladb.com>
(cherry picked from commit eb3b138ee2)
2017-12-07 13:42:17 +02:00
Duarte Nunes
16d5f68886 thrift/server: Handle exception within gate
The exception handling code inspects server state, which could be
destroyed before the handle_exception() task runs since it runs after
exiting the gate. Move the exception handling inside the gate and
avoid scheduling another accept if the server has been stopped.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20171116122921.21273-1-duarte@scylladb.com>
(cherry picked from commit 34a0b85982)
2017-12-07 13:07:11 +02:00
Pekka Enberg
91540c8181 Update seastar submodule
* seastar 0dbedf0...66eb33f (1):
  > core/gate: Add is_closed() function
2017-12-07 13:06:39 +02:00
Raphael S. Carvalho
eaa8ed929f thrift: fix compilation error
thrift/server.cc:237:6:   required from here
thrift/server.cc:236:9: error: cannot call member function ‘void thrift_server::maybe_retry_accept(int, bool, std::__exception_ptr::exception_ptr)’ without object
         maybe_retry_accept(which, keepalive, std::move(ex));

gcc version: gcc (GCC) 6.3.1 20161221 (Red Hat 6.3.1-1)

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20171113184537.10472-1-raphaelsc@scylladb.com>
(cherry picked from commit 564046a135)
2017-12-07 12:55:34 +02:00
Avi Kivity
5ba1621716 Merge "thrift/server: Ensure stop() waits for accepts" from Duarte
"Ensure stop() waits for the accept loop to complete to avoid crashes
during shutdown."

* 'thrift-server-stop/v4' of https://github.com/duarten/scylla:
  thrift/server: Restore code format
  thrift/server: Stopping the server waits for connection shutdown
  thrift/server: Abort listeners on stop()
  thrift/server: Avoid manual memory management
  thrift/server: Add move ctor for connection
  thrift/server: Extract retry logic
  thrift/server: Retry with backoff for some error types
  thrift/server: Retry accept in case of error

(cherry picked from commit 061f6830fa)
2017-12-07 12:54:45 +02:00
Avi Kivity
b4f515035a build: disable -fsanitize-address-use-after-scope on CqlParser.o
The parser generator somehow confuses the use-after-scope sanitizer, causing it
to use large amounts of stack space. Disable that sanitizer on that file.
Message-Id: <20170905110628.18047-1-avi@scylladb.com>

(cherry picked from commit 4751402709)
2017-12-04 12:41:05 +02:00
Avi Kivity
d55e3f6a7f build: fix excessive stack usage in CqlParser in debug mode
The state machines generated by antlr allocate many local variables per function.
In release mode, the stack space occupied by the variables is reused, but in debug
build, it is not, due to Address Sanitizer setting -fstack-reuse=none. This causes
a single function to take above 100k of stack space.

Fix by hacking the generated code to use just one variable.

Fixes #2546
Message-Id: <20170704135824.13225-1-avi@scylladb.com>

(cherry picked from commit a6d9cf09a7)
2017-12-04 12:39:27 +02:00
Shlomi Livne
07b039feab release: prepare for 2.0.2
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2017-11-30 21:02:42 +02:00
Avi Kivity
35b7353efd Update seastar submodule
* seastar 0489655...0dbedf0 (1):
  > fstream: do not ignore dma_write return value
2017-11-30 17:36:36 +02:00
Duarte Nunes
200e01cc31 compound_compact: Change universal reference to const reference
The universal reference was introduced so we could bind an rvalue to
the argument, but it would have sufficed to make the argument a const
reference. This is also more consistent with the function's other
overload.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20171129132758.19654-1-duarte@scylladb.com>
(cherry picked from commit cda3ddd146)
(cherry picked from commit 106c69ad45)
2017-11-30 16:51:16 +02:00
Tomasz Grabiec
b5c4cf2d87 Merge "compact_storage serialization fixes" from Duarte
Fix two issues with serializing non-compound range tombstones as
compound: convert a non-compound clustering element to compound and
actually advertise the issue to other nodes.

* git@github.com:duarten/scylla.git  rt-compact-fixes/v1:
  compound_compact: Allow rvalues in size()
  sstables/sstables: Convert non-compound clustering element to compound
  tests/sstable_mutation_test: Verify we can write/read non-correct RTs
  service/storage_service: Export non-compound RT feature

(cherry picked from commit e9cce59b85)
(cherry picked from commit 740fcc73b8)

Undid changes to size_estimates_virtual_reader
Changed test from memtable::make_flat_reader to memtable::make_reader
2017-11-30 16:50:15 +02:00
Duarte Nunes
f96cb361aa tests: Initialize storage service for some tests
These tests now require having the storage service initialize, which
is needed to decide whether correct non-compound range tombstones
should be emitted or not.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20171126152921.5199-1-duarte@scylladb.com>
(cherry picked from commit 922f095f22)
(cherry picked from commit 8567723a7b)
2017-11-30 16:27:43 +02:00
Duarte Nunes
bd59d7c968 cql3/delete_statement: Allow non-range deletions on non-compound schemas
This patch fixes a regression introduced in
1c872e2ddc.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20171126102333.3736-1-duarte@scylladb.com>
(cherry picked from commit 15fbb8e1ca)
(cherry picked from commit b0b7c73acd)
2017-11-30 16:22:53 +02:00
Tomasz Grabiec
9d923a61e1 Merge "Fixes to sstable files for non-compound schemas" from Duarte
This series mainly fixes issues with the serialization of promoted
index entries for non-compound schemas and with the serialization of
range tombstones, also for non-compound schemas.

We lift the correct cell name writing code into its own function,
and direct all users to it. We also ensure backward compatibility with
incorrectly generated promoted indexes and range tombstones.

Fixes #2995
Fixes #2986
Fixes #2979
Fixes #2992
Fixes #2993

* git@github.com:duarten/scylla.git  promoted-index-serialization/v3:
  sstables/sstables: Unify column name writers
  sstables/sstables: Don't write index entry for a missing row maker
  sstables/sstables: Reuse write_range_tombstone() for row tombstones
  sstables/sstables: Lift index writing for row tombstones
  sstables/sstables: Leverage index code upon range tombstone consume
  sstables/sstables: Move out tombstone check in write_range_tombstone()
  sstables/sstables: A schema with static columns is always compound
  sstables/sstables: Lift column name writing logic
  sstables/sstables: Use schema-aware write_column_name() for
    collections
  sstables/sstables: Use schema-aware write_column_name() for row marker
  sstables/sstables: Use schema-aware write_column_name() for static row
  sstables/sstables: Writing promoted index entry leverages
    column_name_writer
  sstables/sstables: Add supported feature list to sstables
  sstables/sstables: Don't use incorrectly serialized promoted index
  cql3/single_column_primary_key_restrictions: Implement is_inclusive()
  cql3/delete_statement: Constrain range deletions for non-compound
    schemas
  tests/cql_query_test: Verify range deletion constraints
  sstables/sstables: Correctly deserialize range tombstones
  service/storage_service: Add feature for correct non-compound RTs
  tests/sstable_*: Start the storage service for some cases
  sstables/sstable_writer: Prepare to control range tombstone
    serialization
  sstables/sstables: Correctly serialize range tombstones
  tests/sstable_assertions: Fix monotonicity check for promoted indexes
  tests/sstable_assertions: Assert a promoted index is empty
  tests/sstable_mutation_test: Verify promoted index serializes
    correctly
  tests/sstable_mutation_test: Verify promoted index repeats tombstones
  tests/sstable_mutation_test: Ensure range tombstone serializes
    correctly
  tests/sstable_datafile_test: Add test for incorrect promoted index
  tests/sstable_datafile_test: Verify reading of incorrect range
    tombstones
  sstables/sstable: Rename schema-oblivious write_column_name() function
  sstables/sstables: No promoted index without clustering keys
  tests/sstable_mutation_test: Verify promoted index is not generated
  sstables/sstables: Optimize column name writing and indexing
  compound_compat: Don't assume compoundness

(cherry picked from commit bd1efbc25c)

Also added sstables::make_sstable() to preserve source compatibility in tests.
2017-11-30 16:21:13 +02:00
Tomasz Grabiec
0b23bcbe29 sstables: index_reader: Reset lower bound for promoted index lookups from advance_to_next_partition()
_current_pi_idx was not reset from advance_to_next_partition(), which
is used when we skip to the next partition before fully consuming
it. As a result, if we try to skip to a clustering position which is
before the index block used by the last skip in the previous
partition, we would not skip assuming that the new position is in the
current block. This may result in more data being read from the
sstable than necessary.

Fixes #2984
Message-Id: <1510915793-20159-1-git-send-email-tgrabiec@scylladb.com>

(cherry picked from commit 2113299b61)
2017-11-21 14:25:49 +01:00
Duarte Nunes
b1899f000a db/view: Use view schema for view pk operations
Instead of base schema.

Fixes #2504

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170718190703.12972-1-duarte@scylladb.com>
(cherry picked from commit 115ff1095e)
2017-11-15 20:41:24 +00:00
Tomasz Grabiec
7b19167cbd gossiper: Replicate endpoint_state::is_alive()
Broken in f570e41d18.

Not replicating this may cause coordinator to treat a node which is
down as alive, or vice verse.

Fixes regression in dtest:

  consistency_test.py:TestAvailability.test_simple_strategy

which was expected to get "unavailable" exception but it was getting a
timeout.

Message-Id: <1510666967-1288-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 7323fe76db)
2017-11-14 16:21:33 +02:00
Shlomi Livne
164f97fd88 release: prepare for 2.0.1
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2017-11-10 16:37:29 +02:00
Paweł Dziepak
b3bc82bc77 Merge "Fix exception safety related to range tombstones in cache" from Tomasz
Fixes #2938.

* 'tgrabiec/fix-range-tombstone-list-exception-safety-v1' of github.com:scylladb/seastar-dev:
  tests: range_tombstone_list: Add test for exception safety of apply()
  tests: Introduce range_tombstone_list assertions
  cache: Make range tombstone merging exception-safe
  range_tombstone_list: Introduce apply_monotonically()
  range_tombstone_list: Make reverter::erase() exception-safe
  range_tombstone_list: Fix memory leaks in case of bad_alloc
  mutation_partition: Fix abort in case range tombstone copying fails
  managed_bytes: Declare copy constructor as allocation point
  Integrate with allocation failure injection framework

(cherry picked from commit 5a4b46f555)
2017-11-10 13:10:26 +01:00
Tomasz Grabiec
8f6ffb0487 Update seastar submodule
* seastar 124467d...0489655 (9):
  > alloc_failure_injector: Fix compilation error with gcc 7.1
  > alloc_failure_injector: Replace set_alloc_failure_callback() with run_with_callback()
  > alloc_failure_injector: Log backtrace of failures
  > alloc_failure_injector: Extract fail()
  > util: Introduce support for allocation failure injection
  > noncopyable_function: improve support for capturing mutable lambdas
  > noncopyable_function add bool operator
  > test.py: fix typo in noncopyable_function_test
  > utils: introduce noncopyable_function
2017-11-10 13:10:26 +01:00
Raphael S. Carvalho
4bba0c403e compaction: Make resharding go through compaction manager
Two reasons for this change:
1) every compaction should be multiplexed to manager which in turn
will make decision when to schedule. improvements on it will
immediately benefit every existing compaction type.
2) active tasks metric will now track ongoing reshard jobs.

Fixes #2671.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20170817224334.6402-1-raphaelsc@scylladb.com>
(cherry picked from commit 10eaa2339e)
Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20171103012758.19428-1-raphaelsc@scylladb.com>
2017-11-07 15:23:45 +02:00
Calle Wilund
59aae504ae storage_service: Only replicate token metadata iff modified in on_change
Fixes #2869

Message-Id: <20171101105629.22104-1-calle@scylladb.com>
(cherry picked from commit 8c257c40b4)
2017-11-07 14:46:36 +02:00
Avi Kivity
941e5eef4f Merge "gossip backport for 2.0" from Asias
"This series backports both the cleanup series from Duarte and large cluster
fixes series from Tomek."

* tag 'gossip-2.0-backport-v2' of github.com:scylladb/seastar-dev:
  Merge 'Solves problems related to gossip which can be observed in a large cluster' from Tomasz
  utils: introduce loading_shared_values
  tests/serialized_action: add missing forced defers
  utils: Introduce serialized_action
  Merge "gms/gossiper: Multiple cleanups" from Duarte
  storage_service: Do not use c_str() in the logger
  gms/gossiper: Introduce copy-less endpoint_state::get_application_state_ptr()
  Merge "gossiper: Optimize endpoint_state lookup" from Duarte
  gms: Add is_shutdown helper for endpoint_state class
  gossip: Better check for gossip stabilization on startup
  Merge "Fix miss opportunity to update gossiper features" from Asias
  gossip: Fix a log message typo in compare_endpoint_startup
  gossip: Do not use c_str() in the logger
  Revert "gossip: Make bootstrap more robust"
  gossip: Switch to seastar::lowres_system_clock
  gossip: Use unordered_map for _unreachable_endpoints and _shadow_unreachable_endpoints
  gossip: Introduce the shadow_round_ms option
2017-11-07 13:44:20 +02:00
Duarte Nunes
b12a2e6b08 Merge 'Solves problems related to gossip which can be observed in a large cluster' from Tomasz
"The main problem fixed is slow processing of application state changes.
This may lead to a bootstrapping node not having up to date view on the
ring, and serve incorrect data.

Fixes #2855."

* tag 'tgrabiec/gossip-performance-v3' of github.com:scylladb/seastar-dev:
  gms/gossiper: Remove periodic replication of endpoint state map
  gossiper: Check for features in the change listener
  gms/gossiper: Replicate changes incrementally to other shards
  gms/gossiper: Document validity of endpoint_state properties
  storage_service: Update token_metadata after changing endpoint_state
  gms/gossiper: Process endpoints in parallel
  gms/gossiper: Serialize state changes and notifications for given node
  utils/loading_shared_values: Allow Loader to return non-future result
  gms/gossiper: Encapsulate lookup of endpoint_state
  storage_service: Batch token metadata and endpoint state replication
  utils/serialized_action: Introduce trigger_later()
  gossiper: Add and improve logging
  gms/gossiper: Don't fire change listeners when there is no change
  gms/gossiper: Allow parallel apply_state_locally()
  gms/gossiper: Avoid copies in endpoint_state::add_application_state()
  gms/failure_detector: Ignore short update intervals

(cherry picked from commit 044b8deae4)
2017-11-07 19:21:30 +08:00
Vlad Zolotarov
eb34937ff6 utils: introduce loading_shared_values
This class implements an key-value container that is populated
using the provided asynchronous callback.

The value is loaded when there are active references to the value for the given key.

Container ensures that only one entry is loaded per key at any given time.

The returned value is a lw_shared_ptr to the actual value.

The value for a specific key is immediately evicted when there are no
more references to it.

The container is based on the boost::intrusive::unordered_set and is rehashed (grown) if needed
every time a new value is added (asynchronously loaded).

The container has a rehash() method that would grow or shrink the container as needed
in order to get the load factor into the [0.25, 0.75] range.

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
(cherry picked from commit ec3fed5c4d)
2017-11-07 19:21:29 +08:00
Paweł Dziepak
127ffff9e5 tests/serialized_action: add missing forced defers
serialized_action_tests depends on the fact that first part of the
serialized_action is executed at cetrtain points (in which it reads a
global variable that is later updated by the main thread).
This worked well in the release mode before ready continuations were
inlined and run immediately, but not in the debug mode since inlining
was not happening and the main seastar::thread was missing some yield
points.
Message-Id: <20170731103013.26542-1-pdziepak@scylladb.com>

(cherry picked from commit e970630272)
2017-11-07 19:21:29 +08:00
Tomasz Grabiec
f06bb656a4 utils: Introduce serialized_action
(cherry picked from commit 6a3703944b)

Conflicts:
	configure.py
2017-11-07 19:21:29 +08:00
Pekka Enberg
cc84cd60c5 Merge "gms/gossiper: Multiple cleanups" from Duarte
"Based on the functions get_endpoint_state_for_endpoint_ptr(),
get_application_state_ptr() and
endpoint_state::get_application_state_ptr(), this series
cleanups miscelaneous functions related to the gossiper.

It not only removes duplicated code, but also omits many copies.

All pointer usages have been audited for safety."

Acked-by: Asias He <asias@scylladb.com>
Acked-by: Tomasz Grabiec <tgrabiec@scylladb.com>

* 'gossiper-cleanup/v2' of github.com:duarten/scylla: (27 commits)
  gms/endpoint_state: Remove get_application_state()
  service/storage_service: Avoid copies in prepare_replacement_info()
  service/storage_service: Cleanup get_application_state_value()
  service/storage_service: Cleanup handle_state_removing()
  service/storage_service: Cleanup get_rpc_address()
  locator/reconnectable_snitch_helper: Avoid versioned_value copies
  locator/production_snitch_base: Cleanup get_endpoint_info()
  service/migration_manager: Avoid copies in is_ready_for_bootstrap()
  service/migration_manager: Cleanup has_compatible_schema_tables_version()
  service/migration_manager: Fix usages of get_application_state()
  cache_hit_rate: Avoid copies in get_hit_rate()
  gms/endpoint_state: Avoid copies in is_shutdown()
  service/load_broadcaster: Avoid copy in on_join()
  gms/gossiper: Cleanup get_supported_features()
  gms/gossiper: Cleanup get_gossip_status()
  gms/gossiper: Cleanup seen_any_seed()
  gms/gossiper: Cleanup get_host_id()
  gms/gossiper: Removed dead uses_vnodes() function
  gms/gossiper: Cleanup uses_host_id()
  gms/gossiper: Add get_application_state_ptr()
  ...

(cherry picked from commit 1701fc2e50)
2017-11-07 19:21:29 +08:00
Asias He
bb6ee1e4b1 storage_service: Do not use c_str() in the logger
Use logger.info("{}", msg) instead.

Message-Id: <d2f15007a54554b58e29fd05331c06ae030d582f.1504832296.git.asias@scylladb.com>
(cherry picked from commit bb9dbc5ade)
2017-11-07 19:21:28 +08:00
Tomasz Grabiec
ce72299a38 gms/gossiper: Introduce copy-less endpoint_state::get_application_state_ptr()
Message-Id: <1507642411-28680-3-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 66a15ccd18)
2017-11-07 19:21:28 +08:00
Avi Kivity
ef39bc4216 Merge "gossiper: Optimize endpoint_state lookup" from Duarte
"gossiper::get_endpoint_state_for_endpoint() returns a copy of
endpoint_state, which we've seen can be very expensive. This
series introduces a function that returns a pointer and avoids
the copy.

Fixes #764"

* 'endpoint-state/v2' of https://github.com/duarten/scylla:
  gossiper: Avoid endpoint_state copies
  endpoint_state: const-qualify functions
  storage_service: Remove duplicate endpoint state check

(cherry picked from commit 4ad3900d8d)
2017-11-07 19:21:28 +08:00
Asias He
fb03f9a73c gms: Add is_shutdown helper for endpoint_state class
It will be used by streaming manager to check if a node is in shutdown
status.

(cherry picked from commit ed7e6974d5)
2017-11-07 19:21:27 +08:00
Asias He
025af9d297 gossip: Better check for gossip stabilization on startup
This is a backport of Apache CASSANDRA-9401
(2b1e6aba405002ce86d5badf4223de9751bf867d)

It is better to check the number of nodes in the endpoint_state_map
is not changing for gossip stabilization.

Fixes #2853
Message-Id: <e9f901ac9cadf5935c9c473433dd93e9d02cb748.1506666004.git.asias@scylladb.com>

(cherry picked from commit c0b965ee56)
2017-11-07 19:21:27 +08:00
Tomasz Grabiec
09da4f3d08 Merge "Fix miss opportunity to update gossiper features" from Asias
The gossiper checks if features should be enabled from its timer
callback when it detects that endpoint_state_map changed, that is
different than shadow_endpoint_state_map.

shadow_endpoint_state_map is also assigned from endpoint_state_map in
storage_service::replicate_tm_and_ep_map(), called from
storage_service::on_change()

Call gossiper:maybe_enable_features() in replicate_tm_and_ep_map so
that we won't miss gossip feature update.

Fixes #2824

* git@github.com:scylladb/seastar-dev asias/gossip_miss_feature_update_v1:
  gossip: Move the _features_condvar signal code to
    maybe_enable_features
  gossip: Make maybe_enable_features public
  storage_service: Check gossip feature update in
    replicate_tm_and_ep_map

(cherry picked from commit 02d41864af)
2017-11-07 19:21:27 +08:00
Asias He
0d22b0c949 gossip: Fix a log message typo in compare_endpoint_startup
Message-Id: <c4958950e1108082b63e08ab81ee2177edc9b232.1505286843.git.asias@scylladb.com>
(cherry picked from commit fa9d47c7f3)
2017-11-07 19:21:27 +08:00
Asias He
5c5296a683 gossip: Do not use c_str() in the logger
Use logger.info("{}", msg) instead.

Message-Id: <52c24d7dfe082ee926f065a6268d83fcb31ddc28.1504832289.git.asias@scylladb.com>
(cherry picked from commit 57dd3cb2c5)
2017-11-07 19:21:27 +08:00
Asias He
5ecb07bbc4 Revert "gossip: Make bootstrap more robust"
This reverts commit b56ba02335.

After commit 8fa35d6ddf (messaging_service: Get rid of timeout and retry
logic for streaming verb), streaming verb in rpc does not check if a
node is in gossip memebership since all the retry logic is removed.

Remove the extra wait before removing the joining node from gossip
membership.

Message-Id: <a416a735bb8aad533bbee190e3324e6b16799415.1504063598.git.asias@scylladb.com>
(cherry picked from commit cc18da5640)
2017-11-07 19:21:26 +08:00
Asias He
a90023a119 gossip: Switch to seastar::lowres_system_clock
The newly added lowres_system_clock is good enough for gossip
resolution. Switch to use it.

Message-Id: <fe0e7a9ef1ea0caffaa8364afe5c78b6988613bf.1503971833.git.asias@scylladb.com>
(cherry picked from commit a36141843a)
2017-11-07 19:21:26 +08:00
Asias He
258f0a383b gossip: Use unordered_map for _unreachable_endpoints and _shadow_unreachable_endpoints
The _unreachable_endpoints will be accessed in fast path soon by the
hinted hand off code.

Message-Id: <500d9cbb2117ab7b070fd1bd111c5590f46c3c3a.1503971826.git.asias@scylladb.com>
(cherry picked from commit 2701bfd1f8)
2017-11-07 19:21:26 +08:00
Asias He
3455bfaa44 gossip: Introduce the shadow_round_ms option
It specifies the maximum gossip shadow round time. It can be used to
reduce the gossip feature check time during node boot up.
For instance, when the first node in the cluster, which listed both
itself and other node as seed in the yaml config, boots up, it will try
to talk to other seed nodes which are not started yet. The gossip shadow
round will be used to fetch the feature info of the cluster. Since there
is no other seed node in the cluster, the shadow round will fail. User
can reduce the default shadow_round_ms option to reduce the boot time.

Fixes #2615
Message-Id: <10916ce9059f3c7f1a1fb465919ae57de3b67d59.1500540297.git.asias@scylladb.com>

(cherry picked from commit cf6f4a5185)
2017-11-07 19:21:26 +08:00
Avi Kivity
cd0b4903e9 Update seastar submodule
* seastar 7ebbb26...124467d (4):
  > peering_sharded_service: prevent over-run the container
  > sharded: fix move constructor for peering_sharded_service services
  > sharded: improve support for cooperating sharded<> services
  > sharded: support for peer services

Includes change to batchlog_manager constructor to adapt it to
seastar::sharded::start() change.

Needed for gossip backport.
2017-11-07 10:49:01 +02:00
Avi Kivity
4d76f564f8 Update seastar submodule
* seastar e4fcb6c...7ebbb26:
  Warn: seastar doesn't contain commit e4fcb6c27cc5dce70d44472522166abe1af29af6

The submodule link pointed nowhere, point it at the tip of scylla-seastar/branch-2.0.
2017-11-06 13:15:16 +02:00
Tomasz Grabiec
a05d3280c4 Update seastar submodule
* seastar b85b0fa...e4fcb6c (1):
  > log: Print nested exceptions

Refs #1011
2017-11-03 10:22:46 +01:00
Glauber Costa
68c41b2346 dist/redhat: do not use s3 addresses in mock profile
They are uglier and less future-proof.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
Message-Id: <20171019142034.30139-1-glauber@scylladb.com>
2017-10-19 18:11:59 +03:00
Glauber Costa
9c907222c5 dist: point mock profile to the right stream
2.0 builds are currently failing because of that.

Message-Id: <20171018182457.5180-1-glauber@scylladb.com>
2017-10-19 11:37:31 +03:00
Tomasz Grabiec
ba02e2688a cache_streamed_mutation: Read static row with cache region locked
_snp->static_row() allocates and needs reference stability.
Message-Id: <1507555031-11567-1-git-send-email-tgrabiec@scylladb.com>

(cherry picked from commit 44faaafc29)

Fixes #2880.
2017-10-10 15:55:08 +02:00
Avi Kivity
fa540581e8 Update ami submodule
* dist/ami/files/scylla-ami 5ffa449...be90a3f (1):
  > amazon kernel: enable updates

Still tracking master branch.
2017-10-02 17:11:30 +03:00
Shlomi Livne
e265c91616 release: prepare for 2.0.0
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2017-09-29 21:12:18 +03:00
Tomasz Grabiec
8a9f8970e4 Update seastar submodule
Refs #2770.

* seastar d763623...b85b0fa (1):
  > scollectd: increment the metadata iterator with the values
2017-09-28 15:32:26 +02:00
Tomasz Grabiec
1e3c777a10 Update seastar submodule
* seastar c853473...d763623 (1):
  > rpc: make sure that _write_buf stream is always properly closed
2017-09-28 15:03:12 +02:00
Tomasz Grabiec
43d785a177 migration_manager: Make sure schema pulls eventually happen when schema_tables_v3 is enabled
We don't pull schema during rolling upgrade, that is until
schema_tables_v3 feature is enabled on all nodes.

Because features are enabled from gossiper timer, there is a race
between feature enablement and processing of endpoint states which may
trigger schema pull.  It can happen that we first try to pull, but
only later enable the feature. In that case the schema pull will not
happen until the next schema change.

The fix is to ensure that pulls abandoned due to feature not being enabled
will be retried when it is enabled.

Fixes sporadic failure in dtest:

  repair_additional_test.py:RepairAdditionalTest.repair_schema_test
Message-Id: <1506428715-8182-2-git-send-email-tgrabiec@scylladb.com>

(cherry picked from commit b704710954)
2017-09-27 12:06:45 +01:00
Tomasz Grabiec
b53d3d225d gossiper: Allow waiting for feature to be enabled
Message-Id: <1506428715-8182-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 7a58fb5767)
2017-09-27 12:06:37 +01:00
Paweł Dziepak
f9864686d2 Merge "Fix cache reader skipping rows in some cases" from Tomasz
"Fixes the problem of concurrent populations of clustering row ranges
leading to some readers skipping over some of the rows.
Spotted during code review.

Fixes #2834."

* tag 'tgrabiec/fix-cache-reader-skipping-rows-v2' of github.com:scylladb/seastar-dev:
  tests: mvcc: Add test for partition_snapshot_row_cursor
  tests: row_cache: Add test for concurrent population
  tests: row_cache: Make populate_range() accept partition_range
  tests: Add simple_schema::make_ckey_range()
  cache_streamed_mutation: Add missing _next_row.maybe_refresh() call
  mvcc: partition_snapshot_row_cursor: Fix cursor skipping over rows added after its position
  mvcc: partition_snapshot_row_cursor: Rename up_to_date() to iterators_valid()
  mvcc: Keep track of all iterators in partition_snapshot_row_cursor
  mvcc: Make partition_snapshot_row_cursor printable

(cherry picked from commit af1976bc30)

[tgrabiec: resolved conflicts]
2017-09-26 19:18:29 +02:00
Tomasz Grabiec
454b90980a streamed_mutation: Allow setting buffer capacity
Needed in tests to limit amount of prefetching done by readers, so
that it's easier to test interleaving of various events.

(cherry picked from commit cb16b038ef)
2017-09-26 19:18:29 +02:00
Tomasz Grabiec
13c66b7145 Update seastar submodule
Fixes #2738.

* seastar e380a07...c853473 (1):
  > httpd: handle exception when shutting down
2017-09-26 18:36:50 +02:00
Asias He
df04418fa4 gossip: Print SCHEMA_TABLES_VERSION correctly
Found this when debugging gossip with debug print. The application state
SCHEMA_TABLES_VERSION was printed as UNKNOWN.
Message-Id: <d7616920d2e6516b5470a758bcf9c88f3d857381.1506391495.git.asias@scylladb.com>

(cherry picked from commit 98e9049820)
2017-09-26 08:39:30 +02:00
Tomasz Grabiec
6e2858a47d storage_service: Register features before joining
Since commit 8378fe190, we disable schema sync in a mixed cluster.
The detection is done using gossiper features. We need to make sure
the features are registerred, and thus can be enabled, before the
bootstrapping of a non-seed node happens. Otherwise the bootstrap will
hang waiting on schema sync which will not happen.
Message-Id: <1505893837-27876-2-git-send-email-tgrabiec@scylladb.com>

(cherry picked from commit 8e46d15f91)
2017-09-25 09:40:22 +01:00
Tomasz Grabiec
0f79503cf1 storage_service: Extract register_features()
Message-Id: <1505893837-27876-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit b92dcb0284)
2017-09-25 09:40:22 +01:00
Tomasz Grabiec
056f6df859 Update seastar submodule
* seastar 06790c0...e380a07 (1):
  > configure: disable exception scalability hack on debug build
2017-09-25 10:13:01 +02:00
Avi Kivity
7833129ab4 Merge "row_cache: Call fast_forward_to() outside allocating section" from Tomasz
"On bad_alloc the section is retried. If the exception happened inside
fast_forward_to() on the underlying reader, that call will be
retried. However, the reader should not be used after exception is
thrown, since it is in unspecified state. Also, calling
fast_forward_to() with cache region locked increases the chances of it
failing to allocate.

We shouldn't call fast_forward_to() with the cache region locked.

Fixes #2791."

* 'tgrabiec/dont-ffwd-in-alloc-section' of github.com:scylladb/seastar-dev:
  cache_streamed_mutation: De-futurize cursor movement
  cache_streamed_mutation: Call fast_forward_to() outside allocating section
  cache_streamed_mutation: Switch from flags to explicit state machine

(cherry picked from commit 5b0cb28af9)

[tgrabiec: resolved minor conflicts]
2017-09-20 10:23:08 +02:00
Asias He
c3c5ec1d4a gossip: Fix indentation in apply_state_locally
Message-Id: <2bdefa8d982ad8da7452b41e894f41d865b83b0b.1505356245.git.asias@scylladb.com>
(cherry picked from commit 5ff0b113c9)
2017-09-19 22:59:46 +08:00
Asias He
7839cebc6c gossip: Use boost::copy_range in apply_state_locally
boost::copy_range is better because the vector is allocated with the
correct size instead of growing when the inserter is called.

[avi: also crashes less]

Message-Id: <b19ca92d56ad070fca1e848daa67c00c024e3a4d.1505291199.git.asias@scylladb.com>
(cherry picked from commit c84dcabb8f)
2017-09-19 22:59:46 +08:00
Pekka Enberg
e428d06f40 Merge "gossip: optimize apply_state_locally for large cluster" from Asias
"This series tries to improve the bootstrap of a node in a large cluster by
improving how gossip applies the gossip node state. In #2404, the joining node
failed to bootstrap, because it did not see the seed node when
storage_service::bootstrap ran. After this series, we apply the whole gossip
state contained in the gossip ack/ack2 message before applying the next one,
and we apply the state of the seed node earlier than non-seed node so we can
have the seed node's state faster. We also add some randomness to the order of
applying gossip node state to prevent some of the nodes' state are always
applied earlier than the others.

This series improves apply_state_locally for large cluster:

 - Tune the order of applying endpoint_state
 - Serialize apply_state_locally
 - Avoid copying of the gossip state map

Fixes #2404"

* tag 'asias/gossip_issue_2404_v2' of github.com:scylladb/seastar-dev:
  gossip: Avoid copying with apply_state_locally
  gossip: Serialize apply_state_locally
  gossip: Tune the order of applying endpoint_state in apply_state_locally
  gossip: Introduce is_seed helper
  gossip: Pass const endpoint_state& in notify_failure_detector
  gossip: Pass reference in notify_failure_detector

(cherry picked from commit d2632ddf1d)
2017-09-19 22:59:45 +08:00
Asias He
6834ba16a3 gossip: Do not wait for echo message in mark_alive
gossiper::apply_state_locally() calls handle_major_state_change() for
each endpoint, in a seastar thread, which calls mark_alive() for new
nodes, which calls ms().send_gossip_echo(id).get(). So it synchronously
waits for each node to respond before it moves on to the next entry. As
a result it may take a while before whole state is processed.

Apache (tm) Cassandra (tm) sends echos in the background.

In a large cluster, we see at the time the joining node starts
streaming, it hasn't managed to apply all the endpoint_state for peer
nodes, so the joining node does not know some of the nodes yet, which
results in the joining node ingores to stream from some of the existing
nodes.

Fixes #2787
Fixes #2797

Message-Id: <3760da2bef1a83f1b6a27702a67ca4170e74b92c.1505719669.git.asias@scylladb.com>
(cherry picked from commit 8f8273969d)
2017-09-19 17:12:26 +03:00
Shlomi Livne
0b49cfcf12 release: prepare for 2.0.rc5
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2017-09-17 17:05:53 +03:00
Duarte Nunes
5e8c9a369e Merge 'Fix schema version mismatch during rolling upgrade from 1.7' from Tomasz
"When there are at least 2 nodes upgraded to 2.0, and the two exchanged schema
for some reason, reads or writes which involve both 1.7 and 2.0 nodes may
start to fail with the following error logged:

    storage_proxy - Exception when communicating with 127.0.0.3: Failed to load schema version 58fc9b89-74ab-37ca-8640-8b38a1204f8d

The situation should heal after whole cluster is upgraded.

Table schema versions are calculated by 2.0 nodes differently than 1.7 nodes
due to change in the schema tables format. Mismatch is meant to be avoided by
having 2.0 nodes calculate the old digest on schema migration during upgrade,
and use that version until next time the table is altered. It is thus not
allowed to alter tables during the rolling upgrade.

Two 2.0 nodes may exchange schema, if they detect through gossip that their
schema versions don't match. They may not match temporarily during boot, until
the upgraded node completes the bootstrap and propagates its new schema
through gossip. One source of such temporary mismatch is construction of new
tracing tables, which didn't exist on 1.7. Such schema pull will result in a
schema merge, which cause all tables to be altered and their schema version to
be recalculated. The new schema will not match the one used by 1.7 nodes,
causing reads and writes to fail, because schema requesting won't work during
rolling upgrade from 1.7 to 2.0.

The main fix employed here is to hold schema pulls, even among 2.0 nodes,
until rolling upgrade is complete."

Fixes #2802.

* 'tgrabiec/fix-schema-mismatch' of github.com:scylladb/seastar-dev:
  tests: schema_change_test: Add test_merging_does_not_alter_tables_which_didnt_change test case
  tests: cql_test_env: Enable all features in tests
  schema_tables: Make make_scylla_tables_mutation() visible
  migration_manager: Disable pulls during rolling upgrade from 1.7
  storage_service: Introduce SCHEMA_TABLES_V3 feature
  schema_tables: Don't alter tables which differ only in version
  schema_mutations: Use mutation_opt instead of stdx::optional<mutation>

(cherry picked from commit 8378fe190a)
2017-09-15 12:07:56 +02:00
Avi Kivity
8567762339 Merge "Refuse to load non-Scylla counter sstables" from Paweł
"These patches make Scylla refuse to load counter sstables that may
contain unsupported counter shards. They are recognised by the lack of
the Scylla component.

Fixes #2766."

* tag 'reject-non-scylla-counter-sstables/v1' of https://github.com/pdziepak/scylla:
  db: reject non-Scylla counter sstables in flush_upload_dir
  db: disallow loading non-Scylla counter sstables
  sstable: add has_scylla_component()

(cherry picked from commit fe019ad84d)
2017-09-11 13:29:32 +03:00
Avi Kivity
f698496ab2 Merge "Fix Scylla upgrades when counters are used" from Paweł
"Scylla 1.7.4 and older use incorrect ordering of counter shards, this
was fixed in 0d87f3dd7d ("utils::UUID:
operator< should behave as comparison of hex strings/bytes"). However,
that patch was not backported to 1.7 branch until very recently. This
means that versions 1.7.4 and older emit counter shards in an incorrect
order and expect them to be so. This is particularly bad when dealing
with imported correct sstables in which case some shards may become
duplicated.

The solution implemented in this patch is to allow any order of counter
shards and automaticly merge all duplicates. The code is written in a
way so that the correct ordering is expected in the fast path in order
not to excessively punish unaffected deployments.

A new feature flag CORRECT_COUNTER_ORDER is introduced to allow seamless
upgrade from 1.7.4 to later Scylla versions. If that feature is not
available Scylla still writes sstables and sends on-wire counters using
the old ordering so that it can be correctly understood by 1.7.4, once
the flag becomes available Scylla switches to the correct order.

Fixes #2752."

* tag 'fix-upgrade-with-counters/v2' of https://github.com/pdziepak/scylla:
  tests/counter: verify counter_id ordering
  counter: check that utils::UUID uses int64_t
  mutation_partition_serializer: use old counter ordering if necessary
  mutation_partition_view: do not expect counter shards to be sorted
  sstables: write counter shards in the order expected by the cluster
  tests/sstables: add storage_service_for_tests to counter write test
  tests/sstables: add test for reading wrong-order counter cells
  sstables: do not expect counter shards to be sorted
  storage_service: introduce CORRECT_COUNTER_ORDER feature
  tests/counter: test 1.7.4 compatible shard ordering
  counters: add helper for retrieving shards in 1.7.4 order
  tests/counter: add tests for 1.7.4 counter shard order
  counters: add counter id comparator compatible with Scylla 1.7.4
  tests/counter: verify order of counter shards
  tests/counter: add test for sorting and deduplicating shards
  counters: add function for sorting and deduplicating counter cells
  counters: add counter_id::operator>

(cherry picked from commit 31706ba989)
2017-09-05 14:25:36 +03:00
Shlomi Livne
6e6de348ea release: prepare for 2.0.rc4
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2017-09-03 14:58:01 +03:00
Avi Kivity
117db58531 Update AMI submodule
* dist/ami/files/scylla-ami b41e5eb...5ffa449 (3):
  > amzn-main.repo: stick to Amazon Linux 2017.03 kernel (4.9.x)
  > Prevent dependency error on 'yum update'
  > scylla_create_devices: don't raise error when no disks found

Fixes #2751.

Still tracking master branch.
2017-08-31 15:15:42 +03:00
Vlad Zolotarov
086f8b7af2 service::storage_service: initialize auth and tracing after we joined the ring
Initialize the system_auth and system_traces keyspaces and their tables after
the Node joins the token ring because as a part of system_auth initialization
there are going to be issues SELECT and possible INSERT CQL statements.

This patch effectively reverts the d3b8b67 patch and brings the initialization order
to how it was before that patch.

Fixes #2273

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
Message-Id: <1500417217-16677-1-git-send-email-vladz@scylladb.com>
(cherry picked from commit e98adb13d5)
2017-08-30 09:33:05 +02:00
Avi Kivity
bee9fbe3fc Merge "Fix sstable reader not working for empty set of clustering ranges" from Tomasz
"Fixes #2734."

* 'tgrabiec/make-sstable-reader-work-with-empty-range-set' of github.com:scylladb/seastar-dev:
  tests: Introduce clustering_ranges_walker_test
  tests: simple_schema: Add missing include
  sstables: reader: Make clustering_ranges_walker work with empty range set
  clustering_ranges_walker: Make adjacency more accurate

(cherry picked from commit 5224ab9c92)
2017-08-29 15:54:58 +02:00
Tomer Sandler
b307a36f1e node_health_check: Various updates
- Removed text from Report's "PURPOSE" section, which was referring to the "MANUAL CHECK LIST" (not needed anymore).
- Removed curl command (no longer using the api_address), instead using scylla --version
- Added -v flag in iptables command, for more verbosity
- Added support to for OEL (Oracle Enterprise Linux) - minor fix
- Some text changes - minor
- OEL support indentation fix + collecting all files under /etc/scylla
- Added line seperation under cp output message

Signed-off-by: Tomer Sandler <tomer@scylladb.com>
Message-Id: <20170828131429.4212-1-tomer@scylladb.com>
(cherry picked from commit f1eb6a8de3)
2017-08-29 15:17:16 +03:00
Tomer Sandler
527e12c432 node_health_check: added line seperation under cp output message
Signed-off-by: Tomer Sandler <tomer@scylladb.com>
Message-Id: <20170828124307.2564-1-tomer@scylladb.com>
(cherry picked from commit 83f249c15d)
2017-08-29 15:17:07 +03:00
Shlomi Livne
c57cc55aa6 release: prepare for 2.0.rc3
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2017-08-28 14:57:54 +03:00
Avi Kivity
5d3c015d27 Merge "Fixes for skipping in sstable reader" from Tomasz
Ref #2733.

* 'tgrabiec/fix-fast-forwarding' of github.com:scylladb/seastar-dev:
  tests: mutation_source_test: Add more tests for fast forwarding across partitions
  sstables: Fix abort in mutation reader for certain skip pattern
  sstables: Fix reader returning partition past the query range in some cases
  sstables: Introduce data_consume_context::eof()

(cherry picked from commit 4e67bc9573)
2017-08-28 12:48:50 +03:00
Avi Kivity
428831b16a Merge "consider the pre-existing cpuset.conf when configuring networking mode" from Vlad
"Preserve the networking configuration mode during the upgrade by generating the /etc/scylla.d/perftune.yaml
file and using it."

Fixes #2725.

* 'dist_respect_cpuset_conf-v3' of https://github.com/vladzcloudius/scylla:
  scylla_prepare: respect the cpuset.conf when configuring the networking
  scylla_cpuset_setup: rm perftune.yaml
  scylla_cpuset_setup: add a missing "include" of scylla_lib.sh

(cherry picked from commit 40aeb00151)
2017-08-24 18:59:37 +03:00
Paweł Dziepak
918339cf2e mvcc: allow invoking maybe_merge_versions() inside allocating section
Message-Id: <20170823083544.4225-1-pdziepak@scylladb.com>
(cherry picked from commit 1006a946e8)
2017-08-24 14:31:00 +02:00
Paweł Dziepak
6c846632e4 abstract_read_executor: make make_requests() exception safe
Message-Id: <20170821162934.25386-5-pdziepak@scylladb.com>
(cherry picked from commit 9d82a1ebfd)
2017-08-24 14:29:32 +02:00
Paweł Dziepak
af7b7f1eff shared_index_lists: restore indentation
Message-Id: <20170821162934.25386-4-pdziepak@scylladb.com>
(cherry picked from commit 31afc2f242)
2017-08-24 14:28:49 +02:00
Paweł Dziepak
701128f8a1 sstables: make shared_index_lists::get_or_load exception safe
Message-Id: <20170821162934.25386-3-pdziepak@scylladb.com>
(cherry picked from commit 93eaa95378)
2017-08-24 14:28:49 +02:00
Avi Kivity
c03118fbe9 Update seastar submodule
* seastar 2993cae...06790c0 (3):
  > scripts: posix_net_conf.sh: allow passing a perftune.py configuration file as a parameter
  > scripts: perftune.py: add the possibility to pass the parameters in a configuration file and print the YAML file with the current configuration
  > scripts: perftune.py: actually use the number of Rx queues when comparing to the number of CPU threads
2017-08-24 11:37:38 +03:00
Piotr Jastrzebski
a98e3aec45 Make streamed_mutation more exception safe
Make sure that push_mutation_fragment leaves
_buffer_size with a correct value if exception
is thrown from emplace_back.

Signed-off-by: Piotr Jastrzebski <piotr@scylladb.com>
Message-Id: <83398412aa78332d88d91336b79140aecc988602.1503474403.git.piotr@scylladb.com>
(cherry picked from commit 477068d2c3)
2017-08-23 19:10:49 +03:00
Avi Kivity
29baf7966c Merge "repair: Do not allow repair until node is in NORMAL status" from Asias
Fixes #2723.

* tag 'asias/repair_issue_2723_v1' of github.com:cloudius-systems/seastar-dev:
  repair: Do not allow repair until node is in NORMAL status
  gossip: Add is_normal helper

(cherry picked from commit 2f41ed8493)
2017-08-23 09:45:34 +03:00
Amnon Heiman
ba63f74d7e Add configuration to disable per keyspace and column family metrics
The number of keysapce and column family metrics reported is
proportional to the number of shards times the number of keysapce/column
families.

This can cause a performance issue both on the reporting system and on
the collecting system.

This patch adds a configuration flag (set to false by default) to enable
or disable those metrics.

Fixes #2701

Signed-off-by: Amnon Heiman <amnon@scylladb.com>
Message-Id: <20170821113843.1036-1-amnon@scylladb.com>
(cherry picked from commit abbd78367c)
2017-08-22 19:20:50 +03:00
Alexys Jacob
1733f092ef dist: Fix Gentoo Linux scylla-jmx and scylla-tools packages detection
These two admin related packages will be packaged under the "app-admin"
category and not the "dev-db" one.

This fixes the detection path of the packages for scylla_setup.

Signed-off-by: Alexys Jacob <ultrabug@gentoo.org>
Message-Id: <20170817094756.21550-1-ultrabug@gentoo.org>
(cherry picked from commit e5ff8efea3)
2017-08-17 15:44:02 +03:00
Paweł Dziepak
179ff956ee sstables: initialise index metrics on all shards
Fixes #2702.

Message-Id: <20170816085454.21554-1-pdziepak@scylladb.com>
(cherry picked from commit 784dcbf1ca)
2017-08-16 15:44:58 +03:00
Avi Kivity
61c2e8c7e2 Update seastar submodule
* seastar d67c344...2993cae (1):
  > fstream: do not ignore unresolved future

Fixes #2697.
2017-08-16 15:11:10 +03:00
Shlomi Livne
8370e1bc2c release: prepare for 2.0.rc2
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2017-08-15 15:52:35 +03:00
Pekka Enberg
3a244a4734 docker: Switch to Scylla 2.0 RPM repository 2017-08-15 13:27:41 +03:00
Avi Kivity
3261c927d2 Update seastar submodule
* seastar 2383d60...d67c344 (1):
  > Merge "Fix crash in rpc due to access to already destroyed server socket" from Gleb

Fixes #2690
2017-08-14 16:24:05 +03:00
Avi Kivity
4577a89982 Update seastar submodule
* seastar cfe280c...2383d60 (1):
  > tls: Only recurse once in shutdown code

Fixes #2691
2017-08-14 15:10:27 +03:00
Avi Kivity
6ea306f898 Update seastar submodule
* seastar b9f4568...cfe280c (1):
  > scripts: perftune.py: change the network module mode auto selection heuristic
2017-08-14 10:30:42 +03:00
Avi Kivity
2afcc684b4 Update seastar submodule
* seastar 867b7c7...b9f4568 (4):
  > http: removed unneeded lamda captures
  > Merge "Prometheus to use output stream" from Amnon
  > http_test: Fix an http output stream test
  > Merge "Add output stream to http message reply" from Amnon

Fixes #2475
2017-08-10 12:05:14 +03:00
Avi Kivity
bdb8c861c7 Fork seastar submodule for 2.0 2017-08-10 12:00:31 +03:00
Takuya ASADA
ea933b4306 dist/debian: append postfix '~DISTRIBUTION' to scylla package version
We are moving to aptly to release .deb packages, that requires debian repository
structure changes.
After the change, we will share 'pool' directory between distributions.
However, our .deb package name on specific release is exactly same between
distributions, so we have file name confliction.
To avoid the problem, we need to append distribution name on package version.

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1502312935-22348-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 8e115d69a9)
2017-08-10 10:54:17 +03:00
Raphael S. Carvalho
19391cff14 sstables: close index file when sstable writer fails
index's file output stream uses write behind but it's not closed
when sstable write fails and that may lead to crash.
It happened before for data file (which is obviously easier to
reproduce for it) and was fixed by 0977f4fdf8.

Fixes #2673.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20170807171146.10243-1-raphaelsc@scylladb.com>
(cherry picked from commit dddbd34b52)
2017-08-08 09:53:36 +03:00
Glauber Costa
87d9a4f1f1 add active streaming reads metric
In commit f38e4ff3f, we have separated streaming reads from normal reads
for the purpose of determining the maximum number of reads going on.
However, we'll now be totally unaware of how many reads will be
happening on behalf of streaming and that can be important information
when debugging issues.

This patch adds this metric so we don't fly blind.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
Message-Id: <1501909973-32519-1-git-send-email-glauber@scylladb.com>
(cherry picked from commit 4a911879a3)
2017-08-05 11:07:18 +03:00
Pekka Enberg
c0f894ccef docker: Disable stall detector
Fixes #2162

Message-Id: <1501759957-4380-1-git-send-email-penberg@scylladb.com>
(cherry picked from commit 90872ffa1f)
2017-08-03 14:53:03 +03:00
Takuya ASADA
2c892488ef dist/debian: check scylla user/group existance before adding them
To prevent install failing on the environment which already has scylla
user/group, existance check is needed.

Fixes #2389

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1495023805-14905-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 91ade1a660)
2017-08-03 13:01:30 +03:00
Avi Kivity
911608e9c4 database: prevent streaming reads from blocking normal reads
Streaming reads and normal reads share a semaphore, so if a bunch of
streaming reads use all available slots, no normal reads can proceed.

Fix by assigning streaming reads their own semaphore; they will compete
with normal reads once issued, and the I/O scheduler will determine the
winner.

Fixes #2663.
Message-Id: <20170802153107.939-1-avi@scylladb.com>

(cherry picked from commit f38e4ff3f9)
2017-08-03 12:27:48 +03:00
Avi Kivity
d8ab07de37 database: remove streaming read queue length limit
If we fail a streaming read due queue overload, we will fail the entire repair.
Remove the limit for streaming, and trust the caller (repair) to have bounded
concurrency.

Fixes #2659.
Message-Id: <20170802143448.28311-1-avi@scylladb.com>

(cherry picked from commit 911536960a)
2017-08-03 12:27:46 +03:00
Duarte Nunes
15eefbc434 tests/sstable_mutation_test: Don't use moved-from object
Fix a bug introduced in dbbb9e93d and exposed by gcc6 by not using a
moved-from object. Twice.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170802161033.4213-1-duarte@scylladb.com>
(cherry picked from commit 4c9206ba2f)
2017-08-03 09:46:18 +03:00
Vlad Zolotarov
4bb6ba6d58 utils::loading_cache: cancel the timer after closing the gate
The timer is armed inside the section guarded by the _timer_reads_gate
therefore it has to be canceled after the gate is closed.

Otherwise we may end up with the armed timer after stop() method has
returned a ready future.

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
Message-Id: <1501603059-32515-1-git-send-email-vladz@scylladb.com>
(cherry picked from commit 4b28ea216d)
2017-08-01 17:23:53 +01:00
Avi Kivity
6dd4a9a5a2 Merge "Ensure correct EOC for PI block cell names" from Duarte
"This series ensures the always write correct cell names to promoted
index cell blocks, taking into account the eoc of range tombstones.

Fixes #2333"

* 'pi-cell-name/v1' of github.com:duarten/scylla:
  tests/sstable_mutation_test: Test promoted index blocks are monotonic
  sstables: Consider eoc when flushing pi block
  sstables: Extract out converting bound_kind to eoc

(cherry picked from commit db7329b1cb)
2017-08-01 18:09:54 +03:00
Gleb Natapov
222e85d502 cql transport: run accept loop in the foreground
It was meant to be run in the foreground since it is waited upon during
stop(), but as it is now from the stop() perspective it is completed
after first connection is accepted.

Fixes #2652

Message-Id: <20170801125558.GS20001@scylladb.com>
(cherry picked from commit 1da4d5c5ee)
2017-08-01 17:06:08 +03:00
Takuya ASADA
8d4a30e852 dist/ami: follow scylla-tools package name change on RedHat variants
Since scylla-tools generates two .rpm packages, we need to copy them to our AMI.

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <20170722090002.9850-1-syuu@scylladb.com>
(cherry picked from commit a998b7b3eb)
2017-07-31 18:57:29 +03:00
Avi Kivity
4710ee229d Merge "educe the effect of the latency metrics" from Amnon
"This series reduce that effect in two ways:
1. Remove the latency counters from the system keyspaces
2. Reduce the histogram size by limiting the maximum number of buckets and
   stop the last bucket."

Fixes #2650.

* 'amnon/remove_cf_latency_v2' of github.com:cloudius-systems/seastar-dev:
  database: remove latency from the system table
  estimated histogram: return a smaller histogram

(cherry picked from commit 3fe6731436)
2017-07-31 16:01:05 +03:00
Vlad Zolotarov
93cb78f21d utils::loading_cache: add stop() method
loading_cache invokes a timer that may issue asynchronous operations
(queries) that would end with writing into the internal fields.

We have to ensure that these operations are over before we can destroy
the loading_cache object.

Fixes #2624

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
Message-Id: <1501208345-3687-1-git-send-email-vladz@scylladb.com>
2017-07-31 15:55:46 +03:00
Avi Kivity
af8151c4b7 Update scylla-ami submodule
* dist/ami/files/scylla-ami 2bd1481...b41e5eb (1):
  > Fix incorrect scylla-server sysconfig file edit for i3 memflush controller
2017-07-31 09:41:56 +03:00
Takuya ASADA
846d9da9c2 dist/debian: refuse upgrade if current scylla < 1.7.3 && commitlog remains
Commitlog replay fails when upgrade from <1.7.3 to 2.0, we need to refuse
updating package if current scylla < 1.7.3 && commitlog remains.

Note: We have the problem on scylla-server package, but to prevent
scylla-conf package upgrade, %pretrans should be define on scylla-conf.

Fixes #2551

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1501187555-4629-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 714540cd4c)
2017-07-31 09:18:58 +03:00
Paweł Dziepak
aaa59d3437 streamed_mutation: do not call fill_buffer() ahead of time
consume_mutation_fragments_until() allows consuming mutation fragments
until a specified condition happens. This patch reorganises its
implementation so that we avoid situations when fill_buffer() is called
with stop condition being true.
Message-Id: <20170727122218.7703-1-pdziepak@scylladb.com>

(cherry picked from commit f02bef7917)
2017-07-27 17:48:26 +02:00
Tomasz Grabiec
66dd817582 mutation_partition: Always mark static row as continuous when no static columns
To avoid unnecessary cache misses after static columns are added.

Message-Id: <1500650057-26036-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 136d205855)
2017-07-27 14:59:33 +02:00
Tomasz Grabiec
5857a4756d Merge "Some fixes for performance regressions in perf_fast_forward" from Paweł
These patches contain some minor fixes for performance regression reported
by perf_fast_forward after partial cache was merged. The solution is still
far from perfect, there is one case that still has 30% degradation, but
there is some improvement so there is no reason to hold these changes back.

Refs #2582.

Some numbers:
before - before cache changes were merged
(555621b537)

cache - at the commit that introduced the partial cache
(9b21a9bfb6)

after - recent master + this series
(based on e988121dbb)

Differences are shown relative to "before".

Testing effectiveness of caching of large partition, single-key slicing reads:
Large partitions, range [0, 500000], populating cache
  before      cache      after
 1636840    1013688    1234606
              -38%        -25%

Large partitions, range [0, 500000], reading from cache
  before      cache      after
 2012615    3076812    3035423
               +53%       +51%

Testing scanning small partitions with skips.
reading small partitions (skip 0)
 before      cache      after
 227060     165261     200639
              -27%       -11%

skipping small partitions (skip 1)
 before      cache      after
  29813      27312      38210
               -8%       +28%

Testing slicing small partitions:
slicing small partitions (offset 0, read 4096)
 before      cache      after
 195282     149695     180497
              -23%        -8%

* https://github.com/pdziepak/scylla.git perf_fast_forward-regression/v3:
  sstables: make sure that fill_buffer() actually fills buffer
  mutation_merger: improve handling of non-deferring fill_buffer()s
  partition_snapshot_row_cursor: avoid apply() in single-version cases
  sstables: introduce decorated_key_view
  ring_position_comparator: accept sstables::decorated_key_view
  sstable: keep a pre-computed token in summary_entry
  sstables: cache token in index entries
  index_reader: advance_and_check_if_present() use index_comparator
  ring_position_comparator: drop unused overloads
  cache_streamed_mutation: avoid moving clustering_row
  streamed_mutation: introduce consume_mutation_fragments_until()
  cache_streamed_mutation: use consumer based read_context reader
  rows_entry: make position() inlineable
  mutation_fragment: make destructor always_inline
  keys: introduce compound_wrapper::from_exploded_view()
  sstables: avoid copying key components
  compound_compat: explode: reserve some elements in a vector
  cache: short-circut static row logic if there are no static columns
  cache: use equality comparators instead of tri_compare
  sstables: avoid indirect calls to abstract_type::is_multi_cell()

(cherry picked from commit e9fc0b0491)
2017-07-27 13:58:23 +02:00
Takuya ASADA
f199047601 dist/redhat: limit metapackage dependencies to specific version of scylla packages
When we install scylla metapackage with version (ex: scylla-1.7.1),
it just always install newest scylla-server/-jmx/-tools on the repo,
instead of installing specified version of packages.

To install same version packages with the metapackage, limited dependencies to
current package version.

Fixes #2642

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <20170726193321.7399-1-syuu@scylladb.com>
(cherry picked from commit 91a75f141b)
2017-07-27 14:21:55 +03:00
Tomasz Grabiec
a8dcbb6bd0 row_cache: Fix potential timeout or deadlock due to sstable read concurrency limit
database::make_sstable_reader() creates a reader which will need to
obtain a semaphore permit when invoked. Therefore, each read may
create at most one such reader in order to be guaranteed to make
progress. If the reader tries to create another reader, that may
deadlock (or for non-system tables, timeout), if enough number of such
readers tries to do the same thing at the same time.

Avoid the problem by dropping previous reader before creating a new
one.

Refs #2644.

Message-Id: <1501152454-4866-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 22948238b6)
2017-07-27 13:58:40 +03:00
Duarte Nunes
bfd99d4e74 db/schema_tables: Drop dropped columns when dropping tables
Fixes #2633

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170726150228.2593-2-duarte@scylladb.com>
(cherry picked from commit 50ad0003c6)
2017-07-26 18:48:59 +02:00
Duarte Nunes
d40df89271 db/schema_tables: Store column_name in text form
As does Cassandra.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170726150228.2593-1-duarte@scylladb.com>
(cherry picked from commit 3425403126)
2017-07-26 18:48:58 +02:00
Duarte Nunes
3da54ffff0 schema_builder: Replace type when re-dropping column
Fixes #2634

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170725183933.5311-1-duarte@scylladb.com>
(cherry picked from commit e988121dbb)
2017-07-26 16:26:59 +02:00
Duarte Nunes
804793e291 tests/schema_change_test: Add test case for add+drop notification
Reproduces #2616

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170725170622.4380-2-duarte@scylladb.com>
(cherry picked from commit 472f32fb06)
2017-07-26 16:26:59 +02:00
Duarte Nunes
83ea9b6fc0 db/schema_tables: Consider differing dropped columns
If a node is notified of a schema change where the schema's dropped
columns have changes, that node will miss the changes to the dropped
columns. A scenario where this can happen is where a column c is
dropped, then added as a different typed, and then dropped again, with
a node n having seen the first drop and being notified of the
subsequent add and drop.

Fixes #2616

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170725170622.4380-1-duarte@scylladb.com>
(cherry picked from commit 33e18a1779)
2017-07-26 16:26:59 +02:00
Asias He
b45855fc1c gossip: Fix nr_live_nodes calculation
We need to consider the _live_endpoints size. The nr_live_nodes should
not be larger than _live_endpoints size, otherwise the loop to collect
the live node can run forever.

It is a regression introduced in commit 437899909d
(gossip: Talk to more live nodes in each gossip round).

Fixes #2637

Message-Id: <863ec3890647038ae1dfcffc73dde0163e29db20.1501026478.git.asias@scylladb.com>
(cherry picked from commit 515a744303)
2017-07-26 16:48:51 +03:00
Duarte Nunes
3900babff2 schema: Remove unnecessary print
Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170725174000.71061-1-duarte@scylladb.com>
(cherry picked from commit 9c831b4e97)
2017-07-26 16:07:41 +03:00
Tomasz Grabiec
7c805187a9 Merge fixes related to row cache from Raphael
* git@github.com:raphaelsc/scylla.git row_cache_fixes:
  db: atomically synchronize cache with changes to the snapshot
  db: refresh row cache's underlying data source after compaction

(cherry picked from commit 18be42f71a)
2017-07-25 15:37:40 +02:00
Paweł Dziepak
345a91d55d tests/row_cache: test queries with no clustering ranges
Reproducer for #2604.
Message-Id: <20170725131220.17467-3-pdziepak@scylladb.com>

(cherry picked from commit 79a1ad7a37)
2017-07-25 15:37:32 +02:00
Paweł Dziepak
fda8b35cda tests: do not overload the meaning of empty clustering range
Empty clustering key range is perfectly valid and signifies that the
reader is not interested in anything but the static row. Let's not
make it mean anything else.
Message-Id: <20170725131220.17467-2-pdziepak@scylladb.com>

(cherry picked from commit 1ea507d6ae)
2017-07-25 15:37:29 +02:00
Paweł Dziepak
08ac0f1100 cache: fix aborts if no clustering range is specified
cache_streamed_mutation assumed that at least one clustering range was
specified. That was wrong since the readers are allowed to query just
for a static row (e.g. counter update that modifies only static
columns).

Fixes #2604.
Message-Id: <20170725131220.17467-1-pdziepak@scylladb.com>

(cherry picked from commit 6572f38450)
2017-07-25 15:37:28 +02:00
Calle Wilund
db455305a2 system_keyspace: Make sure "system" is written to keyspaces (visible)
Fixes #2514

Bug in schema version 3 update: We failed to write "system" to the
schema tables. Only visible on an empty instance of course.

Message-Id: <1500469809-23546-2-git-send-email-calle@scylladb.com>
(cherry picked from commit 7a583585a2)
2017-07-24 11:33:25 +02:00
Avi Kivity
e1a3052e76 tests: fix sstable_datafile_test build with boost 1.55
Boost 1.55 accidentally removed support for "range for" on
recursive_directory_iterator (previous and latter versions do
support it). Use old-style iteration instead.

Message-Id: <20170724080128.8824-1-avi@scylladb.com>
(cherry picked from commit c21bb5ae05)
2017-07-24 11:20:53 +03:00
Tomasz Grabiec
50fa3f3b89 schema_registry: Keep unused entries around for 1 second
This is in order to avoid frequent misses which have a relatively high
cost. A miss means we need to fetch schema definition from another
node and in case of writes do a schema merge.

If the schema is kept alive only by the incoming request, then it
will be forgotten immediately when the request is done, and the next
request using the same schema version will miss again.

Refs #2608.
Message-Id: <1500632447-10104-1-git-send-email-tgrabiec@scylladb.com>

(cherry picked from commit 29a82f5554)
2017-07-24 10:12:09 +02:00
Tomasz Grabiec
8474b7a725 legacy_schema_migrator: Don't snapshot empty legacy tables
Otherwise we will create a new (empty) snapshot each time we boot.
Message-Id: <1500573920-31478-2-git-send-email-tgrabiec@scylladb.com>

(cherry picked from commit ecc85988dd)
2017-07-24 09:56:22 +02:00
Tomasz Grabiec
0fc874e129 database: Allow disabling auto snapshots during drop/truncate
Message-Id: <1500573920-31478-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 408cea66cd)
2017-07-24 09:56:19 +02:00
Duarte Nunes
5cf1a19f3f Merge 'Fix possible inconsistency of table schema version' from Tomasz
"Fixes issues uncovered in longevity test (#2608).

Main problem is that due to time drift scylla_tables.version column
may not get deleted on all nodes doing the schema merge, which will
make some nodes come up with different table schema version than others.

The inconsistency will not heal because scylla_tables doesn't
take part in the schema sync. This is fixed by the last patch.

This will cause nodes to constantly try to sync the schema, which under
some conditions triggers #2617."

* tag 'tgrabiec/fix-table-schema-version-inconsistency-v1' of github.com:scylladb/seastar-dev:
  schema_tables: Add scylla_tables to ALL
  schema: Make schema_mutations equality consistent with digest
  schema_tables: Extract compact_for_schema_digest()
  schema_tables: Always drop scylla_tables::version

(cherry picked from commit 937fe80a1a)
2017-07-24 09:54:45 +02:00
Tomasz Grabiec
f48466824f schema_registry: Ensure schema_ptr is always synced on the other core
global_schema_ptr ensures that schema object is replicated to other
cores on access. It was replicating the "synced" state as well, but
only when the shard didn't know about the schema. It could happen that
the other shard has the entry, but it's not yet synced, in which case
we would fail to replicate the "synced" state. This will result in
exception from mutate(), which rejects attempts to mutate using an
unsynced schema.

The fix is to always replicate the "synced" state. If the entry is
syncing, we will preemptively mark it as synced earlier. The syncing
code is already prepared for this.

Refs #2617.
Message-Id: <1500555224-15825-1-git-send-email-tgrabiec@scylladb.com>

(cherry picked from commit 65c64614aa)
2017-07-24 09:52:31 +02:00
Avi Kivity
914f6f019f Update ami submodule
* dist/ami/files/scylla-ami 5dfe42f...2bd1481 (1):
  > Enable support for experimental CPU controller in i3 instances
2017-07-24 10:27:35 +03:00
Shlomi Livne
f5bb363f96 release: prepare for 2.0.rc1
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2017-07-23 09:47:11 +03:00
Duarte Nunes
61ba56f628 schema: Support compaction enabled attribute
Fixes #2547

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170721132206.3037-1-duarte@scylladb.com>
(cherry picked from commit 7eecda3a61)
2017-07-21 15:39:48 +02:00
Tomasz Grabiec
f4d3e5cdcf Merge "Drop mutations that raced with truncate" from Duarte
Instead of retrying, just drop mutations that raced with a truncate.

* git@github.com:duarten/scylla.git truncate-reorder/v1:
  database: Rename replay_position_reordered_exception
  database: Drop mutations that raced with truncate

(cherry picked from commit 63caa58b70)
2017-07-21 15:39:20 +02:00
Avi Kivity
0291a4491e Merge "restrict background writers with scheduling groups" from Glauber
"This patchset restricts background writers - such as compactions,
streaming flushes and memtable flushes to a maximum amount of CPU usage
through a seastar::thread_scheduling_group.

