Compare commits

..

197 Commits

Author SHA1 Message Date
Avi Kivity
19907fad15 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)
2018-02-01 14:28:59 +01:00
Avi Kivity
97f781c4d8 Update seastar submodule
* seastar e23b9b8...a66e0c5 (3):
  > posix.hh: add missing include
  > tls_test: Fix echo test not setting server trust store
  > tls: Actually verify client certificate if requested

Fixes #3072
2018-01-29 15:26:24 +02:00
Avi Kivity
88e69701bd 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 15:55:09 +02:00
Takuya ASADA
9007b38002 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 22:05:38 +02:00
Glauber Costa
f2e0affcc5 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 10:26:07 +02:00
Avi Kivity
6fce847000 Update seastar submodule
* seastar f27b240...e23b9b8 (1):
  > rpc: make sure that _write_buf stream is always properly closed

Fixes #3018.
2017-11-26 10:40:23 +02:00
Avi Kivity
f6f91a49cb Update seastar submodule
* seastar 121f468...f27b240 (1):
  > scripts/posix_net_conf.sh: supress unwanted output from get_irqs_one

Fixes #2808.
2017-10-08 16:40:00 +03:00
Tomasz Grabiec
266a45ad1e Update seastar submodule
* seastar b3ef898...121f468 (1):
  > configure: disable exception scalability hack on debug build
2017-09-25 10:13:59 +02:00
Tomasz Grabiec
7d88026f22 tests: row_cache_test: Fix test failure
Broken after 0ac2c388b6, which assigns
empty reader to _delegate on hitting wide partition limit. The test
assumed that the original _delegate will be invoked when the
single-partition reader is asked for the next partition, which is no
longer the case.

Message-Id: <20170912172739.6851-1-tgrabiec@scylladb.com>
2017-09-12 20:33:10 +03:00
Duarte Nunes
760af5635d tests: Remove sstable_assertions
The test using these assertions has been removed, and the
infrastructure required for them to work is absent from 1.7.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170912113714.24223-1-duarte@scylladb.com>
2017-09-12 14:41:44 +03:00
Duarte Nunes
8c18bfa8d6 sstable_mutation_test: Remove promoted index monotonicity test
The infrastructure this test relies on is not present in 1.7, so
just remove the test as backporting the required changes would be a
risky, non-trivial effort.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170912081304.10116-1-duarte@scylladb.com>
2017-09-12 11:18:05 +03:00
Avi Kivity
04e3785f77 Update seastar submodule
* seastar 688bb6f...b3ef898 (1):
  > build: fix bad merge artifacts
2017-09-11 16:27:52 +03:00
Avi Kivity
e00e6ad1b6 Update seastar submodule
* seastar 949b710...688bb6f (2):
  > build: export full cflags in pkgconfig file
  > build: disable -Wattributes when gcc -fvisibility=hidden bug strikes

Fixes build with gcc 6.4/gcc 7.
2017-09-11 15:41:52 +03:00
Pekka Enberg
5653ea9f8d release: prepare for 1.7.5 2017-09-11 14:03:12 +03:00
Avi Kivity
4dbd1b77cd Merge "Fix Scylla upgrades when counters are used" from Paweł
"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-1.7/v1' 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 more comparison operators
2017-09-11 13:27:01 +03:00
Paweł Dziepak
0e61212c20 tests/counter: verify counter_id ordering 2017-09-05 13:49:01 +01:00
Paweł Dziepak
6f4bc82b6e counter: check that utils::UUID uses int64_t 2017-09-05 13:49:01 +01:00
Paweł Dziepak
c1a30d3f60 mutation_partition_serializer: use old counter ordering if necessary
Until the cluster is fully upgraded from a version that uses the
incorrect counter shard ordering it is essential to keep using it lest
the old nodes corrupt the data upon receiving mutations with a counter
shard ordering they do not expect.
2017-09-05 13:49:01 +01:00
Paweł Dziepak
cbad33033f mutation_partition_view: do not expect counter shards to be sorted 2017-09-05 13:49:01 +01:00
Paweł Dziepak
1f31be9ba3 sstables: write counter shards in the order expected by the cluster
If the feature signaling that we have switched to the correct ordering
of counter shards is not enabled it means that the user still can do a
rollback to a version that expects wrong ordering. In order to avoid any
disasters when that happens write sstables using the 1.7.4 order until
we know for sure that it is no longer needed.
2017-09-05 13:49:01 +01:00
Paweł Dziepak
7e89dc3bbf tests/sstables: add storage_service_for_tests to counter write test
Writing a counters to a sstable is going to require cluster feature
information, which requires accessing some singletons.
2017-09-05 13:49:01 +01:00
Paweł Dziepak
2cdcaeba6e tests/sstables: add test for reading wrong-order counter cells 2017-09-05 13:49:01 +01:00
Paweł Dziepak
55cb0cafa8 sstables: do not expect counter shards to be sorted 2017-09-05 13:49:01 +01:00
Paweł Dziepak
660572e85c storage_service: introduce CORRECT_COUNTER_ORDER feature
Scylla 1.7.4 used incorrect ordering of counter shards. In order to fix
this problem a new feature is introduced that will be used to determine
when nodes with that bug fixed can start sending counter shard in the
correct order.
2017-09-05 13:49:01 +01:00
Paweł Dziepak
b86da0c479 tests/counter: test 1.7.4 compatible shard ordering 2017-09-05 13:49:01 +01:00
Paweł Dziepak
b1b8599b1a counters: add helper for retrieving shards in 1.7.4 order 2017-09-05 13:49:00 +01:00
Paweł Dziepak
89c037dfc8 tests/counter: add tests for 1.7.4 counter shard order 2017-09-05 13:49:00 +01:00
Paweł Dziepak
25eec66935 counters: add counter id comparator compatible with Scylla 1.7.4 2017-09-05 13:49:00 +01:00
Paweł Dziepak
b5787ca640 tests/counter: verify order of counter shards 2017-09-05 13:49:00 +01:00
Paweł Dziepak
838dbd98ac tests/counter: add test for sorting and deduplicating shards 2017-09-05 13:49:00 +01:00
Paweł Dziepak
022c2ff53a counters: add function for sorting and deduplicating counter cells
Due to a bug in an implementation of UUID less compare some Scylla
versions sort counter shards in an incorrect order. Moreover, when
dealing with imported correct data the inconsistencies in ordering
caused some counter