The said maximum is recommended to be set  50 % - it is default
disabled, but can be adjusted through a configuration option until we
are able to auto-tune this.

The second patch in this series provides a preview on how such auto-tune
would look like. By implementing a simple controller we automatically
adjust the quota for the memtable writer processes, so that the rate at
which bytes come in is equal to the rates at which bytes are flushed.

Tail latencies are greatly reduced by this series, and heavy spikes that
previously appeared on CPU-bound workloads are no more."

* 'memtable-controller-v5' of https://github.com/glommer/scylla:
  simple controller for memtable/streaming writer shares.
  restrict background writers to 50 % of CPU.

(cherry picked from commit c5ee62a6a4)
2017-07-20 15:13:39 +03:00
Duarte Nunes
83cc640c6a Merge 'Revert back to 1.7 schema layout in memory' from Tomasz
"Fixes schema layout incompatibility in a mixed 1.7 and 2.0 cluster (#2555)
by reverting back to using the old layout in memory and thus also
in across-node requests. We still use the new v3 layout in schema
tables (needed by drivers and external tools). Translations happen
when converting to/from schema mutations."

* tag 'tgrabiec/use-v2-schema-layout-in-memory-v2' of github.com:scylladb/seastar-dev:
  schema: Revert back to the 1.7 layout of static compact tables in memory
  schema: Use v3 column layout when converting to/from schema mutations
  schema: Encapsulate column layout translations in the v3_columns class

(cherry picked from commit 1daf1bc4bb)
2017-07-19 19:49:43 +03:00
Duarte Nunes
2f06c54033 thrift/handler: Remove leftover debug artifacts
Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170705161156.2307-1-duarte@scylladb.com>
(cherry picked from commit d583ef6860)
2017-07-19 19:49:35 +03:00
Calle Wilund
9abe7651f7 system_schema: Fix remaining places not handing two system keyspaces
Some places remained where code looked directly at
system_keyspace::NAME to determine iff a ks is
considered special/system/protected. Including
schema digest calculation.

Export "is_system_keyspace" and use accordingly.

Message-Id: <1500469809-23546-1-git-send-email-calle@scylladb.com>
(cherry picked from commit 247c36e048)
2017-07-19 19:48:30 +03:00
Amos Kong
784aea12e7 scylla_raid_setup: fix syntax error
/usr/lib/scylla/scylla_raid_setup: line 132: syntax error
near unexpected token `fi'

Fixes #2610

Signed-off-by: Amos Kong <amos@scylladb.com>
Message-Id: <af3a5bc77c5ba2b49a8f48a5aaa19afffb787886.1500430021.git.amos@scylladb.com>
(cherry picked from commit 2bdcad5bc3)
2017-07-19 11:10:43 +03:00
Avi Kivity
3a98959eba dist: tolerate sysctl failures
sysctl may fail in a container environment if /proc is not virtualized
properly.

Fixes #1990
Message-Id: <20170625145930.31619-1-avi@scylladb.com>

(cherry picked from commit 08488a75e0)
2017-07-18 15:45:41 +03:00
Duarte Nunes
2c7d597307 wrapping_range: Fix lvalue transform()
Instead of copying and moving the bound, pass it by reference so the
transformer can decide whether it wants to copy or not. The only
caller so far doesn't want a copy and takes the value by reference,
which would be capturing a temporary value. Caught by the
view_schema_test with gcc7.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170705210255.29669-1-duarte@scylladb.com>
(cherry picked from commit 3dd0397700)
2017-07-18 14:35:58 +03:00
Duarte Nunes
8d46c4e049 thrift: Fail when mixed CFs are detected
Fixes #2588

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170717222612.7429-1-duarte@scylladb.com>
(cherry picked from commit d9fa3bf322)
2017-07-18 10:21:45 +03:00
Asias He
b1c080984f gossip: Implement the missing fd_max_interval_ms and fd_initial_value_ms option
It is useful for larger cluster with larger gossip message latency. By
default the fd_max_interval_ms is 2 seconds which means the
failure_detector will ignore any gossip message update interval larger
than 2 seconds. However, in larger cluster, the gossip message udpate
interval can be larger than 2 seconds.

Fixes #2603.

Message-Id: <49b387955fbf439e49f22e109723d3a19d11a1b9.1500278434.git.asias@scylladb.com>
(cherry picked from commit adc5f0bd21)
2017-07-17 13:29:30 +03:00
Duarte Nunes
e1706c36b7 Merge 'Fixes around migration to v3 schema tables' from Tomasz
branch 'tgrabiec/schema-migration-fixes' of github.com:scylladb/seastar-dev:
  schema: Use proper name comparator
  legacy_schema_migrator: Properly migrate non-UTF8 named columns
  schema_tables: Store column_name in text form
  legacy_schema_migrator: Migrate columns like Cassandra
  schema_builder: Add factory method for default_names
  legacy_schema_migrator: Simplify logic
  thrift: Don't set regular_column_name_type
  schema: Use proper column name type for static columns
  schema: Fix column_name_type() for static compact tables
  schema: Introduce clustering_column_at()
  thrift: Reuse cell_comparator::to_sstring() for obtaining comparator type
  partition_slice_builder: Use proper column's type instead of regular_column_name_type()

(cherry picked from commit 13caccf1cf)
2017-07-17 12:42:19 +03:00
Avi Kivity
63c8306733 Update seastar submodule
* seastar b812cee...867b7c7 (1):
  > rpc: start server's send loop only after protocol negotiation

Fixes #2600.

Still tracking upstream.
2017-07-17 10:41:59 +03:00
Avi Kivity
a7dfdc0155 tests: move tmpdir to /tmp
Reduces view_schema_test runtime to 5 seconds, from 53 seconds on an NVMe disk
with write-back cache, and forever on a spinning disk.
Message-Id: <20170716081653.10018-1-avi@scylladb.com>

(cherry picked from commit d9c64ef737)
2017-07-17 08:47:17 +03:00
Avi Kivity
70be29173a tests: copy the sstable with an unknown component to the data directory
We will be creating links to those sstable's files, and those don't work
if the data directory and the test sstable are on different devices.

Copying the files to the same directory fixes the problem.
Message-Id: <20170716090405.14307-1-avi@scylladb.com>

(cherry picked from commit 9116dd91cb)
2017-07-17 08:47:08 +03:00
Avi Kivity
e09d4a9b75 Update seastar submodule
* seastar 844bcfb...b812cee (1):
  > Update dpdk submodule

Fixes #2595 (again).

Still tracking master.
2017-07-16 17:01:48 +03:00
Avi Kivity
67f25e56a6 Update seastar submodule
* seastar ff34c42...844bcfb (1):
  > Update dpdk submodule

Still tracking master.

Fixes #2595.
2017-07-15 19:18:10 +03:00
Tomasz Grabiec
74c4651b95 Merge "Fixes for memtable flushing and replay positions" from Duarte
We don't ensure mutations are applied in memory following the order of their
replay positions. A memtable can thus be flushed with replay position rp,
with the new one being at replay position rp', where rp' < rp. This breaks
an intrinsic assumption in the code, which this series addresses.

Fixes #2074

branch memtable-flush/v3 of git@github.com:duarten/scylla.git:
  commitlog: Always flush latest memtable
  column_family: More precise count of switched memtables
  column_family: Fix typo in pending_tasks metric name
  column_family: More precise count of pending flushes
  dirty_memory_manager: Remove unnecessary check from flush_one()
  column_family: Don't rely on flush_queue to guarantee flushes finished
  column_family: Don't bother closing the flush_queue on stop()
  column_family: Stop using flush_queue
  column_family: Remove outdated comment about the flush_queue
  memtable: Stop tracking the highest flushed rp

(cherry picked from commit caa62f7f05)
2017-07-14 19:07:33 +02:00
Duarte Nunes
58bfb86d73 storage_proxy: Preserve replica order across mutations
In storage_proxy we arrange the mutations sent by the replicas in a
vector of vectors, such that each row corresponds to a partition key
and each column contains the mutation, possibly empty, as sent by a
particular replica.

There is reconciliation-related code that assumes that all the
mutations sent by a particular replica can be found in a single
column, but that isn't guaranteed by the way we initially arrange the
mutations.

This patch fixes this and enforces the expected order.

Fixes #2531
Fixes #2593

Signed-off-by: Gleb Natapov <gleb@scylladb.com>
Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170713162014.15343-1-duarte@scylladb.com>
(cherry picked from commit b8235f2e88)
2017-07-14 12:11:50 +03:00
Tomasz Grabiec
cb94c66823 legacy_schema_migrator: Fix calculation of is_dense
Current algorithm was marking tables with regular columns not named
"value" as not dense, which doesn't have to be the case. It can be
either way.

It should be enough to look at clustering components. If there is a
clustering key, then table is dense if and only if all comparator
components belong to the clustering key.

If there is no clustering key, then if there are any regular columns
we're sure it's not dense.

Fixes #2587.

Message-Id: <1499877777-7083-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 30ec4af949)
2017-07-13 17:28:25 +03:00
Tomasz Grabiec
5aa3e23fcd gdb: Fix "scylla columnfamilies" command
Broken in 0e4d5bc2f3.

Message-Id: <1499951956-26206-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 54953c8d27)
2017-07-13 16:33:50 +03:00
Takuya ASADA
aac1d5d54d dist/common/systemd: move scylla-server.service to be after network-online.target instead of network.target
To make sure start Scylla after network is up, we need to move from
network.target to network-online.target.

Fixes #2337

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1493661832-9545-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 0c81974bc4)
2017-07-12 13:36:52 +03:00
Glauber Costa
a371b8a5bf change task quota's default
The default of 2ms is somewhat arbitrary. Now that we have a lot more
mileage deploying Scylla applications in production it does sound not
only arbitrary, but high.

In particular, it is really hard to achieve 1ms latencies in the face of
CPU-heavy workloads with it.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
Message-Id: <1499354495-27173-1-git-send-email-glauber@scylladb.com>
(cherry picked from commit 780a6e4d2e)
2017-07-12 10:21:35 +03:00
Avi Kivity
a69fb8a8ed Update seastar submodule
* seastar 89cc97c...ff34c42 (6):
  > tls: Wrap all IO in semaphore (Fixes #2575)
  > tests/lowres_clock_test.cc: Declare helper static
  > tests/lowres_clock_test.cc: fix compilation error for older GCC
  > configure.py: verifies boost version
  > pkg-config: Eliminate spaces in include path arguments
  > allow applications to override task-quota-ms

Still tracking seastar master.
2017-07-12 10:20:49 +03:00
Avi Kivity
00b9640b2c Merge "Preserve table schema digest on schema tables migration" from Tomasz
"Currently new nodes calculate digests based on v3 schema mutations,
which are very different from v2 mutations. As a result they will
use schemas with different table_schema_version that the old nodes.
The old nodes will not recognize the version and will try to request
its definition. That will fail, because old nodes don't understand
v3 schema mutations.

To fix this problem, let's preserve the digests during migration,
so that they're the same on new and old nodes. This will allow
requests to proceed as usual.

This does not solve the problem of schema being changed during
the rolling upgrade. This is not allowed, as it would bring the
same problem back.

Fixes #2549."

* tag 'tgrabiec/use-consistent-schema-table-digests-v2' of github.com:cloudius-systems/seastar-dev:
  tests: Add test for concurrent column addition
  legacy_schema_migrator: Set digest to one compatible with the old nodes
  schema_tables: Persist table_schema_version
  schema_tables: Introduce system_schema.scylla_tables
  schema_tables: Simplify read_table_mutations()
  schema_tables: Resurrect v2 read_table_mutations()
  system_keyspace: Forward-declare legacy schemas
  legacy_schema_migrator: Take storage_proxy as dependency

(cherry picked from commit a397889c81)
2017-07-11 17:23:21 +03:00
Gleb Natapov
59d608f77f consistency_level: report less live endpoints in Unavailable exception if there are pending nodes
DowngradingConsistencyRetryPolicy uses live replicas count from
Unavailable exception to adjust CL for retry, but when there are pending
nodes CL is increased internally by a coordinator and that may prevent
retried query from succeeding. Adjust live replica count in case of
pending node presence so that retried query will be able to proceed.

Fixes #2535

Message-Id: <20170710085238.GY2324@scylladb.com>
(cherry picked from commit 739dd878e3)
2017-07-11 17:16:46 +03:00
Botond Dénes
1717922219 Fix crash in the out-of order restrictions error msg composition
Use name of the existing preceeding column with restriction
(last_column) instead of assuming that the column right after the
current column already has restrictions.
This will yield an error message that is different from that of
Cassandra, albeit still a correct one.

Fixes #2421

Signed-off-by: Botond Dénes <bdenes@scylladb.com>
Message-Id: <40335768a2c8bd6c911b881c27e9ea55745c442e.1499781685.git.bdenes@scylladb.com>
(cherry picked from commit 33bc62a9cf)
2017-07-11 17:15:45 +03:00
Paweł Dziepak
7cd4bb0c4a transport: send correct type id for counter columns
CQL reply may contain metadata that describes columns present in the
response including the information about their type.

However, Scylla incorrectly reports counter types as bigint. The
serialised format of counters and bigint is exactly the same, which
could explain why the problem hasn't been noticed earlier but it is a
bug nevertheless.

Fixes #2569.
Message-Id: <20170711130520.27603-1-pdziepak@scylladb.com>

(cherry picked from commit 5aa523aaf9)
2017-07-11 16:37:24 +03:00
Tomasz Grabiec
588ae935e7 legacy_schema_migrator: Use separate joinpoint instance for each table
Otherwise we may deadlock, as explained in commit 5e8f0efc8:

Table drop starts with creating a snapshot on all shards. All shards
must use the same snapshot timestamp which, among other things, is
part of the snapshot name. The timestamp is generated using supplied
timestamp generating function (joinpoint object). The joinpoint object
will wait for all shards to arrive and then generate and return the
timestamp.

However, we drop tables in parallel, using the same joinpoint
instance. So joinpoint may be contacted by snapshotting shards of
tables A and B concurrently, generating timestamp t1 for some shards
of table A and some shards of table B. Later the remaining shards of
table A will get a different timestamp. As a result, different shards
may use different snapshot names for the same table. The snapshot
creation will never complete because the sealing fiber waits for all
shards to signal it, on the same name.
Message-Id: <1499762663-21967-1-git-send-email-tgrabiec@scylladb.com>

(cherry picked from commit 310d2a54d2)
2017-07-11 12:31:21 +03:00
Avi Kivity
c292e86b3c sstables: fix use-after-free in read_simple()
`r` is moved-from, and later captured in a different lambda. The compiler may
choose to move and perform the other capture later, resulting in a use-after-free.

Fix by copying `r` instead of moving it.

Discovered by sstable_test in debug mode.
Message-Id: <20170702082546.20570-1-avi@scylladb.com>

(cherry picked from commit 07b8adce0e)
2017-07-10 15:32:57 +03:00
Asias He
3dc0d734b0 repair: Do not store the failed ranges
The number of failed ranges can be large so it can consume a lot of memory.
We already logged the failed ranges in the log. No need to storge them
in memory.

Message-Id: <7a70c4732667c5c3a69211785e8efff0c222fc28.1498809367.git.asias@scylladb.com>
(cherry picked from commit b2a2fbcf73)
2017-07-10 14:37:47 +03:00
Takuya ASADA
2d612022ba dist/common/scripts/scylla_cpuscaling_setup: skip configuration when cpufreq driver doesn't loaded
Configuring cpufreq service on VMs/IaaS causes an error because it doesn't supported cpufreq.
To prevent causing error, skip whole configuration when the driver not loaded.

Fixes #2051

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1498809504-27029-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 1c35549932)
2017-07-10 14:08:54 +03:00
Nadav Har'El
5f6100c0aa repair: further limit parallelism of checksum calculation
Repair today has a semaphore limiting the number of ongoing checksum
comparisons running in parallel (on one shard) to 100. We needed this
number to be fairly high, because a "checksum comparison" can involve
high latency operations - namely, sending an RPC request to another node
in a remote DC and waiting for it to calculate a checksum there, and while
waiting for a response we need to proceed calculating checksums in parallel.

But as a consequence, in the current code, we can end up with as many as
100 fibers all at the same stage of reading partitions to checksum from
sstables. This requires tons of memory, to hold at least 128K of buffer
(even more with read-ahead) for each of these fibers, plus partition data
for each. But doing 100 reads in parallel is pointless - one (or very few)
should be enough.

So this patch adds another semaphore to limit the number of checksum
*calculations* (including the read and checksum calculation) on each shard
to just 2. There may still be 100 ongoing checksum *comparisons*, in
other stages of the comparisons (sending the checksum requests to other
and waiting for them to return), but only 2 will ever be in the stage of
reading from disk and checksumming them.

The limit of 2 checksum calculations (per shard) applies on the repair
slave, not just to the master: The slave may receive many checksum
requests in parallel, but will only actually work on 2 at a time.

Because the parallelism=100 now rate-limits operations which use very little
memory, in the future we can safely increase it even more, to support
situations where the disk is very fast but the link between nodes has
very high latency.

Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Message-Id: <20170703151329.25716-1-nyh@scylladb.com>
(cherry picked from commit d177ec05cb)
2017-07-10 14:08:28 +03:00
Avi Kivity
d475a44b01 Merge "Silence schema pull errors during upgrade from 1.7 to 2.0" from Tomasz
"Old and new nodes will advertise different schema version because
of different format of schema tables. This will result in attempts
to sync the schema by each of the node.

Currently this will result in scary error messages in logs about
sync failing due to not being able to find schema of given version.
It's benign, but may scare users. It the future incompatibilities
could result in more subtle errors. Better to inhibit it completely."

* 'tgrabiec/fix-schema-pull-errors-during-upgrade' of github.com:cloudius-systems/seastar-dev:
  migration_manager: Give empty response to schema pulls from incompatible nodes
  migration_manager: Don't pull schema from incompatible nodes
  service: Advertise schema tables format version through gossip

(cherry picked from commit 91221e020b)
2017-07-10 14:04:41 +03:00
Pekka Enberg
e02d4935ee idl: Fix frozen_schema version numbers
The IDL changes will appear in 2.0 so fix up the version numbers.

Message-Id: <1499680669-6757-1-git-send-email-penberg@scylladb.com>
(cherry picked from commit 8112d7c5c0)
2017-07-10 14:02:37 +03:00
Botond Dénes
25f8d365b5 Add text(sstring) version of count, max and min functions
Fixes #2459

Signed-off-by: Botond Dénes <bdenes@scylladb.com>
Message-Id: <b6abb97f21c0caea8e36c7590b92a12d148195db.1499666251.git.bdenes@scylladb.com>
(cherry picked from commit 66cbc45321)
2017-07-10 12:48:29 +03:00
Tomasz Grabiec
de7cb7bfa4 tests: commitlog: Check there are no segments left on disk after clean shutdown
Reproduces #2550.

Message-Id: <1499358825-17855-2-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 72e01b7fe8)
2017-07-09 19:25:44 +03:00
Tomasz Grabiec
b8eb4ed9cd commitlog: Discard active but unused segments on shutdown
So that they are not left on disk even though we did a clean shutdown.

First part of the fix is to ensure that closed segments are recognized
as not allocating (_closed flag). Not doing this prevents them from
being collected by discard_unused_segments(). Second part is to
actually call discard_unused_segments() on shutdown after all segments
were shut down, so that those whose position are cleared can be
removed.

Fixes #2550.

Message-Id: <1499358825-17855-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 6555a2f50b)
2017-07-09 19:25:42 +03:00
Tomasz Grabiec
fcc05e8ae9 legacy_schema_migrator: Drop tables instead of truncate()+remove()
It achieves similar effect, but is safer than non-standard remove()
path. The latter was missing unregistration from compaction manager.

Fixes 2554.

Message-Id: <1499447165-30253-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit d33d29ad95)
2017-07-09 18:36:56 +03:00
Botond Dénes
05e2ac80af cql3: Add K_FROZEN and K_TUPLE to basic_unreserved_keyword
To allow the non-reserved keywords "frozen" and "tuple" to be used as
column names without double-quotes.

Fixes #2507

Signed-off-by: Botond Dénes <bdenes@scylladb.com>
Message-Id: <9ae17390662aca90c14ae695c9b4a39531c6cde6.1499329781.git.bdenes@scylladb.com>
(cherry picked from commit c4277d6774)
2017-07-06 18:20:22 +03:00
Avi Kivity
8fa1add26d Update seastar submodule
* seastar 0ab7ae5...89cc97c (4):
  > future-utils: fix do_for_each exception reporting
  > core/thread: Fix unwind information for seastar threads
  > build: export full cflags in pkgconfig file
  > configure: Avoid putting tmp file on /tmp

Still tracking seastar master.
2017-07-06 17:31:06 +03:00
Takuya ASADA
c0a2ca96dd dist/common/scripts/scylla_raid_setup: prevent renaming MDRAID device after reboot
On Debian variants, mdadm.conf should placed at /etc/mdadm instead of /etc.
Also it seems we need update-initramfs to fix renaming issue.

Fixes #2502

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1499179912-14125-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 71624d7919)
2017-07-04 18:07:33 +03:00
Avi Kivity
c9ed522fa8 Merge "Adjust row cache metrics for row granularity" from Tomasz
* tag 'tgrabiec/row-cache-metrics-v2' of github.com:cloudius-systems/seastar-dev:
  row_cache: Switch _stats.hits/misses to row granularity
  row_cache: Rename num_entries() to partitions() for clarity
  row_cache: Track mispopulations also at row level
  row_cache: Track row insertions
  row_cache: Track row hits and misses
  row_cache: Make mispopulation counter also apply for continuity information
  row_cache: Add partition_ prefix to current counters
  misc_services: Switch to using reads_with[_no]_misses counters
  row_cache: Add metrics for operations on underlying reader
  row_cache: Add reader-related metrics
  row_cache: Remove dead code

(cherry picked from commit b1a0e37fcb)
2017-07-04 15:21:00 +03:00
Tomasz Grabiec
9078433a7f row_cache: Restore update of concurrent_misses_same_key
It was lost in action in 6f6575f456.

Message-Id: <1499168837-5072-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit e720b317c9)
2017-07-04 14:51:19 +03:00
Avi Kivity
7893a3aad2 Merge "Use selective_token_range_sharder in repair" from Asias
"This series introduces selective_token_range_sharder and uses it in repair to
generate dht::token_range belongs to a specific shard."

* tag 'asias/repair-selective_token_range_sharder-v3' of github.com:cloudius-systems/seastar-dev:
  repair: Use selective_token_range_sharder
  tests: Add test_selective_token_range_sharder
  dht: Add selective_token_range_sharder

(cherry picked from commit 66e56511d6)
2017-07-04 14:18:08 +03:00
Nadav Har'El
e467eef58d Fix test to use non-wrapping range
The test put a wrapping range into a non-wrapping range variable.
This was harmless at the time this test was written, but newer code
may not be as forgiving so better use a non-wrapping range as intended.

Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Message-Id: <20170704103128.29689-1-nyh@scylladb.com>
(cherry picked from commit d95f908586)
2017-07-04 14:18:01 +03:00
Tomasz Grabiec
19a07143eb row_cache: Drop not very useful prefixes from metric names
This drops "total_opertaions_" and "objects_" prefixes. There is no
convention of adding them in other parts of the system, and they don't
add much value.

Fixes scylladb/scylla-grafana-monitoring#169.

Message-Id: <1499160342-25865-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 1d6fec0755)
2017-07-04 13:37:24 +03:00
Raphael S. Carvalho
a619b978c4 database: fix potential use-after-free in sstable cleanup
when do_for_each is in its last iteration and with_semaphore defers
because there's an ongoing cleanup, sstable object will be used after
freed because it was taken by ref and the container it lives in was
destroyed prematurely.

Let's fix it with a do_with, also making code nicer.

Fixes #2537.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20170630035324.19881-1-raphaelsc@scylladb.com>
(cherry picked from commit b9d0645199)
2017-07-03 12:49:13 +03:00
Gleb Natapov
2c66b40a69 main: wait for wait_for_gossip_to_settle() to complete during boot
Boot should not continue until a future returned by
wait_for_gossip_to_settle() is resolved.  Commit 991ec4a16 mistakenly
broke that, so restore it back. Also fix calls for supervisor::notify()
to be in the right places.

Message-Id: <20170702082355.GQ14563@scylladb.com>
(cherry picked from commit d23111312f)
2017-07-02 11:33:04 +03:00
Tomasz Grabiec
079844a51d row_cache: Fix compilation errors with gcc 5
Message-Id: <1498741526-27055-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 97005825bf)
2017-06-29 16:35:02 +03:00
Avi Kivity
ea59e1fbd6 Update ami submodule
* dist/ami/files/scylla-ami f10db69...5dfe42f (1):
  > don't fetch perf from amazon repo

(cherry picked from commit 1317c4a03e)
2017-06-29 09:39:29 +03:00
Tomasz Grabiec
089b58ddfe row_cache: Use continuity information to decide whether to populate
If cache is missing given key, but the range is marked as continuous,
it means sstables don't have that entry and we can insert it without
asking the presence checker (bloom filter based). The latter is more
expensive and gives false positives. So this improves update
performance and hit ratio.

Another positive effect is that we don't have to clear continuity now.

Fixes #1999.

Message-Id: <1498643043-21117-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 786e75dbf7)
2017-06-28 13:33:34 +03:00
Tomasz Grabiec
d76e9e4026 lsa: Fix performance regression in eviction and compact_on_idle
Region comparator, used by the two, calls region_impl::min_occupancy(),
which calls log_histogram::largest(). The latter is O(N) in terms of
the number of segments, and is supposed to be used only in tests.
We should call one_of_largest() instead, which is O(1).

This caused compact_on_idle() to take more CPU as the number of
segments grew (even when there was nothing to compact). Eviction
would see the same kind of slow down as well.

Introduced in 11b5076b3c.

Message-Id: <1498641973-20054-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 3489c68a68)
2017-06-28 12:33:11 +03:00
Glauber Costa
7709b885c4 disable defragment-memory-on-idle-by-default
It's been linked with various performance issues, either by causing
them or making them worse. One example is #1634, and also recently
I have investigated continuous performance degradation that was also
linked to defrag on idle activity.

Until we can figure out how to reduce its impact, we should disable it.

Signed-off-by: Glauber Costa <glauber@glauber.scylladb>
Message-Id: <20170627201109.10775-1-glauber@scylladb.com>
(cherry picked from commit f3742d1e38)
2017-06-28 00:21:35 +03:00
Avi Kivity
3de701dbe1 Merge "Fix compilation issues in older environments" from Tomasz
* 'tgrabiec/fix-compilation-issues' of github.com:cloudius-systems/seastar-dev:
  tests: streamed_mutation_test: Avoid using boost::size() on row ranges
  tests: row_cache: Remove unused method

(cherry picked from commit ff7be8241f)
2017-06-27 16:31:42 +03:00
Shlomi Livne
9912b7d1eb release: prepare for 2.0-rc0 2017-06-27 12:37:59 +03:00
5777 changed files with 82943 additions and 262774 deletions

View File

@@ -1,4 +0,0 @@
.git
build
seastar/build
testlog

View File

@@ -1,9 +1,3 @@
This is Scylla's bug tracker, to be used for reporting bugs only.
If you have a question about Scylla, and not a bug, please ask it in
our mailing-list at scylladb-dev@googlegroups.com or in our slack channel.
- [] I have read the disclaimer above, and I am reporting a suspected malfunction in Scylla.
*Installation details*
Scylla version (or git commit hash):
Cluster size:

15
.gitignore vendored
View File

@@ -9,18 +9,3 @@ dist/ami/files/*.rpm
dist/ami/variables.json
dist/ami/scylla_deploy.sh
*.pyc
Cql.tokens
.kdev4
*.kdev4
CMakeLists.txt.user
.cache
.tox
*.egg-info
__pycache__CMakeLists.txt.user
.gdbinit
resources
.pytest_cache
/expressions.tokens
tags
testlog/*
test/*/*.reject

15
.gitmodules vendored
View File

@@ -6,15 +6,6 @@
path = swagger-ui
url = ../scylla-swagger-ui
ignore = dirty
[submodule "libdeflate"]
path = libdeflate
url = ../libdeflate
[submodule "abseil"]
path = abseil
url = ../abseil-cpp
[submodule "scylla-jmx"]
path = scylla-jmx
url = ../scylla-jmx
[submodule "scylla-tools"]
path = scylla-tools
url = ../scylla-tools-java
[submodule "dist/ami/files/scylla-ami"]
path = dist/ami/files/scylla-ami
url = ../scylla-ami

View File

@@ -5,24 +5,12 @@
cmake_minimum_required(VERSION 3.7)
project(scylla)
if(NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
message(STATUS "Setting build type to 'Release' as none was specified.")
set(CMAKE_BUILD_TYPE "Release" CACHE
STRING "Choose the type of build." FORCE)
# Set the possible values of build type for cmake-gui
set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS
"Debug" "Release" "Dev" "Sanitize")
if (NOT DEFINED ENV{CLION_IDE})
message(FATAL_ERROR "This CMakeLists.txt file is only valid for use in CLion")
endif()
if(CMAKE_BUILD_TYPE)
string(TOLOWER "${CMAKE_BUILD_TYPE}" BUILD_TYPE)
else()
set(BUILD_TYPE "release")
endif()
if (NOT DEFINED FOR_IDE AND NOT DEFINED ENV{FOR_IDE} AND NOT DEFINED ENV{CLION_IDE})
message(FATAL_ERROR "This CMakeLists.txt file is only valid for use in IDEs, please define FOR_IDE to acknowledge this.")
endif()
# Default value. A more accurate list is populated through `pkg-config` below if `seastar.pc` is available.
set(SEASTAR_INCLUDE_DIRS "seastar")
# These paths are always available, since they're included in the repository. Additional DPDK headers are placed while
# Seastar is built, and are captured in `SEASTAR_INCLUDE_DIRS` through parsing the Seastar pkg-config file (below).
@@ -34,14 +22,9 @@ set(SEASTAR_DPDK_INCLUDE_DIRS
find_package(PkgConfig REQUIRED)
set(ENV{PKG_CONFIG_PATH} "${CMAKE_SOURCE_DIR}/build/${BUILD_TYPE}/seastar:$ENV{PKG_CONFIG_PATH}")
set(ENV{PKG_CONFIG_PATH} "${CMAKE_SOURCE_DIR}/seastar/build/release:$ENV{PKG_CONFIG_PATH}")
pkg_check_modules(SEASTAR seastar)
if(NOT SEASTAR_INCLUDE_DIRS)
# Default value. A more accurate list is populated through `pkg-config` below if `seastar.pc` is available.
set(SEASTAR_INCLUDE_DIRS "seastar/include")
endif()
find_package(Boost COMPONENTS filesystem program_options system thread)
##
@@ -87,7 +70,7 @@ scan_scylla_source_directories(
seastar/json
seastar/net
seastar/rpc
seastar/testing
seastar/tests
seastar/util)
scan_scylla_source_directories(
@@ -114,7 +97,7 @@ scan_scylla_source_directories(
service
sstables
streaming
test
tests
thrift
tracing
transport
@@ -123,7 +106,7 @@ scan_scylla_source_directories(
scan_scylla_source_directories(
VAR SCYLLA_GEN_SOURCE_FILES
RECURSIVE
PATHS build/${BUILD_TYPE}/gen)
PATHS build/release/gen)
set(SCYLLA_SOURCE_FILES
${SCYLLA_ROOT_SOURCE_FILES}
@@ -134,11 +117,15 @@ add_executable(scylla
${SEASTAR_SOURCE_FILES}
${SCYLLA_SOURCE_FILES})
# Note that since CLion does not undestand GCC6 concepts, we always disable them (even if users configure otherwise).
# CLion seems to have trouble with `-U` (macro undefinition), so we do it this way instead.
list(REMOVE_ITEM SEASTAR_CFLAGS "-DHAVE_GCC6_CONCEPTS")
# If the Seastar pkg-config information is available, append to the default flags.
#
# For ease of browsing the source code, we always pretend that DPDK is enabled.
target_compile_options(scylla PUBLIC
-std=gnu++20
-std=gnu++14
-DHAVE_DPDK
-DHAVE_HWLOC
"${SEASTAR_CFLAGS}")
@@ -150,6 +137,4 @@ target_include_directories(scylla PUBLIC
${SEASTAR_DPDK_INCLUDE_DIRS}
${SEASTAR_INCLUDE_DIRS}
${Boost_INCLUDE_DIRS}
xxhash
libdeflate
build/${BUILD_TYPE}/gen)
build/release/gen)

View File

@@ -1,6 +1,6 @@
# Asking questions or requesting help
Use the [ScyllaDB user mailing list](https://groups.google.com/forum/#!forum/scylladb-users) or the [Slack workspace](http://slack.scylladb.com) for general questions and help.
Use the [ScyllaDB user mailing list](https://groups.google.com/forum/#!forum/scylladb-users) for general questions and help.
# Reporting an issue
@@ -8,4 +8,4 @@ Please use the [Issue Tracker](https://github.com/scylladb/scylla/issues/) to re
# Contributing Code to Scylla
To contribute code to Scylla, you need to sign the [Contributor License Agreement](https://www.scylladb.com/open-source/contributor-agreement/) and send your changes as [patches](https://github.com/scylladb/scylla/wiki/Formatting-and-sending-patches) to the [mailing list](https://groups.google.com/forum/#!forum/scylladb-dev). We don't accept pull requests on GitHub.
To contribute code to Scylla, you need to sign the [Contributor License Agreement](http://www.scylladb.com/opensource/cla/) and send your changes as [patches](https://github.com/scylladb/scylla/wiki/Formatting-and-sending-patches) to the [mailing list](https://groups.google.com/forum/#!forum/scylladb-dev). We don't accept pull requests on GitHub.

View File

@@ -1,372 +0,0 @@
# Guidelines for developing Scylla
This document is intended to help developers and contributors to Scylla get started. The first part consists of general guidelines that make no assumptions about a development environment or tooling. The second part describes a particular environment and work-flow for exemplary purposes.
## Overview
This section covers some high-level information about the Scylla source code and work-flow.
### Getting the source code
Scylla uses [Git submodules](https://git-scm.com/book/en/v2/Git-Tools-Submodules) to manage its dependency on Seastar and other tools. Be sure that all submodules are correctly initialized when cloning the project:
```bash
$ git clone https://github.com/scylladb/scylla
$ cd scylla
$ git submodule update --init --recursive
```
### Dependencies
Scylla is fairly fussy about its build environment, requiring a very recent
version of the C++20 compiler and numerous tools and libraries to build.
Run `./install-dependencies.sh` (as root) to use your Linux distributions's
package manager to install the appropriate packages on your build machine.
However, this will only work on very recent distributions. For example,
currently Fedora users must upgrade to Fedora 32 otherwise the C++ compiler
will be too old, and not support the new C++20 standard that Scylla uses.
Alternatively, to avoid having to upgrade your build machine or install
various packages on it, we provide another option - the **frozen toolchain**.
This is a script, `./tools/toolchain/dbuild`, that can execute build or run
commands inside a Docker image that contains exactly the right build tools and
libraries. The `dbuild` technique is useful for beginners, but is also the way
in which ScyllaDB produces official releases, so it is highly recommended.
To use `dbuild`, you simply prefix any build or run command with it. Building
and running Scylla becomes as easy as:
```bash
$ ./tools/toolchain/dbuild ./configure.py
$ ./tools/toolchain/dbuild ninja build/release/scylla
$ ./tools/toolchain/dbuild ./build/release/scylla --developer-mode 1
```
### Build system
**Note**: Compiling Scylla requires, conservatively, 2 GB of memory per native
thread, and up to 3 GB per native thread while linking. GCC >= 10 is
required.
Scylla is built with [Ninja](https://ninja-build.org/), a low-level rule-based system. A Python script, `configure.py`, generates a Ninja file (`build.ninja`) based on configuration options.
To build for the first time:
```bash
$ ./configure.py
$ ninja-build
```
Afterwards, it is sufficient to just execute Ninja.
The full suite of options for project configuration is available via
```bash
$ ./configure.py --help
```
The most important option is:
- `--enable-dpdk`: [DPDK](http://dpdk.org/) is a set of libraries and drivers for fast packet processing. During development, it's not necessary to enable support even if it is supported by your platform.
Source files and build targets are tracked manually in `configure.py`, so the script needs to be updated when new files or targets are added or removed.
To save time -- for instance, to avoid compiling all unit tests -- you can also specify specific targets to Ninja. For example,
```bash
$ ninja-build build/release/tests/schema_change_test
$ ninja-build build/release/service/storage_proxy.o
```
You can also specify a single mode. For example
```bash
$ ninja-build release
```
Will build everytihng in release mode. The valid modes are
* Debug: Enables [AddressSanitizer](https://github.com/google/sanitizers/wiki/AddressSanitizer)
and other sanity checks. It has no optimizations, which allows for debugging with tools like
GDB. Debugging builds are generally slower and generate much larger object files than release builds.
* Release: Fewer checks and more optimizations. It still has debug info.
* Dev: No optimizations or debug info. The objective is to compile and link as fast as possible.
This is useful for the first iterations of a patch.
Note that by default unit tests binaries are stripped so they can't be used with gdb or seastar-addr2line.
To include debug information in the unit test binary, build the test binary with a `_g` suffix. For example,
```bash
$ ninja-build build/release/tests/schema_change_test_g
```
### Unit testing
Unit tests live in the `/tests` directory. Like with application source files, test sources and executables are specified manually in `configure.py` and need to be updated when changes are made.
A test target can be any executable. A non-zero return code indicates test failure.
Most tests in the Scylla repository are built using the [Boost.Test](http://www.boost.org/doc/libs/1_64_0/libs/test/doc/html/index.html) library. Utilities for writing tests with Seastar futures are also included.
Run all tests through the test execution wrapper with
```bash
$ ./test.py --mode={debug,release}
```
The `--name` argument can be specified to run a particular test.
Alternatively, you can execute the test executable directly. For example,
```bash
$ build/release/tests/row_cache_test -- -c1 -m1G
```
The `-c1 -m1G` arguments limit this Seastar-based test to a single system thread and 1 GB of memory.
### Preparing patches
All changes to Scylla are submitted as patches to the public [mailing list](mailto:scylladb-dev@googlegroups.com). Once a patch is approved by one of the maintainers of the project, it is committed to the maintainers' copy of the repository at https://github.com/scylladb/scylla.
Detailed instructions for formatting patches for the mailing list and advice on preparing good patches are available at the [ScyllaDB website](http://docs.scylladb.com/contribute/). There are also some guidelines that can help you make the patch review process smoother:
1. Before generating patches, make sure your Git configuration points to `.gitorderfile`. You can do it by running
```bash
$ git config diff.orderfile .gitorderfile
```
2. If you are sending more than a single patch, push your changes into a new branch of your fork of Scylla on GitHub and add a URL pointing to this branch to your cover letter.
3. If you are sending a new revision of an earlier patchset, add a brief summary of changes in this version, for example:
```
In v3:
- declared move constructor and move assignment operator as noexcept
- used std::variant instead of a union
...
```
4. Add information about the tests run with this fix. It can look like
```
"Tests: unit ({mode}), dtest ({smp})"
```
The usual is "Tests: unit (dev)", although running debug tests is encouraged.
5. When answering review comments, prefer inline quotes as they make it easier to track the conversation across multiple e-mails.
6. The Linux kernel's [Submitting Patches](https://www.kernel.org/doc/html/v4.19/process/submitting-patches.html) document offers excellent advice on how to prepare patches and patchsets for review. Since the Scylla development process is derived from the kernel's, almost all of the advice there is directly applicable.
### Finding a person to review and merge your patches
You can use the `scripts/find-maintainer` script to find a subsystem maintainer and/or reviewer for your patches. The script accepts a filename in the git source tree as an argument and outputs a list of subsystems the file belongs to and their respective maintainers and reviewers. For example, if you changed the `cql3/statements/create_view_statement.hh` file, run the script as follows:
```bash
$ ./scripts/find-maintainer cql3/statements/create_view_statement.hh
```
and you will get output like this:
```
CQL QUERY LANGUAGE
Tomasz Grabiec <tgrabiec@scylladb.com> [maintainer]
Pekka Enberg <penberg@scylladb.com> [maintainer]
MATERIALIZED VIEWS
Pekka Enberg <penberg@scylladb.com> [maintainer]
Duarte Nunes <duarte@scylladb.com> [maintainer]
Nadav Har'El <nyh@scylladb.com> [reviewer]
Duarte Nunes <duarte@scylladb.com> [reviewer]
```
### Running Scylla
Once Scylla has been compiled, executing the (`debug` or `release`) target will start a running instance in the foreground:
```bash
$ build/release/scylla
```
The `scylla` executable requires a configuration file, `scylla.yaml`. By default, this is read from `$SCYLLA_HOME/conf/scylla.yaml`. A good starting point for development is located in the repository at `/conf/scylla.yaml`.
For development, a directory at `$HOME/scylla` can be used for all Scylla-related files:
```bash
$ mkdir -p $HOME/scylla $HOME/scylla/conf
$ cp conf/scylla.yaml $HOME/scylla/conf/scylla.yaml
$ # Edit configuration options as appropriate
$ SCYLLA_HOME=$HOME/scylla build/release/scylla
```
The `scylla.yaml` file in the repository by default writes all database data to `/var/lib/scylla`, which likely requires root access. Change the `data_file_directories` and `commitlog_directory` fields as appropriate.
Scylla has a number of requirements for the file-system and operating system to operate ideally and at peak performance. However, during development, these requirements can be relaxed with the `--developer-mode` flag.
Additionally, when running on under-powered platforms like portable laptops, the `--overprovisined` flag is useful.
On a development machine, one might run Scylla as
```bash
$ SCYLLA_HOME=$HOME/scylla build/release/scylla --overprovisioned --developer-mode=yes
```
To interact with scylla it is recommended to build our versions of
cqlsh and nodetool. They are available at
https://github.com/scylladb/scylla-tools-java and can be built with
```bash
$ sudo ./install-dependencies.sh
$ ant jar
```
cqlsh should work out of the box, but nodetool depends on a running
scylla-jmx (https://github.com/scylladb/scylla-jmx). It can be build
with
```bash
$ mvn package
```
and must be started with
```bash
$ ./scripts/scylla-jmx
```
### Branches and tags
Multiple release branches are maintained on the Git repository at https://github.com/scylladb/scylla. Release 1.5, for instance, is tracked on the `branch-1.5` branch.
Similarly, tags are used to pin-point precise release versions, including hot-fix versions like 1.5.4. These are named `scylla-1.5.4`, for example.
Most development happens on the `master` branch. Release branches are cut from `master` based on time and/or features. When a patch against `master` fixes a serious issue like a node crash or data loss, it is backported to a particular release branch with `git cherry-pick` by the project maintainers.
## Example: development on Fedora 25
This section describes one possible work-flow for developing Scylla on a Fedora 25 system. It is presented as an example to help you to develop a work-flow and tools that you are comfortable with.
### Preface
This guide will be written from the perspective of a fictitious developer, Taylor Smith.
### Git work-flow
Having two Git remotes is useful:
- A public clone of Seastar (`"public"`)
- A private clone of Seastar (`"private"`) for in-progress work or work that is not yet ready to share
The first step to contributing a change to Scylla is to create a local branch dedicated to it. For example, a feature that fixes a bug in the CQL statement for creating tables could be called `ts/cql_create_table_error/v1`. The branch name is prefaced by the developer's initials and has a suffix indicating that this is the first version. The version suffix is useful when branches are shared publicly and changes are requested on the mailing list. Having a branch for each version of the patch (or patch set) shared publicly makes it easier to reference and compare the history of a change.
Setting the upstream branch of your development branch to `master` is a useful way to track your changes. You can do this with
```bash
$ git branch -u master ts/cql_create_table_error/v1
```
As a patch set is developed, you can periodically push the branch to the private remote to back-up work.
Once the patch set is ready to be reviewed, push the branch to the public remote and prepare an email to the `scylladb-dev` mailing list. Including a link to the branch on your public remote allows for reviewers to quickly test and explore your changes.
### Development environment and source code navigation
Scylla includes a [CMake](https://cmake.org/) file, `CMakeLists.txt`, for use only with development environments (not for building) so that they can properly analyze the source code.
[CLion](https://www.jetbrains.com/clion/) is a commercial IDE offers reasonably good source code navigation and advice for code hygiene, though its C++ parser sometimes makes errors and flags false issues.
Other good options that directly parse CMake files are [KDevelop](https://www.kdevelop.org/) and [QtCreator](https://wiki.qt.io/Qt_Creator).
To use the `CMakeLists.txt` file with these programs, define the `FOR_IDE` CMake variable or shell environmental variable.
[Eclipse](https://eclipse.org/cdt/) is another open-source option. It doesn't natively work with CMake projects, and its C++ parser has many similar issues as CLion.
### Distributed compilation: `distcc` and `ccache`
Scylla's compilations times can be long. Two tools help somewhat:
- [ccache](https://ccache.samba.org/) caches compiled object files on disk and re-uses them when possible
- [distcc](https://github.com/distcc/distcc) distributes compilation jobs to remote machines
A reasonably-powered laptop acts as the coordinator for compilation. A second, more powerful, machine acts as a passive compilation server.
Having a direct wired connection between the machines ensures that object files can be transmitted quickly and limits the overhead of remote compilation.
The coordinator has been assigned the static IP address `10.0.0.1` and the passive compilation machine has been assigned `10.0.0.2`.
On Fedora, installing the `ccache` package places symbolic links for `gcc` and `g++` in the `PATH`. This allows normal compilation to transparently invoke `ccache` for compilation and cache object files on the local file-system.
Next, set `CCACHE_PREFIX` so that `ccache` is responsible for invoking `distcc` as necessary:
```bash
export CCACHE_PREFIX="distcc"
```
On each host, edit `/etc/sysconfig/distccd` to include the allowed coordinators and the total number of jobs that the machine should accept.
This example is for the laptop, which has 2 physical cores (4 logical cores with hyper-threading):
```
OPTIONS="--allow 10.0.0.2 --allow 127.0.0.1 --jobs 4"
```
`10.0.0.2` has 8 physical cores (16 logical cores) and 64 GB of memory.
As a rule-of-thumb, the number of jobs that a machine should be specified to support should be equal to the number of its native threads.
Restart the `distccd` service on all machines.
On the coordinator machine, edit `$HOME/.distcc/hosts` with the available hosts for compilation. Order of the hosts indicates preference.
```
10.0.0.2/16 localhost/2
```
In this example, `10.0.0.2` will be sent up to 16 jobs and the local machine will be sent up to 2. Allowing for two extra threads on the host machine for coordination, we run compilation with `16 + 2 + 2 = 20` jobs in total: `ninja-build -j20`.
When a compilation is in progress, the status of jobs on all remote machines can be visualized in the terminal with `distccmon-text` or graphically as a GTK application with `distccmon-gnome`.
One thing to keep in mind is that linking object files happens on the coordinating machine, which can be a bottleneck. See the next sections speeding up this process.
### Using the `gold` linker
Linking Scylla can be slow. The gold linker can replace GNU ld and often speeds the linking process. On Fedora, you can switch the system linker using
```bash
$ sudo alternatives --config ld
```
### Using split dwarf
With debug info enabled, most of the link time is spent copying and
relocating it. It is possible to leave most of the debug info out of
the link by writing it to a side .dwo file. This is done by passing
`-gsplit-dwarf` to gcc.
Unfortunately just `-gsplit-dwarf` would slow down `gdb` startup. To
avoid that the gold linker can be told to create an index with
`--gdb-index`.
More info at https://gcc.gnu.org/wiki/DebugFission.
Both options can be enable by passing `--split-dwarf` to configure.py.
Note that distcc is *not* compatible with it, but icecream
(https://github.com/icecc/icecream) is.
### Testing changes in Seastar with Scylla
Sometimes Scylla development is closely tied with a feature being developed in Seastar. It can be useful to compile Scylla with a particular check-out of Seastar.
One way to do this it to create a local remote for the Seastar submodule in the Scylla repository:
```bash
$ cd $HOME/src/scylla
$ cd seastar
$ git remote add local /home/tsmith/src/seastar
$ git remote update
$ git checkout -t local/my_local_seastar_branch
```
### Core dump debugging
Slides:
2018.11.20: https://www.slideshare.net/tomekgrabiec/scylla-core-dump-debugging-tools

View File

View File

@@ -1,114 +0,0 @@
M: Maintainer with commit access
R: Reviewer with subsystem expertise
F: Filename, directory, or pattern for the subsystem
---
AUTH
R: Calle Wilund <calle@scylladb.com>
R: Vlad Zolotarov <vladz@scylladb.com>
R: Jesse Haber-Kucharsky <jhaberku@scylladb.com>
F: auth/*
CACHE
M: Tomasz Grabiec <tgrabiec@scylladb.com>
R: Piotr Jastrzebski <piotr@scylladb.com>
F: row_cache*
F: *mutation*
F: tests/mvcc*
COMMITLOG / BATCHLOGa
R: Calle Wilund <calle@scylladb.com>
F: db/commitlog/*
F: db/batch*
COORDINATOR
R: Gleb Natapov <gleb@scylladb.com>
F: service/storage_proxy*
COMPACTION
R: Raphael S. Carvalho <raphaelsc@scylladb.com>
R: Glauber Costa <glauber@scylladb.com>
R: Nadav Har'El <nyh@scylladb.com>
F: sstables/compaction*
CQL TRANSPORT LAYER
M: Pekka Enberg <penberg@scylladb.com>
F: transport/*
CQL QUERY LANGUAGE
M: Tomasz Grabiec <tgrabiec@scylladb.com>
M: Pekka Enberg <penberg@scylladb.com>
F: cql3/*
COUNTERS
F: counters*
F: tests/counter_test*
GOSSIP
M: Tomasz Grabiec <tgrabiec@scylladb.com>
R: Asias He <asias@scylladb.com>
F: gms/*
DOCKER
M: Pekka Enberg <penberg@scylladb.com>
F: dist/docker/*
LSA
M: Tomasz Grabiec <tgrabiec@scylladb.com>
F: utils/logalloc*
MATERIALIZED VIEWS
M: Pekka Enberg <penberg@scylladb.com>
M: Nadav Har'El <nyh@scylladb.com>
F: db/view/*
F: cql3/statements/*view*
PACKAGING
R: Takuya ASADA <syuu@scylladb.com>
F: dist/*
REPAIR
M: Tomasz Grabiec <tgrabiec@scylladb.com>
R: Asias He <asias@scylladb.com>
R: Nadav Har'El <nyh@scylladb.com>
F: repair/*
SCHEMA MANAGEMENT
M: Tomasz Grabiec <tgrabiec@scylladb.com>
M: Pekka Enberg <penberg@scylladb.com>
F: db/schema_tables*
F: db/legacy_schema_migrator*
F: service/migration*
F: schema*
SECONDARY INDEXES
M: Pekka Enberg <penberg@scylladb.com>
M: Nadav Har'El <nyh@scylladb.com>
R: Pekka Enberg <penberg@scylladb.com>
F: db/index/*
F: cql3/statements/*index*
SSTABLES
M: Tomasz Grabiec <tgrabiec@scylladb.com>
R: Raphael S. Carvalho <raphaelsc@scylladb.com>
R: Glauber Costa <glauber@scylladb.com>
R: Nadav Har'El <nyh@scylladb.com>
F: sstables/*
STREAMING
M: Tomasz Grabiec <tgrabiec@scylladb.com>
R: Asias He <asias@scylladb.com>
F: streaming/*
F: service/storage_service.*
ALTERNATOR
M: Nadav Har'El <nyh@scylladb.com>
F: alternator/*
F: alternator-test/*
THE REST
M: Avi Kivity <avi@scylladb.com>
M: Tomasz Grabiec <tgrabiec@scylladb.com>
M: Nadav Har'El <nyh@scylladb.com>
F: *

View File

@@ -1,7 +1,2 @@
This project includes code developed by the Apache Software Foundation (http://www.apache.org/),
especially Apache Cassandra.
It includes files from https://github.com/antonblanchard/crc32-vpmsum (author Anton Blanchard <anton@au.ibm.com>, IBM).
These files are located in utils/arch/powerpc/crc32-vpmsum. Their license may be found in licenses/LICENSE-crc32-vpmsum.TXT.
It includes modified code from https://gitbox.apache.org/repos/asf?p=cassandra-dtest.git (owned by The Apache Software Foundation)

29
README-DPDK.md Normal file
View File

@@ -0,0 +1,29 @@
Seastar and DPDK
================
Seastar uses the Data Plane Development Kit to drive NIC hardware directly. This
provides an enormous performance boost.
To enable DPDK, specify `--enable-dpdk` to `./configure.py`, and `--dpdk-pmd` as a
run-time parameter. This will use the DPDK package provided as a git submodule with the
seastar sources.
To use your own self-compiled DPDK package, follow this procedure:
1. Setup host to compile DPDK:
- Ubuntu
`sudo apt-get install -y build-essential linux-image-extra-$(uname -r)`
2. Prepare a DPDK SDK:
- Download the latest DPDK release: `wget http://dpdk.org/browse/dpdk/snapshot/dpdk-1.8.0.tar.gz`
- Untar it.
- Edit config/common_linuxapp: set CONFIG_RTE_MBUF_REFCNT and CONFIG_RTE_LIBRTE_KNI to 'n'.
- For DPDK 1.7.x: edit config/common_linuxapp:
- Set CONFIG_RTE_LIBRTE_PMD_BOND to 'n'.
- Set CONFIG_RTE_MBUF_SCATTER_GATHER to 'n'.
- Set CONFIG_RTE_LIBRTE_IP_FRAG to 'n'.
- Start the tools/setup.sh script as root.
- Compile a linuxapp target (option 9).
- Install IGB_UIO module (option 11).
- Bind some physical port to IGB_UIO (option 17).
- Configure hugepage mappings (option 14/15).
3. Run a configure.py: `./configure.py --dpdk-target <Path to untared dpdk-1.8.0 above>/x86_64-native-linuxapp-gcc`.

View File

@@ -1,27 +1,29 @@
# Scylla
## Quick-start
## Building Scylla
Scylla is fairly fussy about its build environment, requiring very recent
versions of the C++20 compiler and of many libraries to build. The document
[HACKING.md](HACKING.md) includes detailed information on building and
developing Scylla, but to get Scylla building quickly on (almost) any build
machine, Scylla offers offers a [frozen toolchain](tools/toolchain/README.md),
This is a pre-configured Docker image which includes recent versions of all
the required compilers, libraries and build tools. Using the frozen toolchain
allows you to avoid changing anything in your build machine to meet Scylla's
requirements - you just need to meet the frozen toolchain's prerequisites
(mostly, Docker or Podman being available).
In addition to required packages by Seastar, the following packages are required by Scylla.
Building and running Scylla with the frozen toolchain is as easy as:
```bash
$ ./tools/toolchain/dbuild ./configure.py
$ ./tools/toolchain/dbuild ninja build/release/scylla
$ ./tools/toolchain/dbuild ./build/release/scylla --developer-mode 1
### Submodules
Scylla uses submodules, so make sure you pull the submodules first by doing:
```
git submodule init
git submodule update --init --recursive
```
## Running Scylla
### Building and Running Scylla on Fedora
* Installing required packages:
```
sudo dnf install yaml-cpp-devel lz4-devel zlib-devel snappy-devel jsoncpp-devel thrift-devel antlr3-tool antlr3-C++-devel libasan libubsan gcc-c++ gnutls-devel ninja-build ragel libaio-devel cryptopp-devel xfsprogs-devel numactl-devel hwloc-devel libpciaccess-devel libxml2-devel python3-pyparsing lksctp-tools-devel protobuf-devel protobuf-compiler systemd-devel libunwind-devel
```
* Build Scylla
```
./configure.py --mode=release --with=scylla --disable-xen
ninja-build build/release/scylla -j2 # you can use more cpus if you have tons of RAM
```
* Run Scylla
```
@@ -29,10 +31,10 @@ $ ./tools/toolchain/dbuild ./build/release/scylla --developer-mode 1
```
* run Scylla with one CPU and ./tmp as work directory
* run Scylla with one CPU and ./tmp as data directory
```
./build/release/scylla --workdir tmp --smp 1
./build/release/scylla --datadir tmp --commitlog-directory tmp --smp 1
```
* For more run options:
@@ -40,49 +42,41 @@ $ ./tools/toolchain/dbuild ./build/release/scylla --developer-mode 1
./build/release/scylla --help
```
## Testing
## Building Fedora RPM
See [test.py manual](docs/testing.md).
As a pre-requisite, you need to install [Mock](https://fedoraproject.org/wiki/Mock) on your machine:
## Scylla APIs and compatibility
By default, Scylla is compatible with Apache Cassandra and its APIs - CQL and
Thrift. There is also experimental support for the API of Amazon DynamoDB,
but being experimental it needs to be explicitly enabled to be used. For more
information on how to enable the experimental DynamoDB compatibility in Scylla,
and the current limitations of this feature, see
[Alternator](docs/alternator/alternator.md) and
[Getting started with Alternator](docs/alternator/getting-started.md).
```
# Install mock:
sudo yum install mock
## Documentation
# Add user to the "mock" group:
usermod -a -G mock $USER && newgrp mock
```
Documentation can be found in [./docs](./docs) and on the
[wiki](https://github.com/scylladb/scylla/wiki). There is currently no clear
definition of what goes where, so when looking for something be sure to check
both.
Seastar documentation can be found [here](http://docs.seastar.io/master/index.html).
User documentation can be found [here](https://docs.scylladb.com/).
Then, to build an RPM, run:
## Training
```
./dist/redhat/build_rpm.sh
```
Training material and online courses can be found at [Scylla University](https://university.scylladb.com/).
The courses are free, self-paced and include hands-on examples. They cover a variety of topics including Scylla data modeling,
administration, architecture, basic NoSQL concepts, using drivers for application development, Scylla setup, failover, compactions,
multi-datacenters and how Scylla integrates with third-party applications.
The built RPM is stored in ``/var/lib/mock/<configuration>/result`` directory.
For example, on Fedora 21 mock reports the following:
## Building a CentOS-based Docker image
```
INFO: Done(scylla-server-0.00-1.fc21.src.rpm) Config(default) 20 minutes 7 seconds
INFO: Results and/or logs in: /var/lib/mock/fedora-21-x86_64/result
```
## Building Fedora-based Docker image
Build a Docker image with:
```
cd dist/docker/redhat
cd dist/docker
docker build -t <image-name> .
```
This build is based on executables downloaded from downloads.scylladb.com,
**not** on the executables built in this source directory. See further
instructions in dist/docker/redhat/README.md to build a docker image from
your own executables.
Run the image with:
```
@@ -91,5 +85,4 @@ docker run -p $(hostname -i):9042:9042 -i -t <image name>
## Contributing to Scylla
[Hacking howto](HACKING.md)
[Guidelines for contributing](CONTRIBUTING.md)

View File

@@ -1,7 +1,6 @@
#!/bin/sh
PRODUCT=scylla
VERSION=4.2.4
VERSION=2.0.4
if test -f version
then
@@ -19,16 +18,7 @@ else
SCYLLA_RELEASE=$SCYLLA_BUILD.$DATE.$GIT_COMMIT
fi
if [ -f build/SCYLLA-RELEASE-FILE ]; then
RELEASE_FILE=$(cat build/SCYLLA-RELEASE-FILE)
GIT_COMMIT_FILE=$(cat build/SCYLLA-RELEASE-FILE |cut -d . -f 3)
if [ "$GIT_COMMIT" = "$GIT_COMMIT_FILE" ]; then
exit 0
fi
fi
echo "$SCYLLA_VERSION-$SCYLLA_RELEASE"
mkdir -p build
echo "$SCYLLA_VERSION" > build/SCYLLA-VERSION-FILE
echo "$SCYLLA_RELEASE" > build/SCYLLA-RELEASE-FILE
echo "$PRODUCT" > build/SCYLLA-PRODUCT-FILE

1
abseil

Submodule abseil deleted from 2069dc796a

View File

@@ -1,47 +0,0 @@
/*
* Copyright (C) 2020 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <absl/container/flat_hash_map.h>
#include <seastar/core/sstring.hh>
using namespace seastar;
struct sstring_hash {
using is_transparent = void;
size_t operator()(std::string_view v) const noexcept;
};
struct sstring_eq {
using is_transparent = void;
bool operator()(std::string_view a, std::string_view b) const noexcept {
return a == b;
}
};
template <typename K, typename V, typename... Ts>
struct flat_hash_map : public absl::flat_hash_map<K, V, Ts...> {
};
template <typename V>
struct flat_hash_map<sstring, V>
: public absl::flat_hash_map<sstring, V, sstring_hash, sstring_eq> {};

View File

@@ -1,147 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "alternator/error.hh"
#include "log.hh"
#include <string>
#include <string_view>
#include <gnutls/crypto.h>
#include <seastar/util/defer.hh>
#include "hashers.hh"
#include "bytes.hh"
#include "alternator/auth.hh"
#include <fmt/format.h>
#include "auth/common.hh"
#include "auth/password_authenticator.hh"
#include "auth/roles-metadata.hh"
#include "cql3/query_processor.hh"
#include "cql3/untyped_result_set.hh"
namespace alternator {
static logging::logger alogger("alternator-auth");
static hmac_sha256_digest hmac_sha256(std::string_view key, std::string_view msg) {
hmac_sha256_digest digest;
int ret = gnutls_hmac_fast(GNUTLS_MAC_SHA256, key.data(), key.size(), msg.data(), msg.size(), digest.data());
if (ret) {
throw std::runtime_error(fmt::format("Computing HMAC failed ({}): {}", ret, gnutls_strerror(ret)));
}
return digest;
}
static hmac_sha256_digest get_signature_key(std::string_view key, std::string_view date_stamp, std::string_view region_name, std::string_view service_name) {
auto date = hmac_sha256("AWS4" + std::string(key), date_stamp);
auto region = hmac_sha256(std::string_view(date.data(), date.size()), region_name);
auto service = hmac_sha256(std::string_view(region.data(), region.size()), service_name);
auto signing = hmac_sha256(std::string_view(service.data(), service.size()), "aws4_request");
return signing;
}
static std::string apply_sha256(std::string_view msg) {
sha256_hasher hasher;
hasher.update(msg.data(), msg.size());
return to_hex(hasher.finalize());
}
static std::string format_time_point(db_clock::time_point tp) {
time_t time_point_repr = db_clock::to_time_t(tp);
std::string time_point_str;
time_point_str.resize(17);
::tm time_buf;
// strftime prints the terminating null character as well
std::strftime(time_point_str.data(), time_point_str.size(), "%Y%m%dT%H%M%SZ", ::gmtime_r(&time_point_repr, &time_buf));
time_point_str.resize(16);
return time_point_str;
}
void check_expiry(std::string_view signature_date) {
//FIXME: The default 15min can be changed with X-Amz-Expires header - we should honor it
std::string expiration_str = format_time_point(db_clock::now() - 15min);
std::string validity_str = format_time_point(db_clock::now() + 15min);
if (signature_date < expiration_str) {
throw api_error("InvalidSignatureException",
fmt::format("Signature expired: {} is now earlier than {} (current time - 15 min.)",
signature_date, expiration_str));
}
if (signature_date > validity_str) {
throw api_error("InvalidSignatureException",
fmt::format("Signature not yet current: {} is still later than {} (current time + 15 min.)",
signature_date, validity_str));
}
}
std::string get_signature(std::string_view access_key_id, std::string_view secret_access_key, std::string_view host, std::string_view method,
std::string_view orig_datestamp, std::string_view signed_headers_str, const std::map<std::string_view, std::string_view>& signed_headers_map,
std::string_view body_content, std::string_view region, std::string_view service, std::string_view query_string) {
auto amz_date_it = signed_headers_map.find("x-amz-date");
if (amz_date_it == signed_headers_map.end()) {
throw api_error("InvalidSignatureException", "X-Amz-Date header is mandatory for signature verification");
}
std::string_view amz_date = amz_date_it->second;
check_expiry(amz_date);
std::string_view datestamp = amz_date.substr(0, 8);
if (datestamp != orig_datestamp) {
throw api_error("InvalidSignatureException",
format("X-Amz-Date date does not match the provided datestamp. Expected {}, got {}",
orig_datestamp, datestamp));
}
std::string_view canonical_uri = "/";
std::stringstream canonical_headers;
for (const auto& header : signed_headers_map) {
canonical_headers << fmt::format("{}:{}", header.first, header.second) << '\n';
}
std::string payload_hash = apply_sha256(body_content);
std::string canonical_request = fmt::format("{}\n{}\n{}\n{}\n{}\n{}", method, canonical_uri, query_string, canonical_headers.str(), signed_headers_str, payload_hash);
std::string_view algorithm = "AWS4-HMAC-SHA256";
std::string credential_scope = fmt::format("{}/{}/{}/aws4_request", datestamp, region, service);
std::string string_to_sign = fmt::format("{}\n{}\n{}\n{}", algorithm, amz_date, credential_scope, apply_sha256(canonical_request));
hmac_sha256_digest signing_key = get_signature_key(secret_access_key, datestamp, region, service);
hmac_sha256_digest signature = hmac_sha256(std::string_view(signing_key.data(), signing_key.size()), string_to_sign);
return to_hex(bytes_view(reinterpret_cast<const int8_t*>(signature.data()), signature.size()));
}
future<std::string> get_key_from_roles(cql3::query_processor& qp, std::string username) {
static const sstring query = format("SELECT salted_hash FROM {} WHERE {} = ?",
auth::meta::roles_table::qualified_name(), auth::meta::roles_table::role_col_name);
auto cl = auth::password_authenticator::consistency_for_user(username);
auto& timeout = auth::internal_distributed_timeout_config();
return qp.execute_internal(query, cl, timeout, {sstring(username)}, true).then_wrapped([username = std::move(username)] (future<::shared_ptr<cql3::untyped_result_set>> f) {
auto res = f.get0();
auto salted_hash = std::optional<sstring>();
if (res->empty()) {
throw api_error("UnrecognizedClientException", fmt::format("User not found: {}", username));
}
salted_hash = res->one().get_opt<sstring>("salted_hash");
if (!salted_hash) {
throw api_error("UnrecognizedClientException", fmt::format("No password found for user: {}", username));
}
return make_ready_future<std::string>(*salted_hash);
});
}
}

View File

@@ -1,46 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <string>
#include <string_view>
#include <array>
#include "gc_clock.hh"
#include "utils/loading_cache.hh"
namespace cql3 {
class query_processor;
}
namespace alternator {
using hmac_sha256_digest = std::array<char, 32>;
using key_cache = utils::loading_cache<std::string, std::string>;
std::string get_signature(std::string_view access_key_id, std::string_view secret_access_key, std::string_view host, std::string_view method,
std::string_view orig_datestamp, std::string_view signed_headers_str, const std::map<std::string_view, std::string_view>& signed_headers_map,
std::string_view body_content, std::string_view region, std::string_view service, std::string_view query_string);
future<std::string> get_key_from_roles(cql3::query_processor& qp, std::string username);
}

View File

@@ -1,145 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
// The DynamoAPI dictates that "binary" (a.k.a. "bytes" or "blob") values
// be encoded in the JSON API as base64-encoded strings. This is code to
// convert byte arrays to base64-encoded strings, and back.
#include "base64.hh"
#include <ctype.h>
// Arrays for quickly converting to and from an integer between 0 and 63,
// and the character used in base64 encoding to represent it.
static class base64_chars {
public:
static constexpr const char* to =
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
int8_t from[255];
base64_chars() {
static_assert(strlen(to) == 64);
for (int i = 0; i < 255; i++) {
from[i] = 255; // signal invalid character
}
for (int i = 0; i < 64; i++) {
from[(unsigned) to[i]] = i;
}
}
} base64_chars;
std::string base64_encode(bytes_view in) {
std::string ret;
ret.reserve(((4 * in.size() / 3) + 3) & ~3);
int i = 0;
unsigned char chunk3[3]; // chunk of input
for (auto byte : in) {
chunk3[i++] = byte;
if (i == 3) {
ret += base64_chars.to[ (chunk3[0] & 0xfc) >> 2 ];
ret += base64_chars.to[ ((chunk3[0] & 0x03) << 4) + ((chunk3[1] & 0xf0) >> 4) ];
ret += base64_chars.to[ ((chunk3[1] & 0x0f) << 2) + ((chunk3[2] & 0xc0) >> 6) ];
ret += base64_chars.to[ chunk3[2] & 0x3f ];
i = 0;
}
}
if (i) {
// i can be 1 or 2.
for(int j = i; j < 3; j++)
chunk3[j] = '\0';
ret += base64_chars.to[ ( chunk3[0] & 0xfc) >> 2 ];
ret += base64_chars.to[ ((chunk3[0] & 0x03) << 4) + ((chunk3[1] & 0xf0) >> 4) ];
if (i == 2) {
ret += base64_chars.to[ ((chunk3[1] & 0x0f) << 2) + ((chunk3[2] & 0xc0) >> 6) ];
} else {
ret += '=';
}
ret += '=';
}
return ret;
}
static std::string base64_decode_string(std::string_view in) {
int i = 0;
int8_t chunk4[4]; // chunk of input, each byte converted to 0..63;
std::string ret;
ret.reserve(in.size() * 3 / 4);
for (unsigned char c : in) {
uint8_t dc = base64_chars.from[c];
if (dc == 255) {
// Any unexpected character, include the "=" character usually
// used for padding, signals the end of the decode.
break;
}
chunk4[i++] = dc;
if (i == 4) {
ret += (chunk4[0] << 2) + ((chunk4[1] & 0x30) >> 4);
ret += ((chunk4[1] & 0xf) << 4) + ((chunk4[2] & 0x3c) >> 2);
ret += ((chunk4[2] & 0x3) << 6) + chunk4[3];
i = 0;
}
}
if (i) {
// i can be 2 or 3, meaning 1 or 2 more output characters
if (i>=2)
ret += (chunk4[0] << 2) + ((chunk4[1] & 0x30) >> 4);
if (i==3)
ret += ((chunk4[1] & 0xf) << 4) + ((chunk4[2] & 0x3c) >> 2);
}
return ret;
}
bytes base64_decode(std::string_view in) {
// FIXME: This copy is sad. The problem is we need back "bytes"
// but "bytes" doesn't have efficient append and std::string.
// To fix this we need to use bytes' "uninitialized" feature.
std::string ret = base64_decode_string(in);
return bytes(ret.begin(), ret.end());
}
static size_t base64_padding_len(std::string_view str) {
size_t padding = 0;
padding += (!str.empty() && str.back() == '=');
padding += (str.size() > 1 && *(str.end() - 2) == '=');
return padding;
}
size_t base64_decoded_len(std::string_view str) {
return str.size() / 4 * 3 - base64_padding_len(str);
}
bool base64_begins_with(std::string_view base, std::string_view operand) {
if (base.size() < operand.size() || base.size() % 4 != 0 || operand.size() % 4 != 0) {
return false;
}
if (base64_padding_len(operand) == 0) {
return base.starts_with(operand);
}
const std::string_view unpadded_base_prefix = base.substr(0, operand.size() - 4);
const std::string_view unpadded_operand = operand.substr(0, operand.size() - 4);
if (unpadded_base_prefix != unpadded_operand) {
return false;
}
// Decode and compare last 4 bytes of base64-encoded strings
const std::string base_remainder = base64_decode_string(base.substr(operand.size() - 4, operand.size()));
const std::string operand_remainder = base64_decode_string(operand.substr(operand.size() - 4));
return base_remainder.starts_with(operand_remainder);
}

View File

@@ -1,38 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <string_view>
#include "bytes.hh"
#include "rjson.hh"
std::string base64_encode(bytes_view);
bytes base64_decode(std::string_view);
inline bytes base64_decode(const rjson::value& v) {
return base64_decode(std::string_view(v.GetString(), v.GetStringLength()));
}
size_t base64_decoded_len(std::string_view str);
bool base64_begins_with(std::string_view base, std::string_view operand);

View File

@@ -1,703 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include <list>
#include <map>
#include <string_view>
#include "alternator/conditions.hh"
#include "alternator/error.hh"
#include "cql3/constants.hh"
#include <unordered_map>
#include "rjson.hh"
#include "serialization.hh"
#include "base64.hh"
#include <stdexcept>
#include <boost/algorithm/cxx11/all_of.hpp>
#include <boost/algorithm/cxx11/any_of.hpp>
#include "utils/overloaded_functor.hh"
#include "expressions.hh"
namespace alternator {
static logging::logger clogger("alternator-conditions");
comparison_operator_type get_comparison_operator(const rjson::value& comparison_operator) {
static std::unordered_map<std::string, comparison_operator_type> ops = {
{"EQ", comparison_operator_type::EQ},
{"NE", comparison_operator_type::NE},
{"LE", comparison_operator_type::LE},
{"LT", comparison_operator_type::LT},
{"GE", comparison_operator_type::GE},
{"GT", comparison_operator_type::GT},
{"IN", comparison_operator_type::IN},
{"NULL", comparison_operator_type::IS_NULL},
{"NOT_NULL", comparison_operator_type::NOT_NULL},
{"BETWEEN", comparison_operator_type::BETWEEN},
{"BEGINS_WITH", comparison_operator_type::BEGINS_WITH},
{"CONTAINS", comparison_operator_type::CONTAINS},
{"NOT_CONTAINS", comparison_operator_type::NOT_CONTAINS},
};
if (!comparison_operator.IsString()) {
throw api_error("ValidationException", format("Invalid comparison operator definition {}", rjson::print(comparison_operator)));
}
std::string op = comparison_operator.GetString();
auto it = ops.find(op);
if (it == ops.end()) {
throw api_error("ValidationException", format("Unsupported comparison operator {}", op));
}
return it->second;
}
namespace {
struct size_check {
// True iff size passes this check.
virtual bool operator()(rapidjson::SizeType size) const = 0;
// Check description, such that format("expected array {}", check.what()) is human-readable.
virtual sstring what() const = 0;
};
class exact_size : public size_check {
rapidjson::SizeType _expected;
public:
explicit exact_size(rapidjson::SizeType expected) : _expected(expected) {}
bool operator()(rapidjson::SizeType size) const override { return size == _expected; }
sstring what() const override { return format("of size {}", _expected); }
};
struct empty : public size_check {
bool operator()(rapidjson::SizeType size) const override { return size < 1; }
sstring what() const override { return "to be empty"; }
};
struct nonempty : public size_check {
bool operator()(rapidjson::SizeType size) const override { return size > 0; }
sstring what() const override { return "to be non-empty"; }
};
} // anonymous namespace
// Check that array has the expected number of elements
static void verify_operand_count(const rjson::value* array, const size_check& expected, const rjson::value& op) {
if (!array && expected(0)) {
// If expected() allows an empty AttributeValueList, it is also fine
// that it is missing.
return;
}
if (!array || !array->IsArray()) {
throw api_error("ValidationException", "With ComparisonOperator, AttributeValueList must be given and an array");
}
if (!expected(array->Size())) {
throw api_error("ValidationException",
format("{} operator requires AttributeValueList {}, instead found list size {}",
op, expected.what(), array->Size()));
}
}
struct rjson_engaged_ptr_comp {
bool operator()(const rjson::value* p1, const rjson::value* p2) const {
return rjson::single_value_comp()(*p1, *p2);
}
};
// It's not enough to compare underlying JSON objects when comparing sets,
// as internally they're stored in an array, and the order of elements is
// not important in set equality. See issue #5021
static bool check_EQ_for_sets(const rjson::value& set1, const rjson::value& set2) {
if (set1.Size() != set2.Size()) {
return false;
}
std::set<const rjson::value*, rjson_engaged_ptr_comp> set1_raw;
for (auto it = set1.Begin(); it != set1.End(); ++it) {
set1_raw.insert(&*it);
}
for (const auto& a : set2.GetArray()) {
if (set1_raw.count(&a) == 0) {
return false;
}
}
return true;
}
// Check if two JSON-encoded values match with the EQ relation
static bool check_EQ(const rjson::value* v1, const rjson::value& v2) {
if (!v1) {
return false;
}
if (v1->IsObject() && v1->MemberCount() == 1 && v2.IsObject() && v2.MemberCount() == 1) {
auto it1 = v1->MemberBegin();
auto it2 = v2.MemberBegin();
if ((it1->name == "SS" && it2->name == "SS") || (it1->name == "NS" && it2->name == "NS") || (it1->name == "BS" && it2->name == "BS")) {
return check_EQ_for_sets(it1->value, it2->value);
}
}
return *v1 == v2;
}
// Check if two JSON-encoded values match with the NE relation
static bool check_NE(const rjson::value* v1, const rjson::value& v2) {
return !v1 || *v1 != v2; // null is unequal to anything.
}
// Check if two JSON-encoded values match with the BEGINS_WITH relation
bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2,
bool v1_from_query, bool v2_from_query) {
bool bad = false;
if (!v1 || !v1->IsObject() || v1->MemberCount() != 1) {
if (v1_from_query) {
throw api_error("ValidationException", "begins_with() encountered malformed argument");
} else {
bad = true;
}
} else if (v1->MemberBegin()->name != "S" && v1->MemberBegin()->name != "B") {
if (v1_from_query) {
throw api_error("ValidationException", format("begins_with supports only string or binary type, got: {}", *v1));
} else {
bad = true;
}
}
if (!v2.IsObject() || v2.MemberCount() != 1) {
if (v2_from_query) {
throw api_error("ValidationException", "begins_with() encountered malformed argument");
} else {
bad = true;
}
} else if (v2.MemberBegin()->name != "S" && v2.MemberBegin()->name != "B") {
if (v2_from_query) {
throw api_error("ValidationException", format("begins_with() supports only string or binary type, got: {}", v2));
} else {
bad = true;
}
}
if (bad) {
return false;
}
auto it1 = v1->MemberBegin();
auto it2 = v2.MemberBegin();
if (it1->name != it2->name) {
return false;
}
if (it2->name == "S") {
return rjson::to_string_view(it1->value).starts_with(rjson::to_string_view(it2->value));
} else /* it2->name == "B" */ {
return base64_begins_with(rjson::to_string_view(it1->value), rjson::to_string_view(it2->value));
}
}
static bool is_set_of(const rjson::value& type1, const rjson::value& type2) {
return (type2 == "S" && type1 == "SS") || (type2 == "N" && type1 == "NS") || (type2 == "B" && type1 == "BS");
}
// Check if two JSON-encoded values match with the CONTAINS relation
bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2) {
if (!v1) {
return false;
}
const auto& kv1 = *v1->MemberBegin();
const auto& kv2 = *v2.MemberBegin();
if (kv1.name == "S" && kv2.name == "S") {
return rjson::to_string_view(kv1.value).find(rjson::to_string_view(kv2.value)) != std::string_view::npos;
} else if (kv1.name == "B" && kv2.name == "B") {
return base64_decode(kv1.value).find(base64_decode(kv2.value)) != bytes::npos;
} else if (is_set_of(kv1.name, kv2.name)) {
for (auto i = kv1.value.Begin(); i != kv1.value.End(); ++i) {
if (*i == kv2.value) {
return true;
}
}
} else if (kv1.name == "L") {
for (auto i = kv1.value.Begin(); i != kv1.value.End(); ++i) {
if (!i->IsObject() || i->MemberCount() != 1) {
clogger.error("check_CONTAINS received a list whose element is malformed");
return false;
}
const auto& el = *i->MemberBegin();
if (el.name == kv2.name && el.value == kv2.value) {
return true;
}
}
}
return false;
}
// Check if two JSON-encoded values match with the NOT_CONTAINS relation
static bool check_NOT_CONTAINS(const rjson::value* v1, const rjson::value& v2) {
if (!v1) {
return false;
}
return !check_CONTAINS(v1, v2);
}
// Check if a JSON-encoded value equals any element of an array, which must have at least one element.
static bool check_IN(const rjson::value* val, const rjson::value& array) {
if (!array[0].IsObject() || array[0].MemberCount() != 1) {
throw api_error("ValidationException",
format("IN operator encountered malformed AttributeValue: {}", array[0]));
}
const auto& type = array[0].MemberBegin()->name;
if (type != "S" && type != "N" && type != "B") {
throw api_error("ValidationException",
"IN operator requires AttributeValueList elements to be of type String, Number, or Binary ");
}
if (!val) {
return false;
}
bool have_match = false;
for (const auto& elem : array.GetArray()) {
if (!elem.IsObject() || elem.MemberCount() != 1 || elem.MemberBegin()->name != type) {
throw api_error("ValidationException",
"IN operator requires all AttributeValueList elements to have the same type ");
}
if (!have_match && *val == elem) {
// Can't return yet, must check types of all array elements. <sigh>
have_match = true;
}
}
return have_match;
}
// Another variant of check_IN, this one for ConditionExpression. It needs to
// check whether the first element in the given vector is equal to any of the
// others.
static bool check_IN(const std::vector<rjson::value>& array) {
const rjson::value* first = &array[0];
for (unsigned i = 1; i < array.size(); i++) {
if (check_EQ(first, array[i])) {
return true;
}
}
return false;
}
static bool check_NULL(const rjson::value* val) {
return val == nullptr;
}
static bool check_NOT_NULL(const rjson::value* val) {
return val != nullptr;
}
// Only types S, N or B (string, number or bytes) may be compared by the
// various comparion operators - lt, le, gt, ge, and between.
static bool check_comparable_type(const rjson::value& v) {
if (!v.IsObject() || v.MemberCount() != 1) {
return false;
}
const rjson::value& type = v.MemberBegin()->name;
return type == "S" || type == "N" || type == "B";
}
// Check if two JSON-encoded values match with cmp.
template <typename Comparator>
bool check_compare(const rjson::value* v1, const rjson::value& v2, const Comparator& cmp,
bool v1_from_query, bool v2_from_query) {
bool bad = false;
if (!v1 || !check_comparable_type(*v1)) {
if (v1_from_query) {
throw api_error("ValidationException", format("{} allow only the types String, Number, or Binary", cmp.diagnostic));
}
bad = true;
}
if (!check_comparable_type(v2)) {
if (v2_from_query) {
throw api_error("ValidationException", format("{} allow only the types String, Number, or Binary", cmp.diagnostic));
}
bad = true;
}
if (bad) {
return false;
}
const auto& kv1 = *v1->MemberBegin();
const auto& kv2 = *v2.MemberBegin();
if (kv1.name != kv2.name) {
return false;
}
if (kv1.name == "N") {
return cmp(unwrap_number(*v1, cmp.diagnostic), unwrap_number(v2, cmp.diagnostic));
}
if (kv1.name == "S") {
return cmp(std::string_view(kv1.value.GetString(), kv1.value.GetStringLength()),
std::string_view(kv2.value.GetString(), kv2.value.GetStringLength()));
}
if (kv1.name == "B") {
return cmp(base64_decode(kv1.value), base64_decode(kv2.value));
}
// cannot reach here, as check_comparable_type() verifies the type is one
// of the above options.
return false;
}
struct cmp_lt {
template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs < rhs; }
// We cannot use the normal comparison operators like "<" on the bytes
// type, because they treat individual bytes as signed but we need to
// compare them as *unsigned*. So we need a specialization for bytes.
bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) < 0; }
static constexpr const char* diagnostic = "LT operator";
};
struct cmp_le {
template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs <= rhs; }
bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) <= 0; }
static constexpr const char* diagnostic = "LE operator";
};
struct cmp_ge {
template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs >= rhs; }
bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) >= 0; }
static constexpr const char* diagnostic = "GE operator";
};
struct cmp_gt {
template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs > rhs; }
bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) > 0; }
static constexpr const char* diagnostic = "GT operator";
};
// True if v is between lb and ub, inclusive. Throws or returns false
// (depending on bounds_from_query parameter) if lb > ub.
template <typename T>
static bool check_BETWEEN(const T& v, const T& lb, const T& ub, bool bounds_from_query) {
if (cmp_lt()(ub, lb)) {
if (bounds_from_query) {
throw api_error("ValidationException",
format("BETWEEN operator requires lower_bound <= upper_bound, but {} > {}", lb, ub));
} else {
return false;
}
}
return cmp_ge()(v, lb) && cmp_le()(v, ub);
}
static bool check_BETWEEN(const rjson::value* v, const rjson::value& lb, const rjson::value& ub,
bool v_from_query, bool lb_from_query, bool ub_from_query) {
if ((v && v_from_query && !check_comparable_type(*v)) ||
(lb_from_query && !check_comparable_type(lb)) ||
(ub_from_query && !check_comparable_type(ub))) {
throw api_error("ValidationException", "between allow only the types String, Number, or Binary");
}
if (!v || !v->IsObject() || v->MemberCount() != 1 ||
!lb.IsObject() || lb.MemberCount() != 1 ||
!ub.IsObject() || ub.MemberCount() != 1) {
return false;
}
const auto& kv_v = *v->MemberBegin();
const auto& kv_lb = *lb.MemberBegin();
const auto& kv_ub = *ub.MemberBegin();
bool bounds_from_query = lb_from_query && ub_from_query;
if (kv_lb.name != kv_ub.name) {
if (bounds_from_query) {
throw api_error("ValidationException",
format("BETWEEN operator requires the same type for lower and upper bound; instead got {} and {}",
kv_lb.name, kv_ub.name));
} else {
return false;
}
}
if (kv_v.name != kv_lb.name) { // Cannot compare different types, so v is NOT between lb and ub.
return false;
}
if (kv_v.name == "N") {
const char* diag = "BETWEEN operator";
return check_BETWEEN(unwrap_number(*v, diag), unwrap_number(lb, diag), unwrap_number(ub, diag), bounds_from_query);
}
if (kv_v.name == "S") {
return check_BETWEEN(std::string_view(kv_v.value.GetString(), kv_v.value.GetStringLength()),
std::string_view(kv_lb.value.GetString(), kv_lb.value.GetStringLength()),
std::string_view(kv_ub.value.GetString(), kv_ub.value.GetStringLength()),
bounds_from_query);
}
if (kv_v.name == "B") {
return check_BETWEEN(base64_decode(kv_v.value), base64_decode(kv_lb.value), base64_decode(kv_ub.value), bounds_from_query);
}
if (v_from_query) {
throw api_error("ValidationException",
format("BETWEEN operator requires AttributeValueList elements to be of type String, Number, or Binary; instead got {}",
kv_lb.name));
} else {
return false;
}
}
// Verify one Expect condition on one attribute (whose content is "got")
// for the verify_expected() below.
// This function returns true or false depending on whether the condition
// succeeded - it does not throw ConditionalCheckFailedException.
// However, it may throw ValidationException on input validation errors.
static bool verify_expected_one(const rjson::value& condition, const rjson::value* got) {
const rjson::value* comparison_operator = rjson::find(condition, "ComparisonOperator");
const rjson::value* attribute_value_list = rjson::find(condition, "AttributeValueList");
const rjson::value* value = rjson::find(condition, "Value");
const rjson::value* exists = rjson::find(condition, "Exists");
// There are three types of conditions that Expected supports:
// A value, not-exists, and a comparison of some kind. Each allows
// and requires a different combinations of parameters in the request
if (value) {
if (exists && (!exists->IsBool() || exists->GetBool() != true)) {
throw api_error("ValidationException", "Cannot combine Value with Exists!=true");
}
if (comparison_operator) {
throw api_error("ValidationException", "Cannot combine Value with ComparisonOperator");
}
return check_EQ(got, *value);
} else if (exists) {
if (comparison_operator) {
throw api_error("ValidationException", "Cannot combine Exists with ComparisonOperator");
}
if (!exists->IsBool() || exists->GetBool() != false) {
throw api_error("ValidationException", "Exists!=false requires Value");
}
// Remember Exists=false, so we're checking that the attribute does *not* exist:
return !got;
} else {
if (!comparison_operator) {
throw api_error("ValidationException", "Missing ComparisonOperator, Value or Exists");
}
comparison_operator_type op = get_comparison_operator(*comparison_operator);
switch (op) {
case comparison_operator_type::EQ:
verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
return check_EQ(got, (*attribute_value_list)[0]);
case comparison_operator_type::NE:
verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
return check_NE(got, (*attribute_value_list)[0]);
case comparison_operator_type::LT:
verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
return check_compare(got, (*attribute_value_list)[0], cmp_lt{}, false, true);
case comparison_operator_type::LE:
verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
return check_compare(got, (*attribute_value_list)[0], cmp_le{}, false, true);
case comparison_operator_type::GT:
verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
return check_compare(got, (*attribute_value_list)[0], cmp_gt{}, false, true);
case comparison_operator_type::GE:
verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
return check_compare(got, (*attribute_value_list)[0], cmp_ge{}, false, true);
case comparison_operator_type::BEGINS_WITH:
verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
return check_BEGINS_WITH(got, (*attribute_value_list)[0], false, true);
case comparison_operator_type::IN:
verify_operand_count(attribute_value_list, nonempty(), *comparison_operator);
return check_IN(got, *attribute_value_list);
case comparison_operator_type::IS_NULL:
verify_operand_count(attribute_value_list, empty(), *comparison_operator);
return check_NULL(got);
case comparison_operator_type::NOT_NULL:
verify_operand_count(attribute_value_list, empty(), *comparison_operator);
return check_NOT_NULL(got);
case comparison_operator_type::BETWEEN:
verify_operand_count(attribute_value_list, exact_size(2), *comparison_operator);
return check_BETWEEN(got, (*attribute_value_list)[0], (*attribute_value_list)[1],
false, true, true);
case comparison_operator_type::CONTAINS:
{
verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
// Expected's "CONTAINS" has this artificial limitation.
// ConditionExpression's "contains()" does not...
const rjson::value& arg = (*attribute_value_list)[0];
const auto& argtype = (*arg.MemberBegin()).name;
if (argtype != "S" && argtype != "N" && argtype != "B") {
throw api_error("ValidationException",
format("CONTAINS operator requires a single AttributeValue of type String, Number, or Binary, "
"got {} instead", argtype));
}
return check_CONTAINS(got, arg);
}
case comparison_operator_type::NOT_CONTAINS:
{
verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
// Expected's "NOT_CONTAINS" has this artificial limitation.
// ConditionExpression's "contains()" does not...
const rjson::value& arg = (*attribute_value_list)[0];
const auto& argtype = (*arg.MemberBegin()).name;
if (argtype != "S" && argtype != "N" && argtype != "B") {
throw api_error("ValidationException",
format("CONTAINS operator requires a single AttributeValue of type String, Number, or Binary, "
"got {} instead", argtype));
}
return check_NOT_CONTAINS(got, arg);
}
}
throw std::logic_error(format("Internal error: corrupted operator enum: {}", int(op)));
}
}
conditional_operator_type get_conditional_operator(const rjson::value& req) {
const rjson::value* conditional_operator = rjson::find(req, "ConditionalOperator");
if (!conditional_operator) {
return conditional_operator_type::MISSING;
}
if (!conditional_operator->IsString()) {
throw api_error("ValidationException", "'ConditionalOperator' parameter, if given, must be a string");
}
auto s = rjson::to_string_view(*conditional_operator);
if (s == "AND") {
return conditional_operator_type::AND;
} else if (s == "OR") {
return conditional_operator_type::OR;
} else {
throw api_error("ValidationException",
format("'ConditionalOperator' parameter must be AND, OR or missing. Found {}.", s));
}
}
// Check if the existing values of the item (previous_item) match the
// conditions given by the Expected and ConditionalOperator parameters
// (if they exist) in the request (an UpdateItem, PutItem or DeleteItem).
// This function can throw an ValidationException API error if there
// are errors in the format of the condition itself.
bool verify_expected(const rjson::value& req, const rjson::value* previous_item) {
const rjson::value* expected = rjson::find(req, "Expected");
auto conditional_operator = get_conditional_operator(req);
if (conditional_operator != conditional_operator_type::MISSING &&
(!expected || (expected->IsObject() && expected->GetObject().ObjectEmpty()))) {
throw api_error("ValidationException", "'ConditionalOperator' parameter cannot be specified for missing or empty Expression");
}
if (!expected) {
return true;
}
if (!expected->IsObject()) {
throw api_error("ValidationException", "'Expected' parameter, if given, must be an object");
}
bool require_all = conditional_operator != conditional_operator_type::OR;
return verify_condition(*expected, require_all, previous_item);
}
bool verify_condition(const rjson::value& condition, bool require_all, const rjson::value* previous_item) {
for (auto it = condition.MemberBegin(); it != condition.MemberEnd(); ++it) {
const rjson::value* got = nullptr;
if (previous_item) {
got = rjson::find(*previous_item, rjson::to_string_view(it->name));
}
bool success = verify_expected_one(it->value, got);
if (success && !require_all) {
// When !require_all, one success is enough!
return true;
} else if (!success && require_all) {
// When require_all, one failure is enough!
return false;
}
}
// If we got here and require_all, none of the checks failed, so succeed.
// If we got here and !require_all, all of the checks failed, so fail.
return require_all;
}
static bool calculate_primitive_condition(const parsed::primitive_condition& cond,
const rjson::value* previous_item) {
std::vector<rjson::value> calculated_values;
calculated_values.reserve(cond._values.size());
for (const parsed::value& v : cond._values) {
calculated_values.push_back(calculate_value(v,
cond._op == parsed::primitive_condition::type::VALUE ?
calculate_value_caller::ConditionExpressionAlone :
calculate_value_caller::ConditionExpression,
previous_item));
}
switch (cond._op) {
case parsed::primitive_condition::type::BETWEEN:
if (calculated_values.size() != 3) {
// Shouldn't happen unless we have a bug in the parser
throw std::logic_error(format("Wrong number of values {} in BETWEEN primitive_condition", cond._values.size()));
}
return check_BETWEEN(&calculated_values[0], calculated_values[1], calculated_values[2],
cond._values[0].is_constant(), cond._values[1].is_constant(), cond._values[2].is_constant());
case parsed::primitive_condition::type::IN:
return check_IN(calculated_values);
case parsed::primitive_condition::type::VALUE:
if (calculated_values.size() != 1) {
// Shouldn't happen unless we have a bug in the parser
throw std::logic_error(format("Unexpected values in primitive_condition", cond._values.size()));
}
// Unwrap the boolean wrapped as the value (if it is a boolean)
if (calculated_values[0].IsObject() && calculated_values[0].MemberCount() == 1) {
auto it = calculated_values[0].MemberBegin();
if (it->name == "BOOL" && it->value.IsBool()) {
return it->value.GetBool();
}
}
throw api_error("ValidationException",
format("ConditionExpression: condition results in a non-boolean value: {}",
calculated_values[0]));
default:
// All the rest of the operators have exactly two parameters (and unless
// we have a bug in the parser, that's what we have in the parsed object:
if (calculated_values.size() != 2) {
throw std::logic_error(format("Wrong number of values {} in primitive_condition object", cond._values.size()));
}
}
switch (cond._op) {
case parsed::primitive_condition::type::EQ:
return check_EQ(&calculated_values[0], calculated_values[1]);
case parsed::primitive_condition::type::NE:
return check_NE(&calculated_values[0], calculated_values[1]);
case parsed::primitive_condition::type::GT:
return check_compare(&calculated_values[0], calculated_values[1], cmp_gt{},
cond._values[0].is_constant(), cond._values[1].is_constant());
case parsed::primitive_condition::type::GE:
return check_compare(&calculated_values[0], calculated_values[1], cmp_ge{},
cond._values[0].is_constant(), cond._values[1].is_constant());
case parsed::primitive_condition::type::LT:
return check_compare(&calculated_values[0], calculated_values[1], cmp_lt{},
cond._values[0].is_constant(), cond._values[1].is_constant());
case parsed::primitive_condition::type::LE:
return check_compare(&calculated_values[0], calculated_values[1], cmp_le{},
cond._values[0].is_constant(), cond._values[1].is_constant());
default:
// Shouldn't happen unless we have a bug in the parser
throw std::logic_error(format("Unknown type {} in primitive_condition object", (int)(cond._op)));
}
}
// Check if the existing values of the item (previous_item) match the
// conditions given by the given parsed ConditionExpression.
bool verify_condition_expression(
const parsed::condition_expression& condition_expression,
const rjson::value* previous_item) {
if (condition_expression.empty()) {
return true;
}
bool ret = std::visit(overloaded_functor {
[&] (const parsed::primitive_condition& cond) -> bool {
return calculate_primitive_condition(cond, previous_item);
},
[&] (const parsed::condition_expression::condition_list& list) -> bool {
auto verify_condition = [&] (const parsed::condition_expression& e) {
return verify_condition_expression(e, previous_item);
};
switch (list.op) {
case '&':
return boost::algorithm::all_of(list.conditions, verify_condition);
case '|':
return boost::algorithm::any_of(list.conditions, verify_condition);
default:
// Shouldn't happen unless we have a bug in the parser
throw std::logic_error("bad operator in condition_list");
}
}
}, condition_expression._expression);
return condition_expression._negated ? !ret : ret;
}
}

View File

@@ -1,61 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
/*
* This file contains definitions and functions related to placing conditions
* on Alternator queries (equivalent of CQL's restrictions).
*
* With conditions, it's possible to add criteria to selection requests (Scan, Query)
* and use them for narrowing down the result set, by means of filtering or indexing.
*
* Ref: https://docs.aws.amazon.com/amazondynamodb/latest/APIReference/API_Condition.html
*/
#pragma once
#include "cql3/restrictions/statement_restrictions.hh"
#include "serialization.hh"
#include "expressions_types.hh"
namespace alternator {
enum class comparison_operator_type {
EQ, NE, LE, LT, GE, GT, IN, BETWEEN, CONTAINS, NOT_CONTAINS, IS_NULL, NOT_NULL, BEGINS_WITH
};
comparison_operator_type get_comparison_operator(const rjson::value& comparison_operator);
enum class conditional_operator_type {
AND, OR, MISSING
};
conditional_operator_type get_conditional_operator(const rjson::value& req);
bool verify_expected(const rjson::value& req, const rjson::value* previous_item);
bool verify_condition(const rjson::value& condition, bool require_all, const rjson::value* previous_item);
bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2);
bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2, bool v1_from_query, bool v2_from_query);
bool verify_condition_expression(
const parsed::condition_expression& condition_expression,
const rjson::value* previous_item);
}

View File

@@ -1,50 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <seastar/http/httpd.hh>
#include "seastarx.hh"
namespace alternator {
// DynamoDB's error messages are described in detail in
// https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Programming.Errors.html
// Ah An error message has a "type", e.g., "ResourceNotFoundException", a coarser
// HTTP code (almost always, 400), and a human readable message. Eventually these
// will be wrapped into a JSON object returned to the client.
class api_error : public std::exception {
public:
using status_type = httpd::reply::status_type;
status_type _http_code;
std::string _type;
std::string _msg;
api_error(std::string type, std::string msg, status_type http_code = status_type::bad_request)
: _http_code(std::move(http_code))
, _type(std::move(type))
, _msg(std::move(msg))
{ }
api_error() = default;
virtual const char* what() const noexcept override { return _msg.c_str(); }
};
}

File diff suppressed because it is too large Load Diff

View File

@@ -1,83 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <seastar/core/future.hh>
#include <seastar/http/httpd.hh>
#include "seastarx.hh"
#include <seastar/json/json_elements.hh>
#include <seastar/core/sharded.hh>
#include "service/storage_proxy.hh"
#include "service/migration_manager.hh"
#include "service/client_state.hh"
#include "alternator/error.hh"
#include "stats.hh"
#include "rjson.hh"
namespace alternator {
class executor : public peering_sharded_service<executor> {
service::storage_proxy& _proxy;
service::migration_manager& _mm;
// An smp_service_group to be used for limiting the concurrency when
// forwarding Alternator request between shards - if necessary for LWT.
smp_service_group _ssg;
public:
using client_state = service::client_state;
using request_return_type = std::variant<json::json_return_type, api_error>;
stats _stats;
static constexpr auto ATTRS_COLUMN_NAME = ":attrs";
static constexpr auto KEYSPACE_NAME_PREFIX = "alternator_";
static constexpr std::string_view INTERNAL_TABLE_PREFIX = ".scylla.alternator.";
executor(service::storage_proxy& proxy, service::migration_manager& mm, smp_service_group ssg)
: _proxy(proxy), _mm(mm), _ssg(ssg) {}
future<request_return_type> create_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> describe_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> delete_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> put_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> get_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> delete_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> update_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> list_tables(client_state& client_state, service_permit permit, rjson::value request);
future<request_return_type> scan(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> describe_endpoints(client_state& client_state, service_permit permit, rjson::value request, std::string host_header);
future<request_return_type> batch_write_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> batch_get_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> query(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
future<request_return_type> tag_resource(client_state& client_state, service_permit permit, rjson::value request);
future<request_return_type> untag_resource(client_state& client_state, service_permit permit, rjson::value request);
future<request_return_type> list_tags_of_resource(client_state& client_state, service_permit permit, rjson::value request);
future<> start();
future<> stop() { return make_ready_future<>(); }
future<> create_keyspace(std::string_view keyspace_name);
static tracing::trace_state_ptr maybe_trace_query(client_state& client_state, sstring_view op, sstring_view query);
};
}

View File

@@ -1,684 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "expressions.hh"
#include "serialization.hh"
#include "base64.hh"
#include "conditions.hh"
#include "alternator/expressionsLexer.hpp"
#include "alternator/expressionsParser.hpp"
#include "utils/overloaded_functor.hh"
#include "error.hh"
#include "seastarx.hh"
#include <seastar/core/print.hh>
#include <seastar/util/log.hh>
#include <boost/algorithm/cxx11/any_of.hpp>
#include <boost/algorithm/cxx11/all_of.hpp>
#include <functional>
#include <unordered_map>
namespace alternator {
template <typename Func, typename Result = std::result_of_t<Func(expressionsParser&)>>
Result do_with_parser(std::string input, Func&& f) {
expressionsLexer::InputStreamType input_stream{
reinterpret_cast<const ANTLR_UINT8*>(input.data()),
ANTLR_ENC_UTF8,
static_cast<ANTLR_UINT32>(input.size()),
nullptr };
expressionsLexer lexer(&input_stream);
expressionsParser::TokenStreamType tstream(ANTLR_SIZE_HINT, lexer.get_tokSource());
expressionsParser parser(&tstream);
auto result = f(parser);
return result;
}
parsed::update_expression
parse_update_expression(std::string query) {
try {
return do_with_parser(query, std::mem_fn(&expressionsParser::update_expression));
} catch (...) {
throw expressions_syntax_error(format("Failed parsing UpdateExpression '{}': {}", query, std::current_exception()));
}
}
std::vector<parsed::path>
parse_projection_expression(std::string query) {
try {
return do_with_parser(query, std::mem_fn(&expressionsParser::projection_expression));
} catch (...) {
throw expressions_syntax_error(format("Failed parsing ProjectionExpression '{}': {}", query, std::current_exception()));
}
}
parsed::condition_expression
parse_condition_expression(std::string query) {
try {
return do_with_parser(query, std::mem_fn(&expressionsParser::condition_expression));
} catch (...) {
throw expressions_syntax_error(format("Failed parsing ConditionExpression '{}': {}", query, std::current_exception()));
}
}
namespace parsed {
void update_expression::add(update_expression::action a) {
std::visit(overloaded_functor {
[&] (action::set&) { seen_set = true; },
[&] (action::remove&) { seen_remove = true; },
[&] (action::add&) { seen_add = true; },
[&] (action::del&) { seen_del = true; }
}, a._action);
_actions.push_back(std::move(a));
}
void update_expression::append(update_expression other) {
if ((seen_set && other.seen_set) ||
(seen_remove && other.seen_remove) ||
(seen_add && other.seen_add) ||
(seen_del && other.seen_del)) {
throw expressions_syntax_error("Each of SET, REMOVE, ADD, DELETE may only appear once in UpdateExpression");
}
std::move(other._actions.begin(), other._actions.end(), std::back_inserter(_actions));
seen_set |= other.seen_set;
seen_remove |= other.seen_remove;
seen_add |= other.seen_add;
seen_del |= other.seen_del;
}
void condition_expression::append(condition_expression&& a, char op) {
std::visit(overloaded_functor {
[&] (condition_list& x) {
// If 'a' has a single condition, we could, instead of inserting
// it insert its single condition (possibly negated if a._negated)
// But considering it we don't evaluate these expressions many
// times, this optimization is not worth extra code complexity.
if (!x.conditions.empty() && x.op != op) {
// Shouldn't happen unless we have a bug in the parser
throw std::logic_error("condition_expression::append called with mixed operators");
}
x.conditions.push_back(std::move(a));
x.op = op;
},
[&] (primitive_condition& x) {
// Shouldn't happen unless we have a bug in the parser
throw std::logic_error("condition_expression::append called on primitive_condition");
}
}, _expression);
}
} // namespace parsed
// The following resolve_*() functions resolve references in parsed
// expressions of different types. Resolving a parsed expression means
// replacing:
// 1. In parsed::path objects, replace references like "#name" with the
// attribute name from ExpressionAttributeNames,
// 2. In parsed::constant objects, replace references like ":value" with
// the value from ExpressionAttributeValues.
// These function also track which name and value references were used, to
// allow complaining if some remain unused.
// Note that the resolve_*() functions modify the expressions in-place,
// so if we ever intend to cache parsed expression, we need to pass a copy
// into this function.
//
// Doing the "resolving" stage before the evaluation stage has two benefits.
// First, it allows us to be compatible with DynamoDB in catching unused
// names and values (see issue #6572). Second, in the FilterExpression case,
// we need to resolve the expression just once but then use it many times
// (once for each item to be filtered).
static void resolve_path(parsed::path& p,
const rjson::value* expression_attribute_names,
std::unordered_set<std::string>& used_attribute_names) {
const std::string& column_name = p.root();
if (column_name.size() > 0 && column_name.front() == '#') {
if (!expression_attribute_names) {
throw api_error("ValidationException",
format("ExpressionAttributeNames missing, entry '{}' required by expression", column_name));
}
const rjson::value* value = rjson::find(*expression_attribute_names, column_name);
if (!value || !value->IsString()) {
throw api_error("ValidationException",
format("ExpressionAttributeNames missing entry '{}' required by expression", column_name));
}
used_attribute_names.emplace(column_name);
p.set_root(std::string(rjson::to_string_view(*value)));
}
}
static void resolve_constant(parsed::constant& c,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_values) {
std::visit(overloaded_functor {
[&] (const std::string& valref) {
if (!expression_attribute_values) {
throw api_error("ValidationException",
format("ExpressionAttributeValues missing, entry '{}' required by expression", valref));
}
const rjson::value* value = rjson::find(*expression_attribute_values, valref);
if (!value) {
throw api_error("ValidationException",
format("ExpressionAttributeValues missing entry '{}' required by expression", valref));
}
if (value->IsNull()) {
throw api_error("ValidationException",
format("ExpressionAttributeValues null value for entry '{}' required by expression", valref));
}
validate_value(*value, "ExpressionAttributeValues");
used_attribute_values.emplace(valref);
c.set(*value);
},
[&] (const parsed::constant::literal& lit) {
// Nothing to do, already resolved
}
}, c._value);
}
void resolve_value(parsed::value& rhs,
const rjson::value* expression_attribute_names,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_names,
std::unordered_set<std::string>& used_attribute_values) {
std::visit(overloaded_functor {
[&] (parsed::constant& c) {
resolve_constant(c, expression_attribute_values, used_attribute_values);
},
[&] (parsed::value::function_call& f) {
for (parsed::value& value : f._parameters) {
resolve_value(value, expression_attribute_names, expression_attribute_values,
used_attribute_names, used_attribute_values);
}
},
[&] (parsed::path& p) {
resolve_path(p, expression_attribute_names, used_attribute_names);
}
}, rhs._value);
}
void resolve_set_rhs(parsed::set_rhs& rhs,
const rjson::value* expression_attribute_names,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_names,
std::unordered_set<std::string>& used_attribute_values) {
resolve_value(rhs._v1, expression_attribute_names, expression_attribute_values,
used_attribute_names, used_attribute_values);
if (rhs._op != 'v') {
resolve_value(rhs._v2, expression_attribute_names, expression_attribute_values,
used_attribute_names, used_attribute_values);
}
}
void resolve_update_expression(parsed::update_expression& ue,
const rjson::value* expression_attribute_names,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_names,
std::unordered_set<std::string>& used_attribute_values) {
for (parsed::update_expression::action& action : ue.actions()) {
resolve_path(action._path, expression_attribute_names, used_attribute_names);
std::visit(overloaded_functor {
[&] (parsed::update_expression::action::set& a) {
resolve_set_rhs(a._rhs, expression_attribute_names, expression_attribute_values,
used_attribute_names, used_attribute_values);
},
[&] (parsed::update_expression::action::remove& a) {
// nothing to do
},
[&] (parsed::update_expression::action::add& a) {
resolve_constant(a._valref, expression_attribute_values, used_attribute_values);
},
[&] (parsed::update_expression::action::del& a) {
resolve_constant(a._valref, expression_attribute_values, used_attribute_values);
}
}, action._action);
}
}
static void resolve_primitive_condition(parsed::primitive_condition& pc,
const rjson::value* expression_attribute_names,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_names,
std::unordered_set<std::string>& used_attribute_values) {
for (parsed::value& value : pc._values) {
resolve_value(value,
expression_attribute_names, expression_attribute_values,
used_attribute_names, used_attribute_values);
}
}
void resolve_condition_expression(parsed::condition_expression& ce,
const rjson::value* expression_attribute_names,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_names,
std::unordered_set<std::string>& used_attribute_values) {
std::visit(overloaded_functor {
[&] (parsed::primitive_condition& cond) {
resolve_primitive_condition(cond,
expression_attribute_names, expression_attribute_values,
used_attribute_names, used_attribute_values);
},
[&] (parsed::condition_expression::condition_list& list) {
for (parsed::condition_expression& cond : list.conditions) {
resolve_condition_expression(cond,
expression_attribute_names, expression_attribute_values,
used_attribute_names, used_attribute_values);
}
}
}, ce._expression);
}
void resolve_projection_expression(std::vector<parsed::path>& pe,
const rjson::value* expression_attribute_names,
std::unordered_set<std::string>& used_attribute_names) {
for (parsed::path& p : pe) {
resolve_path(p, expression_attribute_names, used_attribute_names);
}
}
// condition_expression_on() checks whether a condition_expression places any
// condition on the given attribute. It can be useful, for example, for
// checking whether the condition tries to restrict a key column.
static bool value_on(const parsed::value& v, std::string_view attribute) {
return std::visit(overloaded_functor {
[&] (const parsed::constant& c) {
return false;
},
[&] (const parsed::value::function_call& f) {
for (const parsed::value& value : f._parameters) {
if (value_on(value, attribute)) {
return true;
}
}
return false;
},
[&] (const parsed::path& p) {
return p.root() == attribute;
}
}, v._value);
}
static bool primitive_condition_on(const parsed::primitive_condition& pc, std::string_view attribute) {
for (const parsed::value& value : pc._values) {
if (value_on(value, attribute)) {
return true;
}
}
return false;
}
bool condition_expression_on(const parsed::condition_expression& ce, std::string_view attribute) {
return std::visit(overloaded_functor {
[&] (const parsed::primitive_condition& cond) {
return primitive_condition_on(cond, attribute);
},
[&] (const parsed::condition_expression::condition_list& list) {
for (const parsed::condition_expression& cond : list.conditions) {
if (condition_expression_on(cond, attribute)) {
return true;
}
}
return false;
}
}, ce._expression);
}
// for_condition_expression_on() runs a given function over all the attributes
// mentioned in the expression. If the same attribute is mentioned more than
// once, the function will be called more than once for the same attribute.
static void for_value_on(const parsed::value& v, const noncopyable_function<void(std::string_view)>& func) {
std::visit(overloaded_functor {
[&] (const parsed::constant& c) { },
[&] (const parsed::value::function_call& f) {
for (const parsed::value& value : f._parameters) {
for_value_on(value, func);
}
},
[&] (const parsed::path& p) {
func(p.root());
}
}, v._value);
}
void for_condition_expression_on(const parsed::condition_expression& ce, const noncopyable_function<void(std::string_view)>& func) {
std::visit(overloaded_functor {
[&] (const parsed::primitive_condition& cond) {
for (const parsed::value& value : cond._values) {
for_value_on(value, func);
}
},
[&] (const parsed::condition_expression::condition_list& list) {
for (const parsed::condition_expression& cond : list.conditions) {
for_condition_expression_on(cond, func);
}
}
}, ce._expression);
}
// The following calculate_value() functions calculate, or evaluate, a parsed
// expression. The parsed expression is assumed to have been "resolved", with
// the matching resolve_* function.
// Take two JSON-encoded list values (remember that a list value is
// {"L": [...the actual list]}) and return the concatenation, again as
// a list value.
static rjson::value list_concatenate(const rjson::value& v1, const rjson::value& v2) {
const rjson::value* list1 = unwrap_list(v1);
const rjson::value* list2 = unwrap_list(v2);
if (!list1 || !list2) {
throw api_error("ValidationException", "UpdateExpression: list_append() given a non-list");
}
rjson::value cat = rjson::copy(*list1);
for (const auto& a : list2->GetArray()) {
rjson::push_back(cat, rjson::copy(a));
}
rjson::value ret = rjson::empty_object();
rjson::set(ret, "L", std::move(cat));
return ret;
}
// calculate_size() is ConditionExpression's size() function, i.e., it takes
// a JSON-encoded value and returns its "size" as defined differently for the
// different types - also as a JSON-encoded number.
// It return a JSON-encoded "null" value if this value's type has no size
// defined. Comparisons against this non-numeric value will later fail.
static rjson::value calculate_size(const rjson::value& v) {
// NOTE: If v is improperly formatted for our JSON value encoding, it
// must come from the request itself, not from the database, so it makes
// sense to throw a ValidationException if we see such a problem.
if (!v.IsObject() || v.MemberCount() != 1) {
throw api_error("ValidationException", format("invalid object: {}", v));
}
auto it = v.MemberBegin();
int ret;
if (it->name == "S") {
if (!it->value.IsString()) {
throw api_error("ValidationException", format("invalid string: {}", v));
}
ret = it->value.GetStringLength();
} else if (it->name == "NS" || it->name == "SS" || it->name == "BS" || it->name == "L") {
if (!it->value.IsArray()) {
throw api_error("ValidationException", format("invalid set: {}", v));
}
ret = it->value.Size();
} else if (it->name == "M") {
if (!it->value.IsObject()) {
throw api_error("ValidationException", format("invalid map: {}", v));
}
ret = it->value.MemberCount();
} else if (it->name == "B") {
if (!it->value.IsString()) {
throw api_error("ValidationException", format("invalid byte string: {}", v));
}
ret = base64_decoded_len(rjson::to_string_view(it->value));
} else {
rjson::value json_ret = rjson::empty_object();
rjson::set(json_ret, "null", rjson::value(true));
return json_ret;
}
rjson::value json_ret = rjson::empty_object();
rjson::set(json_ret, "N", rjson::from_string(std::to_string(ret)));
return json_ret;
}
static const rjson::value& calculate_value(const parsed::constant& c) {
return std::visit(overloaded_functor {
[&] (const parsed::constant::literal& v) -> const rjson::value& {
return *v;
},
[&] (const std::string& valref) -> const rjson::value& {
// Shouldn't happen, we should have called resolve_value() earlier
// and replaced the value reference by the literal constant.
throw std::logic_error("calculate_value() called before resolve_value()");
}
}, c._value);
}
static rjson::value to_bool_json(bool b) {
rjson::value json_ret = rjson::empty_object();
rjson::set(json_ret, "BOOL", rjson::value(b));
return json_ret;
}
static bool known_type(std::string_view type) {
static thread_local const std::unordered_set<std::string_view> types = {
"N", "S", "B", "NS", "SS", "BS", "L", "M", "NULL", "BOOL"
};
return types.contains(type);
}
using function_handler_type = rjson::value(calculate_value_caller, const rjson::value*, const parsed::value::function_call&);
static const
std::unordered_map<std::string_view, function_handler_type*> function_handlers {
{"list_append", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::UpdateExpression) {
throw api_error("ValidationException",
format("{}: list_append() not allowed here", caller));
}
if (f._parameters.size() != 2) {
throw api_error("ValidationException",
format("{}: list_append() accepts 2 parameters, got {}", caller, f._parameters.size()));
}
rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
return list_concatenate(v1, v2);
}
},
{"if_not_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::UpdateExpression) {
throw api_error("ValidationException",
format("{}: if_not_exists() not allowed here", caller));
}
if (f._parameters.size() != 2) {
throw api_error("ValidationException",
format("{}: if_not_exists() accepts 2 parameters, got {}", caller, f._parameters.size()));
}
if (!std::holds_alternative<parsed::path>(f._parameters[0]._value)) {
throw api_error("ValidationException",
format("{}: if_not_exists() must include path as its first argument", caller));
}
rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
return v1.IsNull() ? std::move(v2) : std::move(v1);
}
},
{"size", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::ConditionExpression) {
throw api_error("ValidationException",
format("{}: size() not allowed here", caller));
}
if (f._parameters.size() != 1) {
throw api_error("ValidationException",
format("{}: size() accepts 1 parameter, got {}", caller, f._parameters.size()));
}
rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
return calculate_size(v);
}
},
{"attribute_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::ConditionExpressionAlone) {
throw api_error("ValidationException",
format("{}: attribute_exists() not allowed here", caller));
}
if (f._parameters.size() != 1) {
throw api_error("ValidationException",
format("{}: attribute_exists() accepts 1 parameter, got {}", caller, f._parameters.size()));
}
if (!std::holds_alternative<parsed::path>(f._parameters[0]._value)) {
throw api_error("ValidationException",
format("{}: attribute_exists()'s parameter must be a path", caller));
}
rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
return to_bool_json(!v.IsNull());
}
},
{"attribute_not_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::ConditionExpressionAlone) {
throw api_error("ValidationException",
format("{}: attribute_not_exists() not allowed here", caller));
}
if (f._parameters.size() != 1) {
throw api_error("ValidationException",
format("{}: attribute_not_exists() accepts 1 parameter, got {}", caller, f._parameters.size()));
}
if (!std::holds_alternative<parsed::path>(f._parameters[0]._value)) {
throw api_error("ValidationException",
format("{}: attribute_not_exists()'s parameter must be a path", caller));
}
rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
return to_bool_json(v.IsNull());
}
},
{"attribute_type", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::ConditionExpressionAlone) {
throw api_error("ValidationException",
format("{}: attribute_type() not allowed here", caller));
}
if (f._parameters.size() != 2) {
throw api_error("ValidationException",
format("{}: attribute_type() accepts 2 parameters, got {}", caller, f._parameters.size()));
}
// There is no real reason for the following check (not
// allowing the type to come from a document attribute), but
// DynamoDB does this check, so we do too...
if (!f._parameters[1].is_constant()) {
throw api_error("ValidationException",
format("{}: attribute_types()'s first parameter must be an expression attribute", caller));
}
rjson::value v0 = calculate_value(f._parameters[0], caller, previous_item);
rjson::value v1 = calculate_value(f._parameters[1], caller, previous_item);
if (v1.IsObject() && v1.MemberCount() == 1 && v1.MemberBegin()->name == "S") {
// If the type parameter is not one of the legal types
// we should generate an error, not a failed condition:
if (!known_type(rjson::to_string_view(v1.MemberBegin()->value))) {
throw api_error("ValidationException",
format("{}: attribute_types()'s second parameter, {}, is not a known type",
caller, v1.MemberBegin()->value));
}
if (v0.IsObject() && v0.MemberCount() == 1) {
return to_bool_json(v1.MemberBegin()->value == v0.MemberBegin()->name);
} else {
return to_bool_json(false);
}
} else {
throw api_error("ValidationException",
format("{}: attribute_type() second parameter must refer to a string, got {}", caller, v1));
}
}
},
{"begins_with", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::ConditionExpressionAlone) {
throw api_error("ValidationException",
format("{}: begins_with() not allowed here", caller));
}
if (f._parameters.size() != 2) {
throw api_error("ValidationException",
format("{}: begins_with() accepts 2 parameters, got {}", caller, f._parameters.size()));
}
rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
return to_bool_json(check_BEGINS_WITH(v1.IsNull() ? nullptr : &v1, v2,
f._parameters[0].is_constant(), f._parameters[1].is_constant()));
}
},
{"contains", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
if (caller != calculate_value_caller::ConditionExpressionAlone) {
throw api_error("ValidationException",
format("{}: contains() not allowed here", caller));
}
if (f._parameters.size() != 2) {
throw api_error("ValidationException",
format("{}: contains() accepts 2 parameters, got {}", caller, f._parameters.size()));
}
rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
return to_bool_json(check_CONTAINS(v1.IsNull() ? nullptr : &v1, v2));
}
},
};
// Given a parsed::value, which can refer either to a constant value from
// ExpressionAttributeValues, to the value of some attribute, or to a function
// of other values, this function calculates the resulting value.
// "caller" determines which expression - ConditionExpression or
// UpdateExpression - is asking for this value. We need to know this because
// DynamoDB allows a different choice of functions for different expressions.
rjson::value calculate_value(const parsed::value& v,
calculate_value_caller caller,
const rjson::value* previous_item) {
return std::visit(overloaded_functor {
[&] (const parsed::constant& c) -> rjson::value {
return rjson::copy(calculate_value(c));
},
[&] (const parsed::value::function_call& f) -> rjson::value {
auto function_it = function_handlers.find(std::string_view(f._function_name));
if (function_it == function_handlers.end()) {
throw api_error("ValidationException",
format("UpdateExpression: unknown function '{}' called.", f._function_name));
}
return function_it->second(caller, previous_item, f);
},
[&] (const parsed::path& p) -> rjson::value {
if (!previous_item) {
return rjson::null_value();
}
std::string update_path = p.root();
if (p.has_operators()) {
// FIXME: support this
throw api_error("ValidationException", "Reading attribute paths not yet implemented");
}
const rjson::value* previous_value = rjson::find(*previous_item, update_path);
return previous_value ? rjson::copy(*previous_value) : rjson::null_value();
}
}, v._value);
}
// Same as calculate_value() above, except takes a set_rhs, which may be
// either a single value, or v1+v2 or v1-v2.
rjson::value calculate_value(const parsed::set_rhs& rhs,
const rjson::value* previous_item) {
switch(rhs._op) {
case 'v':
return calculate_value(rhs._v1, calculate_value_caller::UpdateExpression, previous_item);
case '+': {
rjson::value v1 = calculate_value(rhs._v1, calculate_value_caller::UpdateExpression, previous_item);
rjson::value v2 = calculate_value(rhs._v2, calculate_value_caller::UpdateExpression, previous_item);
return number_add(v1, v2);
}
case '-': {
rjson::value v1 = calculate_value(rhs._v1, calculate_value_caller::UpdateExpression, previous_item);
rjson::value v2 = calculate_value(rhs._v2, calculate_value_caller::UpdateExpression, previous_item);
return number_subtract(v1, v2);
}
}
// Can't happen
return rjson::null_value();
}
} // namespace alternator

View File

@@ -1,265 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*
* This file is part of Scylla. See the LICENSE.PROPRIETARY file in the
* top-level directory for licensing information.
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
/*
* The DynamoDB protocol is based on JSON, and most DynamoDB requests
* describe the operation and its parameters via JSON objects such as maps
* and lists. Nevertheless, in some types of requests an "expression" is
* passed as a single string, and we need to parse this string. These
* cases include:
* 1. Attribute paths, such as "a[3].b.c", are used in projection
* expressions as well as inside other expressions described below.
* 2. Condition expressions, such as "(NOT (a=b OR c=d)) AND e=f",
* used in conditional updates, filters, and other places.
* 3. Update expressions, such as "SET #a.b = :x, c = :y DELETE d"
*
* All these expression syntaxes are very simple: Most of them could be
* parsed as regular expressions, and the parenthesized condition expression
* could be done with a simple hand-written lexical analyzer and recursive-
* descent parser. Nevertheless, we decided to specify these parsers in the
* ANTLR3 language already used in the Scylla project, hopefully making these
* parsers easier to reason about, and easier to change if needed - and
* reducing the amount of boiler-plate code.
*/
grammar expressions;
options {
language = Cpp;
}
@parser::namespace{alternator}
@lexer::namespace{alternator}
/* TODO: explain what these traits things are. I haven't seen them explained
* in any document... Compilation fails without these fail because a definition
* of "expressionsLexerTraits" and "expressionParserTraits" is needed.
*/
@lexer::traits {
class expressionsLexer;
class expressionsParser;
typedef antlr3::Traits<expressionsLexer, expressionsParser> expressionsLexerTraits;
}
@parser::traits {
typedef expressionsLexerTraits expressionsParserTraits;
}
@lexer::header {
#include "alternator/expressions.hh"
// ANTLR generates a bunch of unused variables and functions. Yuck...
#pragma GCC diagnostic ignored "-Wunused-variable"
#pragma GCC diagnostic ignored "-Wunused-function"
}
@parser::header {
#include "expressionsLexer.hpp"
}
/* By default, ANTLR3 composes elaborate syntax-error messages, saying which
* token was unexpected, where, and so on on, but then dutifully writes these
* error messages to the standard error, and returns from the parser as if
* everything was fine, with a half-constructed output object! If we define
* the "displayRecognitionError" method, it will be called upon to build this
* error message, and we can instead throw an exception to stop the parsing
* immediately. This is good enough for now, for our simple needs, but if
* we ever want to show more information about the syntax error, Cql3.g
* contains an elaborate implementation (it would be nice if we could reuse
* it, not duplicate it).
* Unfortunately, we have to repeat the same definition twice - once for the
* parser, and once for the lexer.
*/
@parser::context {
void displayRecognitionError(ANTLR_UINT8** token_names, ExceptionBaseType* ex) {
throw expressions_syntax_error("syntax error");
}
}
@lexer::context {
void displayRecognitionError(ANTLR_UINT8** token_names, ExceptionBaseType* ex) {
throw expressions_syntax_error("syntax error");
}
}
/*
* Lexical analysis phase, i.e., splitting the input up to tokens.
* Lexical analyzer rules have names starting in capital letters.
* "fragment" rules do not generate tokens, and are just aliases used to
* make other rules more readable.
* Characters *not* listed here, e.g., '=', '(', etc., will be handled
* as individual tokens on their own right.
* Whitespace spans are skipped, so do not generate tokens.
*/
WHITESPACE: (' ' | '\t' | '\n' | '\r')+ { skip(); };
/* shortcuts for case-insensitive keywords */
fragment A:('a'|'A');
fragment B:('b'|'B');
fragment C:('c'|'C');
fragment D:('d'|'D');
fragment E:('e'|'E');
fragment F:('f'|'F');
fragment G:('g'|'G');
fragment H:('h'|'H');
fragment I:('i'|'I');
fragment J:('j'|'J');
fragment K:('k'|'K');
fragment L:('l'|'L');
fragment M:('m'|'M');
fragment N:('n'|'N');
fragment O:('o'|'O');
fragment P:('p'|'P');
fragment Q:('q'|'Q');
fragment R:('r'|'R');
fragment S:('s'|'S');
fragment T:('t'|'T');
fragment U:('u'|'U');
fragment V:('v'|'V');
fragment W:('w'|'W');
fragment X:('x'|'X');
fragment Y:('y'|'Y');
fragment Z:('z'|'Z');
/* These keywords must be appear before the generic NAME token below,
* because NAME matches too, and the first to match wins.
*/
SET: S E T;
REMOVE: R E M O V E;
ADD: A D D;
DELETE: D E L E T E;
AND: A N D;
OR: O R;
NOT: N O T;
BETWEEN: B E T W E E N;
IN: I N;
fragment ALPHA: 'A'..'Z' | 'a'..'z';
fragment DIGIT: '0'..'9';
fragment ALNUM: ALPHA | DIGIT | '_';
INTEGER: DIGIT+;
NAME: ALPHA ALNUM*;
NAMEREF: '#' ALNUM+;
VALREF: ':' ALNUM+;
/*
* Parsing phase - parsing the string of tokens generated by the lexical
* analyzer defined above.
*/
path_component: NAME | NAMEREF;
path returns [parsed::path p]:
root=path_component { $p.set_root($root.text); }
( '.' name=path_component { $p.add_dot($name.text); }
| '[' INTEGER ']' { $p.add_index(std::stoi($INTEGER.text)); }
)*;
value returns [parsed::value v]:
VALREF { $v.set_valref($VALREF.text); }
| path { $v.set_path($path.p); }
| NAME { $v.set_func_name($NAME.text); }
'(' x=value { $v.add_func_parameter($x.v); }
(',' x=value { $v.add_func_parameter($x.v); })*
')'
;
update_expression_set_rhs returns [parsed::set_rhs rhs]:
v=value { $rhs.set_value(std::move($v.v)); }
( '+' v=value { $rhs.set_plus(std::move($v.v)); }
| '-' v=value { $rhs.set_minus(std::move($v.v)); }
)?
;
update_expression_set_action returns [parsed::update_expression::action a]:
path '=' rhs=update_expression_set_rhs { $a.assign_set($path.p, $rhs.rhs); };
update_expression_remove_action returns [parsed::update_expression::action a]:
path { $a.assign_remove($path.p); };
update_expression_add_action returns [parsed::update_expression::action a]:
path VALREF { $a.assign_add($path.p, $VALREF.text); };
update_expression_delete_action returns [parsed::update_expression::action a]:
path VALREF { $a.assign_del($path.p, $VALREF.text); };
update_expression_clause returns [parsed::update_expression e]:
SET s=update_expression_set_action { $e.add(s); }
(',' s=update_expression_set_action { $e.add(s); })*
| REMOVE r=update_expression_remove_action { $e.add(r); }
(',' r=update_expression_remove_action { $e.add(r); })*
| ADD a=update_expression_add_action { $e.add(a); }
(',' a=update_expression_add_action { $e.add(a); })*
| DELETE d=update_expression_delete_action { $e.add(d); }
(',' d=update_expression_delete_action { $e.add(d); })*
;
// Note the "EOF" token at the end of the update expression. We want to the
// parser to match the entire string given to it - not just its beginning!
update_expression returns [parsed::update_expression e]:
(update_expression_clause { e.append($update_expression_clause.e); })* EOF;
projection_expression returns [std::vector<parsed::path> v]:
p=path { $v.push_back(std::move($p.p)); }
(',' p=path { $v.push_back(std::move($p.p)); } )* EOF;
primitive_condition returns [parsed::primitive_condition c]:
v=value { $c.add_value(std::move($v.v));
$c.set_operator(parsed::primitive_condition::type::VALUE); }
( ( '=' { $c.set_operator(parsed::primitive_condition::type::EQ); }
| '<' '>' { $c.set_operator(parsed::primitive_condition::type::NE); }
| '<' { $c.set_operator(parsed::primitive_condition::type::LT); }
| '<' '=' { $c.set_operator(parsed::primitive_condition::type::LE); }
| '>' { $c.set_operator(parsed::primitive_condition::type::GT); }
| '>' '=' { $c.set_operator(parsed::primitive_condition::type::GE); }
)
v=value { $c.add_value(std::move($v.v)); }
| BETWEEN { $c.set_operator(parsed::primitive_condition::type::BETWEEN); }
v=value { $c.add_value(std::move($v.v)); }
AND
v=value { $c.add_value(std::move($v.v)); }
| IN '(' { $c.set_operator(parsed::primitive_condition::type::IN); }
v=value { $c.add_value(std::move($v.v)); }
(',' v=value { $c.add_value(std::move($v.v)); })*
')'
)?
;
// The following rules for parsing boolean expressions are verbose and
// somewhat strange because of Antlr 3's limitations on recursive rules,
// common rule prefixes, and (lack of) support for operator precedence.
// These rules could have been written more clearly using a more powerful
// parser generator - such as Yacc.
boolean_expression returns [parsed::condition_expression e]:
b=boolean_expression_1 { $e.append(std::move($b.e), '|'); }
(OR b=boolean_expression_1 { $e.append(std::move($b.e), '|'); } )*
;
boolean_expression_1 returns [parsed::condition_expression e]:
b=boolean_expression_2 { $e.append(std::move($b.e), '&'); }
(AND b=boolean_expression_2 { $e.append(std::move($b.e), '&'); } )*
;
boolean_expression_2 returns [parsed::condition_expression e]:
p=primitive_condition { $e.set_primitive(std::move($p.c)); }
| NOT b=boolean_expression_2 { $e = std::move($b.e); $e.apply_not(); }
| '(' b=boolean_expression ')' { $e = std::move($b.e); }
;
condition_expression returns [parsed::condition_expression e]:
boolean_expression { e=std::move($boolean_expression.e); } EOF;

View File

@@ -1,102 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <string>
#include <stdexcept>
#include <vector>
#include <unordered_set>
#include <string_view>
#include <seastar/util/noncopyable_function.hh>
#include "expressions_types.hh"
#include "rjson.hh"
namespace alternator {
class expressions_syntax_error : public std::runtime_error {
public:
using runtime_error::runtime_error;
};
parsed::update_expression parse_update_expression(std::string query);
std::vector<parsed::path> parse_projection_expression(std::string query);
parsed::condition_expression parse_condition_expression(std::string query);
void resolve_update_expression(parsed::update_expression& ue,
const rjson::value* expression_attribute_names,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_names,
std::unordered_set<std::string>& used_attribute_values);
void resolve_projection_expression(std::vector<parsed::path>& pe,
const rjson::value* expression_attribute_names,
std::unordered_set<std::string>& used_attribute_names);
void resolve_condition_expression(parsed::condition_expression& ce,
const rjson::value* expression_attribute_names,
const rjson::value* expression_attribute_values,
std::unordered_set<std::string>& used_attribute_names,
std::unordered_set<std::string>& used_attribute_values);
void validate_value(const rjson::value& v, const char* caller);
bool condition_expression_on(const parsed::condition_expression& ce, std::string_view attribute);
// for_condition_expression_on() runs the given function on the attributes
// that the expression uses. It may run for the same attribute more than once
// if the same attribute is used more than once in the expression.
void for_condition_expression_on(const parsed::condition_expression& ce, const noncopyable_function<void(std::string_view)>& func);
// calculate_value() behaves slightly different (especially, different
// functions supported) when used in different types of expressions, as
// enumerated in this enum:
enum class calculate_value_caller {
UpdateExpression, ConditionExpression, ConditionExpressionAlone
};
inline std::ostream& operator<<(std::ostream& out, calculate_value_caller caller) {
switch (caller) {
case calculate_value_caller::UpdateExpression:
out << "UpdateExpression";
break;
case calculate_value_caller::ConditionExpression:
out << "ConditionExpression";
break;
case calculate_value_caller::ConditionExpressionAlone:
out << "ConditionExpression";
break;
default:
out << "unknown type of expression";
break;
}
return out;
}
rjson::value calculate_value(const parsed::value& v,
calculate_value_caller caller,
const rjson::value* previous_item);
rjson::value calculate_value(const parsed::set_rhs& rhs,
const rjson::value* previous_item);
} /* namespace alternator */

View File

@@ -1,255 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <vector>
#include <string>
#include <variant>
#include <seastar/core/shared_ptr.hh>
#include "rjson.hh"
/*
* Parsed representation of expressions and their components.
*
* Types in alternator::parse namespace are used for holding the parse
* tree - objects generated by the Antlr rules after parsing an expression.
* Because of the way Antlr works, all these objects are default-constructed
* first, and then assigned when the rule is completed, so all these types
* have only default constructors - but setter functions to set them later.
*/
namespace alternator {
namespace parsed {
// "path" is an attribute's path in a document, e.g., a.b[3].c.
class path {
// All paths have a "root", a top-level attribute, and any number of
// "dereference operators" - each either an index (e.g., "[2]") or a
// dot (e.g., ".xyz").
std::string _root;
std::vector<std::variant<std::string, unsigned>> _operators;
public:
void set_root(std::string root) {
_root = std::move(root);
}
void add_index(unsigned i) {
_operators.emplace_back(i);
}
void add_dot(std::string(name)) {
_operators.emplace_back(std::move(name));
}
const std::string& root() const {
return _root;
}
bool has_operators() const {
return !_operators.empty();
}
};
// When an expression is first parsed, all constants are references, like
// ":val1", into ExpressionAttributeValues. This uses std::string() variant.
// The resolve_value() function replaces these constants by the JSON item
// extracted from the ExpressionAttributeValues.
struct constant {
// We use lw_shared_ptr<rjson::value> just to make rjson::value copyable,
// to make this entire object copyable as ANTLR needs.
using literal = lw_shared_ptr<rjson::value>;
std::variant<std::string, literal> _value;
void set(const rjson::value& v) {
_value = make_lw_shared<rjson::value>(rjson::copy(v));
}
void set(std::string& s) {
_value = s;
}
};
// "value" is is a value used in the right hand side of an assignment
// expression, "SET a = ...". It can be a constant (a reference to a value
// included in the request, e.g., ":val"), a path to an attribute from the
// existing item (e.g., "a.b[3].c"), or a function of other such values.
// Note that the real right-hand-side of an assignment is actually a bit
// more general - it allows either a value, or a value+value or value-value -
// see class set_rhs below.
struct value {
struct function_call {
std::string _function_name;
std::vector<value> _parameters;
};
std::variant<constant, path, function_call> _value;
void set_constant(constant c) {
_value = std::move(c);
}
void set_valref(std::string s) {
_value = constant { std::move(s) };
}
void set_path(path p) {
_value = std::move(p);
}
void set_func_name(std::string s) {
_value = function_call {std::move(s), {}};
}
void add_func_parameter(value v) {
std::get<function_call>(_value)._parameters.emplace_back(std::move(v));
}
bool is_constant() const {
return std::holds_alternative<constant>(_value);
}
bool is_path() const {
return std::holds_alternative<path>(_value);
}
bool is_func() const {
return std::holds_alternative<function_call>(_value);
}
};
// The right-hand-side of a SET in an update expression can be either a
// single value (see above), or value+value, or value-value.
class set_rhs {
public:
char _op; // '+', '-', or 'v''
value _v1;
value _v2;
void set_value(value&& v1) {
_op = 'v';
_v1 = std::move(v1);
}
void set_plus(value&& v2) {
_op = '+';
_v2 = std::move(v2);
}
void set_minus(value&& v2) {
_op = '-';
_v2 = std::move(v2);
}
};
class update_expression {
public:
struct action {
path _path;
struct set {
set_rhs _rhs;
};
struct remove {
};
struct add {
constant _valref;
};
struct del {
constant _valref;
};
std::variant<set, remove, add, del> _action;
void assign_set(path p, set_rhs rhs) {
_path = std::move(p);
_action = set { std::move(rhs) };
}
void assign_remove(path p) {
_path = std::move(p);
_action = remove { };
}
void assign_add(path p, std::string v) {
_path = std::move(p);
_action = add { constant { std::move(v) } };
}
void assign_del(path p, std::string v) {
_path = std::move(p);
_action = del { constant { std::move(v) } };
}
};
private:
std::vector<action> _actions;
bool seen_set = false;
bool seen_remove = false;
bool seen_add = false;
bool seen_del = false;
public:
void add(action a);
void append(update_expression other);
bool empty() const {
return _actions.empty();
}
const std::vector<action>& actions() const {
return _actions;
}
std::vector<action>& actions() {
return _actions;
}
};
// A primitive_condition is a condition expression involving one condition,
// while the full condition_expression below adds boolean logic over these
// primitive conditions.
// The supported primitive conditions are:
// 1. Binary operators - v1 OP v2, where OP is =, <>, <, <=, >, or >= and
// v1 and v2 are values - from the item (an attribute path), the query
// (a ":val" reference), or a function of the the above (only the size()
// function is supported).
// 2. Ternary operator - v1 BETWEEN v2 and v3 (means v1 >= v2 AND v1 <= v3).
// 3. N-ary operator - v1 IN ( v2, v3, ... )
// 4. A single function call (attribute_exists etc.). The parser actually
// accepts a more general "value" here but later stages reject a value
// which is not a function call (because DynamoDB does it too).
class primitive_condition {
public:
enum class type {
UNDEFINED, VALUE, EQ, NE, LT, LE, GT, GE, BETWEEN, IN
};
type _op = type::UNDEFINED;
std::vector<value> _values;
void set_operator(type op) {
_op = op;
}
void add_value(value&& v) {
_values.push_back(std::move(v));
}
bool empty() const {
return _op == type::UNDEFINED;
}
};
class condition_expression {
public:
bool _negated = false; // If true, the entire condition is negated
struct condition_list {
char op = '|'; // '&' or '|'
std::vector<condition_expression> conditions;
};
std::variant<primitive_condition, condition_list> _expression = condition_list();
void set_primitive(primitive_condition&& p) {
_expression = std::move(p);
}
void append(condition_expression&& c, char op);
void apply_not() {
_negated = !_negated;
}
bool empty() const {
return std::holds_alternative<condition_list>(_expression) &&
std::get<condition_list>(_expression).conditions.empty();
}
};
} // namespace parsed
} // namespace alternator

View File

@@ -1,300 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "rjson.hh"
#include "error.hh"
#include <seastar/core/print.hh>
#include <seastar/core/thread.hh>
namespace rjson {
static allocator the_allocator;
/*
* This wrapper class adds nested level checks to rapidjson's handlers.
* Each rapidjson handler implements functions for accepting JSON values,
* which includes strings, numbers, objects, arrays, etc.
* Parsing objects and arrays needs to be performed carefully with regard
* to stack overflow - each object/array layer adds another stack frame
* to parsing, printing and destroying the parent JSON document.
* To prevent stack overflow, a rapidjson handler can be wrapped with
* guarded_json_handler, which accepts an additional max_nested_level parameter.
* After trying to exceed the max nested level, a proper rjson::error will be thrown.
*/
template<typename Handler, bool EnableYield>
struct guarded_yieldable_json_handler : public Handler {
size_t _nested_level = 0;
size_t _max_nested_level;
public:
using handler_base = Handler;
explicit guarded_yieldable_json_handler(size_t max_nested_level) : _max_nested_level(max_nested_level) {}
guarded_yieldable_json_handler(string_buffer& buf, size_t max_nested_level)
: handler_base(buf), _max_nested_level(max_nested_level) {}
void Parse(const char* str, size_t length) {
rapidjson::MemoryStream ms(static_cast<const char*>(str), length * sizeof(typename encoding::Ch));
rapidjson::EncodedInputStream<encoding, rapidjson::MemoryStream> is(ms);
rapidjson::GenericReader<encoding, encoding, allocator> reader(&the_allocator);
reader.Parse(is, *this);
if (reader.HasParseError()) {
throw rjson::error(format("Parsing JSON failed: {}", rapidjson::GetParseError_En(reader.GetParseErrorCode())));
}
//NOTICE: The handler has parsed the string, but in case of rapidjson::GenericDocument
// the data now resides in an internal stack_ variable, which is private instead of
// protected... which means we cannot simply access its data. Fortunately, another
// function for populating documents from SAX events can be abused to extract the data
// from the stack via gadget-oriented programming - we use an empty event generator
// which does nothing, and use it to call Populate(), which assumes that the generator
// will fill the stack with something. It won't, but our stack is already filled with
// data we want to steal, so once Populate() ends, our document will be properly parsed.
// A proper solution could be programmed once rapidjson declares this stack_ variable
// as protected instead of private, so that this class can access it.
auto dummy_generator = [](handler_base&){return true;};
handler_base::Populate(dummy_generator);
}
bool StartObject() {
++_nested_level;
check_nested_level();
maybe_yield();
return handler_base::StartObject();
}
bool EndObject(rapidjson::SizeType elements_count = 0) {
--_nested_level;
return handler_base::EndObject(elements_count);
}
bool StartArray() {
++_nested_level;
check_nested_level();
maybe_yield();
return handler_base::StartArray();
}
bool EndArray(rapidjson::SizeType elements_count = 0) {
--_nested_level;
return handler_base::EndArray(elements_count);
}
bool Null() { maybe_yield(); return handler_base::Null(); }
bool Bool(bool b) { maybe_yield(); return handler_base::Bool(b); }
bool Int(int i) { maybe_yield(); return handler_base::Int(i); }
bool Uint(unsigned u) { maybe_yield(); return handler_base::Uint(u); }
bool Int64(int64_t i64) { maybe_yield(); return handler_base::Int64(i64); }
bool Uint64(uint64_t u64) { maybe_yield(); return handler_base::Uint64(u64); }
bool Double(double d) { maybe_yield(); return handler_base::Double(d); }
bool String(const value::Ch* str, size_t length, bool copy = false) { maybe_yield(); return handler_base::String(str, length, copy); }
bool Key(const value::Ch* str, size_t length, bool copy = false) { maybe_yield(); return handler_base::Key(str, length, copy); }
protected:
static void maybe_yield() {
if constexpr (EnableYield) {
thread::maybe_yield();
}
}
void check_nested_level() const {
if (RAPIDJSON_UNLIKELY(_nested_level > _max_nested_level)) {
throw rjson::error(format("Max nested level reached: {}", _max_nested_level));
}
}
};
std::string print(const rjson::value& value) {
string_buffer buffer;
guarded_yieldable_json_handler<writer, false> writer(buffer, 78);
value.Accept(writer);
return std::string(buffer.GetString());
}
rjson::value copy(const rjson::value& value) {
return rjson::value(value, the_allocator);
}
rjson::value parse(std::string_view str) {
guarded_yieldable_json_handler<document, false> d(78);
d.Parse(str.data(), str.size());
if (d.HasParseError()) {
throw rjson::error(format("Parsing JSON failed: {}", GetParseError_En(d.GetParseError())));
}
rjson::value& v = d;
return std::move(v);
}
rjson::value parse_yieldable(std::string_view str) {
guarded_yieldable_json_handler<document, true> d(78);
d.Parse(str.data(), str.size());
if (d.HasParseError()) {
throw rjson::error(format("Parsing JSON failed: {}", GetParseError_En(d.GetParseError())));
}
rjson::value& v = d;
return std::move(v);
}
rjson::value& get(rjson::value& value, std::string_view name) {
// Although FindMember() has a variant taking a StringRef, it ignores the
// given length (see https://github.com/Tencent/rapidjson/issues/1649).
// Luckily, the variant taking a GenericValue doesn't share this bug,
// and we can create a string GenericValue without copying the string.
auto member_it = value.FindMember(rjson::value(name.data(), name.size()));
if (member_it != value.MemberEnd())
return member_it->value;
else {
throw rjson::error(format("JSON parameter {} not found", name));
}
}
const rjson::value& get(const rjson::value& value, std::string_view name) {
auto member_it = value.FindMember(rjson::value(name.data(), name.size()));
if (member_it != value.MemberEnd())
return member_it->value;
else {
throw rjson::error(format("JSON parameter {} not found", name));
}
}
rjson::value from_string(const std::string& str) {
return rjson::value(str.c_str(), str.size(), the_allocator);
}
rjson::value from_string(const sstring& str) {
return rjson::value(str.c_str(), str.size(), the_allocator);
}
rjson::value from_string(const char* str, size_t size) {
return rjson::value(str, size, the_allocator);
}
rjson::value from_string(std::string_view view) {
return rjson::value(view.data(), view.size(), the_allocator);
}
const rjson::value* find(const rjson::value& value, std::string_view name) {
// Although FindMember() has a variant taking a StringRef, it ignores the
// given length (see https://github.com/Tencent/rapidjson/issues/1649).
// Luckily, the variant taking a GenericValue doesn't share this bug,
// and we can create a string GenericValue without copying the string.
auto member_it = value.FindMember(rjson::value(name.data(), name.size()));
return member_it != value.MemberEnd() ? &member_it->value : nullptr;
}
rjson::value* find(rjson::value& value, std::string_view name) {
auto member_it = value.FindMember(rjson::value(name.data(), name.size()));
return member_it != value.MemberEnd() ? &member_it->value : nullptr;
}
bool remove_member(rjson::value& value, std::string_view name) {
// Although RemoveMember() has a variant taking a StringRef, it ignores
// given length (see https://github.com/Tencent/rapidjson/issues/1649).
// Luckily, the variant taking a GenericValue doesn't share this bug,
// and we can create a string GenericValue without copying the string.
return value.RemoveMember(rjson::value(name.data(), name.size()));
}
void set_with_string_name(rjson::value& base, const std::string& name, rjson::value&& member) {
base.AddMember(rjson::value(name.c_str(), name.size(), the_allocator), std::move(member), the_allocator);
}
void set_with_string_name(rjson::value& base, std::string_view name, rjson::value&& member) {
base.AddMember(rjson::value(name.data(), name.size(), the_allocator), std::move(member), the_allocator);
}
void set_with_string_name(rjson::value& base, const std::string& name, rjson::string_ref_type member) {
base.AddMember(rjson::value(name.c_str(), name.size(), the_allocator), rjson::value(member), the_allocator);
}
void set_with_string_name(rjson::value& base, std::string_view name, rjson::string_ref_type member) {
base.AddMember(rjson::value(name.data(), name.size(), the_allocator), rjson::value(member), the_allocator);
}
void set(rjson::value& base, rjson::string_ref_type name, rjson::value&& member) {
base.AddMember(name, std::move(member), the_allocator);
}
void set(rjson::value& base, rjson::string_ref_type name, rjson::string_ref_type member) {
base.AddMember(name, rjson::value(member), the_allocator);
}
void push_back(rjson::value& base_array, rjson::value&& item) {
base_array.PushBack(std::move(item), the_allocator);
}
bool single_value_comp::operator()(const rjson::value& r1, const rjson::value& r2) const {
auto r1_type = r1.GetType();
auto r2_type = r2.GetType();
// null is the smallest type and compares with every other type, nothing is lesser than null
if (r1_type == rjson::type::kNullType || r2_type == rjson::type::kNullType) {
return r1_type < r2_type;
}
// only null, true, and false are comparable with each other, other types are not compatible
if (r1_type != r2_type) {
if (r1_type > rjson::type::kTrueType || r2_type > rjson::type::kTrueType) {
throw rjson::error(format("Types are not comparable: {} {}", r1, r2));
}
}
switch (r1_type) {
case rjson::type::kNullType:
// fall-through
case rjson::type::kFalseType:
// fall-through
case rjson::type::kTrueType:
return r1_type < r2_type;
case rjson::type::kObjectType:
throw rjson::error("Object type comparison is not supported");
case rjson::type::kArrayType:
throw rjson::error("Array type comparison is not supported");
case rjson::type::kStringType: {
const size_t r1_len = r1.GetStringLength();
const size_t r2_len = r2.GetStringLength();
size_t len = std::min(r1_len, r2_len);
int result = std::strncmp(r1.GetString(), r2.GetString(), len);
return result < 0 || (result == 0 && r1_len < r2_len);
}
case rjson::type::kNumberType: {
if (r1.IsInt() && r2.IsInt()) {
return r1.GetInt() < r2.GetInt();
} else if (r1.IsUint() && r2.IsUint()) {
return r1.GetUint() < r2.GetUint();
} else if (r1.IsInt64() && r2.IsInt64()) {
return r1.GetInt64() < r2.GetInt64();
} else if (r1.IsUint64() && r2.IsUint64()) {
return r1.GetUint64() < r2.GetUint64();
} else {
// it's safe to call GetDouble() on any number type
return r1.GetDouble() < r2.GetDouble();
}
}
default:
return false;
}
}
} // end namespace rjson
std::ostream& std::operator<<(std::ostream& os, const rjson::value& v) {
return os << rjson::print(v);
}

View File

@@ -1,177 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
/*
* rjson is a wrapper over rapidjson library, providing fast JSON parsing and generation.
*
* rapidjson has strict copy elision policies, which, among other things, involves
* using provided char arrays without copying them and allows copying objects only explicitly.
* As such, one should be careful when passing strings with limited liveness
* (e.g. data underneath local std::strings) to rjson functions, because created JSON objects
* may end up relying on dangling char pointers. All rjson functions that create JSONs from strings
* by rjson have both APIs for string_ref_type (more optimal, used when the string is known to live
* at least as long as the object, e.g. a static char array) and for std::strings. The more optimal
* variants should be used *only* if the liveness of the string is guaranteed, otherwise it will
* result in undefined behaviour.
* Also, bear in mind that methods exposed by rjson::value are generic, but some of them
* work fine only for specific types. In case the type does not match, an rjson::error will be thrown.
* Examples of such mismatched usages is calling MemberCount() on a JSON value not of object type
* or calling Size() on a non-array value.
*/
#include <string>
#include <stdexcept>
namespace rjson {
class error : public std::exception {
std::string _msg;
public:
error() = default;
error(const std::string& msg) : _msg(msg) {}
virtual const char* what() const noexcept override { return _msg.c_str(); }
};
}
// rapidjson configuration macros
#define RAPIDJSON_HAS_STDSTRING 1
// Default rjson policy is to use assert() - which is dangerous for two reasons:
// 1. assert() can be turned off with -DNDEBUG
// 2. assert() crashes a program
// Fortunately, the default policy can be overridden, and so rapidjson errors will
// throw an rjson::error exception instead.
#define RAPIDJSON_ASSERT(x) do { if (!(x)) throw rjson::error(std::string("JSON error: condition not met: ") + #x); } while (0)
#include <rapidjson/document.h>
#include <rapidjson/writer.h>
#include <rapidjson/stringbuffer.h>
#include <rapidjson/error/en.h>
#include <seastar/core/sstring.hh>
#include "seastarx.hh"
namespace rjson {
using allocator = rapidjson::CrtAllocator;
using encoding = rapidjson::UTF8<>;
using document = rapidjson::GenericDocument<encoding, allocator>;
using value = rapidjson::GenericValue<encoding, allocator>;
using string_ref_type = value::StringRefType;
using string_buffer = rapidjson::GenericStringBuffer<encoding>;
using writer = rapidjson::Writer<string_buffer, encoding>;
using type = rapidjson::Type;
// Returns an object representing JSON's null
inline rjson::value null_value() {
return rjson::value(rapidjson::kNullType);
}
// Returns an empty JSON object - {}
inline rjson::value empty_object() {
return rjson::value(rapidjson::kObjectType);
}
// Returns an empty JSON array - []
inline rjson::value empty_array() {
return rjson::value(rapidjson::kArrayType);
}
// Returns an empty JSON string - ""
inline rjson::value empty_string() {
return rjson::value(rapidjson::kStringType);
}
// Convert the JSON value to a string with JSON syntax, the opposite of parse().
// The representation is dense - without any redundant indentation.
std::string print(const rjson::value& value);
// Returns a string_view to the string held in a JSON value (which is
// assumed to hold a string, i.e., v.IsString() == true). This is a view
// to the existing data - no copying is done.
inline std::string_view to_string_view(const rjson::value& v) {
return std::string_view(v.GetString(), v.GetStringLength());
}
// Copies given JSON value - involves allocation
rjson::value copy(const rjson::value& value);
// Parses a JSON value from given string or raw character array.
// The string/char array liveness does not need to be persisted,
// as parse() will allocate member names and values.
// Throws rjson::error if parsing failed.
rjson::value parse(std::string_view str);
// Needs to be run in thread context
rjson::value parse_yieldable(std::string_view str);
// Creates a JSON value (of JSON string type) out of internal string representations.
// The string value is copied, so str's liveness does not need to be persisted.
rjson::value from_string(const std::string& str);
rjson::value from_string(const sstring& str);
rjson::value from_string(const char* str, size_t size);
rjson::value from_string(std::string_view view);
// Returns a pointer to JSON member if it exists, nullptr otherwise
rjson::value* find(rjson::value& value, std::string_view name);
const rjson::value* find(const rjson::value& value, std::string_view name);
// Returns a reference to JSON member if it exists, throws otherwise
rjson::value& get(rjson::value& value, std::string_view name);
const rjson::value& get(const rjson::value& value, std::string_view name);
// Sets a member in given JSON object by moving the member - allocates the name.
// Throws if base is not a JSON object.
void set_with_string_name(rjson::value& base, const std::string& name, rjson::value&& member);
void set_with_string_name(rjson::value& base, std::string_view name, rjson::value&& member);
// Sets a string member in given JSON object by assigning its reference - allocates the name.
// NOTICE: member string liveness must be ensured to be at least as long as base's.
// Throws if base is not a JSON object.
void set_with_string_name(rjson::value& base, const std::string& name, rjson::string_ref_type member);
void set_with_string_name(rjson::value& base, std::string_view name, rjson::string_ref_type member);
// Sets a member in given JSON object by moving the member.
// NOTICE: name liveness must be ensured to be at least as long as base's.
// Throws if base is not a JSON object.
void set(rjson::value& base, rjson::string_ref_type name, rjson::value&& member);
// Sets a string member in given JSON object by assigning its reference.
// NOTICE: name liveness must be ensured to be at least as long as base's.
// NOTICE: member liveness must be ensured to be at least as long as base's.
// Throws if base is not a JSON object.
void set(rjson::value& base, rjson::string_ref_type name, rjson::string_ref_type member);
// Adds a value to a JSON list by moving the item to its end.
// Throws if base_array is not a JSON array.
void push_back(rjson::value& base_array, rjson::value&& item);
// Remove a member from a JSON object. Throws if value isn't an object.
bool remove_member(rjson::value& value, std::string_view name);
struct single_value_comp {
bool operator()(const rjson::value& r1, const rjson::value& r2) const;
};
} // end namespace rjson
namespace std {
std::ostream& operator<<(std::ostream& os, const rjson::value& v);
}

View File

@@ -1,128 +0,0 @@
/*
* Copyright 2020 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include "seastarx.hh"
#include "service/storage_proxy.hh"
#include "service/storage_proxy.hh"
#include "rjson.hh"
#include "executor.hh"
namespace alternator {
// An rmw_operation encapsulates the common logic of all the item update
// operations which may involve a read of the item before the write
// (so-called Read-Modify-Write operations). These operations include PutItem,
// UpdateItem and DeleteItem: All of these may be conditional operations (the
// "Expected" parameter) which requir a read before the write, and UpdateItem
// may also have an update expression which refers to the item's old value.
//
// The code below supports running the read and the write together as one
// transaction using LWT (this is why rmw_operation is a subclass of
// cas_request, as required by storage_proxy::cas()), but also has optional
// modes not using LWT.
class rmw_operation : public service::cas_request, public enable_shared_from_this<rmw_operation> {
public:
// The following options choose which mechanism to use for isolating
// parallel write operations:
// * The FORBID_RMW option forbids RMW (read-modify-write) operations
// such as conditional updates. For the remaining write-only
// operations, ordinary quorum writes are isolated enough.
// * The LWT_ALWAYS option always uses LWT (lightweight transactions)
// for any write operation - whether or not it also has a read.
// * The LWT_RMW_ONLY option uses LWT only for RMW operations, and uses
// ordinary quorum writes for write-only operations.
// This option is not safe if the user may send both RMW and write-only
// operations on the same item.
// * The UNSAFE_RMW option does read-modify-write operations as separate
// read and write. It is unsafe - concurrent RMW operations are not
// isolated at all. This option will likely be removed in the future.
enum class write_isolation {
FORBID_RMW, LWT_ALWAYS, LWT_RMW_ONLY, UNSAFE_RMW
};
static constexpr auto WRITE_ISOLATION_TAG_KEY = "system:write_isolation";
static write_isolation get_write_isolation_for_schema(schema_ptr schema);
static write_isolation default_write_isolation;
public:
static void set_default_write_isolation(std::string_view mode);
protected:
// The full request JSON
rjson::value _request;
// All RMW operations involve a single item with a specific partition
// and optional clustering key, in a single table, so the following
// information is common to all of them:
schema_ptr _schema;
partition_key _pk = partition_key::make_empty();
clustering_key _ck = clustering_key::make_empty();
write_isolation _write_isolation;
// All RMW operations can have a ReturnValues parameter from the following
// choices. But note that only UpdateItem actually supports all of them:
enum class returnvalues {
NONE, ALL_OLD, UPDATED_OLD, ALL_NEW, UPDATED_NEW
} _returnvalues;
static returnvalues parse_returnvalues(const rjson::value& request);
// When _returnvalues != NONE, apply() should store here, in JSON form,
// the values which are to be returned in the "Attributes" field.
// The default null JSON means do not return an Attributes field at all.
// This field is marked "mutable" so that the const apply() can modify
// it (see explanation below), but note that because apply() may be
// called more than once, if apply() will sometimes set this field it
// must set it (even if just to the default empty value) every time.
mutable rjson::value _return_attributes;
public:
// The constructor of a rmw_operation subclass should parse the request
// and try to discover as many input errors as it can before really
// attempting the read or write operations.
rmw_operation(service::storage_proxy& proxy, rjson::value&& request);
// rmw_operation subclasses (update_item_operation, put_item_operation
// and delete_item_operation) shall implement an apply() function which
// takes the previous value of the item (if it was read) and creates the
// write mutation. If the previous value of item does not pass the needed
// conditional expression, apply() should return an empty optional.
// apply() may throw if it encounters input errors not discovered during
// the constructor.
// apply() may be called more than once in case of contention, so it must
// not change the state saved in the object (issue #7218 was caused by
// violating this). We mark apply() "const" to let the compiler validate
// this for us. The output-only field _return_attributes is marked
// "mutable" above so that apply() can still write to it.
virtual std::optional<mutation> apply(std::unique_ptr<rjson::value> previous_item, api::timestamp_type ts) const = 0;
// Convert the above apply() into the signature needed by cas_request:
virtual std::optional<mutation> apply(foreign_ptr<lw_shared_ptr<query::result>> qr, const query::partition_slice& slice, api::timestamp_type ts) override;
virtual ~rmw_operation() = default;
schema_ptr schema() const { return _schema; }
const rjson::value& request() const { return _request; }
rjson::value&& move_request() && { return std::move(_request); }
future<executor::request_return_type> execute(service::storage_proxy& proxy,
service::client_state& client_state,
tracing::trace_state_ptr trace_state,
service_permit permit,
bool needs_read_before_write,
stats& stats);
std::optional<shard_id> shard_for_execute(bool needs_read_before_write);
};
} // namespace alternator

View File

@@ -1,367 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "base64.hh"
#include "log.hh"
#include "serialization.hh"
#include "error.hh"
#include "rapidjson/writer.h"
#include "concrete_types.hh"
#include "cql3/type_json.hh"
static logging::logger slogger("alternator-serialization");
namespace alternator {
type_info type_info_from_string(std::string_view type) {
static thread_local const std::unordered_map<std::string_view, type_info> type_infos = {
{"S", {alternator_type::S, utf8_type}},
{"B", {alternator_type::B, bytes_type}},
{"BOOL", {alternator_type::BOOL, boolean_type}},
{"N", {alternator_type::N, decimal_type}}, //FIXME: Replace with custom Alternator type when implemented
};
auto it = type_infos.find(type);
if (it == type_infos.end()) {
return {alternator_type::NOT_SUPPORTED_YET, utf8_type};
}
return it->second;
}
type_representation represent_type(alternator_type atype) {
static thread_local const std::unordered_map<alternator_type, type_representation> type_representations = {
{alternator_type::S, {"S", utf8_type}},
{alternator_type::B, {"B", bytes_type}},
{alternator_type::BOOL, {"BOOL", boolean_type}},
{alternator_type::N, {"N", decimal_type}}, //FIXME: Replace with custom Alternator type when implemented
};
auto it = type_representations.find(atype);
if (it == type_representations.end()) {
throw std::runtime_error(format("Unknown alternator type {}", int8_t(atype)));
}
return it->second;
}
struct from_json_visitor {
const rjson::value& v;
bytes_ostream& bo;
void operator()(const reversed_type_impl& t) const { visit(*t.underlying_type(), from_json_visitor{v, bo}); };
void operator()(const string_type_impl& t) {
bo.write(t.from_string(sstring_view(v.GetString(), v.GetStringLength())));
}
void operator()(const bytes_type_impl& t) const {
bo.write(base64_decode(v));
}
void operator()(const boolean_type_impl& t) const {
bo.write(boolean_type->decompose(v.GetBool()));
}
void operator()(const decimal_type_impl& t) const {
bo.write(t.from_string(sstring_view(v.GetString(), v.GetStringLength())));
}
// default
void operator()(const abstract_type& t) const {
bo.write(from_json_object(t, Json::Value(rjson::print(v)), cql_serialization_format::internal()));
}
};
bytes serialize_item(const rjson::value& item) {
if (item.IsNull() || item.MemberCount() != 1) {
throw api_error("ValidationException", format("An item can contain only one attribute definition: {}", item));
}
auto it = item.MemberBegin();
type_info type_info = type_info_from_string(rjson::to_string_view(it->name)); // JSON keys are guaranteed to be strings
if (type_info.atype == alternator_type::NOT_SUPPORTED_YET) {
slogger.trace("Non-optimal serialization of type {}", it->name.GetString());
return bytes{int8_t(type_info.atype)} + to_bytes(rjson::print(item));
}
bytes_ostream bo;
bo.write(bytes{int8_t(type_info.atype)});
visit(*type_info.dtype, from_json_visitor{it->value, bo});
return bytes(bo.linearize());
}
struct to_json_visitor {
rjson::value& deserialized;
const std::string& type_ident;
bytes_view bv;
void operator()(const reversed_type_impl& t) const { visit(*t.underlying_type(), to_json_visitor{deserialized, type_ident, bv}); };
void operator()(const decimal_type_impl& t) const {
auto s = to_json_string(*decimal_type, bytes(bv));
//FIXME(sarna): unnecessary copy
rjson::set_with_string_name(deserialized, type_ident, rjson::from_string(s));
}
void operator()(const string_type_impl& t) {
rjson::set_with_string_name(deserialized, type_ident, rjson::from_string(reinterpret_cast<const char *>(bv.data()), bv.size()));
}
void operator()(const bytes_type_impl& t) const {
std::string b64 = base64_encode(bv);
rjson::set_with_string_name(deserialized, type_ident, rjson::from_string(b64));
}
// default
void operator()(const abstract_type& t) const {
rjson::set_with_string_name(deserialized, type_ident, rjson::parse(to_json_string(t, bytes(bv))));
}
};
rjson::value deserialize_item(bytes_view bv) {
rjson::value deserialized(rapidjson::kObjectType);
if (bv.empty()) {
throw api_error("ValidationException", "Serialized value empty");
}
alternator_type atype = alternator_type(bv[0]);
bv.remove_prefix(1);
if (atype == alternator_type::NOT_SUPPORTED_YET) {
slogger.trace("Non-optimal deserialization of alternator type {}", int8_t(atype));
return rjson::parse(std::string_view(reinterpret_cast<const char *>(bv.data()), bv.size()));
}
type_representation type_representation = represent_type(atype);
visit(*type_representation.dtype, to_json_visitor{deserialized, type_representation.ident, bv});
return deserialized;
}
std::string type_to_string(data_type type) {
static thread_local std::unordered_map<data_type, std::string> types = {
{utf8_type, "S"},
{bytes_type, "B"},
{boolean_type, "BOOL"},
{decimal_type, "N"}, // FIXME: use a specialized Alternator number type instead of the general decimal_type
};
auto it = types.find(type);
if (it == types.end()) {
// fall back to string, in order to be able to present
// internal Scylla types in a human-readable way
return "S";
}
return it->second;
}
bytes get_key_column_value(const rjson::value& item, const column_definition& column) {
std::string column_name = column.name_as_text();
const rjson::value* key_typed_value = rjson::find(item, column_name);
if (!key_typed_value) {
throw api_error("ValidationException", format("Key column {} not found", column_name));
}
return get_key_from_typed_value(*key_typed_value, column);
}
// Parses the JSON encoding for a key value, which is a map with a single
// entry, whose key is the type (expected to match the key column's type)
// and the value is the encoded value.
bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column_definition& column) {
if (!key_typed_value.IsObject() || key_typed_value.MemberCount() != 1 ||
!key_typed_value.MemberBegin()->value.IsString()) {
throw api_error("ValidationException",
format("Malformed value object for key column {}: {}",
column.name_as_text(), key_typed_value));
}
auto it = key_typed_value.MemberBegin();
if (it->name != type_to_string(column.type)) {
throw api_error("ValidationException",
format("Type mismatch: expected type {} for key column {}, got type {}",
type_to_string(column.type), column.name_as_text(), it->name.GetString()));
}
std::string_view value_view = rjson::to_string_view(it->value);
if (value_view.empty()) {
throw api_error("ValidationException",
format("The AttributeValue for a key attribute cannot contain an empty string value. Key: {}", column.name_as_text()));
}
if (column.type == bytes_type) {
return base64_decode(it->value);
} else {
return column.type->from_string(rjson::to_string_view(it->value));
}
}
rjson::value json_key_column_value(bytes_view cell, const column_definition& column) {
if (column.type == bytes_type) {
std::string b64 = base64_encode(cell);
return rjson::from_string(b64);
} if (column.type == utf8_type) {
return rjson::from_string(std::string(reinterpret_cast<const char*>(cell.data()), cell.size()));
} else if (column.type == decimal_type) {
// FIXME: use specialized Alternator number type, not the more
// general "decimal_type". A dedicated type can be more efficient
// in storage space and in parsing speed.
auto s = to_json_string(*decimal_type, bytes(cell));
return rjson::from_string(s);
} else {
// Support for arbitrary key types is useful for parsing values of virtual tables,
// which can involve any type supported by Scylla.
// In order to guarantee that the returned type is parsable by alternator clients,
// they are represented simply as strings.
return rjson::from_string(column.type->to_string(bytes(cell)));
}
}
partition_key pk_from_json(const rjson::value& item, schema_ptr schema) {
std::vector<bytes> raw_pk;
// FIXME: this is a loop, but we really allow only one partition key column.
for (const column_definition& cdef : schema->partition_key_columns()) {
bytes raw_value = get_key_column_value(item, cdef);
raw_pk.push_back(std::move(raw_value));
}
return partition_key::from_exploded(raw_pk);
}
clustering_key ck_from_json(const rjson::value& item, schema_ptr schema) {
if (schema->clustering_key_size() == 0) {
return clustering_key::make_empty();
}
std::vector<bytes> raw_ck;
// FIXME: this is a loop, but we really allow only one clustering key column.
for (const column_definition& cdef : schema->clustering_key_columns()) {
bytes raw_value = get_key_column_value(item, cdef);
raw_ck.push_back(std::move(raw_value));
}
return clustering_key::from_exploded(raw_ck);
}
big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic) {
if (!v.IsObject() || v.MemberCount() != 1) {
throw api_error("ValidationException", format("{}: invalid number object", diagnostic));
}
auto it = v.MemberBegin();
if (it->name != "N") {
throw api_error("ValidationException", format("{}: expected number, found type '{}'", diagnostic, it->name));
}
if (it->value.IsNumber()) {
// FIXME(sarna): should use big_decimal constructor with numeric values directly:
return big_decimal(rjson::print(it->value));
}
if (!it->value.IsString()) {
throw api_error("ValidationException", format("{}: improperly formatted number constant", diagnostic));
}
return big_decimal(it->value.GetString());
}
const std::pair<std::string, const rjson::value*> unwrap_set(const rjson::value& v) {
if (!v.IsObject() || v.MemberCount() != 1) {
return {"", nullptr};
}
auto it = v.MemberBegin();
const std::string it_key = it->name.GetString();
if (it_key != "SS" && it_key != "BS" && it_key != "NS") {
return {"", nullptr};
}
return std::make_pair(it_key, &(it->value));
}
const rjson::value* unwrap_list(const rjson::value& v) {
if (!v.IsObject() || v.MemberCount() != 1) {
return nullptr;
}
auto it = v.MemberBegin();
if (it->name != std::string("L")) {
return nullptr;
}
return &(it->value);
}
// Take two JSON-encoded numeric values ({"N": "thenumber"}) and return the
// sum, again as a JSON-encoded number.
rjson::value number_add(const rjson::value& v1, const rjson::value& v2) {
auto n1 = unwrap_number(v1, "UpdateExpression");
auto n2 = unwrap_number(v2, "UpdateExpression");
rjson::value ret = rjson::empty_object();
std::string str_ret = std::string((n1 + n2).to_string());
rjson::set(ret, "N", rjson::from_string(str_ret));
return ret;
}
rjson::value number_subtract(const rjson::value& v1, const rjson::value& v2) {
auto n1 = unwrap_number(v1, "UpdateExpression");
auto n2 = unwrap_number(v2, "UpdateExpression");
rjson::value ret = rjson::empty_object();
std::string str_ret = std::string((n1 - n2).to_string());
rjson::set(ret, "N", rjson::from_string(str_ret));
return ret;
}
// Take two JSON-encoded set values (e.g. {"SS": [...the actual set]}) and
// return the sum of both sets, again as a set value.
rjson::value set_sum(const rjson::value& v1, const rjson::value& v2) {
auto [set1_type, set1] = unwrap_set(v1);
auto [set2_type, set2] = unwrap_set(v2);
if (set1_type != set2_type) {
throw api_error("ValidationException", format("Mismatched set types: {} and {}", set1_type, set2_type));
}
if (!set1 || !set2) {
throw api_error("ValidationException", "UpdateExpression: ADD operation for sets must be given sets as arguments");
}
rjson::value sum = rjson::copy(*set1);
std::set<rjson::value, rjson::single_value_comp> set1_raw;
for (auto it = sum.Begin(); it != sum.End(); ++it) {
set1_raw.insert(rjson::copy(*it));
}
for (const auto& a : set2->GetArray()) {
if (set1_raw.count(a) == 0) {
rjson::push_back(sum, rjson::copy(a));
}
}
rjson::value ret = rjson::empty_object();
rjson::set_with_string_name(ret, set1_type, std::move(sum));
return ret;
}
// Take two JSON-encoded set values (e.g. {"SS": [...the actual list]}) and
// return the difference of s1 - s2, again as a set value.
// DynamoDB does not allow empty sets, so if resulting set is empty, return
// an unset optional instead.
std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value& v2) {
auto [set1_type, set1] = unwrap_set(v1);
auto [set2_type, set2] = unwrap_set(v2);
if (set1_type != set2_type) {
throw api_error("ValidationException", format("Mismatched set types: {} and {}", set1_type, set2_type));
}
if (!set1 || !set2) {
throw api_error("ValidationException", "UpdateExpression: DELETE operation can only be performed on a set");
}
std::set<rjson::value, rjson::single_value_comp> set1_raw;
for (auto it = set1->Begin(); it != set1->End(); ++it) {
set1_raw.insert(rjson::copy(*it));
}
for (const auto& a : set2->GetArray()) {
set1_raw.erase(a);
}
if (set1_raw.empty()) {
return std::nullopt;
}
rjson::value ret = rjson::empty_object();
rjson::set_with_string_name(ret, set1_type, rjson::empty_array());
rjson::value& result_set = ret[set1_type];
for (const auto& a : set1_raw) {
rjson::push_back(result_set, rjson::copy(a));
}
return ret;
}
}

View File

@@ -1,89 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <string>
#include <string_view>
#include "types.hh"
#include "schema_fwd.hh"
#include "keys.hh"
#include "rjson.hh"
#include "utils/big_decimal.hh"
namespace alternator {
enum class alternator_type : int8_t {
S, B, BOOL, N, NOT_SUPPORTED_YET
};
struct type_info {
alternator_type atype;
data_type dtype;
};
struct type_representation {
std::string ident;
data_type dtype;
};
type_info type_info_from_string(std::string_view type);
type_representation represent_type(alternator_type atype);
bytes serialize_item(const rjson::value& item);
rjson::value deserialize_item(bytes_view bv);
std::string type_to_string(data_type type);
bytes get_key_column_value(const rjson::value& item, const column_definition& column);
bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column_definition& column);
rjson::value json_key_column_value(bytes_view cell, const column_definition& column);
partition_key pk_from_json(const rjson::value& item, schema_ptr schema);
clustering_key ck_from_json(const rjson::value& item, schema_ptr schema);
// If v encodes a number (i.e., it is a {"N": [...]}, returns an object representing it. Otherwise,
// raises ValidationException with diagnostic.
big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic);
// Check if a given JSON object encodes a set (i.e., it is a {"SS": [...]}, or "NS", "BS"
// and returns set's type and a pointer to that set. If the object does not encode a set,
// returned value is {"", nullptr}
const std::pair<std::string, const rjson::value*> unwrap_set(const rjson::value& v);
// Check if a given JSON object encodes a list (i.e., it is a {"L": [...]}
// and returns a pointer to that list.
const rjson::value* unwrap_list(const rjson::value& v);
// Take two JSON-encoded numeric values ({"N": "thenumber"}) and return the
// sum, again as a JSON-encoded number.
rjson::value number_add(const rjson::value& v1, const rjson::value& v2);
rjson::value number_subtract(const rjson::value& v1, const rjson::value& v2);
// Take two JSON-encoded set values (e.g. {"SS": [...the actual set]}) and
// return the sum of both sets, again as a set value.
rjson::value set_sum(const rjson::value& v1, const rjson::value& v2);
// Take two JSON-encoded set values (e.g. {"SS": [...the actual list]}) and
// return the difference of s1 - s2, again as a set value.
// DynamoDB does not allow empty sets, so if resulting set is empty, return
// an unset optional instead.
std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value& v2);
}

View File

@@ -1,487 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "alternator/server.hh"
#include "log.hh"
#include <seastar/http/function_handlers.hh>
#include <seastar/json/json_elements.hh>
#include "seastarx.hh"
#include "error.hh"
#include "rjson.hh"
#include "auth.hh"
#include <cctype>
#include "cql3/query_processor.hh"
#include "service/storage_service.hh"
#include "utils/overloaded_functor.hh"
static logging::logger slogger("alternator-server");
using namespace httpd;
namespace alternator {
static constexpr auto TARGET = "X-Amz-Target";
inline std::vector<std::string_view> split(std::string_view text, char separator) {
std::vector<std::string_view> tokens;
if (text == "") {
return tokens;
}
while (true) {
auto pos = text.find_first_of(separator);
if (pos != std::string_view::npos) {
tokens.emplace_back(text.data(), pos);
text.remove_prefix(pos + 1);
} else {
tokens.emplace_back(text);
break;
}
}
return tokens;
}
// DynamoDB HTTP error responses are structured as follows
// https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Programming.Errors.html
// Our handlers throw an exception to report an error. If the exception
// is of type alternator::api_error, it unwrapped and properly reported to
// the user directly. Other exceptions are unexpected, and reported as
// Internal Server Error.
class api_handler : public handler_base {
public:
api_handler(const std::function<future<executor::request_return_type>(std::unique_ptr<request> req)>& _handle) : _f_handle(
[this, _handle](std::unique_ptr<request> req, std::unique_ptr<reply> rep) {
return seastar::futurize_invoke(_handle, std::move(req)).then_wrapped([this, rep = std::move(rep)](future<executor::request_return_type> resf) mutable {
if (resf.failed()) {
// Exceptions of type api_error are wrapped as JSON and
// returned to the client as expected. Other types of
// exceptions are unexpected, and returned to the user
// as an internal server error:
api_error ret;
try {
resf.get();
} catch (api_error &ae) {
ret = ae;
} catch (rjson::error & re) {
ret = api_error("ValidationException", re.what());
} catch (...) {
ret = api_error(
"Internal Server Error",
format("Internal server error: {}", std::current_exception()),
reply::status_type::internal_server_error);
}
generate_error_reply(*rep, ret);
return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
}
auto res = resf.get0();
std::visit(overloaded_functor {
[&] (const json::json_return_type& json_return_value) {
slogger.trace("api_handler success case");
if (json_return_value._body_writer) {
rep->write_body("json", std::move(json_return_value._body_writer));
} else {
rep->_content += json_return_value._res;
}
},
[&] (const api_error& err) {
generate_error_reply(*rep, err);
}
}, res);
return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
});
}), _type("json") { }
api_handler(const api_handler&) = default;
future<std::unique_ptr<reply>> handle(const sstring& path,
std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
return _f_handle(std::move(req), std::move(rep)).then(
[this](std::unique_ptr<reply> rep) {
rep->done(_type);
return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
});
}
protected:
void generate_error_reply(reply& rep, const api_error& err) {
rep._content += "{\"__type\":\"com.amazonaws.dynamodb.v20120810#" + err._type + "\"," +
"\"message\":\"" + err._msg + "\"}";
rep._status = err._http_code;
slogger.trace("api_handler error case: {}", rep._content);
}
future_handler_function _f_handle;
sstring _type;
};
class gated_handler : public handler_base {
seastar::gate& _gate;
public:
gated_handler(seastar::gate& gate) : _gate(gate) {}
virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) = 0;
virtual future<std::unique_ptr<reply>> handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) final override {
return with_gate(_gate, [this, &path, req = std::move(req), rep = std::move(rep)] () mutable {
return do_handle(path, std::move(req), std::move(rep));
});
}
};
class health_handler : public gated_handler {
public:
health_handler(seastar::gate& pending_requests) : gated_handler(pending_requests) {}
protected:
virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
rep->set_status(reply::status_type::ok);
rep->write_body("txt", format("healthy: {}", req->get_header("Host")));
return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
}
};
class local_nodelist_handler : public gated_handler {
public:
local_nodelist_handler(seastar::gate& pending_requests) : gated_handler(pending_requests) {}
protected:
virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
rjson::value results = rjson::empty_array();
// It's very easy to get a list of all live nodes on the cluster,
// using gms::get_local_gossiper().get_live_members(). But getting
// just the list of live nodes in this DC needs more elaborate code:
sstring local_dc = locator::i_endpoint_snitch::get_local_snitch_ptr()->get_datacenter(
utils::fb_utilities::get_broadcast_address());
std::unordered_set<gms::inet_address> local_dc_nodes =
service::get_local_storage_service().get_token_metadata().
get_topology().get_datacenter_endpoints().at(local_dc);
for (auto& ip : local_dc_nodes) {
if (gms::get_local_gossiper().is_alive(ip)) {
rjson::push_back(results, rjson::from_string(ip.to_sstring()));
}
}
rep->set_status(reply::status_type::ok);
rep->set_content_type("json");
rep->_content = rjson::print(results);
return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
}
};
future<> server::verify_signature(const request& req) {
if (!_enforce_authorization) {
slogger.debug("Skipping authorization");
return make_ready_future<>();
}
auto host_it = req._headers.find("Host");
if (host_it == req._headers.end()) {
throw api_error("InvalidSignatureException", "Host header is mandatory for signature verification");
}
auto authorization_it = req._headers.find("Authorization");
if (authorization_it == req._headers.end()) {
throw api_error("InvalidSignatureException", "Authorization header is mandatory for signature verification");
}
std::string host = host_it->second;
std::vector<std::string_view> credentials_raw = split(authorization_it->second, ' ');
std::string credential;
std::string user_signature;
std::string signed_headers_str;
std::vector<std::string_view> signed_headers;
for (std::string_view entry : credentials_raw) {
std::vector<std::string_view> entry_split = split(entry, '=');
if (entry_split.size() != 2) {
if (entry != "AWS4-HMAC-SHA256") {
throw api_error("InvalidSignatureException", format("Only AWS4-HMAC-SHA256 algorithm is supported. Found: {}", entry));
}
continue;
}
std::string_view auth_value = entry_split[1];
// Commas appear as an additional (quite redundant) delimiter
if (auth_value.back() == ',') {
auth_value.remove_suffix(1);
}
if (entry_split[0] == "Credential") {
credential = std::string(auth_value);
} else if (entry_split[0] == "Signature") {
user_signature = std::string(auth_value);
} else if (entry_split[0] == "SignedHeaders") {
signed_headers_str = std::string(auth_value);
signed_headers = split(auth_value, ';');
std::sort(signed_headers.begin(), signed_headers.end());
}
}
std::vector<std::string_view> credential_split = split(credential, '/');
if (credential_split.size() != 5) {
throw api_error("ValidationException", format("Incorrect credential information format: {}", credential));
}
std::string user(credential_split[0]);
std::string datestamp(credential_split[1]);
std::string region(credential_split[2]);
std::string service(credential_split[3]);
std::map<std::string_view, std::string_view> signed_headers_map;
for (const auto& header : signed_headers) {
signed_headers_map.emplace(header, std::string_view());
}
for (auto& header : req._headers) {
std::string header_str;
header_str.resize(header.first.size());
std::transform(header.first.begin(), header.first.end(), header_str.begin(), ::tolower);
auto it = signed_headers_map.find(header_str);
if (it != signed_headers_map.end()) {
it->second = std::string_view(header.second);
}
}
auto cache_getter = [] (std::string username) {
return get_key_from_roles(cql3::get_query_processor().local(), std::move(username));
};
return _key_cache.get_ptr(user, cache_getter).then([this, &req,
user = std::move(user),
host = std::move(host),
datestamp = std::move(datestamp),
signed_headers_str = std::move(signed_headers_str),
signed_headers_map = std::move(signed_headers_map),
region = std::move(region),
service = std::move(service),
user_signature = std::move(user_signature)] (key_cache::value_ptr key_ptr) {
std::string signature = get_signature(user, *key_ptr, std::string_view(host), req._method,
datestamp, signed_headers_str, signed_headers_map, req.content, region, service, "");
if (signature != std::string_view(user_signature)) {
_key_cache.remove(user);
throw api_error("UnrecognizedClientException", "The security token included in the request is invalid.");
}
});
}
future<executor::request_return_type> server::handle_api_request(std::unique_ptr<request>&& req) {
_executor._stats.total_operations++;
sstring target = req->get_header(TARGET);
std::vector<std::string_view> split_target = split(target, '.');
//NOTICE(sarna): Target consists of Dynamo API version followed by a dot '.' and operation type (e.g. CreateTable)
std::string op = split_target.empty() ? std::string() : std::string(split_target.back());
slogger.trace("Request: {} {}", op, req->content);
return verify_signature(*req).then([this, op, req = std::move(req)] () mutable {
auto callback_it = _callbacks.find(op);
if (callback_it == _callbacks.end()) {
_executor._stats.unsupported_operations++;
throw api_error("UnknownOperationException",
format("Unsupported operation {}", op));
}
return with_gate(_pending_requests, [this, callback_it = std::move(callback_it), op = std::move(op), req = std::move(req)] () mutable {
//FIXME: Client state can provide more context, e.g. client's endpoint address
// We use unique_ptr because client_state cannot be moved or copied
return do_with(std::make_unique<executor::client_state>(executor::client_state::internal_tag()),
[this, callback_it = std::move(callback_it), op = std::move(op), req = std::move(req)] (std::unique_ptr<executor::client_state>& client_state) mutable {
tracing::trace_state_ptr trace_state = executor::maybe_trace_query(*client_state, op, req->content);
tracing::trace(trace_state, op);
// JSON parsing can allocate up to roughly 2x the size of the raw document, + a couple of bytes for maintenance.
// FIXME: by this time, the whole HTTP request was already read, so some memory is already occupied.
// Once HTTP allows working on streams, we should grab the permit *before* reading the HTTP payload.
size_t mem_estimate = req->content.size() * 3 + 8000;
auto units_fut = get_units(*_memory_limiter, mem_estimate);
if (_memory_limiter->waiters()) {
++_executor._stats.requests_blocked_memory;
}
return units_fut.then([this, callback_it = std::move(callback_it), &client_state, trace_state, req = std::move(req)] (semaphore_units<> units) mutable {
return _json_parser.parse(req->content).then([this, callback_it = std::move(callback_it), &client_state, trace_state,
units = std::move(units), req = std::move(req)] (rjson::value json_request) mutable {
return callback_it->second(_executor, *client_state, trace_state, make_service_permit(std::move(units)), std::move(json_request), std::move(req)).finally([trace_state] {});
});
});
});
});
});
}
void server::set_routes(routes& r) {
api_handler* req_handler = new api_handler([this] (std::unique_ptr<request> req) mutable {
return handle_api_request(std::move(req));
});
r.put(operation_type::POST, "/", req_handler);
r.put(operation_type::GET, "/", new health_handler(_pending_requests));
// The "/localnodes" request is a new Alternator feature, not supported by
// DynamoDB and not required for DynamoDB compatibility. It allows a
// client to enquire - using a trivial HTTP request without requiring
// authentication - the list of all live nodes in the same data center of
// the Alternator cluster. The client can use this list to balance its
// request load to all the nodes in the same geographical region.
// Note that this API exposes - openly without authentication - the
// information on the cluster's members inside one data center. We do not
// consider this to be a security risk, because an attacker can already
// scan an entire subnet for nodes responding to the health request,
// or even just scan for open ports.
r.put(operation_type::GET, "/localnodes", new local_nodelist_handler(_pending_requests));
}
//FIXME: A way to immediately invalidate the cache should be considered,
// e.g. when the system table which stores the keys is changed.
// For now, this propagation may take up to 1 minute.
server::server(executor& exec)
: _http_server("http-alternator")
, _https_server("https-alternator")
, _executor(exec)
, _key_cache(1024, 1min, slogger)
, _enforce_authorization(false)
, _enabled_servers{}
, _pending_requests{}
, _callbacks{
{"CreateTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.create_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"DescribeTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.describe_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"DeleteTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.delete_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"PutItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.put_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"UpdateItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.update_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"GetItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.get_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"DeleteItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.delete_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"ListTables", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.list_tables(client_state, std::move(permit), std::move(json_request));
}},
{"Scan", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.scan(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"DescribeEndpoints", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.describe_endpoints(client_state, std::move(permit), std::move(json_request), req->get_header("Host"));
}},
{"BatchWriteItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.batch_write_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"BatchGetItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.batch_get_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"Query", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.query(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
}},
{"TagResource", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.tag_resource(client_state, std::move(permit), std::move(json_request));
}},
{"UntagResource", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.untag_resource(client_state, std::move(permit), std::move(json_request));
}},
{"ListTagsOfResource", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
return e.list_tags_of_resource(client_state, std::move(permit), std::move(json_request));
}},
} {
}
future<> server::init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds,
bool enforce_authorization, semaphore* memory_limiter) {
_memory_limiter = memory_limiter;
_enforce_authorization = enforce_authorization;
if (!port && !https_port) {
return make_exception_future<>(std::runtime_error("Either regular port or TLS port"
" must be specified in order to init an alternator HTTP server instance"));
}
return seastar::async([this, addr, port, https_port, creds] {
try {
_executor.start().get();
if (port) {
set_routes(_http_server._routes);
_http_server.set_content_length_limit(server::content_length_limit);
_http_server.listen(socket_address{addr, *port}).get();
_enabled_servers.push_back(std::ref(_http_server));
}
if (https_port) {
set_routes(_https_server._routes);
_https_server.set_content_length_limit(server::content_length_limit);
_https_server.set_tls_credentials(creds->build_reloadable_server_credentials([](const std::unordered_set<sstring>& files, std::exception_ptr ep) {
if (ep) {
slogger.warn("Exception loading {}: {}", files, ep);
} else {
slogger.info("Reloaded {}", files);
}
}).get0());
_https_server.listen(socket_address{addr, *https_port}).get();
_enabled_servers.push_back(std::ref(_https_server));
}
} catch (...) {
slogger.error("Failed to set up Alternator HTTP server on {} port {}, TLS port {}: {}",
addr, port ? std::to_string(*port) : "OFF", https_port ? std::to_string(*https_port) : "OFF", std::current_exception());
std::throw_with_nested(std::runtime_error(
format("Failed to set up Alternator HTTP server on {} port {}, TLS port {}",
addr, port ? std::to_string(*port) : "OFF", https_port ? std::to_string(*https_port) : "OFF")));
}
});
}
future<> server::stop() {
return parallel_for_each(_enabled_servers, [] (http_server& server) {
return server.stop();
}).then([this] {
return _pending_requests.close();
}).then([this] {
return _json_parser.stop();
});
}
server::json_parser::json_parser() : _run_parse_json_thread(async([this] {
while (true) {
_document_waiting.wait().get();
if (_as.abort_requested()) {
return;
}
try {
_parsed_document = rjson::parse_yieldable(_raw_document);
_current_exception = nullptr;
} catch (...) {
_current_exception = std::current_exception();
}
_document_parsed.signal();
}
})) {
}
future<rjson::value> server::json_parser::parse(std::string_view content) {
if (content.size() < yieldable_parsing_threshold) {
return make_ready_future<rjson::value>(rjson::parse(content));
}
return with_semaphore(_parsing_sem, 1, [this, content] {
_raw_document = content;
_document_waiting.signal();
return _document_parsed.wait().then([this] {
if (_current_exception) {
return make_exception_future<rjson::value>(_current_exception);
}
return make_ready_future<rjson::value>(std::move(_parsed_document));
});
});
}
future<> server::json_parser::stop() {
_as.request_abort();
_document_waiting.signal();
_document_parsed.broken();
return std::move(_run_parse_json_thread);
}
}

View File

@@ -1,83 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include "alternator/executor.hh"
#include <seastar/core/future.hh>
#include <seastar/http/httpd.hh>
#include <seastar/net/tls.hh>
#include <optional>
#include "alternator/auth.hh"
#include "utils/small_vector.hh"
#include <seastar/core/units.hh>
namespace alternator {
class server {
static constexpr size_t content_length_limit = 16*MB;
using alternator_callback = std::function<future<executor::request_return_type>(executor&, executor::client_state&,
tracing::trace_state_ptr, service_permit, rjson::value, std::unique_ptr<request>)>;
using alternator_callbacks_map = std::unordered_map<std::string_view, alternator_callback>;
http_server _http_server;
http_server _https_server;
executor& _executor;
key_cache _key_cache;
bool _enforce_authorization;
utils::small_vector<std::reference_wrapper<seastar::httpd::http_server>, 2> _enabled_servers;
gate _pending_requests;
alternator_callbacks_map _callbacks;
semaphore* _memory_limiter;
class json_parser {
static constexpr size_t yieldable_parsing_threshold = 16*KB;
std::string_view _raw_document;
rjson::value _parsed_document;
std::exception_ptr _current_exception;
semaphore _parsing_sem{1};
condition_variable _document_waiting;
condition_variable _document_parsed;
abort_source _as;
future<> _run_parse_json_thread;
public:
json_parser();
future<rjson::value> parse(std::string_view content);
future<> stop();
};
json_parser _json_parser;
public:
server(executor& executor);
future<> init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds,
bool enforce_authorization, semaphore* memory_limiter);
future<> stop();
private:
void set_routes(seastar::httpd::routes& r);
future<> verify_signature(const seastar::httpd::request& r);
future<executor::request_return_type> handle_api_request(std::unique_ptr<request>&& req);
};
}

View File

@@ -1,104 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "stats.hh"
#include <seastar/core/metrics.hh>
namespace alternator {
const char* ALTERNATOR_METRICS = "alternator";
stats::stats() : api_operations{} {
// Register the
seastar::metrics::label op("op");
_metrics.add_group("alternator", {
#define OPERATION(name, CamelCaseName) \
seastar::metrics::make_total_operations("operation", api_operations.name, \
seastar::metrics::description("number of operations via Alternator API"), {op(CamelCaseName)}),
#define OPERATION_LATENCY(name, CamelCaseName) \
seastar::metrics::make_histogram("op_latency", \
seastar::metrics::description("Latency histogram of an operation via Alternator API"), {op(CamelCaseName)}, [this]{return api_operations.name.get_histogram(1,20);}),
OPERATION(batch_write_item, "BatchWriteItem")
OPERATION(create_backup, "CreateBackup")
OPERATION(create_global_table, "CreateGlobalTable")
OPERATION(create_table, "CreateTable")
OPERATION(delete_backup, "DeleteBackup")
OPERATION(delete_item, "DeleteItem")
OPERATION(delete_table, "DeleteTable")
OPERATION(describe_backup, "DescribeBackup")
OPERATION(describe_continuous_backups, "DescribeContinuousBackups")
OPERATION(describe_endpoints, "DescribeEndpoints")
OPERATION(describe_global_table, "DescribeGlobalTable")
OPERATION(describe_global_table_settings, "DescribeGlobalTableSettings")
OPERATION(describe_limits, "DescribeLimits")
OPERATION(describe_table, "DescribeTable")
OPERATION(describe_time_to_live, "DescribeTimeToLive")
OPERATION(get_item, "GetItem")
OPERATION(list_backups, "ListBackups")
OPERATION(list_global_tables, "ListGlobalTables")
OPERATION(list_tables, "ListTables")
OPERATION(list_tags_of_resource, "ListTagsOfResource")
OPERATION(put_item, "PutItem")
OPERATION(query, "Query")
OPERATION(restore_table_from_backup, "RestoreTableFromBackup")
OPERATION(restore_table_to_point_in_time, "RestoreTableToPointInTime")
OPERATION(scan, "Scan")
OPERATION(tag_resource, "TagResource")
OPERATION(transact_get_items, "TransactGetItems")
OPERATION(transact_write_items, "TransactWriteItems")
OPERATION(untag_resource, "UntagResource")
OPERATION(update_continuous_backups, "UpdateContinuousBackups")
OPERATION(update_global_table, "UpdateGlobalTable")
OPERATION(update_global_table_settings, "UpdateGlobalTableSettings")
OPERATION(update_item, "UpdateItem")
OPERATION(update_table, "UpdateTable")
OPERATION(update_time_to_live, "UpdateTimeToLive")
OPERATION_LATENCY(put_item_latency, "PutItem")
OPERATION_LATENCY(get_item_latency, "GetItem")
OPERATION_LATENCY(delete_item_latency, "DeleteItem")
OPERATION_LATENCY(update_item_latency, "UpdateItem")
});
_metrics.add_group("alternator", {
seastar::metrics::make_total_operations("unsupported_operations", unsupported_operations,
seastar::metrics::description("number of unsupported operations via Alternator API")),
seastar::metrics::make_total_operations("total_operations", total_operations,
seastar::metrics::description("number of total operations via Alternator API")),
seastar::metrics::make_total_operations("reads_before_write", reads_before_write,
seastar::metrics::description("number of performed read-before-write operations")),
seastar::metrics::make_total_operations("write_using_lwt", write_using_lwt,
seastar::metrics::description("number of writes that used LWT")),
seastar::metrics::make_total_operations("shard_bounce_for_lwt", shard_bounce_for_lwt,
seastar::metrics::description("number writes that had to be bounced from this shard because of LWT requirements")),
seastar::metrics::make_total_operations("requests_blocked_memory", requests_blocked_memory,
seastar::metrics::description("Counts a number of requests blocked due to memory pressure.")),
seastar::metrics::make_total_operations("filtered_rows_read_total", cql_stats.filtered_rows_read_total,
seastar::metrics::description("number of rows read during filtering operations")),
seastar::metrics::make_total_operations("filtered_rows_matched_total", cql_stats.filtered_rows_matched_total,
seastar::metrics::description("number of rows read and matched during filtering operations")),
seastar::metrics::make_total_operations("filtered_rows_dropped_total", [this] { return cql_stats.filtered_rows_read_total - cql_stats.filtered_rows_matched_total; },
seastar::metrics::description("number of rows read and dropped during filtering operations")),
});
}
}

View File

@@ -1,98 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <cstdint>
#include <seastar/core/metrics_registration.hh>
#include "seastarx.hh"
#include "utils/estimated_histogram.hh"
#include "cql3/stats.hh"
namespace alternator {
// Object holding per-shard statistics related to Alternator.
// While this object is alive, these metrics are also registered to be
// visible by the metrics REST API, with the "alternator" prefix.
class stats {
public:
stats();
// Count of DynamoDB API operations by types
struct {
uint64_t batch_get_item = 0;
uint64_t batch_write_item = 0;
uint64_t create_backup = 0;
uint64_t create_global_table = 0;
uint64_t create_table = 0;
uint64_t delete_backup = 0;
uint64_t delete_item = 0;
uint64_t delete_table = 0;
uint64_t describe_backup = 0;
uint64_t describe_continuous_backups = 0;
uint64_t describe_endpoints = 0;
uint64_t describe_global_table = 0;
uint64_t describe_global_table_settings = 0;
uint64_t describe_limits = 0;
uint64_t describe_table = 0;
uint64_t describe_time_to_live = 0;
uint64_t get_item = 0;
uint64_t list_backups = 0;
uint64_t list_global_tables = 0;
uint64_t list_tables = 0;
uint64_t list_tags_of_resource = 0;
uint64_t put_item = 0;
uint64_t query = 0;
uint64_t restore_table_from_backup = 0;
uint64_t restore_table_to_point_in_time = 0;
uint64_t scan = 0;
uint64_t tag_resource = 0;
uint64_t transact_get_items = 0;
uint64_t transact_write_items = 0;
uint64_t untag_resource = 0;
uint64_t update_continuous_backups = 0;
uint64_t update_global_table = 0;
uint64_t update_global_table_settings = 0;
uint64_t update_item = 0;
uint64_t update_table = 0;
uint64_t update_time_to_live = 0;
utils::estimated_histogram put_item_latency;
utils::estimated_histogram get_item_latency;
utils::estimated_histogram delete_item_latency;
utils::estimated_histogram update_item_latency;
} api_operations;
// Miscellaneous event counters
uint64_t total_operations = 0;
uint64_t unsupported_operations = 0;
uint64_t reads_before_write = 0;
uint64_t write_using_lwt = 0;
uint64_t shard_bounce_for_lwt = 0;
uint64_t requests_blocked_memory = 0;
// CQL-derived stats
cql3::cql_stats cql_stats;
private:
// The metric_groups object holds this stat object's metrics registered
// as long as the stats object is alive.
seastar::metrics::metric_groups _metrics;
};
}

View File

@@ -1,53 +0,0 @@
/*
* Copyright 2019 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include "serializer.hh"
#include "schema.hh"
#include "db/extensions.hh"
namespace alternator {
class tags_extension : public schema_extension {
public:
static constexpr auto NAME = "scylla_tags";
tags_extension() = default;
explicit tags_extension(const std::map<sstring, sstring>& tags) : _tags(std::move(tags)) {}
explicit tags_extension(bytes b) : _tags(tags_extension::deserialize(b)) {}
explicit tags_extension(const sstring& s) {
throw std::logic_error("Cannot create tags from string");
}
bytes serialize() const override {
return ser::serialize_to_buffer<bytes>(_tags);
}
static std::map<sstring, sstring> deserialize(bytes_view buffer) {
return ser::deserialize_from_buffer(buffer, boost::type<std::map<sstring, sstring>>());
}
const std::map<sstring, sstring>& tags() const {
return _tags;
}
private:
std::map<sstring, sstring> _tags;
};
}

View File

@@ -13,7 +13,7 @@
{
"method":"GET",
"summary":"get row cache save period in seconds",
"type": "long",
"type":"int",
"nickname":"get_row_cache_save_period_in_seconds",
"produces":[
"application/json"
@@ -35,7 +35,7 @@
"description":"row cache save period in seconds",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -48,7 +48,7 @@
{
"method":"GET",
"summary":"get key cache save period in seconds",
"type": "long",
"type":"int",
"nickname":"get_key_cache_save_period_in_seconds",
"produces":[
"application/json"
@@ -70,7 +70,7 @@
"description":"key cache save period in seconds",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -83,7 +83,7 @@
{
"method":"GET",
"summary":"get counter cache save period in seconds",
"type": "long",
"type":"int",
"nickname":"get_counter_cache_save_period_in_seconds",
"produces":[
"application/json"
@@ -105,7 +105,7 @@
"description":"counter cache save period in seconds",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -118,7 +118,7 @@
{
"method":"GET",
"summary":"get row cache keys to save",
"type": "long",
"type":"int",
"nickname":"get_row_cache_keys_to_save",
"produces":[
"application/json"
@@ -140,7 +140,7 @@
"description":"row cache keys to save",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -153,7 +153,7 @@
{
"method":"GET",
"summary":"get key cache keys to save",
"type": "long",
"type":"int",
"nickname":"get_key_cache_keys_to_save",
"produces":[
"application/json"
@@ -175,7 +175,7 @@
"description":"key cache keys to save",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -188,7 +188,7 @@
{
"method":"GET",
"summary":"get counter cache keys to save",
"type": "long",
"type":"int",
"nickname":"get_counter_cache_keys_to_save",
"produces":[
"application/json"
@@ -210,7 +210,7 @@
"description":"counter cache keys to save",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -448,7 +448,7 @@
{
"method": "GET",
"summary": "Get key entries",
"type": "long",
"type": "int",
"nickname": "get_key_entries",
"produces": [
"application/json"
@@ -568,7 +568,7 @@
{
"method": "GET",
"summary": "Get row entries",
"type": "long",
"type": "int",
"nickname": "get_row_entries",
"produces": [
"application/json"
@@ -688,7 +688,7 @@
{
"method": "GET",
"summary": "Get counter entries",
"type": "long",
"type": "int",
"nickname": "get_counter_entries",
"produces": [
"application/json"

View File

@@ -70,7 +70,7 @@
{
"method":"POST",
"summary":"Force a major compaction of this column family",
"type":"void",
"type":"string",
"nickname":"force_major_compaction",
"produces":[
"application/json"
@@ -121,7 +121,7 @@
"description":"The minimum number of sstables in queue before compaction kicks off",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -172,7 +172,7 @@
"description":"The maximum number of sstables in queue before compaction kicks off",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -223,7 +223,7 @@
"description":"The maximum number of sstables in queue before compaction kicks off",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
},
{
@@ -231,7 +231,7 @@
"description":"The minimum number of sstables in queue before compaction kicks off",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -380,54 +380,16 @@
"operations":[
{
"method":"GET",
"summary":"check if the auto_compaction property is enabled for a given table",
"summary":"check if the auto compaction disabled",
"type":"boolean",
"nickname":"get_auto_compaction",
"nickname":"is_auto_compaction_disabled",
"produces":[
"application/json"
],
"parameters":[
{
"name":"name",
"description":"The table name in keyspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
}
]
},
{
"method":"POST",
"summary":"Enable table auto compaction",
"type":"void",
"nickname":"enable_auto_compaction",
"produces":[
"application/json"
],
"parameters":[
{
"name":"name",
"description":"The table name in keyspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
}
]
},
{
"method":"DELETE",
"summary":"Disable table auto compaction",
"type":"void",
"nickname":"disable_auto_compaction",
"produces":[
"application/json"
],
"parameters":[
{
"name":"name",
"description":"The table name in keyspace:name format",
"description":"The column family name in keyspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -493,7 +455,7 @@
"operations":[
{
"method":"GET",
"summary":"Returns a list of sstable filenames that contain the given partition key on this node",
"summary":"Returns a list of filenames that contain the given key on this node",
"type":"array",
"items":{
"type":"string"
@@ -513,7 +475,7 @@
},
{
"name":"key",
"description":"The partition key. In a composite-key scenario, use ':' to separate the columns in the key.",
"description":"The key",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -582,7 +544,7 @@
"summary":"sstable count for each level. empty unless leveled compaction is used",
"type":"array",
"items":{
"type": "long"
"type":"int"
},
"nickname":"get_sstable_count_per_level",
"produces":[
@@ -649,54 +611,6 @@
}
]
},
{
"path":"/column_family/toppartitions/{name}",
"operations":[
{
"method":"GET",
"summary":"Toppartitions query",
"type":"toppartitions_query_results",
"nickname":"toppartitions",
"produces":[
"application/json"
],
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
},
{
"name":"duration",
"description":"Duration (in milliseconds) of monitoring operation",
"required":true,
"allowMultiple":false,
"type": "long",
"paramType":"query"
},
{
"name":"list_size",
"description":"number of the top partitions to list",
"required":false,
"allowMultiple":false,
"type": "long",
"paramType":"query"
},
{
"name":"capacity",
"description":"capacity of stream summary: determines amount of resources used in query processing",
"required":false,
"allowMultiple":false,
"type": "long",
"paramType":"query"
}
]
}
]
},
{
"path":"/column_family/metrics/memtable_columns_count/",
"operations":[
@@ -959,7 +873,7 @@
{
"method":"GET",
"summary":"Get memtable switch count",
"type": "long",
"type":"int",
"nickname":"get_memtable_switch_count",
"produces":[
"application/json"
@@ -983,7 +897,7 @@
{
"method":"GET",
"summary":"Get all memtable switch count",
"type": "long",
"type":"int",
"nickname":"get_all_memtable_switch_count",
"produces":[
"application/json"
@@ -1120,7 +1034,7 @@
{
"method":"GET",
"summary":"Get read latency",
"type": "long",
"type":"int",
"nickname":"get_read_latency",
"produces":[
"application/json"
@@ -1273,7 +1187,7 @@
{
"method":"GET",
"summary":"Get all read latency",
"type": "long",
"type":"int",
"nickname":"get_all_read_latency",
"produces":[
"application/json"
@@ -1289,7 +1203,7 @@
{
"method":"GET",
"summary":"Get range latency",
"type": "long",
"type":"int",
"nickname":"get_range_latency",
"produces":[
"application/json"
@@ -1313,7 +1227,7 @@
{
"method":"GET",
"summary":"Get all range latency",
"type": "long",
"type":"int",
"nickname":"get_all_range_latency",
"produces":[
"application/json"
@@ -1329,7 +1243,7 @@
{
"method":"GET",
"summary":"Get write latency",
"type": "long",
"type":"int",
"nickname":"get_write_latency",
"produces":[
"application/json"
@@ -1482,7 +1396,7 @@
{
"method":"GET",
"summary":"Get all write latency",
"type": "long",
"type":"int",
"nickname":"get_all_write_latency",
"produces":[
"application/json"
@@ -1498,7 +1412,7 @@
{
"method":"GET",
"summary":"Get pending flushes",
"type": "long",
"type":"int",
"nickname":"get_pending_flushes",
"produces":[
"application/json"
@@ -1522,7 +1436,7 @@
{
"method":"GET",
"summary":"Get all pending flushes",
"type": "long",
"type":"int",
"nickname":"get_all_pending_flushes",
"produces":[
"application/json"
@@ -1538,7 +1452,7 @@
{
"method":"GET",
"summary":"Get pending compactions",
"type": "long",
"type":"int",
"nickname":"get_pending_compactions",
"produces":[
"application/json"
@@ -1562,7 +1476,7 @@
{
"method":"GET",
"summary":"Get all pending compactions",
"type": "long",
"type":"int",
"nickname":"get_all_pending_compactions",
"produces":[
"application/json"
@@ -1578,7 +1492,7 @@
{
"method":"GET",
"summary":"Get live ss table count",
"type": "long",
"type":"int",
"nickname":"get_live_ss_table_count",
"produces":[
"application/json"
@@ -1602,7 +1516,7 @@
{
"method":"GET",
"summary":"Get all live ss table count",
"type": "long",
"type":"int",
"nickname":"get_all_live_ss_table_count",
"produces":[
"application/json"
@@ -1618,7 +1532,7 @@
{
"method":"GET",
"summary":"Get live disk space used",
"type": "long",
"type":"int",
"nickname":"get_live_disk_space_used",
"produces":[
"application/json"
@@ -1642,7 +1556,7 @@
{
"method":"GET",
"summary":"Get all live disk space used",
"type": "long",
"type":"int",
"nickname":"get_all_live_disk_space_used",
"produces":[
"application/json"
@@ -1658,7 +1572,7 @@
{
"method":"GET",
"summary":"Get total disk space used",
"type": "long",
"type":"int",
"nickname":"get_total_disk_space_used",
"produces":[
"application/json"
@@ -1682,7 +1596,7 @@
{
"method":"GET",
"summary":"Get all total disk space used",
"type": "long",
"type":"int",
"nickname":"get_all_total_disk_space_used",
"produces":[
"application/json"
@@ -2138,7 +2052,7 @@
{
"method":"GET",
"summary":"Get speculative retries",
"type": "long",
"type":"int",
"nickname":"get_speculative_retries",
"produces":[
"application/json"
@@ -2162,7 +2076,7 @@
{
"method":"GET",
"summary":"Get all speculative retries",
"type": "long",
"type":"int",
"nickname":"get_all_speculative_retries",
"produces":[
"application/json"
@@ -2242,7 +2156,7 @@
{
"method":"GET",
"summary":"Get row cache hit out of range",
"type": "long",
"type":"int",
"nickname":"get_row_cache_hit_out_of_range",
"produces":[
"application/json"
@@ -2266,7 +2180,7 @@
{
"method":"GET",
"summary":"Get all row cache hit out of range",
"type": "long",
"type":"int",
"nickname":"get_all_row_cache_hit_out_of_range",
"produces":[
"application/json"
@@ -2282,7 +2196,7 @@
{
"method":"GET",
"summary":"Get row cache hit",
"type": "long",
"type":"int",
"nickname":"get_row_cache_hit",
"produces":[
"application/json"
@@ -2306,7 +2220,7 @@
{
"method":"GET",
"summary":"Get all row cache hit",
"type": "long",
"type":"int",
"nickname":"get_all_row_cache_hit",
"produces":[
"application/json"
@@ -2322,7 +2236,7 @@
{
"method":"GET",
"summary":"Get row cache miss",
"type": "long",
"type":"int",
"nickname":"get_row_cache_miss",
"produces":[
"application/json"
@@ -2346,7 +2260,7 @@
{
"method":"GET",
"summary":"Get all row cache miss",
"type": "long",
"type":"int",
"nickname":"get_all_row_cache_miss",
"produces":[
"application/json"
@@ -2362,7 +2276,7 @@
{
"method":"GET",
"summary":"Get cas prepare",
"type": "long",
"type":"int",
"nickname":"get_cas_prepare",
"produces":[
"application/json"
@@ -2386,7 +2300,7 @@
{
"method":"GET",
"summary":"Get cas propose",
"type": "long",
"type":"int",
"nickname":"get_cas_propose",
"produces":[
"application/json"
@@ -2410,7 +2324,7 @@
{
"method":"GET",
"summary":"Get cas commit",
"type": "long",
"type":"int",
"nickname":"get_cas_commit",
"produces":[
"application/json"
@@ -2902,44 +2816,6 @@
"description":"The column family type"
}
}
},
"toppartitions_record":{
"id":"toppartitions_record",
"description":"nodetool toppartitions query record",
"properties":{
"partition":{
"type":"string",
"description":"Partition key"
},
"count":{
"type":"long",
"description":"Number of read/write operations"
},
"error":{
"type":"long",
"description":"Indication of inaccuracy in counting PKs"
}
}
},
"toppartitions_query_results":{
"id":"toppartitions_query_results",
"description":"nodetool toppartitions query results",
"properties":{
"read":{
"type":"array",
"items":{
"type":"toppartitions_record"
},
"description":"Read results"
},
"write":{
"type":"array",
"items":{
"type":"toppartitions_record"
},
"description":"Write results"
}
}
}
}
}

View File

@@ -118,7 +118,7 @@
{
"method": "GET",
"summary": "Get pending tasks",
"type": "long",
"type": "int",
"nickname": "get_pending_tasks",
"produces": [
"application/json"
@@ -127,24 +127,6 @@
}
]
},
{
"path": "/compaction_manager/metrics/pending_tasks_by_table",
"operations": [
{
"method": "GET",
"summary": "Get pending tasks by table name",
"type": "array",
"items": {
"type": "pending_compaction"
},
"nickname": "get_pending_tasks_by_table",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/compaction_manager/metrics/completed_tasks",
"operations": [
@@ -181,7 +163,7 @@
{
"method": "GET",
"summary": "Get bytes compacted",
"type": "long",
"type": "int",
"nickname": "get_bytes_compacted",
"produces": [
"application/json"
@@ -197,7 +179,7 @@
"description":"A row merged information",
"properties":{
"key":{
"type": "long",
"type":"int",
"description":"The number of sstable"
},
"value":{
@@ -262,23 +244,6 @@
}
}
},
"pending_compaction": {
"id": "pending_compaction",
"properties": {
"cf": {
"type": "string",
"description": "The column family name"
},
"ks": {
"type":"string",
"description": "The keyspace name"
},
"task": {
"type":"long",
"description": "The number of pending tasks"
}
}
},
"history": {
"id":"history",
"description":"Compaction history information",

View File

@@ -1,30 +0,0 @@
"/v2/config/{id}": {
"get": {
"description": "Return a config value",
"operationId": "find_config_id",
"produces": [
"application/json"
],
"tags": ["config"],
"parameters": [
{
"name": "id",
"in": "path",
"description": "ID of config to return",
"required": true,
"type": "string"
}
],
"responses": {
"200": {
"description": "Config value"
},
"default": {
"description": "unexpected error",
"schema": {
"$ref": "#/definitions/ErrorModel"
}
}
}
}
}

View File

@@ -1,90 +0,0 @@
{
"apiVersion":"0.0.1",
"swaggerVersion":"1.2",
"basePath":"{{Protocol}}://{{Host}}",
"resourcePath":"/error_injection",
"produces":[
"application/json"
],
"apis":[
{
"path":"/v2/error_injection/injection/{injection}",
"operations":[
{
"method":"POST",
"summary":"Activate an injection that triggers an error in code",
"type":"void",
"nickname":"enable_injection",
"produces":[
"application/json"
],
"parameters":[
{
"name":"injection",
"description":"injection name, should correspond to an injection added in code",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
},
{
"name":"one_shot",
"description":"boolean flag indicating whether the injection should be enabled to trigger only once",
"required":false,
"allowMultiple":false,
"type":"boolean",
"paramType":"query"
}
]
},
{
"method":"DELETE",
"summary":"Deactivate an injection previously activated by the API",
"type":"void",
"nickname":"disable_injection",
"produces":[
"application/json"
],
"parameters":[
{
"name":"injection",
"description":"injection name",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
}
]
}
]
},
{
"path":"/v2/error_injection/injection",
"operations":[
{
"method":"GET",
"summary":"List all enabled injections on all shards, i.e. injections that will trigger an error in the code",
"type":"array",
"items":{
"type":"string"
},
"nickname":"get_enabled_injections_on_all",
"produces":[
"application/json"
],
"parameters":[]
},
{
"method":"DELETE",
"summary":"Deactivate all injections previously activated on all shards by the API",
"type":"void",
"nickname":"disable_on_all",
"produces":[
"application/json"
],
"parameters":[]
}
]
}
]
}

View File

@@ -110,7 +110,7 @@
{
"method":"GET",
"summary":"Get count down endpoint",
"type": "long",
"type":"int",
"nickname":"get_down_endpoint_count",
"produces":[
"application/json"
@@ -126,7 +126,7 @@
{
"method":"GET",
"summary":"Get count up endpoint",
"type": "long",
"type":"int",
"nickname":"get_up_endpoint_count",
"produces":[
"application/json"
@@ -180,11 +180,11 @@
"description": "The endpoint address"
},
"generation": {
"type": "long",
"type": "int",
"description": "The heart beat generation"
},
"version": {
"type": "long",
"type": "int",
"description": "The heart beat version"
},
"update_time": {
@@ -209,7 +209,7 @@
"description": "Holds a version value for an application state",
"properties": {
"application_state": {
"type": "long",
"type": "int",
"description": "The application state enum index"
},
"value": {
@@ -217,7 +217,7 @@
"description": "The version value"
},
"version": {
"type": "long",
"type": "int",
"description": "The application state version"
}
}

View File

@@ -75,7 +75,7 @@
{
"method":"GET",
"summary":"Returns files which are pending for archival attempt. Does NOT include failed archive attempts",
"type": "long",
"type":"int",
"nickname":"get_current_generation_number",
"produces":[
"application/json"
@@ -99,7 +99,7 @@
{
"method":"GET",
"summary":"Get heart beat version for a node",
"type": "long",
"type":"int",
"nickname":"get_current_heart_beat_version",
"produces":[
"application/json"

View File

@@ -99,7 +99,7 @@
{
"method": "GET",
"summary": "Get create hint count",
"type": "long",
"type": "int",
"nickname": "get_create_hint_count",
"produces": [
"application/json"
@@ -123,7 +123,7 @@
{
"method": "GET",
"summary": "Get not stored hints count",
"type": "long",
"type": "int",
"nickname": "get_not_stored_hints_count",
"produces": [
"application/json"

View File

@@ -191,7 +191,7 @@
{
"method":"GET",
"summary":"Get the version number",
"type": "long",
"type":"int",
"nickname":"get_version",
"produces":[
"application/json"

View File

@@ -105,7 +105,7 @@
{
"method":"GET",
"summary":"Get the max hint window",
"type": "long",
"type":"int",
"nickname":"get_max_hint_window",
"produces":[
"application/json"
@@ -128,7 +128,7 @@
"description":"max hint window in ms",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -141,7 +141,7 @@
{
"method":"GET",
"summary":"Get max hints in progress",
"type": "long",
"type":"int",
"nickname":"get_max_hints_in_progress",
"produces":[
"application/json"
@@ -164,7 +164,7 @@
"description":"max hints in progress",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -177,7 +177,7 @@
{
"method":"GET",
"summary":"get hints in progress",
"type": "long",
"type":"int",
"nickname":"get_hints_in_progress",
"produces":[
"application/json"
@@ -602,7 +602,7 @@
{
"method": "GET",
"summary": "Get cas write metrics",
"type": "long",
"type": "int",
"nickname": "get_cas_write_metrics_unfinished_commit",
"produces": [
"application/json"
@@ -632,7 +632,7 @@
{
"method": "GET",
"summary": "Get cas write metrics",
"type": "long",
"type": "int",
"nickname": "get_cas_write_metrics_condition_not_met",
"produces": [
"application/json"
@@ -641,28 +641,13 @@
}
]
},
{
"path": "/storage_proxy/metrics/cas_write/failed_read_round_optimization",
"operations": [
{
"method": "GET",
"summary": "Get cas write metrics",
"type": "long",
"nickname": "get_cas_write_metrics_failed_read_round_optimization",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/storage_proxy/metrics/cas_read/unfinished_commit",
"operations": [
{
"method": "GET",
"summary": "Get cas read metrics",
"type": "long",
"type": "int",
"nickname": "get_cas_read_metrics_unfinished_commit",
"produces": [
"application/json"
@@ -686,13 +671,28 @@
}
]
},
{
"path": "/storage_proxy/metrics/cas_read/condition_not_met",
"operations": [
{
"method": "GET",
"summary": "Get cas read metrics",
"type": "int",
"nickname": "get_cas_read_metrics_condition_not_met",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/storage_proxy/metrics/read/timeouts",
"operations": [
{
"method": "GET",
"summary": "Get read metrics",
"type": "long",
"type": "int",
"nickname": "get_read_metrics_timeouts",
"produces": [
"application/json"
@@ -707,7 +707,7 @@
{
"method": "GET",
"summary": "Get read metrics",
"type": "long",
"type": "int",
"nickname": "get_read_metrics_unavailables",
"produces": [
"application/json"
@@ -791,36 +791,6 @@
}
]
},
{
"path": "/storage_proxy/metrics/cas_read/moving_average_histogram",
"operations": [
{
"method": "GET",
"summary": "Get CAS read rate and latency histogram",
"$ref": "#/utils/rate_moving_average_and_histogram",
"nickname": "get_cas_read_metrics_latency_histogram",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/storage_proxy/metrics/view_write/moving_average_histogram",
"operations": [
{
"method": "GET",
"summary": "Get view write rate and latency histogram",
"$ref": "#/utils/rate_moving_average_and_histogram",
"nickname": "get_view_write_metrics_latency_histogram",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/storage_proxy/metrics/range/moving_average_histogram",
"operations": [
@@ -842,7 +812,7 @@
{
"method": "GET",
"summary": "Get range metrics",
"type": "long",
"type": "int",
"nickname": "get_range_metrics_timeouts",
"produces": [
"application/json"
@@ -857,7 +827,7 @@
{
"method": "GET",
"summary": "Get range metrics",
"type": "long",
"type": "int",
"nickname": "get_range_metrics_unavailables",
"produces": [
"application/json"
@@ -902,7 +872,7 @@
{
"method": "GET",
"summary": "Get write metrics",
"type": "long",
"type": "int",
"nickname": "get_write_metrics_timeouts",
"produces": [
"application/json"
@@ -917,7 +887,7 @@
{
"method": "GET",
"summary": "Get write metrics",
"type": "long",
"type": "int",
"nickname": "get_write_metrics_unavailables",
"produces": [
"application/json"
@@ -986,21 +956,6 @@
}
]
},
{
"path": "/storage_proxy/metrics/cas_write/moving_average_histogram",
"operations": [
{
"method": "GET",
"summary": "Get CAS write rate and latency histogram",
"$ref": "#/utils/rate_moving_average_and_histogram",
"nickname": "get_cas_write_metrics_latency_histogram",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path":"/storage_proxy/metrics/read/estimated_histogram/",
"operations":[
@@ -1023,7 +978,7 @@
{
"method":"GET",
"summary":"Get read latency",
"type": "long",
"type":"int",
"nickname":"get_read_latency",
"produces":[
"application/json"
@@ -1055,7 +1010,7 @@
{
"method":"GET",
"summary":"Get write latency",
"type": "long",
"type":"int",
"nickname":"get_write_latency",
"produces":[
"application/json"
@@ -1087,7 +1042,7 @@
{
"method":"GET",
"summary":"Get range latency",
"type": "long",
"type":"int",
"nickname":"get_range_latency",
"produces":[
"application/json"

View File

@@ -458,7 +458,7 @@
{
"method":"GET",
"summary":"Return the generation value for this node.",
"type": "long",
"type":"int",
"nickname":"get_current_generation_number",
"produces":[
"application/json"
@@ -511,21 +511,6 @@
}
]
},
{
"path":"/storage_service/cdc_streams_check_and_repair",
"operations":[
{
"method":"POST",
"summary":"Checks that CDC streams reflect current cluster topology and regenerates them if not.",
"type":"void",
"nickname":"cdc_streams_check_and_repair",
"produces":[
"application/json"
],
"parameters":[]
}
]
},
{
"path":"/storage_service/snapshots",
"operations":[
@@ -597,15 +582,7 @@
},
{
"name":"kn",
"description":"Comma seperated keyspaces name that their snapshot will be deleted",
"required":false,
"allowMultiple":false,
"type":"string",
"paramType":"query"
},
{
"name":"cf",
"description":"an optional table name that its snapshot will be deleted",
"description":"Comma seperated keyspaces name to snapshot",
"required":false,
"allowMultiple":false,
"type":"string",
@@ -669,7 +646,7 @@
{
"method":"POST",
"summary":"Trigger a cleanup of keys on a single keyspace",
"type": "long",
"type":"int",
"nickname":"force_keyspace_cleanup",
"produces":[
"application/json"
@@ -701,7 +678,7 @@
{
"method":"GET",
"summary":"Scrub (deserialize + reserialize at the latest version, skipping bad rows if any) the given keyspace. If columnFamilies array is empty, all CFs are scrubbed. Scrubbed CFs will be snapshotted first, if disableSnapshot is false",
"type": "long",
"type":"int",
"nickname":"scrub",
"produces":[
"application/json"
@@ -749,7 +726,7 @@
{
"method":"GET",
"summary":"Rewrite all sstables to the latest version. Unlike scrub, it doesn't skip bad rows and do not snapshot sstables first.",
"type": "long",
"type":"int",
"nickname":"upgrade_sstables",
"produces":[
"application/json"
@@ -815,31 +792,13 @@
}
]
},
{
"path":"/storage_service/active_repair/",
"operations":[
{
"method":"GET",
"summary":"Return an array with the ids of the currently active repairs",
"type":"array",
"items":{
"type": "long"
},
"nickname":"get_active_repair_async",
"produces":[
"application/json"
],
"parameters":[]
}
]
},
{
"path":"/storage_service/repair_async/{keyspace}",
"operations":[
{
"method":"POST",
"summary":"Invoke repair asynchronously. You can track repair progress by using the get supplying id",
"type": "long",
"type":"int",
"nickname":"repair_async",
"produces":[
"application/json"
@@ -970,7 +929,7 @@
"description":"The repair ID to check for status",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -993,22 +952,6 @@
}
]
},
{
"path":"/storage_service/force_terminate_repair",
"operations":[
{
"method":"POST",
"summary":"Force terminate all repair sessions",
"type":"void",
"nickname":"force_terminate_all_repair_sessions_new",
"produces":[
"application/json"
],
"parameters":[
]
}
]
},
{
"path":"/storage_service/decommission",
"operations":[
@@ -1300,18 +1243,18 @@
},
{
"name":"dynamic_update_interval",
"description":"interval in ms (default 100)",
"description":"integer, in ms (default 100)",
"required":false,
"allowMultiple":false,
"type":"long",
"type":"integer",
"paramType":"query"
},
{
"name":"dynamic_reset_interval",
"description":"interval in ms (default 600,000)",
"description":"integer, in ms (default 600,000)",
"required":false,
"allowMultiple":false,
"type":"long",
"type":"integer",
"paramType":"query"
},
{
@@ -1516,7 +1459,7 @@
"description":"Stream throughput",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -1524,7 +1467,7 @@
{
"method":"GET",
"summary":"Get stream throughput mb per sec",
"type": "long",
"type":"int",
"nickname":"get_stream_throughput_mb_per_sec",
"produces":[
"application/json"
@@ -1540,7 +1483,7 @@
{
"method":"GET",
"summary":"get compaction throughput mb per sec",
"type": "long",
"type":"int",
"nickname":"get_compaction_throughput_mb_per_sec",
"produces":[
"application/json"
@@ -1562,7 +1505,7 @@
"description":"compaction throughput",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -1966,7 +1909,7 @@
{
"method":"GET",
"summary":"Returns the threshold for warning of queries with many tombstones",
"type": "long",
"type":"int",
"nickname":"get_tombstone_warn_threshold",
"produces":[
"application/json"
@@ -1988,7 +1931,7 @@
"description":"tombstone debug threshold",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -2001,7 +1944,7 @@
{
"method":"GET",
"summary":"",
"type": "long",
"type":"int",
"nickname":"get_tombstone_failure_threshold",
"produces":[
"application/json"
@@ -2023,7 +1966,7 @@
"description":"tombstone debug threshold",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -2036,7 +1979,7 @@
{
"method":"GET",
"summary":"Returns the threshold for rejecting queries due to a large batch size",
"type": "long",
"type":"int",
"nickname":"get_batch_size_failure_threshold",
"produces":[
"application/json"
@@ -2058,7 +2001,7 @@
"description":"batch size debug threshold",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -2082,7 +2025,7 @@
"description":"throttle in kb",
"required":true,
"allowMultiple":false,
"type": "long",
"type":"int",
"paramType":"query"
}
]
@@ -2095,7 +2038,7 @@
{
"method":"GET",
"summary":"Get load",
"type": "long",
"type":"int",
"nickname":"get_metrics_load",
"produces":[
"application/json"
@@ -2111,7 +2054,7 @@
{
"method":"GET",
"summary":"Get exceptions",
"type": "long",
"type":"int",
"nickname":"get_exceptions",
"produces":[
"application/json"
@@ -2127,7 +2070,7 @@
{
"method":"GET",
"summary":"Get total hints in progress",
"type": "long",
"type":"int",
"nickname":"get_total_hints_in_progress",
"produces":[
"application/json"
@@ -2143,7 +2086,7 @@
{
"method":"GET",
"summary":"Get total hints",
"type": "long",
"type":"int",
"nickname":"get_total_hints",
"produces":[
"application/json"
@@ -2152,77 +2095,7 @@
]
}
]
},
{
"path":"/storage_service/view_build_statuses/{keyspace}/{view}",
"operations":[
{
"method":"GET",
"summary":"Gets the progress of a materialized view build",
"type":"array",
"items":{
"type":"mapper"
},
"nickname":"view_build_statuses",
"produces":[
"application/json"
],
"parameters":[
{
"name":"keyspace",
"description":"The keyspace",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
},
{
"name":"view",
"description":"View name",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
}
]
}
]
},
{
"path":"/storage_service/sstable_info",
"operations":[
{
"method":"GET",
"summary":"SSTable information",
"type":"array",
"items":{
"type":"table_sstables"
},
"nickname":"sstable_info",
"produces":[
"application/json"
],
"parameters":[
{
"name":"keyspace",
"description":"The keyspace",
"required":false,
"allowMultiple":false,
"type":"string",
"paramType":"query"
},
{
"name":"cf",
"description":"column family name",
"required":false,
"allowMultiple":false,
"type":"string",
"paramType":"query"
}
]
}
]
}
}
],
"models":{
"mapper":{
@@ -2286,11 +2159,11 @@
"description":"The column family"
},
"total":{
"type":"long",
"type":"int",
"description":"The total snapshot size"
},
"live":{
"type":"long",
"type":"int",
"description":"The live snapshot size"
}
}
@@ -2382,92 +2255,6 @@
"description":"The endpoint details"
}
}
},
"named_maps":{
"id":"named_maps",
"properties":{
"group":{
"type":"string"
},
"attributes":{
"type":"array",
"items":{
"type":"mapper"
}
}
}
},
"sstable":{
"id":"sstable",
"properties":{
"size":{
"type":"long",
"description":"Total size in bytes of sstable"
},
"data_size":{
"type":"long",
"description":"The size in bytes on disk of data"
},
"index_size":{
"type":"long",
"description":"The size in bytes on disk of index"
},
"filter_size":{
"type":"long",
"description":"The size in bytes on disk of filter"
},
"timestamp":{
"type":"datetime",
"description":"File creation time"
},
"generation":{
"type":"long",
"description":"SSTable generation"
},
"level":{
"type":"long",
"description":"SSTable level"
},
"version":{
"type":"string",
"enum":[
"ka", "la", "mc"
],
"description":"SSTable version"
},
"properties":{
"type":"array",
"description":"SSTable attributes",
"items":{
"type":"mapper"
}
},
"extended_properties":{
"type":"array",
"description":"SSTable extended attributes",
"items":{
"type":"named_maps"
}
}
}
},
"table_sstables":{
"id":"table_sstables",
"description":"Per-table SSTable info and attributes",
"properties":{
"keyspace":{
"type":"string"
},
"table":{
"type":"string"
},
"sstables":{
"type":"array",
"items":{
"$ref":"sstable"
}
}
}
}
}
}

View File

@@ -32,7 +32,7 @@
{
"method":"GET",
"summary":"Get number of active outbound streams",
"type": "long",
"type":"int",
"nickname":"get_all_active_streams_outbound",
"produces":[
"application/json"
@@ -48,7 +48,7 @@
{
"method":"GET",
"summary":"Get total incoming bytes",
"type": "long",
"type":"int",
"nickname":"get_total_incoming_bytes",
"produces":[
"application/json"
@@ -72,7 +72,7 @@
{
"method":"GET",
"summary":"Get all total incoming bytes",
"type": "long",
"type":"int",
"nickname":"get_all_total_incoming_bytes",
"produces":[
"application/json"
@@ -88,7 +88,7 @@
{
"method":"GET",
"summary":"Get total outgoing bytes",
"type": "long",
"type":"int",
"nickname":"get_total_outgoing_bytes",
"produces":[
"application/json"
@@ -112,7 +112,7 @@
{
"method":"GET",
"summary":"Get all total outgoing bytes",
"type": "long",
"type":"int",
"nickname":"get_all_total_outgoing_bytes",
"produces":[
"application/json"
@@ -154,7 +154,7 @@
"description":"The peer"
},
"session_index":{
"type": "long",
"type":"int",
"description":"The session index"
},
"connecting":{
@@ -211,7 +211,7 @@
"description":"The ID"
},
"files":{
"type": "long",
"type":"int",
"description":"Number of files to transfer. Can be 0 if nothing to transfer for some streaming request."
},
"total_size":{
@@ -242,7 +242,7 @@
"description":"The peer address"
},
"session_index":{
"type": "long",
"type":"int",
"description":"The session index"
},
"file_name":{

View File

@@ -1,29 +0,0 @@
{
"swagger": "2.0",
"info": {
"version": "1.0.0",
"title": "Scylla API",
"description": "The scylla API version 2.0",
"termsOfService": "http://www.scylladb.com/tos/",
"contact": {
"name": "Scylla Team",
"email": "info@scylladb.com",
"url": "http://scylladb.com"
},
"license": {
"name": "AGPL",
"url": "https://github.com/scylladb/scylla/blob/master/LICENSE.AGPL"
}
},
"host": "{{Host}}",
"basePath": "/v2",
"schemes": [
"http"
],
"consumes": [
"application/json"
],
"produces": [
"application/json"
],
"paths": {

View File

@@ -52,21 +52,6 @@
}
]
},
{
"path":"/system/uptime_ms",
"operations":[
{
"method":"GET",
"summary":"Get system uptime, in milliseconds",
"type":"long",
"nickname":"get_system_uptime",
"produces":[
"application/json"
],
"parameters":[]
}
]
},
{
"path":"/system/logger/{name}",
"operations":[

View File

@@ -20,9 +20,9 @@
*/
#include "api.hh"
#include <seastar/http/file_handler.hh>
#include <seastar/http/transformers.hh>
#include <seastar/http/api_docs.hh>
#include "http/file_handler.hh"
#include "http/transformers.hh"
#include "http/api_docs.hh"
#include "storage_service.hh"
#include "commitlog.hh"
#include "gossiper.hh"
@@ -36,13 +36,9 @@
#include "endpoint_snitch.hh"
#include "compaction_manager.hh"
#include "hinted_handoff.hh"
#include "error_injection.hh"
#include <seastar/http/exception.hh>
#include "http/exception.hh"
#include "stream_manager.hh"
#include "system.hh"
#include "api/config.hh"
logging::logger apilog("api");
namespace api {
@@ -53,35 +49,25 @@ static std::unique_ptr<reply> exception_reply(std::exception_ptr eptr) {
throw bad_param_exception(ex.what());
}
// We never going to get here
throw std::runtime_error("exception_reply");
return std::make_unique<reply>();
}
future<> set_server_init(http_context& ctx) {
auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
auto rb02 = std::make_shared < api_registry_builder20 > (ctx.api_doc, "/v2");
return ctx.http_server.set_routes([rb, &ctx, rb02](routes& r) {
return ctx.http_server.set_routes([rb, &ctx](routes& r) {
r.register_exeption_handler(exception_reply);
r.put(GET, "/ui", new httpd::file_handler(ctx.api_dir + "/index.html",
new content_replace("html")));
r.add(GET, url("/ui").remainder("path"), new httpd::directory_handler(ctx.api_dir,
new content_replace("html")));
rb->set_api_doc(r);
rb02->set_api_doc(r);
rb02->register_api_file(r, "swagger20_header");
rb->register_function(r, "system",
"The system related API");
set_system(ctx, r);
});
}
future<> set_server_config(http_context& ctx) {
auto rb02 = std::make_shared < api_registry_builder20 > (ctx.api_doc, "/v2");
return ctx.http_server.set_routes([&ctx, rb02](routes& r) {
set_config(rb02, ctx, r);
});
}
static future<> register_api(http_context& ctx, const sstring& api_name,
const sstring api_desc,
std::function<void(http_context& ctx, routes& r)> f) {
@@ -93,30 +79,10 @@ static future<> register_api(http_context& ctx, const sstring& api_name,
});
}
future<> set_transport_controller(http_context& ctx, cql_transport::controller& ctl) {
return ctx.http_server.set_routes([&ctx, &ctl] (routes& r) { set_transport_controller(ctx, r, ctl); });
}
future<> unset_transport_controller(http_context& ctx) {
return ctx.http_server.set_routes([&ctx] (routes& r) { unset_transport_controller(ctx, r); });
}
future<> set_rpc_controller(http_context& ctx, thrift_controller& ctl) {
return ctx.http_server.set_routes([&ctx, &ctl] (routes& r) { set_rpc_controller(ctx, r, ctl); });
}
future<> unset_rpc_controller(http_context& ctx) {
return ctx.http_server.set_routes([&ctx] (routes& r) { unset_rpc_controller(ctx, r); });
}
future<> set_server_storage_service(http_context& ctx) {
return register_api(ctx, "storage_service", "The storage service API", set_storage_service);
}
future<> set_server_snapshot(http_context& ctx) {
return ctx.http_server.set_routes([&ctx] (routes& r) { set_snapshot(ctx, r); });
}
future<> set_server_snitch(http_context& ctx) {
return register_api(ctx, "endpoint_snitch_info", "The endpoint snitch info API", set_endpoint_snitch);
}
@@ -146,11 +112,6 @@ future<> set_server_stream_manager(http_context& ctx) {
"The stream manager API", set_stream_manager);
}
future<> set_server_cache(http_context& ctx) {
return register_api(ctx, "cache_service",
"The cache service API", set_cache_service);
}
future<> set_server_gossip_settle(http_context& ctx) {
auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
@@ -158,6 +119,9 @@ future<> set_server_gossip_settle(http_context& ctx) {
rb->register_function(r, "failure_detector",
"The failure detector API");
set_failure_detector(ctx,r);
rb->register_function(r, "cache_service",
"The cache service API");
set_cache_service(ctx,r);
});
}
@@ -180,9 +144,6 @@ future<> set_server_done(http_context& ctx) {
rb->register_function(r, "collectd",
"The collectd API");
set_collectd(ctx, r);
rb->register_function(r, "error_injection",
"The error injection API");
set_error_injection(ctx, r);
});
}

View File

@@ -21,15 +21,13 @@
#pragma once
#include <seastar/json/json_elements.hh>
#include <type_traits>
#include "json/json_elements.hh"
#include <boost/lexical_cast.hpp>
#include <boost/algorithm/string/split.hpp>
#include <boost/algorithm/string/classification.hpp>
#include <boost/units/detail/utility.hpp>
#include "api/api-doc/utils.json.hh"
#include "utils/histogram.hh"
#include <seastar/http/exception.hh>
#include "http/exception.hh"
#include "api_init.hh"
#include "seastarx.hh"
@@ -218,42 +216,4 @@ std::vector<T> concat(std::vector<T> a, std::vector<T>&& b) {
return a;
}
template <class T, class Base = T>
class req_param {
public:
sstring name;
sstring param;
T value;
req_param(const request& req, sstring name, T default_val) : name(name) {
param = req.get_query_param(name);
if (param.empty()) {
value = default_val;
return;
}
try {
// boost::lexical_cast does not use boolalpha. Converting a
// true/false throws exceptions. We don't want that.
if constexpr (std::is_same_v<Base, bool>) {
// Cannot use boolalpha because we (probably) want to
// accept 1 and 0 as well as true and false. And True. And fAlse.
std::transform(param.begin(), param.end(), param.begin(), ::tolower);
if (param == "true" || param == "1") {
value = T(true);
} else if (param == "false" || param == "0") {
value = T(false);
} else {
throw boost::bad_lexical_cast{};
}
} else {
value = T{boost::lexical_cast<Base>(param)};
}
} catch (boost::bad_lexical_cast&) {
throw bad_param_exception(format("{} ({}): type error - should be {}", name, param, boost::units::detail::demangle(typeid(Base).name())));
}
}
operator T() const { return value; }
};
}

View File

@@ -19,14 +19,9 @@
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include "database_fwd.hh"
#include "database.hh"
#include "service/storage_proxy.hh"
#include <seastar/http/httpd.hh>
namespace service { class load_meter; }
namespace locator { class token_metadata; }
namespace cql_transport { class controller; }
class thrift_controller;
#include "http/httpd.hh"
namespace api {
@@ -36,32 +31,22 @@ struct http_context {
httpd::http_server_control http_server;
distributed<database>& db;
distributed<service::storage_proxy>& sp;
service::load_meter& lmeter;
sharded<locator::token_metadata>& token_metadata;
http_context(distributed<database>& _db,
distributed<service::storage_proxy>& _sp,
service::load_meter& _lm, sharded<locator::token_metadata>& _tm)
: db(_db), sp(_sp), lmeter(_lm), token_metadata(_tm) {
distributed<service::storage_proxy>& _sp)
: db(_db), sp(_sp) {
}
};
future<> set_server_init(http_context& ctx);
future<> set_server_config(http_context& ctx);
future<> set_server_snitch(http_context& ctx);
future<> set_server_storage_service(http_context& ctx);
future<> set_transport_controller(http_context& ctx, cql_transport::controller& ctl);
future<> unset_transport_controller(http_context& ctx);
future<> set_rpc_controller(http_context& ctx, thrift_controller& ctl);
future<> unset_rpc_controller(http_context& ctx);
future<> set_server_snapshot(http_context& ctx);
future<> set_server_gossip(http_context& ctx);
future<> set_server_load_sstable(http_context& ctx);
future<> set_server_messaging_service(http_context& ctx);
future<> set_server_storage_proxy(http_context& ctx);
future<> set_server_stream_manager(http_context& ctx);
future<> set_server_gossip_settle(http_context& ctx);
future<> set_server_cache(http_context& ctx);
future<> set_server_done(http_context& ctx);
}

View File

@@ -208,11 +208,9 @@ void set_cache_service(http_context& ctx, routes& r) {
});
cs::get_row_capacity.set(r, [&ctx] (std::unique_ptr<request> req) {
return ctx.db.map_reduce0([](database& db) -> uint64_t {
return db.row_cache_tracker().region().occupancy().used_space();
}, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
return make_ready_future<json::json_return_type>(res);
});
return map_reduce_cf(ctx, uint64_t(0), [](const column_family& cf) {
return cf.get_row_cache().get_cache_tracker().region().occupancy().used_space();
}, std::plus<uint64_t>());
});
cs::get_row_hits.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -253,19 +251,15 @@ void set_cache_service(http_context& ctx, routes& r) {
cs::get_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
// In origin row size is the weighted size.
// We currently do not support weights, so we use num entries instead
return ctx.db.map_reduce0([](database& db) -> uint64_t {
return db.row_cache_tracker().partitions();
}, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
return make_ready_future<json::json_return_type>(res);
});
return map_reduce_cf(ctx, 0, [](const column_family& cf) {
return cf.get_row_cache().partitions();
}, std::plus<uint64_t>());
});
cs::get_row_entries.set(r, [&ctx] (std::unique_ptr<request> req) {
return ctx.db.map_reduce0([](database& db) -> uint64_t {
return db.row_cache_tracker().partitions();
}, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
return make_ready_future<json::json_return_type>(res);
});
return map_reduce_cf(ctx, 0, [](const column_family& cf) {
return cf.get_row_cache().partitions();
}, std::plus<uint64_t>());
});
cs::get_counter_capacity.set(r, [] (std::unique_ptr<request> req) {

View File

@@ -21,8 +21,8 @@
#include "collectd.hh"
#include "api/api-doc/collectd.json.hh"
#include <seastar/core/scollectd.hh>
#include <seastar/core/scollectd_api.hh>
#include "core/scollectd.hh"
#include "core/scollectd_api.hh"
#include "endian.h"
#include <boost/range/irange.hpp>
#include <regex>
@@ -64,7 +64,7 @@ static const char* str_to_regex(const sstring& v) {
void set_collectd(http_context& ctx, routes& r) {
cd::get_collectd.set(r, [&ctx](std::unique_ptr<request> req) {
auto id = ::make_shared<scollectd::type_instance_id>(req->param["pluginid"],
auto id = make_shared<scollectd::type_instance_id>(req->param["pluginid"],
req->get_query_param("instance"), req->get_query_param("type"),
req->get_query_param("type_instance"));

View File

@@ -22,14 +22,10 @@
#include "column_family.hh"
#include "api/api-doc/column_family.json.hh"
#include <vector>
#include <seastar/http/exception.hh>
#include "http/exception.hh"
#include "sstables/sstables.hh"
#include "utils/estimated_histogram.hh"
#include <algorithm>
#include "db/system_keyspace_view_types.hh"
#include "db/data_listeners.hh"
extern logging::logger apilog;
namespace api {
using namespace httpd;
@@ -38,7 +34,7 @@ using namespace std;
using namespace json;
namespace cf = httpd::column_family_json;
std::tuple<sstring, sstring> parse_fully_qualified_cf_name(sstring name) {
const utils::UUID& get_uuid(const sstring& name, const database& db) {
auto pos = name.find("%3A");
size_t end;
if (pos == sstring::npos) {
@@ -50,22 +46,14 @@ std::tuple<sstring, sstring> parse_fully_qualified_cf_name(sstring name) {
} else {
end = pos + 3;
}
return std::make_tuple(name.substr(0, pos), name.substr(end));
}
const utils::UUID& get_uuid(const sstring& ks, const sstring& cf, const database& db) {
try {
return db.find_uuid(ks, cf);
return db.find_uuid(name.substr(0, pos), name.substr(end));
} catch (std::out_of_range& e) {
throw bad_param_exception(format("Column family '{}:{}' not found", ks, cf));
throw bad_param_exception("Column family '" + name.substr(0, pos) + ":"
+ name.substr(end) + "' not found");
}
}
const utils::UUID& get_uuid(const sstring& name, const database& db) {
auto [ks, cf] = parse_fully_qualified_cf_name(name);
return get_uuid(ks, cf, db);
}
future<> foreach_column_family(http_context& ctx, const sstring& name, function<void(column_family&)> f) {
auto uuid = get_uuid(name, ctx.db.local());
@@ -75,28 +63,28 @@ future<> foreach_column_family(http_context& ctx, const sstring& name, function<
}
future<json::json_return_type> get_cf_stats(http_context& ctx, const sstring& name,
int64_t column_family_stats::*f) {
int64_t column_family::stats::*f) {
return map_reduce_cf(ctx, name, int64_t(0), [f](const column_family& cf) {
return cf.get_stats().*f;
}, std::plus<int64_t>());
}
future<json::json_return_type> get_cf_stats(http_context& ctx,
int64_t column_family_stats::*f) {
int64_t column_family::stats::*f) {
return map_reduce_cf(ctx, int64_t(0), [f](const column_family& cf) {
return cf.get_stats().*f;
}, std::plus<int64_t>());
}
static future<json::json_return_type> get_cf_stats_count(http_context& ctx, const sstring& name,
utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
return map_reduce_cf(ctx, name, int64_t(0), [f](const column_family& cf) {
return (cf.get_stats().*f).hist.count;
}, std::plus<int64_t>());
}
static future<json::json_return_type> get_cf_stats_sum(http_context& ctx, const sstring& name,
utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
auto uuid = get_uuid(name, ctx.db.local());
return ctx.db.map_reduce0([uuid, f](database& db) {
// Histograms information is sample of the actual load
@@ -112,14 +100,14 @@ static future<json::json_return_type> get_cf_stats_sum(http_context& ctx, const
static future<json::json_return_type> get_cf_stats_count(http_context& ctx,
utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
return map_reduce_cf(ctx, int64_t(0), [f](const column_family& cf) {
return (cf.get_stats().*f).hist.count;
}, std::plus<int64_t>());
}
static future<json::json_return_type> get_cf_histogram(http_context& ctx, const sstring& name,
utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
utils::UUID uuid = get_uuid(name, ctx.db.local());
return ctx.db.map_reduce0([f, uuid](const database& p) {
return (p.find_column_family(uuid).get_stats().*f).hist;},
@@ -130,7 +118,7 @@ static future<json::json_return_type> get_cf_histogram(http_context& ctx, const
});
}
static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
std::function<utils::ihistogram(const database&)> fun = [f] (const database& db) {
utils::ihistogram res;
for (auto i : db.get_column_families()) {
@@ -146,7 +134,7 @@ static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils:
}
static future<json::json_return_type> get_cf_rate_and_histogram(http_context& ctx, const sstring& name,
utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
utils::UUID uuid = get_uuid(name, ctx.db.local());
return ctx.db.map_reduce0([f, uuid](const database& p) {
return (p.find_column_family(uuid).get_stats().*f).rate();},
@@ -157,7 +145,7 @@ static future<json::json_return_type> get_cf_rate_and_histogram(http_context& c
});
}
static future<json::json_return_type> get_cf_rate_and_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
static future<json::json_return_type> get_cf_rate_and_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
std::function<utils::rate_moving_average_and_histogram(const database&)> fun = [f] (const database& db) {
utils::rate_moving_average_and_histogram res;
for (auto i : db.get_column_families()) {
@@ -178,27 +166,27 @@ static future<json::json_return_type> get_cf_unleveled_sstables(http_context& ct
}, std::plus<int64_t>());
}
static int64_t min_partition_size(column_family& cf) {
static int64_t min_row_size(column_family& cf) {
int64_t res = INT64_MAX;
for (auto i: *cf.get_sstables() ) {
res = std::min(res, i->get_stats_metadata().estimated_partition_size.min());
res = std::min(res, i->get_stats_metadata().estimated_row_size.min());
}
return (res == INT64_MAX) ? 0 : res;
}
static int64_t max_partition_size(column_family& cf) {
static int64_t max_row_size(column_family& cf) {
int64_t res = 0;
for (auto i: *cf.get_sstables() ) {
res = std::max(i->get_stats_metadata().estimated_partition_size.max(), res);
res = std::max(i->get_stats_metadata().estimated_row_size.max(), res);
}
return res;
}
static integral_ratio_holder mean_partition_size(column_family& cf) {
static integral_ratio_holder mean_row_size(column_family& cf) {
integral_ratio_holder res;
for (auto i: *cf.get_sstables() ) {
auto c = i->get_stats_metadata().estimated_partition_size.count();
res.sub += i->get_stats_metadata().estimated_partition_size.mean() * c;
auto c = i->get_stats_metadata().estimated_row_size.count();
res.sub += i->get_stats_metadata().estimated_row_size.mean() * c;
res.total += c;
}
return res;
@@ -254,11 +242,12 @@ class sum_ratio {
uint64_t _n = 0;
T _total = 0;
public:
void operator()(T value) {
future<> operator()(T value) {
if (value > 0) {
_total += value;
_n++;
}
return make_ready_future<>();
}
// Returns average value of all registered ratios.
T get() && {
@@ -407,31 +396,29 @@ void set_column_family(http_context& ctx, routes& r) {
});
cf::get_memtable_switch_count.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_stats(ctx,req->param["name"] ,&column_family_stats::memtable_switch_count);
return get_cf_stats(ctx,req->param["name"] ,&column_family::stats::memtable_switch_count);
});
cf::get_all_memtable_switch_count.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_stats(ctx, &column_family_stats::memtable_switch_count);
return get_cf_stats(ctx, &column_family::stats::memtable_switch_count);
});
// FIXME: this refers to partitions, not rows.
cf::get_estimated_row_size_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
utils::estimated_histogram res(0);
for (auto i: *cf.get_sstables() ) {
res.merge(i->get_stats_metadata().estimated_partition_size);
res.merge(i->get_stats_metadata().estimated_row_size);
}
return res;
},
utils::estimated_histogram_merge, utils_json::estimated_histogram());
});
// FIXME: this refers to partitions, not rows.
cf::get_estimated_row_count.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
uint64_t res = 0;
for (auto i: *cf.get_sstables() ) {
res += i->get_stats_metadata().estimated_partition_size.count();
res += i->get_stats_metadata().estimated_row_size.count();
}
return res;
},
@@ -442,7 +429,7 @@ void set_column_family(http_context& ctx, routes& r) {
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
utils::estimated_histogram res(0);
for (auto i: *cf.get_sstables() ) {
res.merge(i->get_stats_metadata().estimated_cells_count);
res.merge(i->get_stats_metadata().estimated_column_count);
}
return res;
},
@@ -456,67 +443,67 @@ void set_column_family(http_context& ctx, routes& r) {
});
cf::get_pending_flushes.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_stats(ctx,req->param["name"] ,&column_family_stats::pending_flushes);
return get_cf_stats(ctx,req->param["name"] ,&column_family::stats::pending_flushes);
});
cf::get_all_pending_flushes.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_stats(ctx, &column_family_stats::pending_flushes);
return get_cf_stats(ctx, &column_family::stats::pending_flushes);
});
cf::get_read.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_stats_count(ctx,req->param["name"] ,&column_family_stats::reads);
return get_cf_stats_count(ctx,req->param["name"] ,&column_family::stats::reads);
});
cf::get_all_read.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_stats_count(ctx, &column_family_stats::reads);
return get_cf_stats_count(ctx, &column_family::stats::reads);
});
cf::get_write.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_stats_count(ctx, req->param["name"] ,&column_family_stats::writes);
return get_cf_stats_count(ctx, req->param["name"] ,&column_family::stats::writes);
});
cf::get_all_write.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_stats_count(ctx, &column_family_stats::writes);
return get_cf_stats_count(ctx, &column_family::stats::writes);
});
cf::get_read_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_histogram(ctx, req->param["name"], &column_family_stats::reads);
return get_cf_histogram(ctx, req->param["name"], &column_family::stats::reads);
});
cf::get_read_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_rate_and_histogram(ctx, req->param["name"], &column_family_stats::reads);
return get_cf_rate_and_histogram(ctx, req->param["name"], &column_family::stats::reads);
});
cf::get_read_latency.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_stats_sum(ctx,req->param["name"] ,&column_family_stats::reads);
return get_cf_stats_sum(ctx,req->param["name"] ,&column_family::stats::reads);
});
cf::get_write_latency.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_stats_sum(ctx, req->param["name"] ,&column_family_stats::writes);
return get_cf_stats_sum(ctx, req->param["name"] ,&column_family::stats::writes);
});
cf::get_all_read_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_histogram(ctx, &column_family_stats::writes);
return get_cf_histogram(ctx, &column_family::stats::writes);
});
cf::get_all_read_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_rate_and_histogram(ctx, &column_family_stats::writes);
return get_cf_rate_and_histogram(ctx, &column_family::stats::writes);
});
cf::get_write_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_histogram(ctx, req->param["name"], &column_family_stats::writes);
return get_cf_histogram(ctx, req->param["name"], &column_family::stats::writes);
});
cf::get_write_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_rate_and_histogram(ctx, req->param["name"], &column_family_stats::writes);
return get_cf_rate_and_histogram(ctx, req->param["name"], &column_family::stats::writes);
});
cf::get_all_write_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_histogram(ctx, &column_family_stats::writes);
return get_cf_histogram(ctx, &column_family::stats::writes);
});
cf::get_all_write_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_rate_and_histogram(ctx, &column_family_stats::writes);
return get_cf_rate_and_histogram(ctx, &column_family::stats::writes);
});
cf::get_pending_compactions.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -532,11 +519,11 @@ void set_column_family(http_context& ctx, routes& r) {
});
cf::get_live_ss_table_count.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_stats(ctx, req->param["name"], &column_family_stats::live_sstable_count);
return get_cf_stats(ctx, req->param["name"], &column_family::stats::live_sstable_count);
});
cf::get_all_live_ss_table_count.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_stats(ctx, &column_family_stats::live_sstable_count);
return get_cf_stats(ctx, &column_family::stats::live_sstable_count);
});
cf::get_unleveled_sstables.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -559,36 +546,30 @@ void set_column_family(http_context& ctx, routes& r) {
return sum_sstable(ctx, true);
});
// FIXME: this refers to partitions, not rows.
cf::get_min_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], INT64_MAX, min_partition_size, min_int64);
return map_reduce_cf(ctx, req->param["name"], INT64_MAX, min_row_size, min_int64);
});
// FIXME: this refers to partitions, not rows.
cf::get_all_min_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, INT64_MAX, min_partition_size, min_int64);
return map_reduce_cf(ctx, INT64_MAX, min_row_size, min_int64);
});
// FIXME: this refers to partitions, not rows.
cf::get_max_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], int64_t(0), max_partition_size, max_int64);
return map_reduce_cf(ctx, req->param["name"], int64_t(0), max_row_size, max_int64);
});
// FIXME: this refers to partitions, not rows.
cf::get_all_max_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, int64_t(0), max_partition_size, max_int64);
return map_reduce_cf(ctx, int64_t(0), max_row_size, max_int64);
});
// FIXME: this refers to partitions, not rows.
cf::get_mean_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
// Cassandra 3.x mean values are truncated as integrals.
return map_reduce_cf(ctx, req->param["name"], integral_ratio_holder(), mean_partition_size, std::plus<integral_ratio_holder>());
return map_reduce_cf(ctx, req->param["name"], integral_ratio_holder(), mean_row_size, std::plus<integral_ratio_holder>());
});
// FIXME: this refers to partitions, not rows.
cf::get_all_mean_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
// Cassandra 3.x mean values are truncated as integrals.
return map_reduce_cf(ctx, integral_ratio_holder(), mean_partition_size, std::plus<integral_ratio_holder>());
return map_reduce_cf(ctx, integral_ratio_holder(), mean_row_size, std::plus<integral_ratio_holder>());
});
cf::get_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -650,7 +631,7 @@ void set_column_family(http_context& ctx, routes& r) {
cf::get_bloom_filter_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return s + sst->filter_size();
return sst->filter_size();
});
}, std::plus<uint64_t>());
});
@@ -658,7 +639,7 @@ void set_column_family(http_context& ctx, routes& r) {
cf::get_all_bloom_filter_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return s + sst->filter_size();
return sst->filter_size();
});
}, std::plus<uint64_t>());
});
@@ -666,7 +647,7 @@ void set_column_family(http_context& ctx, routes& r) {
cf::get_bloom_filter_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return s + sst->filter_memory_size();
return sst->filter_memory_size();
});
}, std::plus<uint64_t>());
});
@@ -674,7 +655,7 @@ void set_column_family(http_context& ctx, routes& r) {
cf::get_all_bloom_filter_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return s + sst->filter_memory_size();
return sst->filter_memory_size();
});
}, std::plus<uint64_t>());
});
@@ -682,7 +663,7 @@ void set_column_family(http_context& ctx, routes& r) {
cf::get_index_summary_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return s + sst->get_summary().memory_footprint();
return sst->get_summary().memory_footprint();
});
}, std::plus<uint64_t>());
});
@@ -690,7 +671,7 @@ void set_column_family(http_context& ctx, routes& r) {
cf::get_all_index_summary_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return s + sst->get_summary().memory_footprint();
return sst->get_summary().memory_footprint();
});
}, std::plus<uint64_t>());
});
@@ -795,25 +776,25 @@ void set_column_family(http_context& ctx, routes& r) {
});
cf::get_cas_prepare.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
return cf.get_stats().estimated_cas_prepare;
},
utils::estimated_histogram_merge, utils_json::estimated_histogram());
cf::get_cas_prepare.set(r, [] (std::unique_ptr<request> req) {
//TBD
unimplemented();
//auto id = get_uuid(req->param["name"], ctx.db.local());
return make_ready_future<json::json_return_type>(0);
});
cf::get_cas_propose.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
return cf.get_stats().estimated_cas_accept;
},
utils::estimated_histogram_merge, utils_json::estimated_histogram());
cf::get_cas_propose.set(r, [] (std::unique_ptr<request> req) {
//TBD
unimplemented();
//auto id = get_uuid(req->param["name"], ctx.db.local());
return make_ready_future<json::json_return_type>(0);
});
cf::get_cas_commit.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
return cf.get_stats().estimated_cas_learn;
},
utils::estimated_histogram_merge, utils_json::estimated_histogram());
cf::get_cas_commit.set(r, [] (std::unique_ptr<request> req) {
//TBD
unimplemented();
//auto id = get_uuid(req->param["name"], ctx.db.local());
return make_ready_future<json::json_return_type>(0);
});
cf::get_sstables_per_read_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -824,11 +805,11 @@ void set_column_family(http_context& ctx, routes& r) {
});
cf::get_tombstone_scanned_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_histogram(ctx, req->param["name"], &column_family_stats::tombstone_scanned);
return get_cf_histogram(ctx, req->param["name"], &column_family::stats::tombstone_scanned);
});
cf::get_live_scanned_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_histogram(ctx, req->param["name"], &column_family_stats::live_scanned);
return get_cf_histogram(ctx, req->param["name"], &column_family::stats::live_scanned);
});
cf::get_col_update_time_delta_histogram.set(r, [] (std::unique_ptr<request> req) {
@@ -839,49 +820,19 @@ void set_column_family(http_context& ctx, routes& r) {
return make_ready_future<json::json_return_type>(res);
});
cf::get_auto_compaction.set(r, [&ctx] (const_req req) {
const utils::UUID& uuid = get_uuid(req.param["name"], ctx.db.local());
column_family& cf = ctx.db.local().find_column_family(uuid);
return !cf.is_auto_compaction_disabled_by_user();
cf::is_auto_compaction_disabled.set(r, [] (const_req req) {
// FIXME
// currently auto compaction is disable
// it should be changed when it would have an API
return true;
});
cf::enable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
cf.enable_auto_compaction();
}).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
cf::get_built_indexes.set(r, [](const_req) {
// FIXME
// Currently there are no index support
return std::vector<sstring>();
});
cf::disable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
cf.disable_auto_compaction();
}).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
cf::get_built_indexes.set(r, [&ctx](std::unique_ptr<request> req) {
auto [ks, cf_name] = parse_fully_qualified_cf_name(req->param["name"]);
return db::system_keyspace::load_view_build_progress().then([ks, cf_name, &ctx](const std::vector<db::system_keyspace::view_build_progress>& vb) mutable {
std::set<sstring> vp;
for (auto b : vb) {
if (b.view.first == ks) {
vp.insert(b.view.second);
}
}
std::vector<sstring> res;
auto uuid = get_uuid(ks, cf_name, ctx.db.local());
column_family& cf = ctx.db.local().find_column_family(uuid);
res.reserve(cf.get_index_manager().list_indexes().size());
for (auto&& i : cf.get_index_manager().list_indexes()) {
if (vp.find(secondary_index::index_table_name(i.metadata().name())) == vp.end()) {
res.emplace_back(i.metadata().name());
}
}
return make_ready_future<json::json_return_type>(res);
});
});
cf::get_compression_metadata_off_heap_memory_used.set(r, [](const_req) {
// FIXME
@@ -954,70 +905,5 @@ void set_column_family(http_context& ctx, routes& r) {
return make_ready_future<json::json_return_type>(res);
});
});
cf::get_sstables_for_key.set(r, [&ctx](std::unique_ptr<request> req) {
auto key = req->get_query_param("key");
auto uuid = get_uuid(req->param["name"], ctx.db.local());
return ctx.db.map_reduce0([key, uuid] (database& db) {
return db.find_column_family(uuid).get_sstables_by_partition_key(key);
}, std::unordered_set<sstring>(),
[](std::unordered_set<sstring> a, std::unordered_set<sstring>&& b) mutable {
a.insert(b.begin(),b.end());
return a;
}).then([](const std::unordered_set<sstring>& res) {
return make_ready_future<json::json_return_type>(container_to_vec(res));
});
});
cf::toppartitions.set(r, [&ctx] (std::unique_ptr<request> req) {
auto name_param = req->param["name"];
auto [ks, cf] = parse_fully_qualified_cf_name(name_param);
api::req_param<std::chrono::milliseconds, unsigned> duration{*req, "duration", 1000ms};
api::req_param<unsigned> capacity(*req, "capacity", 256);
api::req_param<unsigned> list_size(*req, "list_size", 10);
apilog.info("toppartitions query: name={} duration={} list_size={} capacity={}",
name_param, duration.param, list_size.param, capacity.param);
return seastar::do_with(db::toppartitions_query(ctx.db, ks, cf, duration.value, list_size, capacity), [&ctx](auto& q) {
return q.scatter().then([&q] {
return sleep(q.duration()).then([&q] {
return q.gather(q.capacity()).then([&q] (auto topk_results) {
apilog.debug("toppartitions query: processing results");
cf::toppartitions_query_results results;
for (auto& d: topk_results.read.top(q.list_size())) {
cf::toppartitions_record r;
r.partition = sstring(d.item);
r.count = d.count;
r.error = d.error;
results.read.push(r);
}
for (auto& d: topk_results.write.top(q.list_size())) {
cf::toppartitions_record r;
r.partition = sstring(d.item);
r.count = d.count;
r.error = d.error;
results.write.push(r);
}
return make_ready_future<json::json_return_type>(results);
});
});
});
});
});
cf::force_major_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
if (req->get_query_param("split_output") != "") {
fail(unimplemented::cause::API);
}
return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
return cf.compact_all_sstables();
}).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
}
}

View File

@@ -24,8 +24,6 @@
#include "api.hh"
#include "api/api-doc/column_family.json.hh"
#include "database.hh"
#include <seastar/core/future-util.hh>
#include <any>
namespace api {
@@ -39,15 +37,9 @@ template<class Mapper, class I, class Reducer>
future<I> map_reduce_cf_raw(http_context& ctx, const sstring& name, I init,
Mapper mapper, Reducer reducer) {
auto uuid = get_uuid(name, ctx.db.local());
using mapper_type = std::function<std::unique_ptr<std::any>(database&)>;
using reducer_type = std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)>;
return ctx.db.map_reduce0(mapper_type([mapper, uuid](database& db) {
return std::make_unique<std::any>(I(mapper(db.find_column_family(uuid))));
}), std::make_unique<std::any>(std::move(init)), reducer_type([reducer = std::move(reducer)] (std::unique_ptr<std::any> a, std::unique_ptr<std::any> b) mutable {
return std::make_unique<std::any>(I(reducer(std::any_cast<I>(std::move(*a)), std::any_cast<I>(std::move(*b)))));
})).then([] (std::unique_ptr<std::any> r) {
return std::any_cast<I>(std::move(*r));
});
return ctx.db.map_reduce0([mapper, uuid](database& db) {
return mapper(db.find_column_family(uuid));
}, init, reducer);
}
@@ -59,44 +51,35 @@ future<json::json_return_type> map_reduce_cf(http_context& ctx, const sstring& n
});
}
template<class Mapper, class I, class Reducer, class Result>
future<I> map_reduce_cf_raw(http_context& ctx, const sstring& name, I init,
Mapper mapper, Reducer reducer, Result result) {
auto uuid = get_uuid(name, ctx.db.local());
return ctx.db.map_reduce0([mapper, uuid](database& db) {
return mapper(db.find_column_family(uuid));
}, init, reducer);
}
template<class Mapper, class I, class Reducer, class Result>
future<json::json_return_type> map_reduce_cf(http_context& ctx, const sstring& name, I init,
Mapper mapper, Reducer reducer, Result result) {
return map_reduce_cf_raw(ctx, name, init, mapper, reducer).then([result](const I& res) mutable {
return map_reduce_cf_raw(ctx, name, init, mapper, reducer, result).then([result](const I& res) mutable {
result = res;
return make_ready_future<json::json_return_type>(result);
});
}
struct map_reduce_column_families_locally {
std::any init;
std::function<std::unique_ptr<std::any>(column_family&)> mapper;
std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)> reducer;
future<std::unique_ptr<std::any>> operator()(database& db) const {
auto res = seastar::make_lw_shared<std::unique_ptr<std::any>>(std::make_unique<std::any>(init));
return do_for_each(db.get_column_families(), [res, this](const std::pair<utils::UUID, seastar::lw_shared_ptr<table>>& i) {
*res = std::move(reducer(std::move(*res), mapper(*i.second.get())));
}).then([res] {
return std::move(*res);
});
}
};
template<class Mapper, class I, class Reducer>
future<I> map_reduce_cf_raw(http_context& ctx, I init,
Mapper mapper, Reducer reducer) {
using mapper_type = std::function<std::unique_ptr<std::any>(column_family&)>;
using reducer_type = std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)>;
auto wrapped_mapper = mapper_type([mapper = std::move(mapper)] (column_family& cf) mutable {
return std::make_unique<std::any>(I(mapper(cf)));
});
auto wrapped_reducer = reducer_type([reducer = std::move(reducer)] (std::unique_ptr<std::any> a, std::unique_ptr<std::any> b) mutable {
return std::make_unique<std::any>(I(reducer(std::any_cast<I>(std::move(*a)), std::any_cast<I>(std::move(*b)))));
});
return ctx.db.map_reduce0(map_reduce_column_families_locally{init,
std::move(wrapped_mapper), wrapped_reducer}, std::make_unique<std::any>(init), wrapped_reducer).then([] (std::unique_ptr<std::any> res) {
return std::any_cast<I>(std::move(*res));
});
return ctx.db.map_reduce0([mapper, init, reducer](database& db) {
auto res = init;
for (auto i : db.get_column_families()) {
res = reducer(res, mapper(*i.second.get()));
}
return res;
}, init, reducer);
}
@@ -109,9 +92,9 @@ future<json::json_return_type> map_reduce_cf(http_context& ctx, I init,
}
future<json::json_return_type> get_cf_stats(http_context& ctx, const sstring& name,
int64_t column_family_stats::*f);
int64_t column_family::stats::*f);
future<json::json_return_type> get_cf_stats(http_context& ctx,
int64_t column_family_stats::*f);
int64_t column_family::stats::*f);
}

View File

@@ -20,18 +20,17 @@
*/
#include "commitlog.hh"
#include "db/commitlog/commitlog.hh"
#include <db/commitlog/commitlog.hh>
#include "api/api-doc/commitlog.json.hh"
#include "database.hh"
#include <vector>
namespace api {
template<typename T>
static auto acquire_cl_metric(http_context& ctx, std::function<T (db::commitlog*)> func) {
typedef T ret_type;
template<typename Func>
static auto acquire_cl_metric(http_context& ctx, Func&& func) {
typedef std::result_of_t<Func(db::commitlog *)> ret_type;
return ctx.db.map_reduce0([func = std::move(func)](database& db) {
return ctx.db.map_reduce0([func = std::forward<Func>(func)](database& db) {
if (db.commitlog() == nullptr) {
return make_ready_future<ret_type>();
}
@@ -64,15 +63,15 @@ void set_commitlog(http_context& ctx, routes& r) {
});
httpd::commitlog_json::get_completed_tasks.set(r, [&ctx](std::unique_ptr<request> req) {
return acquire_cl_metric<uint64_t>(ctx, std::bind(&db::commitlog::get_completed_tasks, std::placeholders::_1));
return acquire_cl_metric(ctx, std::bind(&db::commitlog::get_completed_tasks, std::placeholders::_1));
});
httpd::commitlog_json::get_pending_tasks.set(r, [&ctx](std::unique_ptr<request> req) {
return acquire_cl_metric<uint64_t>(ctx, std::bind(&db::commitlog::get_pending_tasks, std::placeholders::_1));
return acquire_cl_metric(ctx, std::bind(&db::commitlog::get_pending_tasks, std::placeholders::_1));
});
httpd::commitlog_json::get_total_commit_log_size.set(r, [&ctx](std::unique_ptr<request> req) {
return acquire_cl_metric<uint64_t>(ctx, std::bind(&db::commitlog::get_total_size, std::placeholders::_1));
return acquire_cl_metric(ctx, std::bind(&db::commitlog::get_total_size, std::placeholders::_1));
});
}

View File

@@ -20,11 +20,9 @@
*/
#include "compaction_manager.hh"
#include "sstables/compaction_manager.hh"
#include "api/api-doc/compaction_manager.json.hh"
#include "db/system_keyspace.hh"
#include "column_family.hh"
#include <utility>
namespace api {
@@ -39,16 +37,6 @@ static future<json::json_return_type> get_cm_stats(http_context& ctx,
return make_ready_future<json::json_return_type>(res);
});
}
static std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash> sum_pending_tasks(std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>&& a,
const std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>& b) {
for (auto&& i : b) {
if (i.second) {
a[i.first] += i.second;
}
}
return std::move(a);
}
void set_compaction_manager(http_context& ctx, routes& r) {
cm::get_compactions.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -58,8 +46,8 @@ void set_compaction_manager(http_context& ctx, routes& r) {
for (const auto& c : cm.get_compactions()) {
cm::summary s;
s.ks = c->ks_name;
s.cf = c->cf_name;
s.ks = c->ks;
s.cf = c->cf;
s.unit = "keys";
s.task_type = sstables::compaction_name(c->type);
s.completed = c->total_keys_written;
@@ -72,32 +60,6 @@ void set_compaction_manager(http_context& ctx, routes& r) {
});
});
cm::get_pending_tasks_by_table.set(r, [&ctx] (std::unique_ptr<request> req) {
return ctx.db.map_reduce0([&ctx](database& db) {
return do_with(std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>(), [&ctx, &db](std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>& tasks) {
return do_for_each(db.get_column_families(), [&tasks](const std::pair<utils::UUID, seastar::lw_shared_ptr<table>>& i) {
table& cf = *i.second.get();
tasks[std::make_pair(cf.schema()->ks_name(), cf.schema()->cf_name())] = cf.get_compaction_strategy().estimated_pending_compactions(cf);
return make_ready_future<>();
}).then([&tasks] {
return std::move(tasks);
});
});
}, std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>(), sum_pending_tasks).then(
[](const std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>& task_map) {
std::vector<cm::pending_compaction> res;
res.reserve(task_map.size());
for (auto i : task_map) {
cm::pending_compaction task;
task.ks = i.first.first;
task.cf = i.first.second;
task.task = i.second;
res.emplace_back(std::move(task));
}
return make_ready_future<json::json_return_type>(res);
});
});
cm::force_user_defined_compaction.set(r, [] (std::unique_ptr<request> req) {
//TBD
// FIXME
@@ -140,37 +102,29 @@ void set_compaction_manager(http_context& ctx, routes& r) {
});
cm::get_compaction_history.set(r, [] (std::unique_ptr<request> req) {
std::function<future<>(output_stream<char>&&)> f = [](output_stream<char>&& s) {
return do_with(output_stream<char>(std::move(s)), true, [] (output_stream<char>& s, bool& first){
return s.write("[").then([&s, &first] {
return db::system_keyspace::get_compaction_history([&s, &first](const db::system_keyspace::compaction_history_entry& entry) mutable {
cm::history h;
h.id = entry.id.to_sstring();
h.ks = std::move(entry.ks);
h.cf = std::move(entry.cf);
h.compacted_at = entry.compacted_at;
h.bytes_in = entry.bytes_in;
h.bytes_out = entry.bytes_out;
for (auto it : entry.rows_merged) {
httpd::compaction_manager_json::row_merged e;
e.key = it.first;
e.value = it.second;
h.rows_merged.push(std::move(e));
}
auto fut = first ? make_ready_future<>() : s.write(", ");
first = false;
return fut.then([&s, h = std::move(h)] {
return formatter::write(s, h);
});
}).then([&s] {
return s.write("]").then([&s] {
return s.close();
});
});
});
});
};
return make_ready_future<json::json_return_type>(std::move(f));
return db::system_keyspace::get_compaction_history().then([] (std::vector<db::system_keyspace::compaction_history_entry> history) {
std::vector<cm::history> res;
res.reserve(history.size());
for (auto& entry : history) {
cm::history h;
h.id = entry.id.to_sstring();
h.ks = std::move(entry.ks);
h.cf = std::move(entry.cf);
h.compacted_at = entry.compacted_at;
h.bytes_in = entry.bytes_in;
h.bytes_out = entry.bytes_out;
for (auto it : entry.rows_merged) {
httpd::compaction_manager_json::row_merged e;
e.key = it.first;
e.value = it.second;
h.rows_merged.push(std::move(e));
}
res.push_back(std::move(h));
}
return make_ready_future<json::json_return_type>(res);
});
});
cm::get_compaction_info.set(r, [] (std::unique_ptr<request> req) {

View File

@@ -1,119 +0,0 @@
/*
* Copyright 2018 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "api/config.hh"
#include "api/api-doc/config.json.hh"
#include "db/config.hh"
#include "database.hh"
#include <sstream>
#include <boost/algorithm/string/replace.hpp>
namespace api {
template<class T>
json::json_return_type get_json_return_type(const T& val) {
return json::json_return_type(val);
}
/*
* As commented on db::seed_provider_type is not used
* and probably never will.
*
* Just in case, we will return its name
*/
template<>
json::json_return_type get_json_return_type(const db::seed_provider_type& val) {
return json::json_return_type(val.class_name);
}
std::string_view format_type(std::string_view type) {
if (type == "int") {
return "integer";
}
return type;
}
future<> get_config_swagger_entry(std::string_view name, const std::string& description, std::string_view type, bool& first, output_stream<char>& os) {
std::stringstream ss;
if (first) {
first=false;
} else {
ss <<',';
};
ss << "\"/config/" << name <<"\": {"
"\"get\": {"
"\"description\": \"" << boost::replace_all_copy(boost::replace_all_copy(boost::replace_all_copy(description,"\n","\\n"),"\"", "''"), "\t", " ") <<"\","
"\"operationId\": \"find_config_"<< name <<"\","
"\"produces\": ["
"\"application/json\""
"],"
"\"tags\": [\"config\"],"
"\"parameters\": ["
"],"
"\"responses\": {"
"\"200\": {"
"\"description\": \"Config value\","
"\"schema\": {"
"\"type\": \"" << format_type(type) << "\""
"}"
"},"
"\"default\": {"
"\"description\": \"unexpected error\","
"\"schema\": {"
"\"$ref\": \"#/definitions/ErrorModel\""
"}"
"}"
"}"
"}"
"}";
return os.write(ss.str());
}
namespace cs = httpd::config_json;
void set_config(std::shared_ptr < api_registry_builder20 > rb, http_context& ctx, routes& r) {
rb->register_function(r, [&ctx] (output_stream<char>& os) {
return do_with(true, [&os, &ctx] (bool& first) {
auto f = make_ready_future();
for (auto&& cfg_ref : ctx.db.local().get_config().values()) {
auto&& cfg = cfg_ref.get();
f = f.then([&os, &first, &cfg] {
return get_config_swagger_entry(cfg.name(), std::string(cfg.desc()), cfg.type_name(), first, os);
});
}
return f;
});
});
cs::find_config_id.set(r, [&ctx] (const_req r) {
auto id = r.param["id"];
for (auto&& cfg_ref : ctx.db.local().get_config().values()) {
auto&& cfg = cfg_ref.get();
if (id == cfg.name()) {
return cfg.value_as_json();
}
}
throw bad_param_exception(sstring("No such config entry: ") + id);
});
}
}

View File

@@ -1,30 +0,0 @@
/*
* Copyright (C) 2018 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include "api.hh"
#include <seastar/http/api_docs.hh>
namespace api {
void set_config(std::shared_ptr<api_registry_builder20> rb, http_context& ctx, routes& r);
}

View File

@@ -1,69 +0,0 @@
/*
* Copyright (C) 2020 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "api/api-doc/error_injection.json.hh"
#include "api/api.hh"
#include <seastar/http/exception.hh>
#include "log.hh"
#include "utils/error_injection.hh"
#include "seastar/core/future-util.hh"
namespace api {
namespace hf = httpd::error_injection_json;
void set_error_injection(http_context& ctx, routes& r) {
hf::enable_injection.set(r, [](std::unique_ptr<request> req) {
sstring injection = req->param["injection"];
bool one_shot = req->get_query_param("one_shot") == "True";
auto& errinj = utils::get_local_injector();
return errinj.enable_on_all(injection, one_shot).then([] {
return make_ready_future<json::json_return_type>(json::json_void());
});
});
hf::get_enabled_injections_on_all.set(r, [](std::unique_ptr<request> req) {
auto& errinj = utils::get_local_injector();
auto ret = errinj.enabled_injections_on_all();
return make_ready_future<json::json_return_type>(ret);
});
hf::disable_injection.set(r, [](std::unique_ptr<request> req) {
sstring injection = req->param["injection"];
auto& errinj = utils::get_local_injector();
return errinj.disable_on_all(injection).then([] {
return make_ready_future<json::json_return_type>(json::json_void());
});
});
hf::disable_on_all.set(r, [](std::unique_ptr<request> req) {
auto& errinj = utils::get_local_injector();
return errinj.disable_on_all().then([] {
return make_ready_future<json::json_return_type>(json::json_void());
});
});
}
} // namespace api

View File

@@ -21,7 +21,7 @@
#include "gossiper.hh"
#include "api/api-doc/gossiper.json.hh"
#include "gms/gossiper.hh"
#include <gms/gossiper.hh>
namespace api {
using namespace json;

View File

@@ -23,7 +23,7 @@
#include "api/lsa.hh"
#include "api/api.hh"
#include <seastar/http/exception.hh>
#include "http/exception.hh"
#include "utils/logalloc.hh"
#include "log.hh"

View File

@@ -21,7 +21,7 @@
#include "messaging_service.hh"
#include "message/messaging_service.hh"
#include <seastar/rpc/rpc_types.hh>
#include "rpc/rpc_types.hh"
#include "api/api-doc/messaging_service.json.hh"
#include <iostream>
#include <sstream>
@@ -76,7 +76,7 @@ future_json_function get_server_getter(std::function<uint64_t(const rpc::stats&)
auto get_shard_map = [f](messaging_service& ms) {
std::unordered_map<gms::inet_address, unsigned long> map;
ms.foreach_server_connection_stats([&map, f] (const rpc::client_info& info, const rpc::stats& stats) mutable {
map[gms::inet_address(info.addr.addr())] = f(stats);
map[gms::inet_address(net::ipv4_address(info.addr))] = f(stats);
});
return map;
};
@@ -139,7 +139,7 @@ void set_messaging_service(http_context& ctx, routes& r) {
messaging_verb v = i; // for type safety we use messaging_verb values
auto idx = static_cast<uint32_t>(v);
if (idx >= map->size()) {
throw std::runtime_error(format("verb index out of bounds: {:d}, map size: {:d}", idx, map->size()));
throw std::runtime_error(sprint("verb index out of bounds: %lu, map size: %lu", idx, map->size()));
}
if ((*map)[idx] > 0) {
c.count = (*map)[idx];

View File

@@ -26,8 +26,6 @@
#include "service/storage_service.hh"
#include "db/config.hh"
#include "utils/histogram.hh"
#include "database.hh"
#include "seastar/core/scheduling_specific.hh"
namespace api {
@@ -35,70 +33,12 @@ namespace sp = httpd::storage_proxy_json;
using proxy = service::storage_proxy;
using namespace json;
/**
* This function implement a two dimentional map reduce where
* the first level is a distributed storage_proxy class and the
* second level is the stats per scheduling group class.
* @param d - a reference to the storage_proxy distributed class.
* @param mapper - the internal mapper that is used to map the internal
* stat class into a value of type `V`.
* @param reducer - the reducer that is used in both outer and inner
* aggregations.
* @param initial_value - the initial value to use for both aggregations
* @return A future that resolves to the result of the aggregation.
*/
template<typename V, typename Reducer, typename InnerMapper>
future<V> two_dimensional_map_reduce(distributed<service::storage_proxy>& d,
InnerMapper mapper, Reducer reducer, V initial_value) {
return d.map_reduce0( [mapper, reducer, initial_value] (const service::storage_proxy& sp) {
return map_reduce_scheduling_group_specific<service::storage_proxy_stats::stats>(
mapper, reducer, initial_value, sp.get_stats_key());
}, initial_value, reducer);
static future<utils::rate_moving_average> sum_timed_rate(distributed<proxy>& d, utils::timed_rate_moving_average proxy::stats::*f) {
return d.map_reduce0([f](const proxy& p) {return (p.get_stats().*f).rate();}, utils::rate_moving_average(),
std::plus<utils::rate_moving_average>());
}
/**
* This function implement a two dimentional map reduce where
* the first level is a distributed storage_proxy class and the
* second level is the stats per scheduling group class.
* @param d - a reference to the storage_proxy distributed class.
* @param f - a field pointer which is the implicit internal reducer.
* @param reducer - the reducer that is used in both outer and inner
* aggregations.
* @param initial_value - the initial value to use for both aggregations* @return
* @return A future that resolves to the result of the aggregation.
*/
template<typename V, typename Reducer, typename F>
future<V> two_dimensional_map_reduce(distributed<service::storage_proxy>& d,
V F::*f, Reducer reducer, V initial_value) {
return two_dimensional_map_reduce(d, [f] (F& stats) {
return stats.*f;
}, reducer, initial_value);
}
/**
* A partial Specialization of sum_stats for the storage proxy
* case where the get stats function doesn't return a
* stats object with fields but a per scheduling group
* stats object, the name was also changed since functions
* partial specialization is not supported in C++.
*
*/
template<typename V, typename F>
future<json::json_return_type> sum_stats_storage_proxy(distributed<proxy>& d, V F::*f) {
return two_dimensional_map_reduce(d, [f] (F& stats) { return stats.*f; }, std::plus<V>(), V(0)).then([] (V val) {
return make_ready_future<json::json_return_type>(val);
});
}
static future<utils::rate_moving_average> sum_timed_rate(distributed<proxy>& d, utils::timed_rate_moving_average service::storage_proxy_stats::stats::*f) {
return two_dimensional_map_reduce(d, [f] (service::storage_proxy_stats::stats& stats) {
return (stats.*f).rate();
}, std::plus<utils::rate_moving_average>(), utils::rate_moving_average());
}
static future<json::json_return_type> sum_timed_rate_as_obj(distributed<proxy>& d, utils::timed_rate_moving_average service::storage_proxy_stats::stats::*f) {
static future<json::json_return_type> sum_timed_rate_as_obj(distributed<proxy>& d, utils::timed_rate_moving_average proxy::stats::*f) {
return sum_timed_rate(d, f).then([](const utils::rate_moving_average& val) {
httpd::utils_json::rate_moving_average m;
m = val;
@@ -106,93 +46,29 @@ static future<json::json_return_type> sum_timed_rate_as_obj(distributed<proxy>&
});
}
httpd::utils_json::rate_moving_average_and_histogram get_empty_moving_average() {
return timer_to_json(utils::rate_moving_average_and_histogram());
}
static future<json::json_return_type> sum_timed_rate_as_long(distributed<proxy>& d, utils::timed_rate_moving_average service::storage_proxy_stats::stats::*f) {
static future<json::json_return_type> sum_timed_rate_as_long(distributed<proxy>& d, utils::timed_rate_moving_average proxy::stats::*f) {
return sum_timed_rate(d, f).then([](const utils::rate_moving_average& val) {
return make_ready_future<json::json_return_type>(val.count);
});
}
utils_json::estimated_histogram time_to_json_histogram(const utils::time_estimated_histogram& val) {
utils_json::estimated_histogram res;
for (size_t i = 0; i < val.size(); i++) {
res.buckets.push(val.get(i));
res.bucket_offsets.push(val.get_bucket_lower_limit(i));
}
return res;
}
static future<json::json_return_type> sum_estimated_histogram(http_context& ctx, utils::time_estimated_histogram service::storage_proxy_stats::stats::*f) {
return two_dimensional_map_reduce(ctx.sp, f, utils::time_estimated_histogram_merge,
utils::time_estimated_histogram()).then([](const utils::time_estimated_histogram& val) {
return make_ready_future<json::json_return_type>(time_to_json_histogram(val));
});
}
static future<json::json_return_type> sum_estimated_histogram(http_context& ctx, utils::estimated_histogram service::storage_proxy_stats::stats::*f) {
return two_dimensional_map_reduce(ctx.sp, f, utils::estimated_histogram_merge,
utils::estimated_histogram()).then([](const utils::estimated_histogram& val) {
static future<json::json_return_type> sum_estimated_histogram(http_context& ctx, utils::estimated_histogram proxy::stats::*f) {
return ctx.sp.map_reduce0([f](const proxy& p) {return p.get_stats().*f;}, utils::estimated_histogram(),
utils::estimated_histogram_merge).then([](const utils::estimated_histogram& val) {
utils_json::estimated_histogram res;
res = val;
return make_ready_future<json::json_return_type>(res);
});
}
static future<json::json_return_type> total_latency(http_context& ctx, utils::timed_rate_moving_average_and_histogram service::storage_proxy_stats::stats::*f) {
return two_dimensional_map_reduce(ctx.sp, [f] (service::storage_proxy_stats::stats& stats) {
return (stats.*f).hist.mean * (stats.*f).hist.count;
}, std::plus<double>(), 0.0).then([](double val) {
static future<json::json_return_type> total_latency(http_context& ctx, utils::timed_rate_moving_average_and_histogram proxy::stats::*f) {
return ctx.sp.map_reduce0([f](const proxy& p) {return (p.get_stats().*f).hist.mean * (p.get_stats().*f).hist.count;}, 0.0,
std::plus<double>()).then([](double val) {
int64_t res = val;
return make_ready_future<json::json_return_type>(res);
});
}
/**
* A partial Specialization of sum_histogram_stats
* for the storage proxy case where the get stats
* function doesn't return a stats object with
* fields but a per scheduling group stats object,
* the name was also changed since function partial
* specialization is not supported in C++.
*/
template<typename F>
future<json::json_return_type>
sum_histogram_stats_storage_proxy(distributed<proxy>& d,
utils::timed_rate_moving_average_and_histogram F::*f) {
return two_dimensional_map_reduce(d, [f] (service::storage_proxy_stats::stats& stats) {
return (stats.*f).hist;
}, std::plus<utils::ihistogram>(), utils::ihistogram()).
then([](const utils::ihistogram& val) {
return make_ready_future<json::json_return_type>(to_json(val));
});
}
/**
* A partial Specialization of sum_timer_stats for the
* storage proxy case where the get stats function
* doesn't return a stats object with fields but a
* per scheduling group stats object, the name
* was also changed since partial function specialization
* is not supported in C++.
*/
template<typename F>
future<json::json_return_type>
sum_timer_stats_storage_proxy(distributed<proxy>& d,
utils::timed_rate_moving_average_and_histogram F::*f) {
return two_dimensional_map_reduce(d, [f] (service::storage_proxy_stats::stats& stats) {
return (stats.*f).rate();
}, std::plus<utils::rate_moving_average_and_histogram>(),
utils::rate_moving_average_and_histogram()).then([](const utils::rate_moving_average_and_histogram& val) {
return make_ready_future<json::json_return_type>(timer_to_json(val));
});
}
void set_storage_proxy(http_context& ctx, routes& r) {
sp::get_total_hints.set(r, [](std::unique_ptr<request> req) {
//TBD
@@ -200,9 +76,12 @@ void set_storage_proxy(http_context& ctx, routes& r) {
return make_ready_future<json::json_return_type>(0);
});
sp::get_hinted_handoff_enabled.set(r, [&ctx](std::unique_ptr<request> req) {
auto enabled = ctx.db.local().get_config().hinted_handoff_enabled();
return make_ready_future<json::json_return_type>(enabled);
sp::get_hinted_handoff_enabled.set(r, [](std::unique_ptr<request> req) {
//TBD
// FIXME
// hinted handoff is not supported currently,
// so we should return false
return make_ready_future<json::json_return_type>(false);
});
sp::set_hinted_handoff_enabled.set(r, [](std::unique_ptr<request> req) {
@@ -342,15 +221,15 @@ void set_storage_proxy(http_context& ctx, routes& r) {
});
sp::get_read_repair_attempted.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read_repair_attempts);
return sum_stats(ctx.sp, &proxy::stats::read_repair_attempts);
});
sp::get_read_repair_repaired_blocking.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read_repair_repaired_blocking);
return sum_stats(ctx.sp, &proxy::stats::read_repair_repaired_blocking);
});
sp::get_read_repair_repaired_background.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read_repair_repaired_background);
return sum_stats(ctx.sp, &proxy::stats::read_repair_repaired_background);
});
sp::get_schema_versions.set(r, [](std::unique_ptr<request> req) {
@@ -366,154 +245,163 @@ void set_storage_proxy(http_context& ctx, routes& r) {
});
});
sp::get_cas_read_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::cas_read_timeouts);
sp::get_cas_read_timeouts.set(r, [](std::unique_ptr<request> req) {
//TBD
// FIXME
// cas is not supported yet, so just return 0
return make_ready_future<json::json_return_type>(0);
});
sp::get_cas_read_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::cas_read_unavailables);
sp::get_cas_read_unavailables.set(r, [](std::unique_ptr<request> req) {
//TBD
// FIXME
// cas is not supported yet, so just return 0
return make_ready_future<json::json_return_type>(0);
});
sp::get_cas_write_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::cas_write_timeouts);
sp::get_cas_write_timeouts.set(r, [](std::unique_ptr<request> req) {
//TBD
// FIXME
// cas is not supported yet, so just return 0
return make_ready_future<json::json_return_type>(0);
});
sp::get_cas_write_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::cas_write_unavailables);
sp::get_cas_write_unavailables.set(r, [](std::unique_ptr<request> req) {
//TBD
// FIXME
// cas is not supported yet, so just return 0
return make_ready_future<json::json_return_type>(0);
});
sp::get_cas_write_metrics_unfinished_commit.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_stats(ctx.sp, &proxy::stats::cas_write_unfinished_commit);
sp::get_cas_write_metrics_unfinished_commit.set(r, [](std::unique_ptr<request> req) {
//TBD
unimplemented();
return make_ready_future<json::json_return_type>(0);
});
sp::get_cas_write_metrics_contention.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_estimated_histogram(ctx, &proxy::stats::cas_write_contention);
sp::get_cas_write_metrics_contention.set(r, [](std::unique_ptr<request> req) {
//TBD
unimplemented();
return make_ready_future<json::json_return_type>(0);
});
sp::get_cas_write_metrics_condition_not_met.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_stats(ctx.sp, &proxy::stats::cas_write_condition_not_met);
sp::get_cas_write_metrics_condition_not_met.set(r, [](std::unique_ptr<request> req) {
//TBD
unimplemented();
return make_ready_future<json::json_return_type>(0);
});
sp::get_cas_write_metrics_failed_read_round_optimization.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_stats(ctx.sp, &proxy::stats::cas_failed_read_round_optimization);
sp::get_cas_read_metrics_unfinished_commit.set(r, [](std::unique_ptr<request> req) {
//TBD
unimplemented();
return make_ready_future<json::json_return_type>(0);
});
sp::get_cas_read_metrics_unfinished_commit.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_stats(ctx.sp, &proxy::stats::cas_read_unfinished_commit);
sp::get_cas_read_metrics_contention.set(r, [](std::unique_ptr<request> req) {
//TBD
unimplemented();
return make_ready_future<json::json_return_type>(0);
});
sp::get_cas_read_metrics_contention.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_estimated_histogram(ctx, &proxy::stats::cas_read_contention);
sp::get_cas_read_metrics_condition_not_met.set(r, [](std::unique_ptr<request> req) {
//TBD
unimplemented();
return make_ready_future<json::json_return_type>(0);
});
sp::get_read_metrics_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::read_timeouts);
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::read_timeouts);
});
sp::get_read_metrics_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::read_unavailables);
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::read_unavailables);
});
sp::get_range_metrics_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::range_slice_timeouts);
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::range_slice_timeouts);
});
sp::get_range_metrics_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::range_slice_unavailables);
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::range_slice_unavailables);
});
sp::get_write_metrics_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::write_timeouts);
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::write_timeouts);
});
sp::get_write_metrics_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::write_unavailables);
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::write_unavailables);
});
sp::get_read_metrics_timeouts_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::read_timeouts);
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::read_timeouts);
});
sp::get_read_metrics_unavailables_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::read_unavailables);
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::read_unavailables);
});
sp::get_range_metrics_timeouts_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::range_slice_timeouts);
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::range_slice_timeouts);
});
sp::get_range_metrics_unavailables_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::range_slice_unavailables);
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::range_slice_unavailables);
});
sp::get_write_metrics_timeouts_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::write_timeouts);
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::write_timeouts);
});
sp::get_write_metrics_unavailables_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::write_unavailables);
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::write_unavailables);
});
sp::get_range_metrics_latency_histogram_depricated.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_histogram_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::range);
return sum_histogram_stats(ctx.sp, &proxy::stats::range);
});
sp::get_write_metrics_latency_histogram_depricated.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_histogram_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::write);
return sum_histogram_stats(ctx.sp, &proxy::stats::write);
});
sp::get_read_metrics_latency_histogram_depricated.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_histogram_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read);
return sum_histogram_stats(ctx.sp, &proxy::stats::read);
});
sp::get_range_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::range);
return sum_timer_stats(ctx.sp, &proxy::stats::range);
});
sp::get_write_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::write);
});
sp::get_cas_write_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timer_stats(ctx.sp, &proxy::stats::cas_write);
});
sp::get_cas_read_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timer_stats(ctx.sp, &proxy::stats::cas_read);
});
sp::get_view_write_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
//TBD
// FIXME
// No View metrics are available, so just return empty moving average
return make_ready_future<json::json_return_type>(get_empty_moving_average());
return sum_timer_stats(ctx.sp, &proxy::stats::write);
});
sp::get_read_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read);
return sum_timer_stats(ctx.sp, &proxy::stats::read);
});
sp::get_read_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_estimated_histogram(ctx, &service::storage_proxy_stats::stats::estimated_read);
return sum_estimated_histogram(ctx, &proxy::stats::estimated_read);
});
sp::get_read_latency.set(r, [&ctx](std::unique_ptr<request> req) {
return total_latency(ctx, &service::storage_proxy_stats::stats::read);
return total_latency(ctx, &proxy::stats::read);
});
sp::get_write_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_estimated_histogram(ctx, &service::storage_proxy_stats::stats::estimated_write);
return sum_estimated_histogram(ctx, &proxy::stats::estimated_write);
});
sp::get_write_latency.set(r, [&ctx](std::unique_ptr<request> req) {
return total_latency(ctx, &service::storage_proxy_stats::stats::write);
return total_latency(ctx, &proxy::stats::write);
});
sp::get_range_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::range);
return sum_timer_stats(ctx.sp, &proxy::stats::read);
});
sp::get_range_latency.set(r, [&ctx](std::unique_ptr<request> req) {
return total_latency(ctx, &service::storage_proxy_stats::stats::range);
return total_latency(ctx, &proxy::stats::range);
});
}

View File

@@ -22,27 +22,18 @@
#include "storage_service.hh"
#include "api/api-doc/storage_service.json.hh"
#include "db/config.hh"
#include <optional>
#include <time.h>
#include <boost/range/adaptor/map.hpp>
#include <boost/range/adaptor/filtered.hpp>
#include "service/storage_service.hh"
#include "service/load_meter.hh"
#include "db/commitlog/commitlog.hh"
#include "gms/gossiper.hh"
#include "db/system_keyspace.hh"
#include "seastar/http/exception.hh"
#include <service/storage_service.hh>
#include <db/commitlog/commitlog.hh>
#include <gms/gossiper.hh>
#include <db/system_keyspace.hh>
#include "http/exception.hh"
#include "repair/repair.hh"
#include "locator/snitch_base.hh"
#include "column_family.hh"
#include "log.hh"
#include "release.hh"
#include "sstables/compaction_manager.hh"
#include "sstables/sstables.hh"
#include "database.hh"
#include "db/extensions.hh"
#include "transport/controller.hh"
#include "thrift/controller.hh"
namespace api {
@@ -56,97 +47,27 @@ static sstring validate_keyspace(http_context& ctx, const parameters& param) {
throw bad_param_exception("Keyspace " + param["keyspace"] + " Does not exist");
}
static ss::token_range token_range_endpoints_to_json(const dht::token_range_endpoints& d) {
ss::token_range r;
r.start_token = d._start_token;
r.end_token = d._end_token;
r.endpoints = d._endpoints;
r.rpc_endpoints = d._rpc_endpoints;
for (auto det : d._endpoint_details) {
ss::endpoint_detail ed;
ed.host = det._host;
ed.datacenter = det._datacenter;
if (det._rack != "") {
ed.rack = det._rack;
static std::vector<ss::token_range> describe_ring(const sstring& keyspace) {
std::vector<ss::token_range> res;
for (auto d : service::get_local_storage_service().describe_ring(keyspace)) {
ss::token_range r;
r.start_token = d._start_token;
r.end_token = d._end_token;
r.endpoints = d._endpoints;
r.rpc_endpoints = d._rpc_endpoints;
for (auto det : d._endpoint_details) {
ss::endpoint_detail ed;
ed.host = det._host;
ed.datacenter = det._datacenter;
if (det._rack != "") {
ed.rack = det._rack;
}
r.endpoint_details.push(ed);
}
r.endpoint_details.push(ed);
res.push_back(r);
}
return r;
}
using ks_cf_func = std::function<future<json::json_return_type>(http_context&, std::unique_ptr<request>, sstring, std::vector<sstring>)>;
static auto wrap_ks_cf(http_context &ctx, ks_cf_func f) {
return [&ctx, f = std::move(f)](std::unique_ptr<request> req) {
auto keyspace = validate_keyspace(ctx, req->param);
auto column_families = split_cf(req->get_query_param("cf"));
if (column_families.empty()) {
column_families = map_keys(ctx.db.local().find_keyspace(keyspace).metadata().get()->cf_meta_data());
}
return f(ctx, std::move(req), std::move(keyspace), std::move(column_families));
};
}
future<json::json_return_type> set_tables_autocompaction(http_context& ctx, const sstring &keyspace, std::vector<sstring> tables, bool enabled) {
if (tables.empty()) {
tables = map_keys(ctx.db.local().find_keyspace(keyspace).metadata().get()->cf_meta_data());
}
return service::get_local_storage_service().set_tables_autocompaction(keyspace, tables, enabled).then([]{
return make_ready_future<json::json_return_type>(json_void());
});
}
void set_transport_controller(http_context& ctx, routes& r, cql_transport::controller& ctl) {
ss::start_native_transport.set(r, [&ctl](std::unique_ptr<request> req) {
return ctl.start_server().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::stop_native_transport.set(r, [&ctl](std::unique_ptr<request> req) {
return ctl.stop_server().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::is_native_transport_running.set(r, [&ctl] (std::unique_ptr<request> req) {
return ctl.is_server_running().then([] (bool running) {
return make_ready_future<json::json_return_type>(running);
});
});
}
void unset_transport_controller(http_context& ctx, routes& r) {
ss::start_native_transport.unset(r);
ss::stop_native_transport.unset(r);
ss::is_native_transport_running.unset(r);
}
void set_rpc_controller(http_context& ctx, routes& r, thrift_controller& ctl) {
ss::stop_rpc_server.set(r, [&ctl](std::unique_ptr<request> req) {
return ctl.stop_server().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::start_rpc_server.set(r, [&ctl](std::unique_ptr<request> req) {
return ctl.start_server().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::is_rpc_server_running.set(r, [&ctl] (std::unique_ptr<request> req) {
return ctl.is_server_running().then([] (bool running) {
return make_ready_future<json::json_return_type>(running);
});
});
}
void unset_rpc_controller(http_context& ctx, routes& r) {
ss::stop_rpc_server.unset(r);
ss::start_rpc_server.unset(r);
ss::is_rpc_server_running.unset(r);
return res;
}
void set_storage_service(http_context& ctx, routes& r) {
@@ -156,43 +77,42 @@ void set_storage_service(http_context& ctx, routes& r) {
});
});
ss::get_tokens.set(r, [&ctx] (std::unique_ptr<request> req) {
return make_ready_future<json::json_return_type>(stream_range_as_array(ctx.token_metadata.local().sorted_tokens(), [](const dht::token& i) {
return boost::lexical_cast<std::string>(i);
}));
ss::get_tokens.set(r, [] (const_req req) {
auto tokens = service::get_local_storage_service().get_token_metadata().sorted_tokens();
return container_to_vec(tokens);
});
ss::get_node_tokens.set(r, [&ctx] (std::unique_ptr<request> req) {
gms::inet_address addr(req->param["endpoint"]);
return make_ready_future<json::json_return_type>(stream_range_as_array(ctx.token_metadata.local().get_tokens(addr), [](const dht::token& i) {
return boost::lexical_cast<std::string>(i);
}));
ss::get_node_tokens.set(r, [] (const_req req) {
gms::inet_address addr(req.param["endpoint"]);
auto tokens = service::get_local_storage_service().get_token_metadata().get_tokens(addr);
return container_to_vec(tokens);
});
ss::get_commitlog.set(r, [&ctx](const_req req) {
return ctx.db.local().commitlog()->active_config().commit_log_location;
});
ss::get_token_endpoint.set(r, [] (std::unique_ptr<request> req) {
return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().get_token_to_endpoint_map(), [](const auto& i) {
storage_service_json::mapper val;
val.key = boost::lexical_cast<std::string>(i.first);
val.value = boost::lexical_cast<std::string>(i.second);
return val;
}));
ss::get_token_endpoint.set(r, [] (const_req req) {
auto token_to_ep = service::get_local_storage_service().get_token_to_endpoint_map();
std::vector<storage_service_json::mapper> res;
return map_to_key_value(token_to_ep, res);
});
ss::get_leaving_nodes.set(r, [&ctx](const_req req) {
return container_to_vec(ctx.token_metadata.local().get_leaving_endpoints());
ss::get_leaving_nodes.set(r, [](const_req req) {
return container_to_vec(service::get_local_storage_service().get_token_metadata().get_leaving_endpoints());
});
ss::get_moving_nodes.set(r, [](const_req req) {
auto points = service::get_local_storage_service().get_token_metadata().get_moving_endpoints();
std::unordered_set<sstring> addr;
for (auto i: points) {
addr.insert(boost::lexical_cast<std::string>(i.second));
}
return container_to_vec(addr);
});
ss::get_joining_nodes.set(r, [&ctx](const_req req) {
auto points = ctx.token_metadata.local().get_bootstrap_tokens();
ss::get_joining_nodes.set(r, [](const_req req) {
auto points = service::get_local_storage_service().get_token_metadata().get_bootstrap_tokens();
std::unordered_set<sstring> addr;
for (auto i: points) {
addr.insert(boost::lexical_cast<std::string>(i.second));
@@ -235,26 +155,27 @@ void set_storage_service(http_context& ctx, routes& r) {
return make_ready_future<json::json_return_type>(res);
});
ss::describe_any_ring.set(r, [&ctx](std::unique_ptr<request> req) {
return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().describe_ring(""), token_range_endpoints_to_json));
ss::describe_any_ring.set(r, [&ctx](const_req req) {
return describe_ring("");
});
ss::describe_ring.set(r, [&ctx](std::unique_ptr<request> req) {
auto keyspace = validate_keyspace(ctx, req->param);
return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().describe_ring(keyspace), token_range_endpoints_to_json));
ss::describe_ring.set(r, [&ctx](const_req req) {
auto keyspace = validate_keyspace(ctx, req.param);
return describe_ring(keyspace);
});
ss::get_host_id_map.set(r, [&ctx](const_req req) {
ss::get_host_id_map.set(r, [](const_req req) {
std::vector<ss::mapper> res;
return map_to_key_value(ctx.token_metadata.local().get_endpoint_to_host_id_map_for_reading(), res);
return map_to_key_value(service::get_local_storage_service().
get_token_metadata().get_endpoint_to_host_id_map_for_reading(), res);
});
ss::get_load.set(r, [&ctx](std::unique_ptr<request> req) {
return get_cf_stats(ctx, &column_family_stats::live_disk_space_used);
return get_cf_stats(ctx, &column_family::stats::live_disk_space_used);
});
ss::get_load_map.set(r, [&ctx] (std::unique_ptr<request> req) {
return ctx.lmeter.get_load_map().then([] (auto&& load_map) {
ss::get_load_map.set(r, [] (std::unique_ptr<request> req) {
return service::get_local_storage_service().get_load_map().then([] (auto&& load_map) {
std::vector<ss::map_string_double> res;
for (auto i : load_map) {
ss::map_string_double val;
@@ -279,12 +200,64 @@ void set_storage_service(http_context& ctx, routes& r) {
req.get_query_param("key")));
});
ss::cdc_streams_check_and_repair.set(r, [&ctx] (std::unique_ptr<request> req) {
return service::get_local_storage_service().check_and_repair_cdc_streams().then([] {
ss::get_snapshot_details.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().get_snapshot_details().then([] (auto result) {
std::vector<ss::snapshots> res;
for (auto& map: result) {
ss::snapshots all_snapshots;
all_snapshots.key = map.first;
std::vector<ss::snapshot> snapshot;
for (auto& cf: map.second) {
ss::snapshot s;
s.ks = cf.ks;
s.cf = cf.cf;
s.live = cf.live;
s.total = cf.total;
snapshot.push_back(std::move(s));
}
all_snapshots.value = std::move(snapshot);
res.push_back(std::move(all_snapshots));
}
return make_ready_future<json::json_return_type>(std::move(res));
});
});
ss::take_snapshot.set(r, [](std::unique_ptr<request> req) {
auto tag = req->get_query_param("tag");
auto column_family = req->get_query_param("cf");
std::vector<sstring> keynames = split(req->get_query_param("kn"), ",");
auto resp = make_ready_future<>();
if (column_family.empty()) {
resp = service::get_local_storage_service().take_snapshot(tag, keynames);
} else {
if (keynames.size() > 1) {
throw httpd::bad_param_exception("Only one keyspace allowed when specifying a column family");
}
resp = service::get_local_storage_service().take_column_family_snapshot(keynames[0], column_family, tag);
}
return resp.then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::del_snapshot.set(r, [](std::unique_ptr<request> req) {
auto tag = req->get_query_param("tag");
std::vector<sstring> keynames = split(req->get_query_param("kn"), ",");
return service::get_local_storage_service().clear_snapshot(tag, keynames).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::true_snapshots_size.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().true_snapshots_size().then([] (int64_t size) {
return make_ready_future<json::json_return_type>(size);
});
});
ss::force_keyspace_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
auto keyspace = validate_keyspace(ctx, req->param);
auto column_families = split_cf(req->get_query_param("cf"));
@@ -310,40 +283,38 @@ void set_storage_service(http_context& ctx, routes& r) {
if (column_families.empty()) {
column_families = map_keys(ctx.db.local().find_keyspace(keyspace).metadata().get()->cf_meta_data());
}
return service::get_local_storage_service().is_cleanup_allowed(keyspace).then([&ctx, keyspace,
column_families = std::move(column_families)] (bool is_cleanup_allowed) mutable {
if (!is_cleanup_allowed) {
return make_exception_future<json::json_return_type>(
std::runtime_error("Can not perform cleanup operation when topology changes"));
return ctx.db.invoke_on_all([keyspace, column_families] (database& db) {
std::vector<column_family*> column_families_vec;
auto& cm = db.get_compaction_manager();
for (auto cf : column_families) {
column_families_vec.push_back(&db.find_column_family(keyspace, cf));
}
return ctx.db.invoke_on_all([keyspace, column_families] (database& db) {
std::vector<column_family*> column_families_vec;
auto& cm = db.get_compaction_manager();
for (auto cf : column_families) {
column_families_vec.push_back(&db.find_column_family(keyspace, cf));
}
return parallel_for_each(column_families_vec, [&cm, &db] (column_family* cf) {
return cm.perform_cleanup(db, cf);
});
}).then([]{
return make_ready_future<json::json_return_type>(0);
});
});
});
ss::upgrade_sstables.set(r, wrap_ks_cf(ctx, [] (http_context& ctx, std::unique_ptr<request> req, sstring keyspace, std::vector<sstring> column_families) {
bool exclude_current_version = req_param<bool>(*req, "exclude_current_version", false);
return ctx.db.invoke_on_all([=] (database& db) {
return do_for_each(column_families, [=, &db](sstring cfname) {
auto& cm = db.get_compaction_manager();
auto& cf = db.find_column_family(keyspace, cfname);
return cm.perform_sstable_upgrade(&cf, exclude_current_version);
return parallel_for_each(column_families_vec, [&cm] (column_family* cf) {
return cm.perform_cleanup(cf);
});
}).then([]{
return make_ready_future<json::json_return_type>(0);
});
}));
});
ss::scrub.set(r, [&ctx](std::unique_ptr<request> req) {
//TBD
unimplemented();
auto keyspace = validate_keyspace(ctx, req->param);
auto column_family = req->get_query_param("cf");
auto disable_snapshot = req->get_query_param("disable_snapshot");
auto skip_corrupted = req->get_query_param("skip_corrupted");
return make_ready_future<json::json_return_type>(json_void());
});
ss::upgrade_sstables.set(r, [&ctx](std::unique_ptr<request> req) {
//TBD
unimplemented();
auto keyspace = validate_keyspace(ctx, req->param);
auto column_family = req->get_query_param("cf");
auto exclude_current_version = req->get_query_param("exclude_current_version");
return make_ready_future<json::json_return_type>(json_void());
});
ss::force_keyspace_flush.set(r, [&ctx](std::unique_ptr<request> req) {
auto keyspace = validate_keyspace(ctx, req->param);
@@ -383,12 +354,6 @@ void set_storage_service(http_context& ctx, routes& r) {
});
});
ss::get_active_repair_async.set(r, [&ctx](std::unique_ptr<request> req) {
return get_active_repairs(ctx.db).then([] (std::vector<int> res){
return make_ready_future<json::json_return_type>(res);
});
});
ss::repair_async_status.set(r, [&ctx](std::unique_ptr<request> req) {
return repair_get_status(ctx.db, boost::lexical_cast<int>( req->get_query_param("id")))
.then_wrapped([] (future<repair_status>&& fut) {
@@ -396,22 +361,16 @@ void set_storage_service(http_context& ctx, routes& r) {
try {
res = fut.get0();
} catch(std::runtime_error& e) {
throw httpd::bad_param_exception(e.what());
return make_ready_future<json::json_return_type>(json_exception(httpd::bad_param_exception(e.what())));
}
return make_ready_future<json::json_return_type>(json::json_return_type(res));
});
});
ss::force_terminate_all_repair_sessions.set(r, [](std::unique_ptr<request> req) {
return repair_abort_all(service::get_local_storage_service().db()).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::force_terminate_all_repair_sessions_new.set(r, [](std::unique_ptr<request> req) {
return repair_abort_all(service::get_local_storage_service().db()).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
//TBD
unimplemented();
return make_ready_future<json::json_return_type>(json_void());
});
ss::decommission.set(r, [](std::unique_ptr<request> req) {
@@ -481,7 +440,7 @@ void set_storage_service(http_context& ctx, routes& r) {
return service::get_storage_service().map_reduce(adder<service::storage_service::drain_progress>(), [] (auto& ss) {
return ss.get_drain_progress();
}).then([] (auto&& progress) {
auto progress_str = format("Drained {}/{} ColumnFamilies", progress.remaining_cfs, progress.total_cfs);
auto progress_str = sprint("Drained %s/%s ColumnFamilies", progress.remaining_cfs, progress.total_cfs);
return make_ready_future<json::json_return_type>(std::move(progress_str));
});
});
@@ -549,8 +508,46 @@ void set_storage_service(http_context& ctx, routes& r) {
});
});
ss::stop_rpc_server.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().stop_rpc_server().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::start_rpc_server.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().start_rpc_server().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::is_rpc_server_running.set(r, [] (std::unique_ptr<request> req) {
return service::get_local_storage_service().is_rpc_server_running().then([] (bool running) {
return make_ready_future<json::json_return_type>(running);
});
});
ss::start_native_transport.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().start_native_transport().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::stop_native_transport.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().stop_native_transport().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::is_native_transport_running.set(r, [] (std::unique_ptr<request> req) {
return service::get_local_storage_service().is_native_transport_running().then([] (bool running) {
return make_ready_future<json::json_return_type>(running);
});
});
ss::join_ring.set(r, [](std::unique_ptr<request> req) {
return make_ready_future<json::json_return_type>(json_void());
return service::get_local_storage_service().join_ring().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::is_joined.set(r, [] (std::unique_ptr<request> req) {
@@ -654,11 +651,7 @@ void set_storage_service(http_context& ctx, routes& r) {
auto coordinator = std::hash<sstring>()(cf) % smp::count;
return service::get_storage_service().invoke_on(coordinator, [ks = std::move(ks), cf = std::move(cf)] (service::storage_service& s) {
return s.load_new_sstables(ks, cf);
}).then_wrapped([] (auto&& f) {
if (f.failed()) {
auto msg = fmt::format("Failed to load new sstables: {}", f.get_exception());
return make_exception_future<json::json_return_type>(httpd::server_error_exception(msg));
}
}).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
@@ -678,7 +671,7 @@ void set_storage_service(http_context& ctx, routes& r) {
ss::set_trace_probability.set(r, [](std::unique_ptr<request> req) {
auto probability = req->get_query_param("probability");
return futurize_invoke([probability] {
return futurize<json::json_return_type>::apply([probability] {
double real_prob = std::stod(probability.c_str());
return tracing::tracing::tracing_instance().invoke_on_all([real_prob] (auto& local_tracing) {
local_tracing.set_trace_probability(real_prob);
@@ -692,7 +685,7 @@ void set_storage_service(http_context& ctx, routes& r) {
} catch (std::out_of_range& e) {
throw httpd::bad_param_exception(e.what());
} catch (std::invalid_argument&){
throw httpd::bad_param_exception(format("Bad format in a probability value: \"{}\"", probability.c_str()));
throw httpd::bad_param_exception(sprint("Bad format in a probability value: \"%s\"", probability.c_str()));
}
});
});
@@ -728,22 +721,24 @@ void set_storage_service(http_context& ctx, routes& r) {
return make_ready_future<json::json_return_type>(json_void());
});
} catch (...) {
throw httpd::bad_param_exception(format("Bad format value: "));
throw httpd::bad_param_exception(sprint("Bad format value: "));
}
});
ss::enable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
//TBD
unimplemented();
auto keyspace = validate_keyspace(ctx, req->param);
auto tables = split_cf(req->get_query_param("cf"));
return set_tables_autocompaction(ctx, keyspace, tables, true);
auto column_family = req->get_query_param("cf");
return make_ready_future<json::json_return_type>(json_void());
});
ss::disable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
//TBD
unimplemented();
auto keyspace = validate_keyspace(ctx, req->param);
auto tables = split_cf(req->get_query_param("cf"));
return set_tables_autocompaction(ctx, keyspace, tables, false);
auto column_family = req->get_query_param("cf");
return make_ready_future<json::json_return_type>(json_void());
});
ss::deliver_hints.set(r, [](std::unique_ptr<request> req) {
@@ -808,7 +803,7 @@ void set_storage_service(http_context& ctx, routes& r) {
});
ss::get_metrics_load.set(r, [&ctx](std::unique_ptr<request> req) {
return get_cf_stats(ctx, &column_family_stats::live_disk_space_used);
return get_cf_stats(ctx, &column_family::stats::live_disk_space_used);
});
ss::get_exceptions.set(r, [](const_req req) {
@@ -841,245 +836,6 @@ void set_storage_service(http_context& ctx, routes& r) {
return make_ready_future<json::json_return_type>(map_to_key_value(ownership, res));
});
});
ss::view_build_statuses.set(r, [&ctx] (std::unique_ptr<request> req) {
auto keyspace = validate_keyspace(ctx, req->param);
auto view = req->param["view"];
return service::get_local_storage_service().view_build_statuses(std::move(keyspace), std::move(view)).then([] (std::unordered_map<sstring, sstring> status) {
std::vector<storage_service_json::mapper> res;
return make_ready_future<json::json_return_type>(map_to_key_value(std::move(status), res));
});
});
ss::sstable_info.set(r, [&ctx] (std::unique_ptr<request> req) {
auto ks = api::req_param<sstring>(*req, "keyspace", {}).value;
auto cf = api::req_param<sstring>(*req, "cf", {}).value;
// The size of this vector is bound by ks::cf. I.e. it is as most Nks + Ncf long
// which is not small, but not huge either.
using table_sstables_list = std::vector<ss::table_sstables>;
return do_with(table_sstables_list{}, [ks, cf, &ctx](table_sstables_list& dst) {
return service::get_local_storage_service().db().map_reduce([&dst](table_sstables_list&& res) {
for (auto&& t : res) {
auto i = std::find_if(dst.begin(), dst.end(), [&t](const ss::table_sstables& t2) {
return t.keyspace() == t2.keyspace() && t.table() == t2.table();
});
if (i == dst.end()) {
dst.emplace_back(std::move(t));
continue;
}
auto& ssd = i->sstables;
for (auto&& sd : t.sstables._elements) {
auto j = std::find_if(ssd._elements.begin(), ssd._elements.end(), [&sd](const ss::sstable& s) {
return s.generation() == sd.generation();
});
if (j == ssd._elements.end()) {
i->sstables.push(std::move(sd));
}
}
}
}, [ks, cf](const database& db) {
// see above
table_sstables_list res;
auto& ext = db.get_config().extensions();
for (auto& t : db.get_column_families() | boost::adaptors::map_values) {
auto& schema = t->schema();
if ((ks.empty() || ks == schema->ks_name()) && (cf.empty() || cf == schema->cf_name())) {
// at most Nsstables long
ss::table_sstables tst;
tst.keyspace = schema->ks_name();
tst.table = schema->cf_name();
for (auto sstable : *t->get_sstables_including_compacted_undeleted()) {
auto ts = db_clock::to_time_t(sstable->data_file_write_time());
::tm t;
::gmtime_r(&ts, &t);
ss::sstable info;
info.timestamp = t;
info.generation = sstable->generation();
info.level = sstable->get_sstable_level();
info.size = sstable->bytes_on_disk();
info.data_size = sstable->ondisk_data_size();
info.index_size = sstable->index_size();
info.filter_size = sstable->filter_size();
info.version = sstable->get_version();
if (sstable->has_component(sstables::component_type::CompressionInfo)) {
auto& c = sstable->get_compression();
auto cp = sstables::get_sstable_compressor(c);
ss::named_maps nm;
nm.group = "compression_parameters";
for (auto& p : cp->options()) {
ss::mapper e;
e.key = p.first;
e.value = p.second;
nm.attributes.push(std::move(e));
}
if (!cp->options().count(compression_parameters::SSTABLE_COMPRESSION)) {
ss::mapper e;
e.key = compression_parameters::SSTABLE_COMPRESSION;
e.value = cp->name();
nm.attributes.push(std::move(e));
}
info.extended_properties.push(std::move(nm));
}
sstables::file_io_extension::attr_value_map map;
for (auto* ep : ext.sstable_file_io_extensions()) {
map.merge(ep->get_attributes(*sstable));
}
for (auto& p : map) {
struct {
const sstring& key;
ss::sstable& info;
void operator()(const std::map<sstring, sstring>& map) const {
ss::named_maps nm;
nm.group = key;
for (auto& p : map) {
ss::mapper e;
e.key = p.first;
e.value = p.second;
nm.attributes.push(std::move(e));
}
info.extended_properties.push(std::move(nm));
}
void operator()(const sstring& value) const {
ss::mapper e;
e.key = key;
e.value = value;
info.properties.push(std::move(e));
}
} v{p.first, info};
std::visit(v, p.second);
}
tst.sstables.push(std::move(info));
}
res.emplace_back(std::move(tst));
}
}
std::sort(res.begin(), res.end(), [](const ss::table_sstables& t1, const ss::table_sstables& t2) {
return t1.keyspace() < t2.keyspace() || (t1.keyspace() == t2.keyspace() && t1.table() < t2.table());
});
return res;
}).then([&dst] {
return make_ready_future<json::json_return_type>(stream_object(dst));
});
});
});
}
void set_snapshot(http_context& ctx, routes& r) {
ss::get_snapshot_details.set(r, [](std::unique_ptr<request> req) {
std::function<future<>(output_stream<char>&&)> f = [](output_stream<char>&& s) {
return do_with(output_stream<char>(std::move(s)), true, [] (output_stream<char>& s, bool& first){
return s.write("[").then([&s, &first] {
return service::get_local_storage_service().get_snapshot_details().then([&s, &first] (std::unordered_map<sstring, std::vector<service::storage_service::snapshot_details>>&& result) {
return do_with(std::move(result), [&s, &first](const std::unordered_map<sstring, std::vector<service::storage_service::snapshot_details>>& result) {
return do_for_each(result, [&s, &result,&first](std::tuple<sstring, std::vector<service::storage_service::snapshot_details>>&& map){
return do_with(ss::snapshots(), [&s, &first, &result, &map](ss::snapshots& all_snapshots) {
all_snapshots.key = std::get<0>(map);
future<> f = first ? make_ready_future<>() : s.write(", ");
first = false;
std::vector<ss::snapshot> snapshot;
for (auto& cf: std::get<1>(map)) {
ss::snapshot snp;
snp.ks = cf.ks;
snp.cf = cf.cf;
snp.live = cf.live;
snp.total = cf.total;
snapshot.push_back(std::move(snp));
}
all_snapshots.value = std::move(snapshot);
return f.then([&s, &all_snapshots] {
return all_snapshots.write(s);
});
});
});
});
}).then([&s] {
return s.write("]").then([&s] {
return s.close();
});
});
});
});
};
return make_ready_future<json::json_return_type>(std::move(f));
});
ss::take_snapshot.set(r, [](std::unique_ptr<request> req) {
auto tag = req->get_query_param("tag");
auto column_families = split(req->get_query_param("cf"), ",");
std::vector<sstring> keynames = split(req->get_query_param("kn"), ",");
auto resp = make_ready_future<>();
if (column_families.empty()) {
resp = service::get_local_storage_service().take_snapshot(tag, keynames);
} else {
if (keynames.empty()) {
throw httpd::bad_param_exception("The keyspace of column families must be specified");
}
if (keynames.size() > 1) {
throw httpd::bad_param_exception("Only one keyspace allowed when specifying a column family");
}
resp = service::get_local_storage_service().take_column_family_snapshot(keynames[0], column_families, tag);
}
return resp.then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::del_snapshot.set(r, [](std::unique_ptr<request> req) {
auto tag = req->get_query_param("tag");
auto column_family = req->get_query_param("cf");
std::vector<sstring> keynames = split(req->get_query_param("kn"), ",");
return service::get_local_storage_service().clear_snapshot(tag, keynames, column_family).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::true_snapshots_size.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().true_snapshots_size().then([] (int64_t size) {
return make_ready_future<json::json_return_type>(size);
});
});
ss::scrub.set(r, wrap_ks_cf(ctx, [] (http_context& ctx, std::unique_ptr<request> req, sstring keyspace, std::vector<sstring> column_families) {
const auto skip_corrupted = req_param<bool>(*req, "skip_corrupted", false);
auto f = make_ready_future<>();
if (!req_param<bool>(*req, "disable_snapshot", false)) {
auto tag = format("pre-scrub-{:d}", db_clock::now().time_since_epoch().count());
f = parallel_for_each(column_families, [keyspace, tag](sstring cf) {
return service::get_local_storage_service().take_column_family_snapshot(keyspace, cf, tag);
});
}
return f.then([&ctx, keyspace, column_families, skip_corrupted] {
return ctx.db.invoke_on_all([=] (database& db) {
return do_for_each(column_families, [=, &db](sstring cfname) {
auto& cm = db.get_compaction_manager();
auto& cf = db.find_column_family(keyspace, cfname);
return cm.perform_sstable_scrub(&cf, skip_corrupted);
});
});
}).then([]{
return make_ready_future<json::json_return_type>(0);
});
}));
}
}

View File

@@ -23,16 +23,8 @@
#include "api.hh"
namespace cql_transport { class controller; }
class thrift_controller;
namespace api {
void set_storage_service(http_context& ctx, routes& r);
void set_transport_controller(http_context& ctx, routes& r, cql_transport::controller& ctl);
void unset_transport_controller(http_context& ctx, routes& r);
void set_rpc_controller(http_context& ctx, routes& r, thrift_controller& ctl);
void unset_rpc_controller(http_context& ctx, routes& r);
void set_snapshot(http_context& ctx, routes& r);
}

View File

@@ -22,8 +22,7 @@
#include "api/api-doc/system.json.hh"
#include "api/api.hh"
#include <seastar/core/reactor.hh>
#include <seastar/http/exception.hh>
#include "http/exception.hh"
#include "log.hh"
namespace api {
@@ -31,10 +30,6 @@ namespace api {
namespace hs = httpd::system_json;
void set_system(http_context& ctx, routes& r) {
hs::get_system_uptime.set(r, [](const_req req) {
return std::chrono::duration_cast<std::chrono::milliseconds>(engine().uptime()).count();
});
hs::get_all_logger_names.set(r, [](const_req req) {
return logging::logger_registry().get_all_logger_names();
});

View File

@@ -1,287 +0,0 @@
/*
* Copyright (C) 2018 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "atomic_cell.hh"
#include "atomic_cell_or_collection.hh"
#include "counters.hh"
#include "types.hh"
/// LSA mirator for cells with irrelevant type
///
///
const data::type_imr_descriptor& no_type_imr_descriptor() {
static thread_local data::type_imr_descriptor state(data::type_info::make_variable_size());
return state;
}
atomic_cell atomic_cell::make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time) {
auto& imr_data = no_type_imr_descriptor();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_dead(timestamp, deletion_time), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value, atomic_cell::collection_member cm) {
auto& imr_data = type.imr_state();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, bool(cm)), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value, atomic_cell::collection_member cm) {
auto& imr_data = type.imr_state();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, bool(cm)), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value, collection_member cm)
{
auto& imr_data = type.imr_state();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, bool(cm)), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value,
gc_clock::time_point expiry, gc_clock::duration ttl, atomic_cell::collection_member cm) {
auto& imr_data = type.imr_state();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, expiry, ttl, bool(cm)), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value,
gc_clock::time_point expiry, gc_clock::duration ttl, atomic_cell::collection_member cm) {
auto& imr_data = type.imr_state();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, expiry, ttl, bool(cm)), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value,
gc_clock::time_point expiry, gc_clock::duration ttl, collection_member cm)
{
auto& imr_data = type.imr_state();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, expiry, ttl, bool(cm)), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live_counter_update(api::timestamp_type timestamp, int64_t value) {
auto& imr_data = no_type_imr_descriptor();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live_counter_update(timestamp, value), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live_uninitialized(const abstract_type& type, api::timestamp_type timestamp, size_t size) {
auto& imr_data = no_type_imr_descriptor();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live_uninitialized(imr_data.type_info(), timestamp, size), &imr_data.lsa_migrator())
);
}
static imr::utils::object<data::cell::structure> copy_cell(const data::type_imr_descriptor& imr_data, const uint8_t* ptr)
{
using imr_object_type = imr::utils::object<data::cell::structure>;
// If the cell doesn't own any memory it is trivial and can be copied with
// memcpy.
auto f = data::cell::structure::get_member<data::cell::tags::flags>(ptr);
if (!f.template get<data::cell::tags::external_data>()) {
data::cell::context ctx(f, imr_data.type_info());
// XXX: We may be better off storing the total cell size in memory. Measure!
auto size = data::cell::structure::serialized_object_size(ptr, ctx);
return imr_object_type::make_raw(size, [&] (uint8_t* dst) noexcept {
std::copy_n(ptr, size, dst);
}, &imr_data.lsa_migrator());
}
return imr_object_type::make(data::cell::copy_fn(imr_data.type_info(), ptr), &imr_data.lsa_migrator());
}
atomic_cell::atomic_cell(const abstract_type& type, atomic_cell_view other)
: atomic_cell(type.imr_state().type_info(),
copy_cell(type.imr_state(), other._view.raw_pointer()))
{ }
atomic_cell_or_collection atomic_cell_or_collection::copy(const abstract_type& type) const {
if (!_data.get()) {
return atomic_cell_or_collection();
}
auto& imr_data = type.imr_state();
return atomic_cell_or_collection(
copy_cell(imr_data, _data.get())
);
}
atomic_cell_or_collection::atomic_cell_or_collection(const abstract_type& type, atomic_cell_view acv)
: _data(copy_cell(type.imr_state(), acv._view.raw_pointer()))
{
}
bool atomic_cell_or_collection::equals(const abstract_type& type, const atomic_cell_or_collection& other) const
{
auto ptr_a = _data.get();
auto ptr_b = other._data.get();
if (!ptr_a || !ptr_b) {
return !ptr_a && !ptr_b;
}
if (type.is_atomic()) {
auto a = atomic_cell_view::from_bytes(type.imr_state().type_info(), _data);
auto b = atomic_cell_view::from_bytes(type.imr_state().type_info(), other._data);
if (a.timestamp() != b.timestamp()) {
return false;
}
if (a.is_live() != b.is_live()) {
return false;
}
if (a.is_live()) {
if (a.is_counter_update() != b.is_counter_update()) {
return false;
}
if (a.is_counter_update()) {
return a.counter_update_value() == b.counter_update_value();
}
if (a.is_live_and_has_ttl() != b.is_live_and_has_ttl()) {
return false;
}
if (a.is_live_and_has_ttl()) {
if (a.ttl() != b.ttl() || a.expiry() != b.expiry()) {
return false;
}
}
return a.value() == b.value();
}
return a.deletion_time() == b.deletion_time();
} else {
return as_collection_mutation().data == other.as_collection_mutation().data;
}
}
size_t atomic_cell_or_collection::external_memory_usage(const abstract_type& t) const
{
if (!_data.get()) {
return 0;
}
auto ctx = data::cell::context(_data.get(), t.imr_state().type_info());
auto view = data::cell::structure::make_view(_data.get(), ctx);
auto flags = view.get<data::cell::tags::flags>();
size_t external_value_size = 0;
if (flags.get<data::cell::tags::external_data>()) {
if (flags.get<data::cell::tags::collection>()) {
external_value_size = as_collection_mutation().data.size_bytes();
} else {
auto cell_view = data::cell::atomic_cell_view(t.imr_state().type_info(), view);
external_value_size = cell_view.value_size();
}
// Add overhead of chunk headers. The last one is a special case.
external_value_size += (external_value_size - 1) / data::cell::maximum_external_chunk_length * data::cell::external_chunk_overhead;
external_value_size += data::cell::external_last_chunk_overhead;
}
return data::cell::structure::serialized_object_size(_data.get(), ctx)
+ imr_object_type::size_overhead + external_value_size;
}
std::ostream&
operator<<(std::ostream& os, const atomic_cell_view& acv) {
if (acv.is_live()) {
return fmt_print(os, "atomic_cell{{{},ts={:d},expiry={:d},ttl={:d}}}",
acv.is_counter_update()
? "counter_update_value=" + to_sstring(acv.counter_update_value())
: to_hex(acv.value().linearize()),
acv.timestamp(),
acv.is_live_and_has_ttl() ? acv.expiry().time_since_epoch().count() : -1,
acv.is_live_and_has_ttl() ? acv.ttl().count() : 0);
} else {
return fmt_print(os, "atomic_cell{{DEAD,ts={:d},deletion_time={:d}}}",
acv.timestamp(), acv.deletion_time().time_since_epoch().count());
}
}
std::ostream&
operator<<(std::ostream& os, const atomic_cell& ac) {
return os << atomic_cell_view(ac);
}
std::ostream&
operator<<(std::ostream& os, const atomic_cell_view::printer& acvp) {
auto& type = acvp._type;
auto& acv = acvp._cell;
if (acv.is_live()) {
std::ostringstream cell_value_string_builder;
if (type.is_counter()) {
if (acv.is_counter_update()) {
cell_value_string_builder << "counter_update_value=" << acv.counter_update_value();
} else {
cell_value_string_builder << "shards: ";
counter_cell_view::with_linearized(acv, [&cell_value_string_builder] (counter_cell_view& ccv) {
cell_value_string_builder << ::join(", ", ccv.shards());
});
}
} else {
cell_value_string_builder << type.to_string(acv.value().linearize());
}
return fmt_print(os, "atomic_cell{{{},ts={:d},expiry={:d},ttl={:d}}}",
cell_value_string_builder.str(),
acv.timestamp(),
acv.is_live_and_has_ttl() ? acv.expiry().time_since_epoch().count() : -1,
acv.is_live_and_has_ttl() ? acv.ttl().count() : 0);
} else {
return fmt_print(os, "atomic_cell{{DEAD,ts={:d},deletion_time={:d}}}",
acv.timestamp(), acv.deletion_time().time_since_epoch().count());
}
}
std::ostream&
operator<<(std::ostream& os, const atomic_cell::printer& acp) {
return operator<<(os, static_cast<const atomic_cell_view::printer&>(acp));
}
std::ostream& operator<<(std::ostream& os, const atomic_cell_or_collection::printer& p) {
if (!p._cell._data.get()) {
return os << "{ null atomic_cell_or_collection }";
}
using dc = data::cell;
os << "{ ";
if (dc::structure::get_member<dc::tags::flags>(p._cell._data.get()).get<dc::tags::collection>()) {
os << "collection ";
auto cmv = p._cell.as_collection_mutation();
os << collection_mutation_view::printer(*p._cdef.type, cmv);
} else {
os << atomic_cell_view::printer(*p._cdef.type, p._cell.as_atomic_cell(p._cdef));
}
return os << " }";
}

View File

@@ -26,54 +26,204 @@
#include "tombstone.hh"
#include "gc_clock.hh"
#include "utils/managed_bytes.hh"
#include <seastar/net//byteorder.hh>
#include "net/byteorder.hh"
#include <cstdint>
#include <iosfwd>
#include "data/cell.hh"
#include "data/schema_info.hh"
#include "imr/utils.hh"
#include "utils/fragmented_temporary_buffer.hh"
#include <seastar/util/gcc6-concepts.hh>
#include "serializer.hh"
template<typename T, typename Input>
static inline
void set_field(Input& v, unsigned offset, T val) {
reinterpret_cast<net::packed<T>*>(v.begin() + offset)->raw = net::hton(val);
}
class abstract_type;
class collection_type_impl;
template<typename T>
static inline
T get_field(const bytes_view& v, unsigned offset) {
return net::ntoh(*reinterpret_cast<const net::packed<T>*>(v.begin() + offset));
}
using atomic_cell_value_view = data::value_view;
using atomic_cell_value_mutable_view = data::value_mutable_view;
class atomic_cell_or_collection;
/// View of an atomic cell
template<mutable_view is_mutable>
class basic_atomic_cell_view {
protected:
data::cell::basic_atomic_cell_view<is_mutable> _view;
friend class atomic_cell;
/*
* Represents atomic cell layout. Works on serialized form.
*
* Layout:
*
* <live> := <int8_t:flags><int64_t:timestamp>(<int32_t:expiry><int32_t:ttl>)?<value>
* <dead> := <int8_t: 0><int64_t:timestamp><int32_t:deletion_time>
*/
class atomic_cell_type final {
private:
static constexpr int8_t LIVE_FLAG = 0x01;
static constexpr int8_t EXPIRY_FLAG = 0x02; // When present, expiry field is present. Set only for live cells
static constexpr int8_t REVERT_FLAG = 0x04; // transient flag used to efficiently implement ReversiblyMergeable for atomic cells.
static constexpr int8_t COUNTER_UPDATE_FLAG = 0x08; // Cell is a counter update.
static constexpr int8_t COUNTER_IN_PLACE_REVERT = 0x10;
static constexpr unsigned flags_size = 1;
static constexpr unsigned timestamp_offset = flags_size;
static constexpr unsigned timestamp_size = 8;
static constexpr unsigned expiry_offset = timestamp_offset + timestamp_size;
static constexpr unsigned expiry_size = 4;
static constexpr unsigned deletion_time_offset = timestamp_offset + timestamp_size;
static constexpr unsigned deletion_time_size = 4;
static constexpr unsigned ttl_offset = expiry_offset + expiry_size;
static constexpr unsigned ttl_size = 4;
friend class counter_cell_builder;
private:
static bool is_counter_update(bytes_view cell) {
return cell[0] & COUNTER_UPDATE_FLAG;
}
static bool is_revert_set(bytes_view cell) {
return cell[0] & REVERT_FLAG;
}
static bool is_counter_in_place_revert_set(bytes_view cell) {
return cell[0] & COUNTER_IN_PLACE_REVERT;
}
template<typename BytesContainer>
static void set_revert(BytesContainer& cell, bool revert) {
cell[0] = (cell[0] & ~REVERT_FLAG) | (revert * REVERT_FLAG);
}
template<typename BytesContainer>
static void set_counter_in_place_revert(BytesContainer& cell, bool flag) {
cell[0] = (cell[0] & ~COUNTER_IN_PLACE_REVERT) | (flag * COUNTER_IN_PLACE_REVERT);
}
static bool is_live(const bytes_view& cell) {
return cell[0] & LIVE_FLAG;
}
static bool is_live_and_has_ttl(const bytes_view& cell) {
return cell[0] & EXPIRY_FLAG;
}
static bool is_dead(const bytes_view& cell) {
return !is_live(cell);
}
// Can be called on live and dead cells
static api::timestamp_type timestamp(const bytes_view& cell) {
return get_field<api::timestamp_type>(cell, timestamp_offset);
}
template<typename BytesContainer>
static void set_timestamp(BytesContainer& cell, api::timestamp_type ts) {
set_field(cell, timestamp_offset, ts);
}
// Can be called on live cells only
private:
template<typename BytesView>
static BytesView do_get_value(BytesView cell) {
auto expiry_field_size = bool(cell[0] & EXPIRY_FLAG) * (expiry_size + ttl_size);
auto value_offset = flags_size + timestamp_size + expiry_field_size;
cell.remove_prefix(value_offset);
return cell;
}
public:
using pointer_type = std::conditional_t<is_mutable == mutable_view::no, const uint8_t*, uint8_t*>;
static bytes_view value(bytes_view cell) {
return do_get_value(cell);
}
static bytes_mutable_view value(bytes_mutable_view cell) {
return do_get_value(cell);
}
// Can be called on live counter update cells only
static int64_t counter_update_value(bytes_view cell) {
return get_field<int64_t>(cell, flags_size + timestamp_size);
}
// Can be called only when is_dead() is true.
static gc_clock::time_point deletion_time(const bytes_view& cell) {
assert(is_dead(cell));
return gc_clock::time_point(gc_clock::duration(
get_field<int32_t>(cell, deletion_time_offset)));
}
// Can be called only when is_live_and_has_ttl() is true.
static gc_clock::time_point expiry(const bytes_view& cell) {
assert(is_live_and_has_ttl(cell));
auto expiry = get_field<int32_t>(cell, expiry_offset);
return gc_clock::time_point(gc_clock::duration(expiry));
}
// Can be called only when is_live_and_has_ttl() is true.
static gc_clock::duration ttl(const bytes_view& cell) {
assert(is_live_and_has_ttl(cell));
return gc_clock::duration(get_field<int32_t>(cell, ttl_offset));
}
static managed_bytes make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time) {
managed_bytes b(managed_bytes::initialized_later(), flags_size + timestamp_size + deletion_time_size);
b[0] = 0;
set_field(b, timestamp_offset, timestamp);
set_field(b, deletion_time_offset, deletion_time.time_since_epoch().count());
return b;
}
static managed_bytes make_live(api::timestamp_type timestamp, bytes_view value) {
auto value_offset = flags_size + timestamp_size;
managed_bytes b(managed_bytes::initialized_later(), value_offset + value.size());
b[0] = LIVE_FLAG;
set_field(b, timestamp_offset, timestamp);
std::copy_n(value.begin(), value.size(), b.begin() + value_offset);
return b;
}
static managed_bytes make_live_counter_update(api::timestamp_type timestamp, int64_t value) {
auto value_offset = flags_size + timestamp_size;
managed_bytes b(managed_bytes::initialized_later(), value_offset + sizeof(value));
b[0] = LIVE_FLAG | COUNTER_UPDATE_FLAG;
set_field(b, timestamp_offset, timestamp);
set_field(b, value_offset, value);
return b;
}
static managed_bytes make_live(api::timestamp_type timestamp, bytes_view value, gc_clock::time_point expiry, gc_clock::duration ttl) {
auto value_offset = flags_size + timestamp_size + expiry_size + ttl_size;
managed_bytes b(managed_bytes::initialized_later(), value_offset + value.size());
b[0] = EXPIRY_FLAG | LIVE_FLAG;
set_field(b, timestamp_offset, timestamp);
set_field(b, expiry_offset, expiry.time_since_epoch().count());
set_field(b, ttl_offset, ttl.count());
std::copy_n(value.begin(), value.size(), b.begin() + value_offset);
return b;
}
// make_live_from_serializer() is intended for users that need to serialise
// some object or objects to the format used in atomic_cell::value().
// With just make_live() the patter would look like follows:
// 1. allocate a buffer and write to it serialised objects
// 2. pass that buffer to make_live()
// 3. make_live() needs to prepend some metadata to the cell value so it
// allocates a new buffer and copies the content of the original one
//
// The allocation and copy of a buffer can be avoided.
// make_live_from_serializer() allows the user code to specify the timestamp
// and size of the cell value as well as provide the serialiser function
// object, which would write the serialised value of the cell to the buffer
// given to it by make_live_from_serializer().
template<typename Serializer>
GCC6_CONCEPT(requires requires(Serializer serializer, bytes::iterator it) {
serializer(it);
})
static managed_bytes make_live_from_serializer(api::timestamp_type timestamp, size_t size, Serializer&& serializer) {
auto value_offset = flags_size + timestamp_size;
managed_bytes b(managed_bytes::initialized_later(), value_offset + size);
b[0] = LIVE_FLAG;
set_field(b, timestamp_offset, timestamp);
serializer(b.begin() + value_offset);
return b;
}
template<typename ByteContainer>
friend class atomic_cell_base;
friend class atomic_cell;
};
template<typename ByteContainer>
class atomic_cell_base {
protected:
explicit basic_atomic_cell_view(data::cell::basic_atomic_cell_view<is_mutable> v)
: _view(std::move(v)) { }
basic_atomic_cell_view(const data::type_info& ti, pointer_type ptr)
: _view(data::cell::make_atomic_cell_view(ti, ptr))
{ }
ByteContainer _data;
protected:
atomic_cell_base(ByteContainer&& data) : _data(std::forward<ByteContainer>(data)) { }
friend class atomic_cell_or_collection;
public:
operator basic_atomic_cell_view<mutable_view::no>() const noexcept {
return basic_atomic_cell_view<mutable_view::no>(_view);
}
void swap(basic_atomic_cell_view& other) noexcept {
using std::swap;
swap(_view, other._view);
}
bool is_counter_update() const {
return _view.is_counter_update();
return atomic_cell_type::is_counter_update(_data);
}
bool is_revert_set() const {
return atomic_cell_type::is_revert_set(_data);
}
bool is_counter_in_place_revert_set() const {
return atomic_cell_type::is_counter_in_place_revert_set(_data);
}
bool is_live() const {
return _view.is_live();
return atomic_cell_type::is_live(_data);
}
bool is_live(tombstone t, bool is_counter) const {
return is_live() && !is_covered_by(t, is_counter);
@@ -82,161 +232,165 @@ public:
return is_live() && !is_covered_by(t, is_counter) && !has_expired(now);
}
bool is_live_and_has_ttl() const {
return _view.is_expiring();
return atomic_cell_type::is_live_and_has_ttl(_data);
}
bool is_dead(gc_clock::time_point now) const {
return !is_live() || has_expired(now);
return atomic_cell_type::is_dead(_data) || has_expired(now);
}
bool is_covered_by(tombstone t, bool is_counter) const {
return timestamp() <= t.timestamp || (is_counter && t.timestamp != api::missing_timestamp);
}
// Can be called on live and dead cells
api::timestamp_type timestamp() const {
return _view.timestamp();
return atomic_cell_type::timestamp(_data);
}
void set_timestamp(api::timestamp_type ts) {
_view.set_timestamp(ts);
atomic_cell_type::set_timestamp(_data, ts);
}
// Can be called on live cells only
data::basic_value_view<is_mutable> value() const {
return _view.value();
}
// Can be called on live cells only
size_t value_size() const {
return _view.value_size();
}
bool is_value_fragmented() const {
return _view.is_value_fragmented();
auto value() const {
return atomic_cell_type::value(_data);
}
// Can be called on live counter update cells only
int64_t counter_update_value() const {
return _view.counter_update_value();
return atomic_cell_type::counter_update_value(_data);
}
// Can be called only when is_dead(gc_clock::time_point)
gc_clock::time_point deletion_time() const {
return !is_live() ? _view.deletion_time() : expiry() - ttl();
return !is_live() ? atomic_cell_type::deletion_time(_data) : expiry() - ttl();
}
// Can be called only when is_live_and_has_ttl()
gc_clock::time_point expiry() const {
return _view.expiry();
return atomic_cell_type::expiry(_data);
}
// Can be called only when is_live_and_has_ttl()
gc_clock::duration ttl() const {
return _view.ttl();
return atomic_cell_type::ttl(_data);
}
// Can be called on live and dead cells
bool has_expired(gc_clock::time_point now) const {
return is_live_and_has_ttl() && expiry() <= now;
return is_live_and_has_ttl() && expiry() < now;
}
bytes_view serialize() const {
return _view.serialize();
return _data;
}
void set_revert(bool revert) {
atomic_cell_type::set_revert(_data, revert);
}
void set_counter_in_place_revert(bool flag) {
atomic_cell_type::set_counter_in_place_revert(_data, flag);
}
};
class atomic_cell_view final : public basic_atomic_cell_view<mutable_view::no> {
atomic_cell_view(const data::type_info& ti, const uint8_t* data)
: basic_atomic_cell_view<mutable_view::no>(ti, data) {}
template<mutable_view is_mutable>
atomic_cell_view(data::cell::basic_atomic_cell_view<is_mutable> view)
: basic_atomic_cell_view<mutable_view::no>(view) { }
friend class atomic_cell;
class atomic_cell_view final : public atomic_cell_base<bytes_view> {
atomic_cell_view(bytes_view data) : atomic_cell_base(std::move(data)) {}
public:
static atomic_cell_view from_bytes(const data::type_info& ti, const imr::utils::object<data::cell::structure>& data) {
return atomic_cell_view(ti, data.get());
}
static atomic_cell_view from_bytes(const data::type_info& ti, bytes_view bv) {
return atomic_cell_view(ti, reinterpret_cast<const uint8_t*>(bv.begin()));
}
static atomic_cell_view from_bytes(bytes_view data) { return atomic_cell_view(data); }
friend class atomic_cell;
friend std::ostream& operator<<(std::ostream& os, const atomic_cell_view& acv);
class printer {
const abstract_type& _type;
const atomic_cell_view& _cell;
public:
printer(const abstract_type& type, const atomic_cell_view& cell) : _type(type), _cell(cell) {}
friend std::ostream& operator<<(std::ostream& os, const printer& acvp);
};
};
class atomic_cell_mutable_view final : public basic_atomic_cell_view<mutable_view::yes> {
atomic_cell_mutable_view(const data::type_info& ti, uint8_t* data)
: basic_atomic_cell_view<mutable_view::yes>(ti, data) {}
class atomic_cell_mutable_view final : public atomic_cell_base<bytes_mutable_view> {
atomic_cell_mutable_view(bytes_mutable_view data) : atomic_cell_base(std::move(data)) {}
public:
static atomic_cell_mutable_view from_bytes(const data::type_info& ti, imr::utils::object<data::cell::structure>& data) {
return atomic_cell_mutable_view(ti, data.get());
}
static atomic_cell_mutable_view from_bytes(bytes_mutable_view data) { return atomic_cell_mutable_view(data); }
friend class atomic_cell;
};
using atomic_cell_ref = atomic_cell_mutable_view;
class atomic_cell final : public basic_atomic_cell_view<mutable_view::yes> {
using imr_object_type = imr::utils::object<data::cell::structure>;
imr_object_type _data;
atomic_cell(const data::type_info& ti, imr::utils::object<data::cell::structure>&& data)
: basic_atomic_cell_view<mutable_view::yes>(ti, data.get()), _data(std::move(data)) {}
class atomic_cell_ref final : public atomic_cell_base<managed_bytes&> {
public:
class collection_member_tag;
using collection_member = bool_class<collection_member_tag>;
atomic_cell_ref(managed_bytes& buf) : atomic_cell_base(buf) {}
};
class atomic_cell final : public atomic_cell_base<managed_bytes> {
atomic_cell(managed_bytes b) : atomic_cell_base(std::move(b)) {}
public:
atomic_cell(const atomic_cell&) = default;
atomic_cell(atomic_cell&&) = default;
atomic_cell& operator=(const atomic_cell&) = delete;
atomic_cell& operator=(const atomic_cell&) = default;
atomic_cell& operator=(atomic_cell&&) = default;
void swap(atomic_cell& other) noexcept {
basic_atomic_cell_view<mutable_view::yes>::swap(other);
_data.swap(other._data);
static atomic_cell from_bytes(managed_bytes b) {
return atomic_cell(std::move(b));
}
operator atomic_cell_view() const { return atomic_cell_view(_view); }
atomic_cell(const abstract_type& t, atomic_cell_view other);
static atomic_cell make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time);
static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value,
collection_member = collection_member::no);
static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value,
collection_member = collection_member::no);
static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value,
collection_member = collection_member::no);
static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, const bytes& value,
collection_member cm = collection_member::no) {
return make_live(type, timestamp, bytes_view(value), cm);
atomic_cell(atomic_cell_view other) : atomic_cell_base(managed_bytes{other._data}) {}
operator atomic_cell_view() const {
return atomic_cell_view(_data);
}
static atomic_cell make_live_counter_update(api::timestamp_type timestamp, int64_t value);
static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, bytes_view value,
gc_clock::time_point expiry, gc_clock::duration ttl, collection_member = collection_member::no);
static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value,
gc_clock::time_point expiry, gc_clock::duration ttl, collection_member = collection_member::no);
static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value,
gc_clock::time_point expiry, gc_clock::duration ttl, collection_member = collection_member::no);
static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, const bytes& value,
gc_clock::time_point expiry, gc_clock::duration ttl, collection_member cm = collection_member::no)
static atomic_cell make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time) {
return atomic_cell_type::make_dead(timestamp, deletion_time);
}
static atomic_cell make_live(api::timestamp_type timestamp, bytes_view value) {
return atomic_cell_type::make_live(timestamp, value);
}
static atomic_cell make_live(api::timestamp_type timestamp, const bytes& value) {
return make_live(timestamp, bytes_view(value));
}
static atomic_cell make_live_counter_update(api::timestamp_type timestamp, int64_t value) {
return atomic_cell_type::make_live_counter_update(timestamp, value);
}
static atomic_cell make_live(api::timestamp_type timestamp, bytes_view value,
gc_clock::time_point expiry, gc_clock::duration ttl)
{
return make_live(type, timestamp, bytes_view(value), expiry, ttl, cm);
return atomic_cell_type::make_live(timestamp, value, expiry, ttl);
}
static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value, ttl_opt ttl, collection_member cm = collection_member::no) {
static atomic_cell make_live(api::timestamp_type timestamp, const bytes& value,
gc_clock::time_point expiry, gc_clock::duration ttl)
{
return make_live(timestamp, bytes_view(value), expiry, ttl);
}
static atomic_cell make_live(api::timestamp_type timestamp, bytes_view value, ttl_opt ttl) {
if (!ttl) {
return make_live(type, timestamp, value, cm);
return atomic_cell_type::make_live(timestamp, value);
} else {
return make_live(type, timestamp, value, gc_clock::now() + *ttl, *ttl, cm);
return atomic_cell_type::make_live(timestamp, value, gc_clock::now() + *ttl, *ttl);
}
}
static atomic_cell make_live_uninitialized(const abstract_type& type, api::timestamp_type timestamp, size_t size);
template<typename Serializer>
static atomic_cell make_live_from_serializer(api::timestamp_type timestamp, size_t size, Serializer&& serializer) {
return atomic_cell_type::make_live_from_serializer(timestamp, size, std::forward<Serializer>(serializer));
}
friend class atomic_cell_or_collection;
friend std::ostream& operator<<(std::ostream& os, const atomic_cell& ac);
class printer : atomic_cell_view::printer {
public:
printer(const abstract_type& type, const atomic_cell_view& cell) : atomic_cell_view::printer(type, cell) {}
friend std::ostream& operator<<(std::ostream& os, const printer& acvp);
};
};
class collection_mutation_view;
// Represents a mutation of a collection. Actual format is determined by collection type,
// and is:
// set: list of atomic_cell
// map: list of pair<atomic_cell, bytes> (for key/value)
// list: tbd, probably ugly
class collection_mutation {
public:
managed_bytes data;
collection_mutation() {}
collection_mutation(managed_bytes b) : data(std::move(b)) {}
collection_mutation(collection_mutation_view v);
operator collection_mutation_view() const;
};
class collection_mutation_view {
public:
bytes_view data;
bytes_view serialize() const { return data; }
static collection_mutation_view from_bytes(bytes_view v) { return { v }; }
};
inline
collection_mutation::collection_mutation(collection_mutation_view v)
: data(v.data) {
}
inline
collection_mutation::operator collection_mutation_view() const {
return { data };
}
class column_definition;
int compare_atomic_cell_for_merge(atomic_cell_view left, atomic_cell_view right);
void merge_column(const abstract_type& def,
void merge_column(const column_definition& def,
atomic_cell_or_collection& old,
const atomic_cell_or_collection& neww);

View File

@@ -24,9 +24,7 @@
// Not part of atomic_cell.hh to avoid cyclic dependency between types.hh and atomic_cell.hh
#include "types.hh"
#include "types/collection.hh"
#include "atomic_cell.hh"
#include "atomic_cell_or_collection.hh"
#include "hashing.hh"
#include "counters.hh"
@@ -34,13 +32,12 @@ template<>
struct appending_hash<collection_mutation_view> {
template<typename Hasher>
void operator()(Hasher& h, collection_mutation_view cell, const column_definition& cdef) const {
cell.with_deserialized(*cdef.type, [&] (collection_mutation_view_description m_view) {
::feed_hash(h, m_view.tomb);
for (auto&& key_and_value : m_view.cells) {
::feed_hash(h, key_and_value.first);
::feed_hash(h, key_and_value.second, cdef);
}
});
auto m_view = collection_type_impl::deserialize_mutation_form(cell);
::feed_hash(h, m_view.tomb);
for (auto&& key_and_value : m_view.cells) {
::feed_hash(h, key_and_value.first);
::feed_hash(h, key_and_value.second, cdef);
}
}
};
@@ -52,9 +49,7 @@ struct appending_hash<atomic_cell_view> {
feed_hash(h, cell.timestamp());
if (cell.is_live()) {
if (cdef.is_counter()) {
counter_cell_view::with_linearized(cell, [&] (counter_cell_view ccv) {
::feed_hash(h, ccv);
});
::feed_hash(h, counter_cell_view(cell));
return;
}
if (cell.is_live_and_has_ttl()) {
@@ -83,15 +78,3 @@ struct appending_hash<collection_mutation> {
feed_hash(h, static_cast<collection_mutation_view>(cm), cdef);
}
};
template<>
struct appending_hash<atomic_cell_or_collection> {
template<typename Hasher>
void operator()(Hasher& h, const atomic_cell_or_collection& c, const column_definition& cdef) const {
if (cdef.is_atomic()) {
feed_hash(h, c.as_atomic_cell(cdef), cdef);
} else {
feed_hash(h, c.as_collection_mutation(), cdef);
}
}
};

View File

@@ -22,72 +22,53 @@
#pragma once
#include "atomic_cell.hh"
#include "collection_mutation.hh"
#include "schema.hh"
#include "hashing.hh"
#include "imr/utils.hh"
// A variant type that can hold either an atomic_cell, or a serialized collection.
// Which type is stored is determined by the schema.
// Has an "empty" state.
// Objects moved-from are left in an empty state.
class atomic_cell_or_collection final {
// FIXME: This has made us lose small-buffer optimisation. Unfortunately,
// due to the changed cell format it would be less effective now, anyway.
// Measure the actual impact because any attempts to fix this will become
// irrelevant once rows are converted to the IMR as well, so maybe we can
// live with this like that.
using imr_object_type = imr::utils::object<data::cell::structure>;
imr_object_type _data;
managed_bytes _data;
private:
atomic_cell_or_collection(imr::utils::object<data::cell::structure>&& data) : _data(std::move(data)) {}
atomic_cell_or_collection(managed_bytes&& data) : _data(std::move(data)) {}
public:
atomic_cell_or_collection() = default;
atomic_cell_or_collection(atomic_cell_or_collection&&) = default;
atomic_cell_or_collection(const atomic_cell_or_collection&) = delete;
atomic_cell_or_collection& operator=(atomic_cell_or_collection&&) = default;
atomic_cell_or_collection& operator=(const atomic_cell_or_collection&) = delete;
atomic_cell_or_collection(atomic_cell ac) : _data(std::move(ac._data)) {}
atomic_cell_or_collection(const abstract_type& at, atomic_cell_view acv);
static atomic_cell_or_collection from_atomic_cell(atomic_cell data) { return { std::move(data._data) }; }
atomic_cell_view as_atomic_cell(const column_definition& cdef) const { return atomic_cell_view::from_bytes(cdef.type->imr_state().type_info(), _data); }
atomic_cell_ref as_atomic_cell_ref(const column_definition& cdef) { return atomic_cell_mutable_view::from_bytes(cdef.type->imr_state().type_info(), _data); }
atomic_cell_mutable_view as_mutable_atomic_cell(const column_definition& cdef) { return atomic_cell_mutable_view::from_bytes(cdef.type->imr_state().type_info(), _data); }
atomic_cell_or_collection(collection_mutation cm) : _data(std::move(cm._data)) { }
atomic_cell_or_collection copy(const abstract_type&) const;
atomic_cell_view as_atomic_cell() const { return atomic_cell_view::from_bytes(_data); }
atomic_cell_ref as_atomic_cell_ref() { return { _data }; }
atomic_cell_mutable_view as_mutable_atomic_cell() { return atomic_cell_mutable_view::from_bytes(_data); }
atomic_cell_or_collection(collection_mutation cm) : _data(std::move(cm.data)) {}
explicit operator bool() const {
return bool(_data);
return !_data.empty();
}
static constexpr bool can_use_mutable_view() {
return true;
bool can_use_mutable_view() const {
return !_data.is_fragmented();
}
void swap(atomic_cell_or_collection& other) noexcept {
_data.swap(other._data);
static atomic_cell_or_collection from_collection_mutation(collection_mutation data) {
return std::move(data.data);
}
static atomic_cell_or_collection from_collection_mutation(collection_mutation data) { return std::move(data._data); }
collection_mutation_view as_collection_mutation() const;
bytes_view serialize() const;
bool equals(const abstract_type& type, const atomic_cell_or_collection& other) const;
size_t external_memory_usage(const abstract_type&) const;
class printer {
const column_definition& _cdef;
const atomic_cell_or_collection& _cell;
public:
printer(const column_definition& cdef, const atomic_cell_or_collection& cell)
: _cdef(cdef), _cell(cell) { }
printer(const printer&) = delete;
printer(printer&&) = delete;
friend std::ostream& operator<<(std::ostream&, const printer&);
};
friend std::ostream& operator<<(std::ostream&, const printer&);
collection_mutation_view as_collection_mutation() const {
return collection_mutation_view{_data};
}
bytes_view serialize() const {
return _data;
}
bool operator==(const atomic_cell_or_collection& other) const {
return _data == other._data;
}
template<typename Hasher>
void feed_hash(Hasher& h, const column_definition& def) const {
if (def.is_atomic()) {
::feed_hash(h, as_atomic_cell(), def);
} else {
::feed_hash(h, as_collection_mutation(), def);
}
}
size_t external_memory_usage() const {
return _data.external_memory_usage();
}
friend std::ostream& operator<<(std::ostream&, const atomic_cell_or_collection&);
};
namespace std {
inline void swap(atomic_cell_or_collection& a, atomic_cell_or_collection& b) noexcept
{
a.swap(b);
}
}

View File

@@ -1,41 +0,0 @@
/*
* Copyright (C) 2017 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "auth/allow_all_authenticator.hh"
#include "service/migration_manager.hh"
#include "utils/class_registrator.hh"
namespace auth {
const sstring& allow_all_authenticator_name() {
static const sstring name = meta::AUTH_PACKAGE_NAME + "AllowAllAuthenticator";
return name;
}
// To ensure correct initialization order, we unfortunately need to use a string literal.
static const class_registrator<
authenticator,
allow_all_authenticator,
cql3::query_processor&,
::service::migration_manager&> registration("org.apache.cassandra.auth.AllowAllAuthenticator");
}

View File

@@ -1,101 +0,0 @@
/*
* Copyright (C) 2017 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <stdexcept>
#include "auth/authenticated_user.hh"
#include "auth/authenticator.hh"
#include "auth/common.hh"
namespace cql3 {
class query_processor;
}
namespace service {
class migration_manager;
}
namespace auth {
const sstring& allow_all_authenticator_name();
class allow_all_authenticator final : public authenticator {
public:
allow_all_authenticator(cql3::query_processor&, ::service::migration_manager&) {
}
virtual future<> start() override {
return make_ready_future<>();
}
virtual future<> stop() override {
return make_ready_future<>();
}
virtual std::string_view qualified_java_name() const override {
return allow_all_authenticator_name();
}
virtual bool require_authentication() const override {
return false;
}
virtual authentication_option_set supported_options() const override {
return authentication_option_set();
}
virtual authentication_option_set alterable_options() const override {
return authentication_option_set();
}
future<authenticated_user> authenticate(const credentials_map& credentials) const override {
return make_ready_future<authenticated_user>(anonymous_user());
}
virtual future<> create(std::string_view, const authentication_options& options) const override {
return make_ready_future();
}
virtual future<> alter(std::string_view, const authentication_options& options) const override {
return make_ready_future();
}
virtual future<> drop(std::string_view) const override {
return make_ready_future();
}
virtual future<custom_options> query_custom_options(std::string_view role_name) const override {
return make_ready_future<custom_options>();
}
virtual const resource_set& protected_resources() const override {
static const resource_set resources;
return resources;
}
virtual ::shared_ptr<sasl_challenge> new_sasl_challenge() const override {
throw std::runtime_error("Should not reach");
}
};
}

View File

@@ -1,41 +0,0 @@
/*
* Copyright (C) 2017 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "auth/allow_all_authorizer.hh"
#include "auth/common.hh"
#include "utils/class_registrator.hh"
namespace auth {
const sstring& allow_all_authorizer_name() {
static const sstring name = meta::AUTH_PACKAGE_NAME + "AllowAllAuthorizer";
return name;
}
// To ensure correct initialization order, we unfortunately need to use a string literal.
static const class_registrator<
authorizer,
allow_all_authorizer,
cql3::query_processor&,
::service::migration_manager&> registration("org.apache.cassandra.auth.AllowAllAuthorizer");
}

View File

@@ -1,92 +0,0 @@
/*
* Copyright (C) 2017 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include "auth/authorizer.hh"
#include "exceptions/exceptions.hh"
namespace cql3 {
class query_processor;
}
namespace service {
class migration_manager;
}
namespace auth {
const sstring& allow_all_authorizer_name();
class allow_all_authorizer final : public authorizer {
public:
allow_all_authorizer(cql3::query_processor&, ::service::migration_manager&) {
}
virtual future<> start() override {
return make_ready_future<>();
}
virtual future<> stop() override {
return make_ready_future<>();
}
virtual std::string_view qualified_java_name() const override {
return allow_all_authorizer_name();
}
virtual future<permission_set> authorize(const role_or_anonymous&, const resource&) const override {
return make_ready_future<permission_set>(permissions::ALL);
}
virtual future<> grant(std::string_view, permission_set, const resource&) const override {
return make_exception_future<>(
unsupported_authorization_operation("GRANT operation is not supported by AllowAllAuthorizer"));
}
virtual future<> revoke(std::string_view, permission_set, const resource&) const override {
return make_exception_future<>(
unsupported_authorization_operation("REVOKE operation is not supported by AllowAllAuthorizer"));
}
virtual future<std::vector<permission_details>> list_all() const override {
return make_exception_future<std::vector<permission_details>>(
unsupported_authorization_operation(
"LIST PERMISSIONS operation is not supported by AllowAllAuthorizer"));
}
virtual future<> revoke_all(std::string_view) const override {
return make_exception_future(
unsupported_authorization_operation("REVOKE operation is not supported by AllowAllAuthorizer"));
}
virtual future<> revoke_all(const resource&) const override {
return make_exception_future(
unsupported_authorization_operation("REVOKE operation is not supported by AllowAllAuthorizer"));
}
virtual const resource_set& protected_resources() const override {
static const resource_set resources;
return resources;
}
};
}

384
auth/auth.cc Normal file
View File

@@ -0,0 +1,384 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/*
* Copyright (C) 2016 ScyllaDB
*
* Modified by ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include <seastar/core/sleep.hh>
#include <seastar/core/distributed.hh>
#include "auth.hh"
#include "authenticator.hh"
#include "authorizer.hh"
#include "database.hh"
#include "cql3/query_processor.hh"
#include "cql3/statements/raw/cf_statement.hh"
#include "cql3/statements/create_table_statement.hh"
#include "db/config.hh"
#include "service/migration_manager.hh"
#include "utils/loading_cache.hh"
#include "utils/hash.hh"
const sstring auth::auth::DEFAULT_SUPERUSER_NAME("cassandra");
const sstring auth::auth::AUTH_KS("system_auth");
const sstring auth::auth::USERS_CF("users");
static const sstring USER_NAME("name");
static const sstring SUPER("super");
static logging::logger alogger("auth");
// TODO: configurable
using namespace std::chrono_literals;
const std::chrono::milliseconds auth::auth::SUPERUSER_SETUP_DELAY = 10000ms;
class auth_migration_listener : public service::migration_listener {
void on_create_keyspace(const sstring& ks_name) override {}
void on_create_column_family(const sstring& ks_name, const sstring& cf_name) override {}
void on_create_user_type(const sstring& ks_name, const sstring& type_name) override {}
void on_create_function(const sstring& ks_name, const sstring& function_name) override {}
void on_create_aggregate(const sstring& ks_name, const sstring& aggregate_name) override {}
void on_create_view(const sstring& ks_name, const sstring& view_name) override {}
void on_update_keyspace(const sstring& ks_name) override {}
void on_update_column_family(const sstring& ks_name, const sstring& cf_name, bool) override {}
void on_update_user_type(const sstring& ks_name, const sstring& type_name) override {}
void on_update_function(const sstring& ks_name, const sstring& function_name) override {}
void on_update_aggregate(const sstring& ks_name, const sstring& aggregate_name) override {}
void on_update_view(const sstring& ks_name, const sstring& view_name, bool columns_changed) override {}
void on_drop_keyspace(const sstring& ks_name) override {
auth::authorizer::get().revoke_all(auth::data_resource(ks_name));
}
void on_drop_column_family(const sstring& ks_name, const sstring& cf_name) override {
auth::authorizer::get().revoke_all(auth::data_resource(ks_name, cf_name));
}
void on_drop_user_type(const sstring& ks_name, const sstring& type_name) override {}
void on_drop_function(const sstring& ks_name, const sstring& function_name) override {}
void on_drop_aggregate(const sstring& ks_name, const sstring& aggregate_name) override {}
void on_drop_view(const sstring& ks_name, const sstring& view_name) override {}
};
static auth_migration_listener auth_migration;
namespace std {
template <>
struct hash<auth::data_resource> {
size_t operator()(const auth::data_resource & v) const {
return v.hash_value();
}
};
template <>
struct hash<auth::authenticated_user> {
size_t operator()(const auth::authenticated_user & v) const {
return utils::tuple_hash()(v.name(), v.is_anonymous());
}
};
}
class auth::auth::permissions_cache {
public:
typedef utils::loading_cache<std::pair<authenticated_user, data_resource>, permission_set, utils::loading_cache_reload_enabled::yes, utils::simple_entry_size<permission_set>, utils::tuple_hash> cache_type;
typedef typename cache_type::key_type key_type;
permissions_cache()
: permissions_cache(
cql3::get_local_query_processor().db().local().get_config()) {
}
permissions_cache(const db::config& cfg)
: _cache(cfg.permissions_cache_max_entries(), std::chrono::milliseconds(cfg.permissions_validity_in_ms()), std::chrono::milliseconds(cfg.permissions_update_interval_in_ms()), alogger,
[] (const key_type& k) {
alogger.debug("Refreshing permissions for {}", k.first.name());
return authorizer::get().authorize(::make_shared<authenticated_user>(k.first), k.second);
}) {}
future<> stop() {
return _cache.stop();
}
future<permission_set> get(::shared_ptr<authenticated_user> user, data_resource resource) {
return _cache.get(key_type(*user, std::move(resource)));
}
private:
cache_type _cache;
};
namespace std { // for ADL, yuch
std::ostream& operator<<(std::ostream& os, const std::pair<auth::authenticated_user, auth::data_resource>& p) {
os << "{user: " << p.first.name() << ", data_resource: " << p.second << "}";
return os;
}
}
static distributed<auth::auth::permissions_cache> perm_cache;
/**
* Poor mans job schedule. For maximum 2 jobs. Sic.
* Still does nothing more clever than waiting 10 seconds
* like origin, then runs the submitted tasks.
*
* Only difference compared to sleep (from which this
* borrows _heavily_) is that if tasks have not run by the time
* we exit (and do static clean up) we delete the promise + cont
*
* Should be abstracted to some sort of global server function
* probably.
*/
struct waiter {
promise<> done;
timer<> tmr;
waiter() : tmr([this] {done.set_value();})
{
tmr.arm(auth::auth::SUPERUSER_SETUP_DELAY);
}
~waiter() {
if (tmr.armed()) {
tmr.cancel();
done.set_exception(std::runtime_error("shutting down"));
}
alogger.trace("Deleting scheduled task");
}
void kill() {
}
};
typedef std::unique_ptr<waiter> waiter_ptr;
static std::vector<waiter_ptr> & thread_waiters() {
static thread_local std::vector<waiter_ptr> the_waiters;
return the_waiters;
}
void auth::auth::schedule_when_up(scheduled_func f) {
alogger.trace("Adding scheduled task");
auto & waiters = thread_waiters();
waiters.emplace_back(std::make_unique<waiter>());
auto* w = waiters.back().get();
w->done.get_future().finally([w] {
auto & waiters = thread_waiters();
auto i = std::find_if(waiters.begin(), waiters.end(), [w](const waiter_ptr& p) {
return p.get() == w;
});
if (i != waiters.end()) {
waiters.erase(i);
}
}).then([f = std::move(f)] {
alogger.trace("Running scheduled task");
return f();
}).handle_exception([](auto ep) {
return make_ready_future();
});
}
bool auth::auth::is_class_type(const sstring& type, const sstring& classname) {
if (type == classname) {
return true;
}
auto i = classname.find_last_of('.');
return classname.compare(i + 1, sstring::npos, type) == 0;
}
future<> auth::auth::setup() {
auto& db = cql3::get_local_query_processor().db().local();
auto& cfg = db.get_config();
future<> f = perm_cache.start();
if (is_class_type(cfg.authenticator(),
authenticator::ALLOW_ALL_AUTHENTICATOR_NAME)
&& is_class_type(cfg.authorizer(),
authorizer::ALLOW_ALL_AUTHORIZER_NAME)
) {
// just create the objects
return f.then([&cfg] {
return authenticator::setup(cfg.authenticator());
}).then([&cfg] {
return authorizer::setup(cfg.authorizer());
});
}
if (!db.has_keyspace(AUTH_KS)) {
std::map<sstring, sstring> opts;
opts["replication_factor"] = "1";
auto ksm = keyspace_metadata::new_keyspace(AUTH_KS, "org.apache.cassandra.locator.SimpleStrategy", opts, true);
// We use min_timestamp so that default keyspace metadata will loose with any manual adjustments. See issue #2129.
f = service::get_local_migration_manager().announce_new_keyspace(ksm, api::min_timestamp, false);
}
return f.then([] {
return setup_table(USERS_CF, sprint("CREATE TABLE %s.%s (%s text, %s boolean, PRIMARY KEY(%s)) WITH gc_grace_seconds=%d",
AUTH_KS, USERS_CF, USER_NAME, SUPER, USER_NAME,
90 * 24 * 60 * 60)); // 3 months.
}).then([&cfg] {
return authenticator::setup(cfg.authenticator());
}).then([&cfg] {
return authorizer::setup(cfg.authorizer());
}).then([] {
service::get_local_migration_manager().register_listener(&auth_migration); // again, only one shard...
// instead of once-timer, just schedule this later
schedule_when_up([] {
// setup default super user
return has_existing_users(USERS_CF, DEFAULT_SUPERUSER_NAME, USER_NAME).then([](bool exists) {
if (!exists) {
auto query = sprint("INSERT INTO %s.%s (%s, %s) VALUES (?, ?) USING TIMESTAMP 0",
AUTH_KS, USERS_CF, USER_NAME, SUPER);
cql3::get_local_query_processor().process(query, db::consistency_level::ONE, {DEFAULT_SUPERUSER_NAME, true}).then([](auto) {
alogger.info("Created default superuser '{}'", DEFAULT_SUPERUSER_NAME);
}).handle_exception([](auto ep) {
try {
std::rethrow_exception(ep);
} catch (exceptions::request_execution_exception&) {
alogger.warn("Skipped default superuser setup: some nodes were not ready");
}
});
}
});
});
});
}
future<> auth::auth::shutdown() {
// just make sure we don't have pending tasks.
// this is mostly relevant for test cases where
// db-env-shutdown != process shutdown
return smp::invoke_on_all([] {
thread_waiters().clear();
}).then([] {
return perm_cache.stop();
});
}
future<auth::permission_set> auth::auth::get_permissions(::shared_ptr<authenticated_user> user, data_resource resource) {
return perm_cache.local().get(std::move(user), std::move(resource));
}
static db::consistency_level consistency_for_user(const sstring& username) {
if (username == auth::auth::DEFAULT_SUPERUSER_NAME) {
return db::consistency_level::QUORUM;
}
return db::consistency_level::LOCAL_ONE;
}
static future<::shared_ptr<cql3::untyped_result_set>> select_user(const sstring& username) {
// Here was a thread local, explicit cache of prepared statement. In normal execution this is
// fine, but since we in testing set up and tear down system over and over, we'd start using
// obsolete prepared statements pretty quickly.
// Rely on query processing caching statements instead, and lets assume
// that a map lookup string->statement is not gonna kill us much.
return cql3::get_local_query_processor().process(
sprint("SELECT * FROM %s.%s WHERE %s = ?",
auth::auth::AUTH_KS, auth::auth::USERS_CF,
USER_NAME), consistency_for_user(username),
{ username }, true);
}
future<bool> auth::auth::is_existing_user(const sstring& username) {
return select_user(username).then(
[](::shared_ptr<cql3::untyped_result_set> res) {
return make_ready_future<bool>(!res->empty());
});
}
future<bool> auth::auth::is_super_user(const sstring& username) {
return select_user(username).then(
[](::shared_ptr<cql3::untyped_result_set> res) {
return make_ready_future<bool>(!res->empty() && res->one().get_as<bool>(SUPER));
});
}
future<> auth::auth::insert_user(const sstring& username, bool is_super) {
return cql3::get_local_query_processor().process(sprint("INSERT INTO %s.%s (%s, %s) VALUES (?, ?)",
AUTH_KS, USERS_CF, USER_NAME, SUPER),
consistency_for_user(username), { username, is_super }).discard_result();
}
future<> auth::auth::delete_user(const sstring& username) {
return cql3::get_local_query_processor().process(sprint("DELETE FROM %s.%s WHERE %s = ?",
AUTH_KS, USERS_CF, USER_NAME),
consistency_for_user(username), { username }).discard_result();
}
future<> auth::auth::setup_table(const sstring& name, const sstring& cql) {
auto& qp = cql3::get_local_query_processor();
auto& db = qp.db().local();
if (db.has_schema(AUTH_KS, name)) {
return make_ready_future();
}
::shared_ptr<cql3::statements::raw::cf_statement> parsed = static_pointer_cast<
cql3::statements::raw::cf_statement>(cql3::query_processor::parse_statement(cql));
parsed->prepare_keyspace(AUTH_KS);
::shared_ptr<cql3::statements::create_table_statement> statement =
static_pointer_cast<cql3::statements::create_table_statement>(
parsed->prepare(db, qp.get_cql_stats())->statement);
auto schema = statement->get_cf_meta_data();
auto uuid = generate_legacy_id(schema->ks_name(), schema->cf_name());
schema_builder b(schema);
b.set_uuid(uuid);
return service::get_local_migration_manager().announce_new_column_family(b.build(), false);
}
future<bool> auth::auth::has_existing_users(const sstring& cfname, const sstring& def_user_name, const sstring& name_column) {
auto default_user_query = sprint("SELECT * FROM %s.%s WHERE %s = ?", AUTH_KS, cfname, name_column);
auto all_users_query = sprint("SELECT * FROM %s.%s LIMIT 1", AUTH_KS, cfname);
return cql3::get_local_query_processor().process(default_user_query, db::consistency_level::ONE, { def_user_name }).then([=](::shared_ptr<cql3::untyped_result_set> res) {
if (!res->empty()) {
return make_ready_future<bool>(true);
}
return cql3::get_local_query_processor().process(default_user_query, db::consistency_level::QUORUM, { def_user_name }).then([all_users_query](::shared_ptr<cql3::untyped_result_set> res) {
if (!res->empty()) {
return make_ready_future<bool>(true);
}
return cql3::get_local_query_processor().process(all_users_query, db::consistency_level::QUORUM).then([](::shared_ptr<cql3::untyped_result_set> res) {
return make_ready_future<bool>(!res->empty());
});
});
});
}

125
auth/auth.hh Normal file
View File

@@ -0,0 +1,125 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/*
* Copyright (C) 2016 ScyllaDB
*
* Modified by ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <chrono>
#include <seastar/core/sstring.hh>
#include <seastar/core/future.hh>
#include <seastar/core/shared_ptr.hh>
#include "exceptions/exceptions.hh"
#include "permission.hh"
#include "data_resource.hh"
#include "authenticated_user.hh"
namespace auth {
class auth {
public:
class permissions_cache;
static const sstring DEFAULT_SUPERUSER_NAME;
static const sstring AUTH_KS;
static const sstring USERS_CF;
static const std::chrono::milliseconds SUPERUSER_SETUP_DELAY;
static bool is_class_type(const sstring& type, const sstring& classname);
static future<permission_set> get_permissions(::shared_ptr<authenticated_user>, data_resource);
/**
* Checks if the username is stored in AUTH_KS.USERS_CF.
*
* @param username Username to query.
* @return whether or not Cassandra knows about the user.
*/
static future<bool> is_existing_user(const sstring& username);
/**
* Checks if the user is a known superuser.
*
* @param username Username to query.
* @return true is the user is a superuser, false if they aren't or don't exist at all.
*/
static future<bool> is_super_user(const sstring& username);
/**
* Inserts the user into AUTH_KS.USERS_CF (or overwrites their superuser status as a result of an ALTER USER query).
*
* @param username Username to insert.
* @param isSuper User's new status.
* @throws RequestExecutionException
*/
static future<> insert_user(const sstring& username, bool is_super);
/**
* Deletes the user from AUTH_KS.USERS_CF.
*
* @param username Username to delete.
* @throws RequestExecutionException
*/
static future<> delete_user(const sstring& username);
/**
* Sets up Authenticator and Authorizer.
*/
static future<> setup();
static future<> shutdown();
/**
* Set up table from given CREATE TABLE statement under system_auth keyspace, if not already done so.
*
* @param name name of the table
* @param cql CREATE TABLE statement
*/
static future<> setup_table(const sstring& name, const sstring& cql);
static future<bool> has_existing_users(const sstring& cfname, const sstring& def_user_name, const sstring& name_column_name);
// For internal use. Run function "when system is up".
typedef std::function<future<>()> scheduled_func;
static void schedule_when_up(scheduled_func);
};
}
std::ostream& operator<<(std::ostream& os, const std::pair<auth::authenticated_user, auth::data_resource>& p);

View File

@@ -39,30 +39,34 @@
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "auth/authenticated_user.hh"
#include <iostream>
#include "authenticated_user.hh"
#include "auth.hh"
namespace auth {
const sstring auth::authenticated_user::ANONYMOUS_USERNAME("anonymous");
authenticated_user::authenticated_user(std::string_view name)
: name(sstring(name)) {
auth::authenticated_user::authenticated_user()
: _anon(true)
{}
auth::authenticated_user::authenticated_user(sstring name)
: _name(name), _anon(false)
{}
auth::authenticated_user::authenticated_user(authenticated_user&&) = default;
auth::authenticated_user::authenticated_user(const authenticated_user&) = default;
const sstring& auth::authenticated_user::name() const {
return _anon ? ANONYMOUS_USERNAME : _name;
}
std::ostream& operator<<(std::ostream& os, const authenticated_user& u) {
if (!u.name) {
os << "anonymous";
} else {
os << *u.name;
future<bool> auth::authenticated_user::is_super() const {
if (is_anonymous()) {
return make_ready_future<bool>(false);
}
return os;
}
static const authenticated_user the_anonymous_user{};
const authenticated_user& anonymous_user() noexcept {
return the_anonymous_user;
return auth::auth::is_super_user(_name);
}
bool auth::authenticated_user::operator==(const authenticated_user& v) const {
return _anon ? v._anon : _name == v._name;
}

View File

@@ -41,62 +41,43 @@
#pragma once
#include <string_view>
#include <functional>
#include <iosfwd>
#include <optional>
#include <seastar/core/sstring.hh>
#include <seastar/core/future.hh>
#include "seastarx.hh"
namespace auth {
///
/// A type-safe wrapper for the name of a logged-in user, or a nameless (anonymous) user.
///
class authenticated_user final {
class authenticated_user {
public:
///
/// An anonymous user has no name.
///
std::optional<sstring> name{};
static const sstring ANONYMOUS_USERNAME;
///
/// An anonymous user.
///
authenticated_user() = default;
explicit authenticated_user(std::string_view name);
};
authenticated_user();
authenticated_user(sstring name);
authenticated_user(authenticated_user&&);
authenticated_user(const authenticated_user&);
///
/// The user name, or "anonymous".
///
std::ostream& operator<<(std::ostream&, const authenticated_user&);
const sstring& name() const;
inline bool operator==(const authenticated_user& u1, const authenticated_user& u2) noexcept {
return u1.name == u2.name;
}
/**
* Checks the user's superuser status.
* Only a superuser is allowed to perform CREATE USER and DROP USER queries.
* Im most cased, though not necessarily, a superuser will have Permission.ALL on every resource
* (depends on IAuthorizer implementation).
*/
future<bool> is_super() const;
inline bool operator!=(const authenticated_user& u1, const authenticated_user& u2) noexcept {
return !(u1 == u2);
}
const authenticated_user& anonymous_user() noexcept;
inline bool is_anonymous(const authenticated_user& u) noexcept {
return u == anonymous_user();
}
}
namespace std {
template <>
struct hash<auth::authenticated_user> final {
size_t operator()(const auth::authenticated_user &u) const {
return std::hash<std::optional<sstring>>()(u.name);
/**
* If IAuthenticator doesn't require authentication, this method may return true.
*/
bool is_anonymous() const {
return _anon;
}
bool operator==(const authenticated_user&) const;
private:
sstring _name;
bool _anon;
};
}

View File

@@ -1,37 +0,0 @@
/*
* Copyright (C) 2018 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "auth/authentication_options.hh"
#include <iostream>
namespace auth {
std::ostream& operator<<(std::ostream& os, authentication_option a) {
switch (a) {
case authentication_option::password: os << "PASSWORD"; break;
case authentication_option::options: os << "OPTIONS"; break;
}
return os;
}
}

View File

@@ -1,64 +0,0 @@
/*
* Copyright (C) 2018 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <iosfwd>
#include <optional>
#include <stdexcept>
#include <unordered_map>
#include <unordered_set>
#include <seastar/core/print.hh>
#include <seastar/core/sstring.hh>
#include "seastarx.hh"
namespace auth {
enum class authentication_option {
password,
options
};
std::ostream& operator<<(std::ostream&, authentication_option);
using authentication_option_set = std::unordered_set<authentication_option>;
using custom_options = std::unordered_map<sstring, sstring>;
struct authentication_options final {
std::optional<sstring> password;
std::optional<custom_options> options;
};
inline bool any_authentication_options(const authentication_options& aos) noexcept {
return aos.password || aos.options;
}
class unsupported_authentication_option : public std::invalid_argument {
public:
explicit unsupported_authentication_option(authentication_option k)
: std::invalid_argument(format("The {} option is not supported.", k)) {
}
};
}

View File

@@ -39,13 +39,89 @@
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "auth/authenticator.hh"
#include "auth/authenticated_user.hh"
#include "auth/common.hh"
#include "auth/password_authenticator.hh"
#include "cql3/query_processor.hh"
#include "utils/class_registrator.hh"
#include "authenticator.hh"
#include "authenticated_user.hh"
#include "password_authenticator.hh"
#include "auth.hh"
#include "db/config.hh"
const sstring auth::authenticator::USERNAME_KEY("username");
const sstring auth::authenticator::PASSWORD_KEY("password");
const sstring auth::authenticator::ALLOW_ALL_AUTHENTICATOR_NAME("org.apache.cassandra.auth.AllowAllAuthenticator");
auth::authenticator::option auth::authenticator::string_to_option(const sstring& name) {
if (strcasecmp(name.c_str(), "password") == 0) {
return option::PASSWORD;
}
throw std::invalid_argument(name);
}
sstring auth::authenticator::option_to_string(option opt) {
switch (opt) {
case option::PASSWORD:
return "PASSWORD";
default:
throw std::invalid_argument(sprint("Unknown option {}", opt));
}
}
/**
* Authenticator is assumed to be a fully state-less immutable object (note all the const).
* We thus store a single instance globally, since it should be safe/ok.
*/
static std::unique_ptr<auth::authenticator> global_authenticator;
future<>
auth::authenticator::setup(const sstring& type) {
if (auth::auth::is_class_type(type, ALLOW_ALL_AUTHENTICATOR_NAME)) {
class allow_all_authenticator : public authenticator {
public:
const sstring& class_name() const override {
return ALLOW_ALL_AUTHENTICATOR_NAME;
}
bool require_authentication() const override {
return false;
}
option_set supported_options() const override {
return option_set();
}
option_set alterable_options() const override {
return option_set();
}
future<::shared_ptr<authenticated_user>> authenticate(const credentials_map& credentials) const override {
return make_ready_future<::shared_ptr<authenticated_user>>(::make_shared<authenticated_user>());
}
future<> create(sstring username, const option_map& options) override {
return make_ready_future();
}
future<> alter(sstring username, const option_map& options) override {
return make_ready_future();
}
future<> drop(sstring username) override {
return make_ready_future();
}
const resource_ids& protected_resources() const override {
static const resource_ids ids;
return ids;
}
::shared_ptr<sasl_challenge> new_sasl_challenge() const override {
throw std::runtime_error("Should not reach");
}
};
global_authenticator = std::make_unique<allow_all_authenticator>();
} else if (auth::auth::is_class_type(type, password_authenticator::PASSWORD_AUTHENTICATOR_NAME)) {
auto pwa = std::make_unique<password_authenticator>();
auto f = pwa->init();
return f.then([pwa = std::move(pwa)]() mutable {
global_authenticator = std::move(pwa);
});
} else {
throw exceptions::configuration_exception("Invalid authenticator type: " + type);
}
return make_ready_future();
}
auth::authenticator& auth::authenticator::get() {
assert(global_authenticator);
return *global_authenticator;
}

View File

@@ -41,22 +41,19 @@
#pragma once
#include <string_view>
#include <memory>
#include <unordered_map>
#include <set>
#include <stdexcept>
#include <unordered_map>
#include <boost/any.hpp>
#include <seastar/core/enum.hh>
#include <seastar/core/future.hh>
#include <seastar/core/sstring.hh>
#include <seastar/core/shared_ptr.hh>
#include "auth/authentication_options.hh"
#include "auth/resource.hh"
#include "auth/sasl_challenge.hh"
#include <seastar/core/sstring.hh>
#include <seastar/core/future.hh>
#include <seastar/core/shared_ptr.hh>
#include <seastar/core/enum.hh>
#include "bytes.hh"
#include "data_resource.hh"
#include "enum_set.hh"
#include "exceptions/exceptions.hh"
@@ -68,90 +65,136 @@ namespace auth {
class authenticated_user;
///
/// Abstract client for authenticating role identity.
///
/// All state necessary to authorize a role is stored externally to the client instance.
///
class authenticator {
public:
///
/// The name of the key to be used for the user-name part of password authentication with \ref authenticate.
///
static const sstring USERNAME_KEY;
///
/// The name of the key to be used for the password part of password authentication with \ref authenticate.
///
static const sstring PASSWORD_KEY;
static const sstring ALLOW_ALL_AUTHENTICATOR_NAME;
/**
* Supported CREATE USER/ALTER USER options.
* Currently only PASSWORD is available.
*/
enum class option {
PASSWORD
};
static option string_to_option(const sstring&);
static sstring option_to_string(option);
using option_set = enum_set<super_enum<option, option::PASSWORD>>;
using option_map = std::unordered_map<option, boost::any, enum_hash<option>>;
using credentials_map = std::unordered_map<sstring, sstring>;
virtual ~authenticator() = default;
/**
* Setup is called once upon system startup to initialize the IAuthenticator.
*
* For example, use this method to create any required keyspaces/column families.
* Note: Only call from main thread.
*/
static future<> setup(const sstring& type);
virtual future<> start() = 0;
/**
* Returns the system authenticator. Must have called setup before calling this.
*/
static authenticator& get();
virtual future<> stop() = 0;
virtual ~authenticator()
{}
///
/// A fully-qualified (class with package) Java-like name for this implementation.
///
virtual std::string_view qualified_java_name() const = 0;
virtual const sstring& class_name() const = 0;
/**
* Whether or not the authenticator requires explicit login.
* If false will instantiate user with AuthenticatedUser.ANONYMOUS_USER.
*/
virtual bool require_authentication() const = 0;
virtual authentication_option_set supported_options() const = 0;
/**
* Set of options supported by CREATE USER and ALTER USER queries.
* Should never return null - always return an empty set instead.
*/
virtual option_set supported_options() const = 0;
///
/// A subset of `supported_options()` that users are permitted to alter for themselves.
///
virtual authentication_option_set alterable_options() const = 0;
/**
* Subset of supportedOptions that users are allowed to alter when performing ALTER USER [themselves].
* Should never return null - always return an empty set instead.
*/
virtual option_set alterable_options() const = 0;
///
/// Authenticate a user given implementation-specific credentials.
///
/// If this implementation does not require authentication (\ref require_authentication), an anonymous user may
/// result.
///
/// \returns an exceptional future with \ref exceptions::authentication_exception if given invalid credentials.
///
virtual future<authenticated_user> authenticate(const credentials_map& credentials) const = 0;
/**
* Authenticates a user given a Map<String, String> of credentials.
* Should never return null - always throw AuthenticationException instead.
* Returning AuthenticatedUser.ANONYMOUS_USER is an option as well if authentication is not required.
*
* @throws authentication_exception if credentials don't match any known user.
*/
virtual future<::shared_ptr<authenticated_user>> authenticate(const credentials_map& credentials) const = 0;
///
/// Create an authentication record for a new user. This is required before the user can log-in.
///
/// The options provided must be a subset of `supported_options()`.
///
virtual future<> create(std::string_view role_name, const authentication_options& options) const = 0;
/**
* Called during execution of CREATE USER query (also may be called on startup, see seedSuperuserOptions method).
* If authenticator is static then the body of the method should be left blank, but don't throw an exception.
* options are guaranteed to be a subset of supportedOptions().
*
* @param username Username of the user to create.
* @param options Options the user will be created with.
* @throws exceptions::request_validation_exception
* @throws exceptions::request_execution_exception
*/
virtual future<> create(sstring username, const option_map& options) = 0;
///
/// Alter the authentication record of an existing user.
///
/// The options provided must be a subset of `supported_options()`.
///
/// Callers must ensure that the specification of `alterable_options()` is adhered to.
///
virtual future<> alter(std::string_view role_name, const authentication_options& options) const = 0;
/**
* Called during execution of ALTER USER query.
* options are always guaranteed to be a subset of supportedOptions(). Furthermore, if the user performing the query
* is not a superuser and is altering himself, then options are guaranteed to be a subset of alterableOptions().
* Keep the body of the method blank if your implementation doesn't support any options.
*
* @param username Username of the user that will be altered.
* @param options Options to alter.
* @throws exceptions::request_validation_exception
* @throws exceptions::request_execution_exception
*/
virtual future<> alter(sstring username, const option_map& options) = 0;
///
/// Delete the authentication record for a user. This will disallow the user from logging in.
///
virtual future<> drop(std::string_view role_name) const = 0;
///
/// Query for custom options (those corresponding to \ref authentication_options::options).
///
/// If no options are set the result is an empty container.
///
virtual future<custom_options> query_custom_options(std::string_view role_name) const = 0;
/**
* Called during execution of DROP USER query.
*
* @param username Username of the user that will be dropped.
* @throws exceptions::request_validation_exception
* @throws exceptions::request_execution_exception
*/
virtual future<> drop(sstring username) = 0;
///
/// System resources used internally as part of the implementation. These are made inaccessible to users.
///
virtual const resource_set& protected_resources() const = 0;
/**
* Set of resources that should be made inaccessible to users and only accessible internally.
*
* @return Keyspaces, column families that will be unmodifiable by users; other resources.
* @see resource_ids
*/
virtual const resource_ids& protected_resources() const = 0;
class sasl_challenge {
public:
virtual ~sasl_challenge() {}
virtual bytes evaluate_response(bytes_view client_response) = 0;
virtual bool is_complete() const = 0;
virtual future<::shared_ptr<authenticated_user>> get_authenticated_user() const = 0;
};
/**
* Provide a sasl_challenge to be used by the CQL binary protocol server. If
* the configured authenticator requires authentication but does not implement this
* interface we refuse to start the binary protocol server as it will have no way
* of authenticating clients.
* @return sasl_challenge implementation
*/
virtual ::shared_ptr<sasl_challenge> new_sasl_challenge() const = 0;
};
inline std::ostream& operator<<(std::ostream& os, authenticator::option opt) {
return os << authenticator::option_to_string(opt);
}
}

104
auth/authorizer.cc Normal file
View File

@@ -0,0 +1,104 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/*
* Copyright (C) 2016 ScyllaDB
*
* Modified by ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "authorizer.hh"
#include "authenticated_user.hh"
#include "default_authorizer.hh"
#include "auth.hh"
#include "db/config.hh"
const sstring auth::authorizer::ALLOW_ALL_AUTHORIZER_NAME("org.apache.cassandra.auth.AllowAllAuthorizer");
/**
* Authenticator is assumed to be a fully state-less immutable object (note all the const).
* We thus store a single instance globally, since it should be safe/ok.
*/
static std::unique_ptr<auth::authorizer> global_authorizer;
future<>
auth::authorizer::setup(const sstring& type) {
if (auth::auth::is_class_type(type, ALLOW_ALL_AUTHORIZER_NAME)) {
class allow_all_authorizer : public authorizer {
public:
future<permission_set> authorize(::shared_ptr<authenticated_user>, data_resource) const override {
return make_ready_future<permission_set>(permissions::ALL);
}
future<> grant(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring) override {
throw exceptions::invalid_request_exception("GRANT operation is not supported by AllowAllAuthorizer");
}
future<> revoke(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring) override {
throw exceptions::invalid_request_exception("REVOKE operation is not supported by AllowAllAuthorizer");
}
future<std::vector<permission_details>> list(::shared_ptr<authenticated_user> performer, permission_set, optional<data_resource>, optional<sstring>) const override {
throw exceptions::invalid_request_exception("LIST PERMISSIONS operation is not supported by AllowAllAuthorizer");
}
future<> revoke_all(sstring dropped_user) override {
return make_ready_future();
}
future<> revoke_all(data_resource) override {
return make_ready_future();
}
const resource_ids& protected_resources() override {
static const resource_ids ids;
return ids;
}
future<> validate_configuration() const override {
return make_ready_future();
}
};
global_authorizer = std::make_unique<allow_all_authorizer>();
} else if (auth::auth::is_class_type(type, default_authorizer::DEFAULT_AUTHORIZER_NAME)) {
auto da = std::make_unique<default_authorizer>();
auto f = da->init();
return f.then([da = std::move(da)]() mutable {
global_authorizer = std::move(da);
});
} else {
throw exceptions::configuration_exception("Invalid authorizer type: " + type);
}
return make_ready_future();
}
auth::authorizer& auth::authorizer::get() {
assert(global_authorizer);
return *global_authorizer;
}

View File

@@ -41,115 +41,133 @@
#pragma once
#include <string_view>
#include <functional>
#include <optional>
#include <stdexcept>
#include <tuple>
#include <vector>
#include <tuple>
#include <experimental/optional>
#include <seastar/core/future.hh>
#include <seastar/core/shared_ptr.hh>
#include "auth/permission.hh"
#include "auth/resource.hh"
#include "permission.hh"
#include "data_resource.hh"
#include "seastarx.hh"
namespace auth {
class role_or_anonymous;
class authenticated_user;
struct permission_details {
sstring role_name;
::auth::resource resource;
sstring user;
data_resource resource;
permission_set permissions;
bool operator<(const permission_details& v) const {
return std::tie(user, resource, permissions) < std::tie(v.user, v.resource, v.permissions);
}
};
inline bool operator==(const permission_details& pd1, const permission_details& pd2) {
return std::forward_as_tuple(pd1.role_name, pd1.resource, pd1.permissions.mask())
== std::forward_as_tuple(pd2.role_name, pd2.resource, pd2.permissions.mask());
}
using std::experimental::optional;
inline bool operator!=(const permission_details& pd1, const permission_details& pd2) {
return !(pd1 == pd2);
}
inline bool operator<(const permission_details& pd1, const permission_details& pd2) {
return std::forward_as_tuple(pd1.role_name, pd1.resource, pd1.permissions)
< std::forward_as_tuple(pd2.role_name, pd2.resource, pd2.permissions);
}
class unsupported_authorization_operation : public std::invalid_argument {
public:
using std::invalid_argument::invalid_argument;
};
///
/// Abstract client for authorizing roles to access resources.
///
/// All state necessary to authorize a role is stored externally to the client instance.
///
class authorizer {
public:
virtual ~authorizer() = default;
static const sstring ALLOW_ALL_AUTHORIZER_NAME;
virtual future<> start() = 0;
virtual ~authorizer() {}
virtual future<> stop() = 0;
/**
* The primary Authorizer method. Returns a set of permissions of a user on a resource.
*
* @param user Authenticated user requesting authorization.
* @param resource Resource for which the authorization is being requested. @see DataResource.
* @return Set of permissions of the user on the resource. Should never return empty. Use permission.NONE instead.
*/
virtual future<permission_set> authorize(::shared_ptr<authenticated_user>, data_resource) const = 0;
///
/// A fully-qualified (class with package) Java-like name for this implementation.
///
virtual std::string_view qualified_java_name() const = 0;
/**
* Grants a set of permissions on a resource to a user.
* The opposite of revoke().
*
* @param performer User who grants the permissions.
* @param permissions Set of permissions to grant.
* @param to Grantee of the permissions.
* @param resource Resource on which to grant the permissions.
*
* @throws RequestValidationException
* @throws RequestExecutionException
*/
virtual future<> grant(::shared_ptr<authenticated_user> performer, permission_set, data_resource, sstring to) = 0;
///
/// Query for the permissions granted directly to a role for a particular \ref resource (and not any of its
/// parents).
///
/// The optional role name is empty when an anonymous user is authorized. Some implementations may still wish to
/// grant default permissions in this case.
///
virtual future<permission_set> authorize(const role_or_anonymous&, const resource&) const = 0;
/**
* Revokes a set of permissions on a resource from a user.
* The opposite of grant().
*
* @param performer User who revokes the permissions.
* @param permissions Set of permissions to revoke.
* @param from Revokee of the permissions.
* @param resource Resource on which to revoke the permissions.
*
* @throws RequestValidationException
* @throws RequestExecutionException
*/
virtual future<> revoke(::shared_ptr<authenticated_user> performer, permission_set, data_resource, sstring from) = 0;
///
/// Grant a set of permissions to a role for a particular \ref resource.
///
/// \throws \ref unsupported_authorization_operation if granting permissions is not supported.
///
virtual future<> grant(std::string_view role_name, permission_set, const resource&) const = 0;
/**
* Returns a list of permissions on a resource of a user.
*
* @param performer User who wants to see the permissions.
* @param permissions Set of Permission values the user is interested in. The result should only include the matching ones.
* @param resource The resource on which permissions are requested. Can be null, in which case permissions on all resources
* should be returned.
* @param of The user whose permissions are requested. Can be null, in which case permissions of every user should be returned.
*
* @return All of the matching permission that the requesting user is authorized to know about.
*
* @throws RequestValidationException
* @throws RequestExecutionException
*/
virtual future<std::vector<permission_details>> list(::shared_ptr<authenticated_user> performer, permission_set, optional<data_resource>, optional<sstring>) const = 0;
///
/// Revoke a set of permissions from a role for a particular \ref resource.
///
/// \throws \ref unsupported_authorization_operation if revoking permissions is not supported.
///
virtual future<> revoke(std::string_view role_name, permission_set, const resource&) const = 0;
/**
* This method is called before deleting a user with DROP USER query so that a new user with the same
* name wouldn't inherit permissions of the deleted user in the future.
*
* @param droppedUser The user to revoke all permissions from.
*/
virtual future<> revoke_all(sstring dropped_user) = 0;
///
/// Query for all directly granted permissions.
///
/// \throws \ref unsupported_authorization_operation if listing permissions is not supported.
///
virtual future<std::vector<permission_details>> list_all() const = 0;
/**
* This method is called after a resource is removed (i.e. keyspace or a table is dropped).
*
* @param droppedResource The resource to revoke all permissions on.
*/
virtual future<> revoke_all(data_resource) = 0;
///
/// Revoke all permissions granted directly to a particular role.
///
/// \throws \ref unsupported_authorization_operation if revoking permissions is not supported.
///
virtual future<> revoke_all(std::string_view role_name) const = 0;
/**
* Set of resources that should be made inaccessible to users and only accessible internally.
*
* @return Keyspaces, column families that will be unmodifiable by users; other resources.
*/
virtual const resource_ids& protected_resources() = 0;
///
/// Revoke all permissions granted to any role for a particular resource.
///
/// \throws \ref unsupported_authorization_operation if revoking permissions is not supported.
///
virtual future<> revoke_all(const resource&) const = 0;
/**
* Validates configuration of IAuthorizer implementation (if configurable).
*
* @throws ConfigurationException when there is a configuration error.
*/
virtual future<> validate_configuration() const = 0;
///
/// System resources used internally as part of the implementation. These are made inaccessible to users.
///
virtual const resource_set& protected_resources() const = 0;
/**
* Setup is called once upon system startup to initialize the IAuthorizer.
*
* For example, use this method to create any required keyspaces/column families.
*/
static future<> setup(const sstring& type);
/**
* Returns the system authorizer. Must have called setup before calling this.
*/
static authorizer& get();
};
}

View File

@@ -1,118 +0,0 @@
/*
* Copyright (C) 2017 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "auth/common.hh"
#include <seastar/core/shared_ptr.hh>
#include "cql3/query_processor.hh"
#include "cql3/statements/create_table_statement.hh"
#include "database.hh"
#include "schema_builder.hh"
#include "service/migration_manager.hh"
#include "timeout_config.hh"
namespace auth {
namespace meta {
const sstring DEFAULT_SUPERUSER_NAME("cassandra");
const sstring AUTH_KS("system_auth");
const sstring USERS_CF("users");
const sstring AUTH_PACKAGE_NAME("org.apache.cassandra.auth.");
}
static logging::logger auth_log("auth");
// Func must support being invoked more than once.
future<> do_after_system_ready(seastar::abort_source& as, seastar::noncopyable_function<future<>()> func) {
struct empty_state { };
return delay_until_system_ready(as).then([&as, func = std::move(func)] () mutable {
return exponential_backoff_retry::do_until_value(1s, 1min, as, [func = std::move(func)] {
return func().then_wrapped([] (auto&& f) -> std::optional<empty_state> {
if (f.failed()) {
auth_log.debug("Auth task failed with error, rescheduling: {}", f.get_exception());
return { };
}
return { empty_state() };
});
});
}).discard_result();
}
static future<> create_metadata_table_if_missing_impl(
std::string_view table_name,
cql3::query_processor& qp,
std::string_view cql,
::service::migration_manager& mm) {
static auto ignore_existing = [] (seastar::noncopyable_function<future<>()> func) {
return futurize_invoke(std::move(func)).handle_exception_type([] (exceptions::already_exists_exception& ignored) { });
};
auto& db = qp.db();
auto parsed_statement = cql3::query_processor::parse_statement(cql);
auto& parsed_cf_statement = static_cast<cql3::statements::raw::cf_statement&>(*parsed_statement);
parsed_cf_statement.prepare_keyspace(meta::AUTH_KS);
auto statement = static_pointer_cast<cql3::statements::create_table_statement>(
parsed_cf_statement.prepare(db, qp.get_cql_stats())->statement);
const auto schema = statement->get_cf_meta_data(qp.db());
const auto uuid = generate_legacy_id(schema->ks_name(), schema->cf_name());
schema_builder b(schema);
b.set_uuid(uuid);
schema_ptr table = b.build();
return ignore_existing([&mm, table = std::move(table)] () {
return mm.announce_new_column_family(table, false);
});
}
future<> create_metadata_table_if_missing(
std::string_view table_name,
cql3::query_processor& qp,
std::string_view cql,
::service::migration_manager& mm) noexcept {
return futurize_invoke(create_metadata_table_if_missing_impl, table_name, qp, cql, mm);
}
future<> wait_for_schema_agreement(::service::migration_manager& mm, const database& db, seastar::abort_source& as) {
static const auto pause = [] { return sleep(std::chrono::milliseconds(500)); };
return do_until([&db, &as] {
as.check();
return db.get_version() != database::empty_version;
}, pause).then([&mm, &as] {
return do_until([&mm, &as] {
as.check();
return mm.have_schema_agreement();
}, pause);
});
}
const timeout_config& internal_distributed_timeout_config() noexcept {
static const auto t = 5s;
static const timeout_config tc{t, t, t, t, t, t, t};
return tc;
}
}

View File

@@ -1,92 +0,0 @@
/*
* Copyright (C) 2017 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <chrono>
#include <string_view>
#include <seastar/core/future.hh>
#include <seastar/core/abort_source.hh>
#include <seastar/util/noncopyable_function.hh>
#include <seastar/core/seastar.hh>
#include <seastar/core/resource.hh>
#include <seastar/core/sstring.hh>
#include <seastar/core/smp.hh>
#include "log.hh"
#include "seastarx.hh"
#include "utils/exponential_backoff_retry.hh"
using namespace std::chrono_literals;
class database;
class timeout_config;
namespace service {
class migration_manager;
}
namespace cql3 {
class query_processor;
}
namespace auth {
namespace meta {
extern const sstring DEFAULT_SUPERUSER_NAME;
extern const sstring AUTH_KS;
extern const sstring USERS_CF;
extern const sstring AUTH_PACKAGE_NAME;
}
template <class Task>
future<> once_among_shards(Task&& f) {
if (this_shard_id() == 0u) {
return f();
}
return make_ready_future<>();
}
inline future<> delay_until_system_ready(seastar::abort_source& as) {
return sleep_abortable(15s, as);
}
// Func must support being invoked more than once.
future<> do_after_system_ready(seastar::abort_source& as, seastar::noncopyable_function<future<>()> func);
future<> create_metadata_table_if_missing(
std::string_view table_name,
cql3::query_processor&,
std::string_view cql,
::service::migration_manager&) noexcept;
future<> wait_for_schema_agreement(::service::migration_manager&, const database&, seastar::abort_source&);
///
/// Time-outs for internal, non-local CQL queries.
///
const timeout_config& internal_distributed_timeout_config() noexcept;
}

171
auth/data_resource.cc Normal file
View File

@@ -0,0 +1,171 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/*
* Copyright (C) 2016 ScyllaDB
*
* Modified by ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "data_resource.hh"
#include <regex>
#include "service/storage_proxy.hh"
const sstring auth::data_resource::ROOT_NAME("data");
auth::data_resource::data_resource(level l, const sstring& ks, const sstring& cf)
: _level(l), _ks(ks), _cf(cf)
{
}
auth::data_resource::data_resource()
: data_resource(level::ROOT)
{}
auth::data_resource::data_resource(const sstring& ks)
: data_resource(level::KEYSPACE, ks)
{}
auth::data_resource::data_resource(const sstring& ks, const sstring& cf)
: data_resource(level::COLUMN_FAMILY, ks, cf)
{}
auth::data_resource::level auth::data_resource::get_level() const {
return _level;
}
auth::data_resource auth::data_resource::from_name(
const sstring& s) {
static std::regex slash_regex("/");
auto i = std::regex_token_iterator<sstring::const_iterator>(s.begin(),
s.end(), slash_regex, -1);
auto e = std::regex_token_iterator<sstring::const_iterator>();
auto n = std::distance(i, e);
if (n > 3 || ROOT_NAME != sstring(*i++)) {
throw std::invalid_argument(sprint("%s is not a valid data resource name", s));
}
if (n == 1) {
return data_resource();
}
auto ks = *i++;
if (n == 2) {
return data_resource(ks.str());
}
auto cf = *i++;
return data_resource(ks.str(), cf.str());
}
sstring auth::data_resource::name() const {
switch (get_level()) {
case level::ROOT:
return ROOT_NAME;
case level::KEYSPACE:
return sprint("%s/%s", ROOT_NAME, _ks);
case level::COLUMN_FAMILY:
default:
return sprint("%s/%s/%s", ROOT_NAME, _ks, _cf);
}
}
auth::data_resource auth::data_resource::get_parent() const {
switch (get_level()) {
case level::KEYSPACE:
return data_resource();
case level::COLUMN_FAMILY:
return data_resource(_ks);
default:
throw std::invalid_argument("Root-level resource can't have a parent");
}
}
const sstring& auth::data_resource::keyspace() const {
if (is_root_level()) {
throw std::invalid_argument("ROOT data resource has no keyspace");
}
return _ks;
}
const sstring& auth::data_resource::column_family() const {
if (!is_column_family_level()) {
throw std::invalid_argument(sprint("%s data resource has no column family", name()));
}
return _cf;
}
bool auth::data_resource::has_parent() const {
return !is_root_level();
}
bool auth::data_resource::exists() const {
switch (get_level()) {
case level::ROOT:
return true;
case level::KEYSPACE:
return service::get_local_storage_proxy().get_db().local().has_keyspace(_ks);
case level::COLUMN_FAMILY:
default:
return service::get_local_storage_proxy().get_db().local().has_schema(_ks, _cf);
}
}
sstring auth::data_resource::to_string() const {
switch (get_level()) {
case level::ROOT:
return "<all keyspaces>";
case level::KEYSPACE:
return sprint("<keyspace %s>", _ks);
case level::COLUMN_FAMILY:
default:
return sprint("<table %s.%s>", _ks, _cf);
}
}
bool auth::data_resource::operator==(const data_resource& v) const {
return _ks == v._ks && _cf == v._cf;
}
bool auth::data_resource::operator<(const data_resource& v) const {
return _ks < v._ks ? true : (v._ks < _ks ? false : _cf < v._cf);
}
std::ostream& auth::operator<<(std::ostream& os, const data_resource& r) {
return os << r.to_string();
}

159
auth/data_resource.hh Normal file
View File

@@ -0,0 +1,159 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/*
* Copyright (C) 2016 ScyllaDB
*
* Modified by ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include "utils/hash.hh"
#include <iosfwd>
#include <set>
#include <seastar/core/sstring.hh>
#include "seastarx.hh"
namespace auth {
class data_resource {
private:
enum class level {
ROOT, KEYSPACE, COLUMN_FAMILY
};
static const sstring ROOT_NAME;
level _level;
sstring _ks;
sstring _cf;
data_resource(level, const sstring& ks = {}, const sstring& cf = {});
level get_level() const;
public:
/**
* Creates a DataResource representing the root-level resource.
* @return the root-level resource.
*/
data_resource();
/**
* Creates a DataResource representing a keyspace.
*
* @param keyspace Name of the keyspace.
*/
data_resource(const sstring& ks);
/**
* Creates a DataResource instance representing a column family.
*
* @param keyspace Name of the keyspace.
* @param columnFamily Name of the column family.
*/
data_resource(const sstring& ks, const sstring& cf);
/**
* Parses a data resource name into a DataResource instance.
*
* @param name Name of the data resource.
* @return DataResource instance matching the name.
*/
static data_resource from_name(const sstring&);
/**
* @return Printable name of the resource.
*/
sstring name() const;
/**
* @return Parent of the resource, if any. Throws IllegalStateException if it's the root-level resource.
*/
data_resource get_parent() const;
bool is_root_level() const {
return get_level() == level::ROOT;
}
bool is_keyspace_level() const {
return get_level() == level::KEYSPACE;
}
bool is_column_family_level() const {
return get_level() == level::COLUMN_FAMILY;
}
/**
* @return keyspace of the resource.
* @throws std::invalid_argument if it's the root-level resource.
*/
const sstring& keyspace() const;
/**
* @return column family of the resource.
* @throws std::invalid_argument if it's not a cf-level resource.
*/
const sstring& column_family() const;
/**
* @return Whether or not the resource has a parent in the hierarchy.
*/
bool has_parent() const;
/**
* @return Whether or not the resource exists in scylla.
*/
bool exists() const;
sstring to_string() const;
bool operator==(const data_resource&) const;
bool operator<(const data_resource&) const;
size_t hash_value() const {
return utils::tuple_hash()(_ks, _cf);
}
};
/**
* Resource id mappings, i.e. keyspace and/or column families.
*/
using resource_ids = std::set<data_resource>;
std::ostream& operator<<(std::ostream&, const data_resource&);
}

View File

@@ -39,286 +39,181 @@
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "auth/default_authorizer.hh"
extern "C" {
#include <crypt.h>
#include <unistd.h>
}
#include <chrono>
#include <crypt.h>
#include <random>
#include <chrono>
#include <boost/algorithm/string/join.hpp>
#include <boost/range.hpp>
#include <seastar/core/seastar.hh>
#include <seastar/core/reactor.hh>
#include "auth/authenticated_user.hh"
#include "auth/common.hh"
#include "auth/permission.hh"
#include "auth/role_or_anonymous.hh"
#include "auth.hh"
#include "default_authorizer.hh"
#include "authenticated_user.hh"
#include "permission.hh"
#include "cql3/query_processor.hh"
#include "cql3/untyped_result_set.hh"
#include "exceptions/exceptions.hh"
#include "log.hh"
#include "database.hh"
namespace auth {
const sstring auth::default_authorizer::DEFAULT_AUTHORIZER_NAME(
"org.apache.cassandra.auth.CassandraAuthorizer");
const sstring& default_authorizer_name() {
static const sstring name = meta::AUTH_PACKAGE_NAME + "CassandraAuthorizer";
return name;
}
static const sstring ROLE_NAME = "role";
static const sstring USER_NAME = "username";
static const sstring RESOURCE_NAME = "resource";
static const sstring PERMISSIONS_NAME = "permissions";
static const sstring PERMISSIONS_CF = "role_permissions";
static const sstring PERMISSIONS_CF = "permissions";
static logging::logger alogger("default_authorizer");
// To ensure correct initialization order, we unfortunately need to use a string literal.
static const class_registrator<
authorizer,
default_authorizer,
cql3::query_processor&,
::service::migration_manager&> password_auth_reg("org.apache.cassandra.auth.CassandraAuthorizer");
default_authorizer::default_authorizer(cql3::query_processor& qp, ::service::migration_manager& mm)
: _qp(qp)
, _migration_manager(mm) {
auth::default_authorizer::default_authorizer() {
}
auth::default_authorizer::~default_authorizer() {
}
default_authorizer::~default_authorizer() {
future<> auth::default_authorizer::init() {
sstring create_table = sprint("CREATE TABLE %s.%s ("
"%s text,"
"%s text,"
"%s set<text>,"
"PRIMARY KEY(%s, %s)"
") WITH gc_grace_seconds=%d", auth::auth::AUTH_KS,
PERMISSIONS_CF, USER_NAME, RESOURCE_NAME, PERMISSIONS_NAME,
USER_NAME, RESOURCE_NAME, 90 * 24 * 60 * 60); // 3 months.
return auth::setup_table(PERMISSIONS_CF, create_table);
}
static const sstring legacy_table_name{"permissions"};
bool default_authorizer::legacy_metadata_exists() const {
return _qp.db().has_schema(meta::AUTH_KS, legacy_table_name);
}
future<auth::permission_set> auth::default_authorizer::authorize(
::shared_ptr<authenticated_user> user, data_resource resource) const {
return user->is_super().then([this, user, resource = std::move(resource)](bool is_super) {
if (is_super) {
return make_ready_future<permission_set>(permissions::ALL);
}
future<bool> default_authorizer::any_granted() const {
static const sstring query = format("SELECT * FROM {}.{} LIMIT 1", meta::AUTH_KS, PERMISSIONS_CF);
/**
* TOOD: could create actual data type for permission (translating string<->perm),
* but this seems overkill right now. We still must store strings so...
*/
auto& qp = cql3::get_local_query_processor();
auto query = sprint("SELECT %s FROM %s.%s WHERE %s = ? AND %s = ?"
, PERMISSIONS_NAME, auth::AUTH_KS, PERMISSIONS_CF, USER_NAME, RESOURCE_NAME);
return qp.process(query, db::consistency_level::LOCAL_ONE, {user->name(), resource.name() })
.then_wrapped([=](future<::shared_ptr<cql3::untyped_result_set>> f) {
try {
auto res = f.get0();
return _qp.execute_internal(
query,
db::consistency_level::LOCAL_ONE,
infinite_timeout_config,
{},
true).then([this](::shared_ptr<cql3::untyped_result_set> results) {
return !results->empty();
});
}
future<> default_authorizer::migrate_legacy_metadata() const {
alogger.info("Starting migration of legacy permissions metadata.");
static const sstring query = format("SELECT * FROM {}.{}", meta::AUTH_KS, legacy_table_name);
return _qp.execute_internal(
query,
db::consistency_level::LOCAL_ONE,
infinite_timeout_config).then([this](::shared_ptr<cql3::untyped_result_set> results) {
return do_for_each(*results, [this](const cql3::untyped_result_set_row& row) {
return do_with(
row.get_as<sstring>("username"),
parse_resource(row.get_as<sstring>(RESOURCE_NAME)),
[this, &row](const auto& username, const auto& r) {
const permission_set perms = permissions::from_strings(row.get_set<sstring>(PERMISSIONS_NAME));
return grant(username, perms, r);
});
}).finally([results] {});
}).then([] {
alogger.info("Finished migrating legacy permissions metadata.");
}).handle_exception([](std::exception_ptr ep) {
alogger.error("Encountered an error during migration!");
std::rethrow_exception(ep);
});
}
future<> default_authorizer::start() {
static const sstring create_table = sprint(
"CREATE TABLE %s.%s ("
"%s text,"
"%s text,"
"%s set<text>,"
"PRIMARY KEY(%s, %s)"
") WITH gc_grace_seconds=%d",
meta::AUTH_KS,
PERMISSIONS_CF,
ROLE_NAME,
RESOURCE_NAME,
PERMISSIONS_NAME,
ROLE_NAME,
RESOURCE_NAME,
90 * 24 * 60 * 60); // 3 months.
return once_among_shards([this] {
return create_metadata_table_if_missing(
PERMISSIONS_CF,
_qp,
create_table,
_migration_manager).then([this] {
_finished = do_after_system_ready(_as, [this] {
return async([this] {
wait_for_schema_agreement(_migration_manager, _qp.db(), _as).get0();
if (legacy_metadata_exists()) {
if (!any_granted().get0()) {
migrate_legacy_metadata().get0();
return;
}
alogger.warn("Ignoring legacy permissions metadata since role permissions exist.");
}
});
});
if (res->empty() || !res->one().has(PERMISSIONS_NAME)) {
return make_ready_future<permission_set>(permissions::NONE);
}
return make_ready_future<permission_set>(permissions::from_strings(res->one().get_set<sstring>(PERMISSIONS_NAME)));
} catch (exceptions::request_execution_exception& e) {
alogger.warn("CassandraAuthorizer failed to authorize {} for {}", user->name(), resource);
return make_ready_future<permission_set>(permissions::NONE);
}
});
});
}
future<> default_authorizer::stop() {
_as.request_abort();
return _finished.handle_exception_type([](const sleep_aborted&) {}).handle_exception_type([](const abort_requested_exception&) {});
#include <boost/range.hpp>
future<> auth::default_authorizer::modify(
::shared_ptr<authenticated_user> performer, permission_set set,
data_resource resource, sstring user, sstring op) {
// TODO: why does this not check super user?
auto& qp = cql3::get_local_query_processor();
auto query = sprint("UPDATE %s.%s SET %s = %s %s ? WHERE %s = ? AND %s = ?",
auth::AUTH_KS, PERMISSIONS_CF, PERMISSIONS_NAME,
PERMISSIONS_NAME, op, USER_NAME, RESOURCE_NAME);
return qp.process(query, db::consistency_level::ONE, {
permissions::to_strings(set), user, resource.name() }).discard_result();
}
future<permission_set>
default_authorizer::authorize(const role_or_anonymous& maybe_role, const resource& r) const {
if (is_anonymous(maybe_role)) {
return make_ready_future<permission_set>(permissions::NONE);
}
static const sstring query = format("SELECT {} FROM {}.{} WHERE {} = ? AND {} = ?",
PERMISSIONS_NAME,
meta::AUTH_KS,
PERMISSIONS_CF,
ROLE_NAME,
RESOURCE_NAME);
future<> auth::default_authorizer::grant(
::shared_ptr<authenticated_user> performer, permission_set set,
data_resource resource, sstring to) {
return modify(std::move(performer), std::move(set), std::move(resource), std::move(to), "+");
}
return _qp.execute_internal(
query,
db::consistency_level::LOCAL_ONE,
infinite_timeout_config,
{*maybe_role.name, r.name()}).then([](::shared_ptr<cql3::untyped_result_set> results) {
if (results->empty()) {
return permissions::NONE;
future<> auth::default_authorizer::revoke(
::shared_ptr<authenticated_user> performer, permission_set set,
data_resource resource, sstring from) {
return modify(std::move(performer), std::move(set), std::move(resource), std::move(from), "-");
}
future<std::vector<auth::permission_details>> auth::default_authorizer::list(
::shared_ptr<authenticated_user> performer, permission_set set,
optional<data_resource> resource, optional<sstring> user) const {
return performer->is_super().then([this, performer, set = std::move(set), resource = std::move(resource), user = std::move(user)](bool is_super) {
if (!is_super && (!user || performer->name() != *user)) {
throw exceptions::unauthorized_exception(sprint("You are not authorized to view %s's permissions", user ? *user : "everyone"));
}
return permissions::from_strings(results->one().get_set<sstring>(PERMISSIONS_NAME));
});
}
auto query = sprint("SELECT %s, %s, %s FROM %s.%s", USER_NAME, RESOURCE_NAME, PERMISSIONS_NAME, auth::AUTH_KS, PERMISSIONS_CF);
auto& qp = cql3::get_local_query_processor();
future<>
default_authorizer::modify(
std::string_view role_name,
permission_set set,
const resource& resource,
std::string_view op) const {
return do_with(
format("UPDATE {}.{} SET {} = {} {} ? WHERE {} = ? AND {} = ?",
meta::AUTH_KS,
PERMISSIONS_CF,
PERMISSIONS_NAME,
PERMISSIONS_NAME,
op,
ROLE_NAME,
RESOURCE_NAME),
[this, &role_name, set, &resource](const auto& query) {
return _qp.execute_internal(
query,
db::consistency_level::ONE,
internal_distributed_timeout_config(),
{permissions::to_strings(set), sstring(role_name), resource.name()}).discard_result();
});
}
// Oh, look, it is a case where it does not pay off to have
// parameters to process in an initializer list.
future<::shared_ptr<cql3::untyped_result_set>> f = make_ready_future<::shared_ptr<cql3::untyped_result_set>>();
if (resource && user) {
query += sprint(" WHERE %s = ? AND %s = ?", USER_NAME, RESOURCE_NAME);
f = qp.process(query, db::consistency_level::ONE, {*user, resource->name()});
} else if (resource) {
query += sprint(" WHERE %s = ? ALLOW FILTERING", RESOURCE_NAME);
f = qp.process(query, db::consistency_level::ONE, {resource->name()});
} else if (user) {
query += sprint(" WHERE %s = ?", USER_NAME);
f = qp.process(query, db::consistency_level::ONE, {*user});
} else {
f = qp.process(query, db::consistency_level::ONE, {});
}
future<> default_authorizer::grant(std::string_view role_name, permission_set set, const resource& resource) const {
return modify(role_name, std::move(set), resource, "+");
}
return f.then([set](::shared_ptr<cql3::untyped_result_set> res) {
std::vector<permission_details> result;
future<> default_authorizer::revoke(std::string_view role_name, permission_set set, const resource& resource) const {
return modify(role_name, std::move(set), resource, "-");
}
for (auto& row : *res) {
if (row.has(PERMISSIONS_NAME)) {
auto username = row.get_as<sstring>(USER_NAME);
auto resource = data_resource::from_name(row.get_as<sstring>(RESOURCE_NAME));
auto ps = permissions::from_strings(row.get_set<sstring>(PERMISSIONS_NAME));
ps = permission_set::from_mask(ps.mask() & set.mask());
future<std::vector<permission_details>> default_authorizer::list_all() const {
static const sstring query = format("SELECT {}, {}, {} FROM {}.{}",
ROLE_NAME,
RESOURCE_NAME,
PERMISSIONS_NAME,
meta::AUTH_KS,
PERMISSIONS_CF);
return _qp.execute_internal(
query,
db::consistency_level::ONE,
internal_distributed_timeout_config(),
{},
true).then([](::shared_ptr<cql3::untyped_result_set> results) {
std::vector<permission_details> all_details;
for (const auto& row : *results) {
if (row.has(PERMISSIONS_NAME)) {
auto role_name = row.get_as<sstring>(ROLE_NAME);
auto resource = parse_resource(row.get_as<sstring>(RESOURCE_NAME));
auto perms = permissions::from_strings(row.get_set<sstring>(PERMISSIONS_NAME));
all_details.push_back(permission_details{std::move(role_name), std::move(resource), std::move(perms)});
result.emplace_back(permission_details {username, resource, ps});
}
}
}
return all_details;
return make_ready_future<std::vector<permission_details>>(std::move(result));
});
});
}
future<> default_authorizer::revoke_all(std::string_view role_name) const {
static const sstring query = format("DELETE FROM {}.{} WHERE {} = ?",
meta::AUTH_KS,
PERMISSIONS_CF,
ROLE_NAME);
return _qp.execute_internal(
query,
db::consistency_level::ONE,
internal_distributed_timeout_config(),
{sstring(role_name)}).discard_result().handle_exception([role_name](auto ep) {
try {
std::rethrow_exception(ep);
} catch (exceptions::request_execution_exception& e) {
alogger.warn("CassandraAuthorizer failed to revoke all permissions of {}: {}", role_name, e);
}
});
future<> auth::default_authorizer::revoke_all(sstring dropped_user) {
auto& qp = cql3::get_local_query_processor();
auto query = sprint("DELETE FROM %s.%s WHERE %s = ?", auth::AUTH_KS,
PERMISSIONS_CF, USER_NAME);
return qp.process(query, db::consistency_level::ONE, { dropped_user }).discard_result().handle_exception(
[dropped_user](auto ep) {
try {
std::rethrow_exception(ep);
} catch (exceptions::request_execution_exception& e) {
alogger.warn("CassandraAuthorizer failed to revoke all permissions of {}: {}", dropped_user, e);
}
});
}
future<> default_authorizer::revoke_all(const resource& resource) const {
static const sstring query = format("SELECT {} FROM {}.{} WHERE {} = ? ALLOW FILTERING",
ROLE_NAME,
meta::AUTH_KS,
PERMISSIONS_CF,
RESOURCE_NAME);
return _qp.execute_internal(
query,
db::consistency_level::LOCAL_ONE,
infinite_timeout_config,
{resource.name()}).then_wrapped([this, resource](future<::shared_ptr<cql3::untyped_result_set>> f) {
future<> auth::default_authorizer::revoke_all(data_resource resource) {
auto& qp = cql3::get_local_query_processor();
auto query = sprint("SELECT %s FROM %s.%s WHERE %s = ? ALLOW FILTERING",
USER_NAME, auth::AUTH_KS, PERMISSIONS_CF, RESOURCE_NAME);
return qp.process(query, db::consistency_level::LOCAL_ONE, { resource.name() })
.then_wrapped([resource, &qp](future<::shared_ptr<cql3::untyped_result_set>> f) {
try {
auto res = f.get0();
return parallel_for_each(
res->begin(),
res->end(),
[this, res, resource](const cql3::untyped_result_set::row& r) {
static const sstring query = format("DELETE FROM {}.{} WHERE {} = ? AND {} = ?",
meta::AUTH_KS,
PERMISSIONS_CF,
ROLE_NAME,
RESOURCE_NAME);
return _qp.execute_internal(
query,
db::consistency_level::LOCAL_ONE,
infinite_timeout_config,
{r.get_as<sstring>(ROLE_NAME), resource.name()}).discard_result().handle_exception(
[resource](auto ep) {
return parallel_for_each(res->begin(), res->end(), [&qp, res, resource](const cql3::untyped_result_set::row& r) {
auto query = sprint("DELETE FROM %s.%s WHERE %s = ? AND %s = ?"
, auth::AUTH_KS, PERMISSIONS_CF, USER_NAME, RESOURCE_NAME);
return qp.process(query, db::consistency_level::LOCAL_ONE, { r.get_as<sstring>(USER_NAME), resource.name() })
.discard_result().handle_exception([resource](auto ep) {
try {
std::rethrow_exception(ep);
} catch (exceptions::request_execution_exception& e) {
@@ -334,9 +229,12 @@ future<> default_authorizer::revoke_all(const resource& resource) const {
});
}
const resource_set& default_authorizer::protected_resources() const {
static const resource_set resources({ make_data_resource(meta::AUTH_KS, PERMISSIONS_CF) });
return resources;
const auth::resource_ids& auth::default_authorizer::protected_resources() {
static const resource_ids ids({ data_resource(auth::AUTH_KS, PERMISSIONS_CF) });
return ids;
}
future<> auth::default_authorizer::validate_configuration() const {
return make_ready_future();
}

View File

@@ -41,62 +41,37 @@
#pragma once
#include <functional>
#include <seastar/core/abort_source.hh>
#include "auth/authorizer.hh"
#include "cql3/query_processor.hh"
#include "service/migration_manager.hh"
#include "authorizer.hh"
namespace auth {
const sstring& default_authorizer_name();
class default_authorizer : public authorizer {
cql3::query_processor& _qp;
::service::migration_manager& _migration_manager;
abort_source _as{};
future<> _finished{make_ready_future<>()};
public:
default_authorizer(cql3::query_processor&, ::service::migration_manager&);
static const sstring DEFAULT_AUTHORIZER_NAME;
default_authorizer();
~default_authorizer();
virtual future<> start() override;
future<> init();
virtual future<> stop() override;
future<permission_set> authorize(::shared_ptr<authenticated_user>, data_resource) const override;
virtual std::string_view qualified_java_name() const override {
return default_authorizer_name();
}
future<> grant(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring) override;
virtual future<permission_set> authorize(const role_or_anonymous&, const resource&) const override;
future<> revoke(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring) override;
virtual future<> grant(std::string_view, permission_set, const resource&) const override;
future<std::vector<permission_details>> list(::shared_ptr<authenticated_user>, permission_set, optional<data_resource>, optional<sstring>) const override;
virtual future<> revoke( std::string_view, permission_set, const resource&) const override;
future<> revoke_all(sstring) override;
virtual future<std::vector<permission_details>> list_all() const override;
future<> revoke_all(data_resource) override;
virtual future<> revoke_all(std::string_view) const override;
const resource_ids& protected_resources() override;
virtual future<> revoke_all(const resource&) const override;
virtual const resource_set& protected_resources() const override;
future<> validate_configuration() const override;
private:
bool legacy_metadata_exists() const;
future<bool> any_granted() const;
future<> migrate_legacy_metadata() const;
future<> modify(std::string_view, permission_set, const resource&, std::string_view) const;
future<> modify(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring, sstring);
};
} /* namespace auth */

View File

@@ -39,187 +39,174 @@
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "auth/password_authenticator.hh"
#include <algorithm>
#include <chrono>
#include <unistd.h>
#include <crypt.h>
#include <random>
#include <string_view>
#include <optional>
#include <chrono>
#include <boost/algorithm/cxx11/all_of.hpp>
#include <seastar/core/seastar.hh>
#include <seastar/core/reactor.hh>
#include "auth/authenticated_user.hh"
#include "auth/common.hh"
#include "auth/passwords.hh"
#include "auth/roles-metadata.hh"
#include "cql3/untyped_result_set.hh"
#include "auth.hh"
#include "password_authenticator.hh"
#include "authenticated_user.hh"
#include "cql3/query_processor.hh"
#include "log.hh"
#include "service/migration_manager.hh"
#include "utils/class_registrator.hh"
#include "database.hh"
namespace auth {
const sstring& password_authenticator_name() {
static const sstring name = meta::AUTH_PACKAGE_NAME + "PasswordAuthenticator";
return name;
}
const sstring auth::password_authenticator::PASSWORD_AUTHENTICATOR_NAME("org.apache.cassandra.auth.PasswordAuthenticator");
// name of the hash column.
static const sstring SALTED_HASH = "salted_hash";
static const sstring DEFAULT_USER_NAME = meta::DEFAULT_SUPERUSER_NAME;
static const sstring DEFAULT_USER_PASSWORD = meta::DEFAULT_SUPERUSER_NAME;
static const sstring USER_NAME = "username";
static const sstring DEFAULT_USER_NAME = auth::auth::DEFAULT_SUPERUSER_NAME;
static const sstring DEFAULT_USER_PASSWORD = auth::auth::DEFAULT_SUPERUSER_NAME;
static const sstring CREDENTIALS_CF = "credentials";
static logging::logger plogger("password_authenticator");
// To ensure correct initialization order, we unfortunately need to use a string literal.
static const class_registrator<
authenticator,
password_authenticator,
cql3::query_processor&,
::service::migration_manager&> password_auth_reg("org.apache.cassandra.auth.PasswordAuthenticator");
auth::password_authenticator::~password_authenticator()
{}
static thread_local auto rng_for_salt = std::default_random_engine(std::random_device{}());
auth::password_authenticator::password_authenticator()
{}
password_authenticator::~password_authenticator() {
// TODO: blowfish
// Origin uses Java bcrypt library, i.e. blowfish salt
// generation and hashing, which is arguably a "better"
// password hash than sha/md5 versions usually available in
// crypt_r. Otoh, glibc 2.7+ uses a modified sha512 algo
// which should be the same order of safe, so the only
// real issue should be salted hash compatibility with
// origin if importing system tables from there.
//
// Since bcrypt/blowfish is _not_ (afaict) not available
// as a dev package/lib on most linux distros, we'd have to
// copy and compile for example OWL crypto
// (http://cvsweb.openwall.com/cgi/cvsweb.cgi/Owl/packages/glibc/crypt_blowfish/)
// to be fully bit-compatible.
//
// Until we decide this is needed, let's just use crypt_r,
// and some old-fashioned random salt generation.
static constexpr size_t rand_bytes = 16;
static sstring hashpw(const sstring& pass, const sstring& salt) {
// crypt_data is huge. should this be a thread_local static?
auto tmp = std::make_unique<crypt_data>();
tmp->initialized = 0;
auto res = crypt_r(pass.c_str(), salt.c_str(), tmp.get());
if (res == nullptr) {
throw std::system_error(errno, std::system_category());
}
return res;
}
password_authenticator::password_authenticator(cql3::query_processor& qp, ::service::migration_manager& mm)
: _qp(qp)
, _migration_manager(mm)
, _stopped(make_ready_future<>()) {
static bool checkpw(const sstring& pass, const sstring& salted_hash) {
auto tmp = hashpw(pass, salted_hash);
return tmp == salted_hash;
}
static bool has_salted_hash(const cql3::untyped_result_set_row& row) {
return !row.get_or<sstring>(SALTED_HASH, "").empty();
}
static sstring gensalt() {
static sstring prefix;
static const sstring& update_row_query() {
static const sstring update_row_query = format("UPDATE {} SET {} = ? WHERE {} = ?",
meta::roles_table::qualified_name(),
SALTED_HASH,
meta::roles_table::role_col_name);
return update_row_query;
}
std::random_device rd;
std::default_random_engine e1(rd());
std::uniform_int_distribution<char> dist;
static const sstring legacy_table_name{"credentials"};
sstring valid_salt = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789./";
sstring input(rand_bytes, 0);
bool password_authenticator::legacy_metadata_exists() const {
return _qp.db().has_schema(meta::AUTH_KS, legacy_table_name);
}
for (char&c : input) {
c = valid_salt[dist(e1) % valid_salt.size()];
}
future<> password_authenticator::migrate_legacy_metadata() const {
plogger.info("Starting migration of legacy authentication metadata.");
static const sstring query = format("SELECT * FROM {}.{}", meta::AUTH_KS, legacy_table_name);
sstring salt;
return _qp.execute_internal(
query,
db::consistency_level::QUORUM,
internal_distributed_timeout_config()).then([this](::shared_ptr<cql3::untyped_result_set> results) {
return do_for_each(*results, [this](const cql3::untyped_result_set_row& row) {
auto username = row.get_as<sstring>("username");
auto salted_hash = row.get_as<sstring>(SALTED_HASH);
if (!prefix.empty()) {
return prefix + salt;
}
return _qp.execute_internal(
update_row_query(),
consistency_for_user(username),
internal_distributed_timeout_config(),
{std::move(salted_hash), username}).discard_result();
}).finally([results] {});
}).then([] {
plogger.info("Finished migrating legacy authentication metadata.");
}).handle_exception([](std::exception_ptr ep) {
plogger.error("Encountered an error during migration!");
std::rethrow_exception(ep);
});
}
auto tmp = std::make_unique<crypt_data>();
tmp->initialized = 0;
future<> password_authenticator::create_default_if_missing() const {
return default_role_row_satisfies(_qp, &has_salted_hash).then([this](bool exists) {
if (!exists) {
return _qp.execute_internal(
update_row_query(),
db::consistency_level::QUORUM,
internal_distributed_timeout_config(),
{passwords::hash(DEFAULT_USER_PASSWORD, rng_for_salt), DEFAULT_USER_NAME}).then([](auto&&) {
plogger.info("Created default superuser authentication record.");
});
// Try in order:
// blowfish 2011 fix, blowfish, sha512, sha256, md5
for (sstring pfx : { "$2y$", "$2a$", "$6$", "$5$", "$1$" }) {
salt = pfx + input;
if (crypt_r("fisk", salt.c_str(), tmp.get())) {
prefix = pfx;
return salt;
}
}
throw std::runtime_error("Could not initialize hashing algorithm");
}
return make_ready_future<>();
static sstring hashpw(const sstring& pass) {
return hashpw(pass, gensalt());
}
future<> auth::password_authenticator::init() {
gensalt(); // do this once to determine usable hashing
sstring create_table = sprint(
"CREATE TABLE %s.%s ("
"%s text,"
"%s text," // salt + hash + number of rounds
"options map<text,text>,"// for future extensions
"PRIMARY KEY(%s)"
") WITH gc_grace_seconds=%d",
auth::auth::AUTH_KS,
CREDENTIALS_CF, USER_NAME, SALTED_HASH, USER_NAME,
90 * 24 * 60 * 60); // 3 months.
return auth::setup_table(CREDENTIALS_CF, create_table).then([this] {
// instead of once-timer, just schedule this later
auth::schedule_when_up([] {
return auth::has_existing_users(CREDENTIALS_CF, DEFAULT_USER_NAME, USER_NAME).then([](bool exists) {
if (!exists) {
cql3::get_local_query_processor().process(sprint("INSERT INTO %s.%s (%s, %s) VALUES (?, ?) USING TIMESTAMP 0",
auth::AUTH_KS,
CREDENTIALS_CF,
USER_NAME, SALTED_HASH
),
db::consistency_level::ONE, {DEFAULT_USER_NAME, hashpw(DEFAULT_USER_PASSWORD)}).then([](auto) {
plogger.info("Created default user '{}'", DEFAULT_USER_NAME);
});
}
});
});
});
}
future<> password_authenticator::start() {
return once_among_shards([this] {
auto f = create_metadata_table_if_missing(
meta::roles_table::name,
_qp,
meta::roles_table::creation_query(),
_migration_manager);
_stopped = do_after_system_ready(_as, [this] {
return async([this] {
wait_for_schema_agreement(_migration_manager, _qp.db(), _as).get0();
if (any_nondefault_role_row_satisfies(_qp, &has_salted_hash).get0()) {
if (legacy_metadata_exists()) {
plogger.warn("Ignoring legacy authentication metadata since nondefault data already exist.");
}
return;
}
if (legacy_metadata_exists()) {
migrate_legacy_metadata().get0();
return;
}
create_default_if_missing().get0();
});
});
return f;
});
}
future<> password_authenticator::stop() {
_as.request_abort();
return _stopped.handle_exception_type([] (const sleep_aborted&) { }).handle_exception_type([](const abort_requested_exception&) {});
}
db::consistency_level password_authenticator::consistency_for_user(std::string_view role_name) {
if (role_name == DEFAULT_USER_NAME) {
db::consistency_level auth::password_authenticator::consistency_for_user(const sstring& username) {
if (username == DEFAULT_USER_NAME) {
return db::consistency_level::QUORUM;
}
return db::consistency_level::LOCAL_ONE;
}
std::string_view password_authenticator::qualified_java_name() const {
return password_authenticator_name();
const sstring& auth::password_authenticator::class_name() const {
return PASSWORD_AUTHENTICATOR_NAME;
}
bool password_authenticator::require_authentication() const {
bool auth::password_authenticator::require_authentication() const {
return true;
}
authentication_option_set password_authenticator::supported_options() const {
return authentication_option_set{authentication_option::password};
auth::authenticator::option_set auth::password_authenticator::supported_options() const {
return option_set::of<option::PASSWORD>();
}
authentication_option_set password_authenticator::alterable_options() const {
return authentication_option_set{authentication_option::password};
auth::authenticator::option_set auth::password_authenticator::alterable_options() const {
return option_set::of<option::PASSWORD>();
}
future<authenticated_user> password_authenticator::authenticate(
future<::shared_ptr<auth::authenticated_user> > auth::password_authenticator::authenticate(
const credentials_map& credentials) const {
if (!credentials.count(USERNAME_KEY)) {
throw exceptions::authentication_exception(format("Required key '{}' is missing", USERNAME_KEY));
throw exceptions::authentication_exception(sprint("Required key '%s' is missing", USERNAME_KEY));
}
if (!credentials.count(PASSWORD_KEY)) {
throw exceptions::authentication_exception(format("Required key '{}' is missing", PASSWORD_KEY));
throw exceptions::authentication_exception(sprint("Required key '%s' is missing", PASSWORD_KEY));
}
auto& username = credentials.at(USERNAME_KEY);
@@ -230,98 +217,135 @@ future<authenticated_user> password_authenticator::authenticate(
// obsolete prepared statements pretty quickly.
// Rely on query processing caching statements instead, and lets assume
// that a map lookup string->statement is not gonna kill us much.
return futurize_invoke([this, username, password] {
static const sstring query = format("SELECT {} FROM {} WHERE {} = ?",
SALTED_HASH,
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.execute_internal(
query,
consistency_for_user(username),
internal_distributed_timeout_config(),
{username},
true);
return futurize_apply([this, username, password] {
auto& qp = cql3::get_local_query_processor();
return qp.process(sprint("SELECT %s FROM %s.%s WHERE %s = ?", SALTED_HASH,
auth::AUTH_KS, CREDENTIALS_CF, USER_NAME),
consistency_for_user(username), {username}, true);
}).then_wrapped([=](future<::shared_ptr<cql3::untyped_result_set>> f) {
try {
auto res = f.get0();
auto salted_hash = std::optional<sstring>();
if (!res->empty()) {
salted_hash = res->one().get_opt<sstring>(SALTED_HASH);
}
if (!salted_hash || !passwords::check(password, *salted_hash)) {
if (res->empty() || !checkpw(password, res->one().get_as<sstring>(SALTED_HASH))) {
throw exceptions::authentication_exception("Username and/or password are incorrect");
}
return make_ready_future<authenticated_user>(username);
return make_ready_future<::shared_ptr<authenticated_user>>(::make_shared<authenticated_user>(username));
} catch (std::system_error &) {
std::throw_with_nested(exceptions::authentication_exception("Could not verify password"));
} catch (exceptions::request_execution_exception& e) {
std::throw_with_nested(exceptions::authentication_exception(e.what()));
} catch (exceptions::authentication_exception& e) {
std::throw_with_nested(e);
} catch (...) {
std::throw_with_nested(exceptions::authentication_exception("authentication failed"));
}
});
}
future<> password_authenticator::create(std::string_view role_name, const authentication_options& options) const {
if (!options.password) {
return make_ready_future<>();
future<> auth::password_authenticator::create(sstring username,
const option_map& options) {
try {
auto password = boost::any_cast<sstring>(options.at(option::PASSWORD));
auto query = sprint("INSERT INTO %s.%s (%s, %s) VALUES (?, ?)",
auth::AUTH_KS, CREDENTIALS_CF, USER_NAME, SALTED_HASH);
auto& qp = cql3::get_local_query_processor();
return qp.process(query, consistency_for_user(username), { username, hashpw(password) }).discard_result();
} catch (std::out_of_range&) {
throw exceptions::invalid_request_exception("PasswordAuthenticator requires PASSWORD option");
}
return _qp.execute_internal(
update_row_query(),
consistency_for_user(role_name),
internal_distributed_timeout_config(),
{passwords::hash(*options.password, rng_for_salt), sstring(role_name)}).discard_result();
}
future<> password_authenticator::alter(std::string_view role_name, const authentication_options& options) const {
if (!options.password) {
return make_ready_future<>();
future<> auth::password_authenticator::alter(sstring username,
const option_map& options) {
try {
auto password = boost::any_cast<sstring>(options.at(option::PASSWORD));
auto query = sprint("UPDATE %s.%s SET %s = ? WHERE %s = ?",
auth::AUTH_KS, CREDENTIALS_CF, SALTED_HASH, USER_NAME);
auto& qp = cql3::get_local_query_processor();
return qp.process(query, consistency_for_user(username), { hashpw(password), username }).discard_result();
} catch (std::out_of_range&) {
throw exceptions::invalid_request_exception("PasswordAuthenticator requires PASSWORD option");
}
static const sstring query = format("UPDATE {} SET {} = ? WHERE {} = ?",
meta::roles_table::qualified_name(),
SALTED_HASH,
meta::roles_table::role_col_name);
return _qp.execute_internal(
query,
consistency_for_user(role_name),
internal_distributed_timeout_config(),
{passwords::hash(*options.password, rng_for_salt), sstring(role_name)}).discard_result();
}
future<> password_authenticator::drop(std::string_view name) const {
static const sstring query = format("DELETE {} FROM {} WHERE {} = ?",
SALTED_HASH,
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.execute_internal(
query, consistency_for_user(name),
internal_distributed_timeout_config(),
{sstring(name)}).discard_result();
future<> auth::password_authenticator::drop(sstring username) {
try {
auto query = sprint("DELETE FROM %s.%s WHERE %s = ?",
auth::AUTH_KS, CREDENTIALS_CF, USER_NAME);
auto& qp = cql3::get_local_query_processor();
return qp.process(query, consistency_for_user(username), { username }).discard_result();
} catch (std::out_of_range&) {
throw exceptions::invalid_request_exception("PasswordAuthenticator requires PASSWORD option");
}
}
future<custom_options> password_authenticator::query_custom_options(std::string_view role_name) const {
return make_ready_future<custom_options>();
const auth::resource_ids& auth::password_authenticator::protected_resources() const {
static const resource_ids ids({ data_resource(auth::AUTH_KS, CREDENTIALS_CF) });
return ids;
}
const resource_set& password_authenticator::protected_resources() const {
static const resource_set resources({make_data_resource(meta::AUTH_KS, meta::roles_table::name)});
return resources;
}
::shared_ptr<auth::authenticator::sasl_challenge> auth::password_authenticator::new_sasl_challenge() const {
class plain_text_password_challenge: public sasl_challenge {
public:
plain_text_password_challenge(const password_authenticator& a)
: _authenticator(a)
{}
::shared_ptr<sasl_challenge> password_authenticator::new_sasl_challenge() const {
return ::make_shared<plain_sasl_challenge>([this](std::string_view username, std::string_view password) {
credentials_map credentials{};
credentials[USERNAME_KEY] = sstring(username);
credentials[PASSWORD_KEY] = sstring(password);
return this->authenticate(credentials);
});
}
/**
* SASL PLAIN mechanism specifies that credentials are encoded in a
* sequence of UTF-8 bytes, delimited by 0 (US-ASCII NUL).
* The form is : {code}authzId<NUL>authnId<NUL>password<NUL>{code}
* authzId is optional, and in fact we don't care about it here as we'll
* set the authzId to match the authnId (that is, there is no concept of
* a user being authorized to act on behalf of another).
*
* @param bytes encoded credentials string sent by the client
* @return map containing the username/password pairs in the form an IAuthenticator
* would expect
* @throws javax.security.sasl.SaslException
*/
bytes evaluate_response(bytes_view client_response) override {
plogger.debug("Decoding credentials from client token");
sstring username, password;
auto b = client_response.crbegin();
auto e = client_response.crend();
auto i = b;
while (i != e) {
if (*i == 0) {
sstring tmp(i.base(), b.base());
if (password.empty()) {
password = std::move(tmp);
} else if (username.empty()) {
username = std::move(tmp);
}
b = ++i;
continue;
}
++i;
}
if (username.empty()) {
throw exceptions::authentication_exception("Authentication ID must not be null");
}
if (password.empty()) {
throw exceptions::authentication_exception("Password must not be null");
}
_credentials[USERNAME_KEY] = std::move(username);
_credentials[PASSWORD_KEY] = std::move(password);
_complete = true;
return {};
}
bool is_complete() const override {
return _complete;
}
future<::shared_ptr<authenticated_user>> get_authenticated_user() const override {
return _authenticator.authenticate(_credentials);
}
private:
const password_authenticator& _authenticator;
credentials_map _credentials;
bool _complete = false;
};
return ::make_shared<plain_text_password_challenge>(*this);
}

View File

@@ -41,64 +41,32 @@
#pragma once
#include <seastar/core/abort_source.hh>
#include "auth/authenticator.hh"
#include "cql3/query_processor.hh"
namespace service {
class migration_manager;
}
#include "authenticator.hh"
namespace auth {
const sstring& password_authenticator_name();
class password_authenticator : public authenticator {
cql3::query_processor& _qp;
::service::migration_manager& _migration_manager;
future<> _stopped;
seastar::abort_source _as;
public:
static db::consistency_level consistency_for_user(std::string_view role_name);
password_authenticator(cql3::query_processor&, ::service::migration_manager&);
static const sstring PASSWORD_AUTHENTICATOR_NAME;
password_authenticator();
~password_authenticator();
virtual future<> start() override;
future<> init();
virtual future<> stop() override;
const sstring& class_name() const override;
bool require_authentication() const override;
option_set supported_options() const override;
option_set alterable_options() const override;
future<::shared_ptr<authenticated_user>> authenticate(const credentials_map& credentials) const override;
future<> create(sstring username, const option_map& options) override;
future<> alter(sstring username, const option_map& options) override;
future<> drop(sstring username) override;
const resource_ids& protected_resources() const override;
::shared_ptr<sasl_challenge> new_sasl_challenge() const override;
virtual std::string_view qualified_java_name() const override;
virtual bool require_authentication() const override;
virtual authentication_option_set supported_options() const override;
virtual authentication_option_set alterable_options() const override;
virtual future<authenticated_user> authenticate(const credentials_map& credentials) const override;
virtual future<> create(std::string_view role_name, const authentication_options& options) const override;
virtual future<> alter(std::string_view role_name, const authentication_options& options) const override;
virtual future<> drop(std::string_view role_name) const override;
virtual future<custom_options> query_custom_options(std::string_view role_name) const override;
virtual const resource_set& protected_resources() const override;
virtual ::shared_ptr<sasl_challenge> new_sasl_challenge() const override;
private:
bool legacy_metadata_exists() const;
future<> migrate_legacy_metadata() const;
future<> create_default_if_missing() const;
static db::consistency_level consistency_for_user(const sstring& username);
};
}

View File

@@ -1,84 +0,0 @@
/*
* Copyright (C) 2018 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "auth/passwords.hh"
#include <cerrno>
#include <optional>
extern "C" {
#include <crypt.h>
#include <unistd.h>
}
namespace auth::passwords {
static thread_local crypt_data tlcrypt = { 0, };
namespace detail {
scheme identify_best_supported_scheme() {
const auto all_schemes = { scheme::bcrypt_y, scheme::bcrypt_a, scheme::sha_512, scheme::sha_256, scheme::md5 };
// "Random", for testing schemes.
const sstring random_part_of_salt = "aaaabbbbccccdddd";
for (scheme c : all_schemes) {
const sstring salt = sstring(prefix_for_scheme(c)) + random_part_of_salt;
const char* e = crypt_r("fisk", salt.c_str(), &tlcrypt);
if (e && (e[0] != '*')) {
return c;
}
}
throw no_supported_schemes();
}
sstring hash_with_salt(const sstring& pass, const sstring& salt) {
auto res = crypt_r(pass.c_str(), salt.c_str(), &tlcrypt);
if (!res || (res[0] == '*')) {
throw std::system_error(errno, std::system_category());
}
return res;
}
const char* prefix_for_scheme(scheme c) noexcept {
switch (c) {
case scheme::bcrypt_y: return "$2y$";
case scheme::bcrypt_a: return "$2a$";
case scheme::sha_512: return "$6$";
case scheme::sha_256: return "$5$";
case scheme::md5: return "$1$";
default: return nullptr;
}
}
} // namespace detail
no_supported_schemes::no_supported_schemes()
: std::runtime_error("No allowed hashing schemes are supported on this system") {
}
bool check(const sstring& pass, const sstring& salted_hash) {
return detail::hash_with_salt(pass, salted_hash) == salted_hash;
}
} // namespace auth::paswords

View File

@@ -1,125 +0,0 @@
/*
* Copyright (C) 2018 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <random>
#include <stdexcept>
#include <seastar/core/sstring.hh>
#include "seastarx.hh"
namespace auth::passwords {
class no_supported_schemes : public std::runtime_error {
public:
no_supported_schemes();
};
///
/// Apache Cassandra uses a library to provide the bcrypt scheme. Many Linux implementations do not support bcrypt, so
/// we support alternatives. The cost is loss of direct compatibility with Apache Cassandra system tables.
///
enum class scheme {
bcrypt_y,
bcrypt_a,
sha_512,
sha_256,
md5
};
namespace detail {
template <typename RandomNumberEngine>
sstring generate_random_salt_bytes(RandomNumberEngine& g) {
static const sstring valid_bytes = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789./";
static constexpr std::size_t num_bytes = 16;
std::uniform_int_distribution<std::size_t> dist(0, valid_bytes.size() - 1);
sstring result(num_bytes, 0);
for (char& c : result) {
c = valid_bytes[dist(g)];
}
return result;
}
///
/// Test each allowed hashing scheme and report the best supported one on the current system.
///
/// \throws \ref no_supported_schemes when none of the known schemes is supported.
///
scheme identify_best_supported_scheme();
const char* prefix_for_scheme(scheme) noexcept;
///
/// Generate a implementation-specific salt string for hashing passwords.
///
/// The `RandomNumberEngine` is used to generate the string, which is an implementation-specific length.
///
/// \throws \ref no_supported_schemes when no known hashing schemes are supported on the system.
///
template <typename RandomNumberEngine>
sstring generate_salt(RandomNumberEngine& g) {
static const scheme scheme = identify_best_supported_scheme();
static const sstring prefix = sstring(prefix_for_scheme(scheme));
return prefix + generate_random_salt_bytes(g);
}
///
/// Hash a password combined with an implementation-specific salt string.
///
/// \throws \ref std::system_error when an unexpected implementation-specific error occurs.
///
sstring hash_with_salt(const sstring& pass, const sstring& salt);
} // namespace detail
///
/// Run a one-way hashing function on cleartext to produce encrypted text.
///
/// Prior to applying the hashing function, random salt is amended to the cleartext. The random salt bytes are generated
/// according to the random number engine `g`.
///
/// The result is the encrypted cyphertext, and also the salt used but in a implementation-specific format.
///
/// \throws \ref std::system_error when the implementation-specific implementation fails to hash the cleartext.
///
template <typename RandomNumberEngine>
sstring hash(const sstring& pass, RandomNumberEngine& g) {
return detail::hash_with_salt(pass, detail::generate_salt(g));
}
///
/// Check that cleartext matches previously hashed cleartext with salt.
///
/// \ref salted_hash is the result of invoking \ref hash, which is the implementation-specific combination of the hashed
/// password and the salt that was generated for it.
///
/// \returns `true` if the cleartext matches the salted hash.
///
/// \throws \ref std::system_error when an unexpected implementation-specific error occurs.
///
bool check(const sstring& pass, const sstring& salted_hash);
} // namespace auth::passwords

View File

@@ -39,33 +39,32 @@
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "auth/permission.hh"
#include <boost/algorithm/string.hpp>
#include <unordered_map>
#include <boost/algorithm/string.hpp>
#include "permission.hh"
const auth::permission_set auth::permissions::ALL = auth::permission_set::of<
auth::permission::CREATE,
auth::permission::ALTER,
auth::permission::DROP,
auth::permission::SELECT,
auth::permission::MODIFY,
auth::permission::AUTHORIZE,
auth::permission::DESCRIBE>();
const auth::permission_set auth::permissions::ALL_DATA =
auth::permission_set::of<auth::permission::CREATE,
auth::permission::ALTER, auth::permission::DROP,
auth::permission::SELECT,
auth::permission::MODIFY,
auth::permission::AUTHORIZE>();
const auth::permission_set auth::permissions::ALL = auth::permissions::ALL_DATA;
const auth::permission_set auth::permissions::NONE;
const auth::permission_set auth::permissions::ALTERATIONS =
auth::permission_set::of<auth::permission::CREATE,
auth::permission::ALTER, auth::permission::DROP>();
static const std::unordered_map<sstring, auth::permission> permission_names({
{"READ", auth::permission::READ},
{"WRITE", auth::permission::WRITE},
{"CREATE", auth::permission::CREATE},
{"ALTER", auth::permission::ALTER},
{"DROP", auth::permission::DROP},
{"SELECT", auth::permission::SELECT},
{"MODIFY", auth::permission::MODIFY},
{"AUTHORIZE", auth::permission::AUTHORIZE},
{"DESCRIBE", auth::permission::DESCRIBE}});
{ "READ", auth::permission::READ },
{ "WRITE", auth::permission::WRITE },
{ "CREATE", auth::permission::CREATE },
{ "ALTER", auth::permission::ALTER },
{ "DROP", auth::permission::DROP },
{ "SELECT", auth::permission::SELECT },
{ "MODIFY", auth::permission::MODIFY },
{ "AUTHORIZE", auth::permission::AUTHORIZE },
});
const sstring& auth::permissions::to_string(permission p) {
for (auto& v : permission_names) {

Some files were not shown because too many files have changed in this diff Show More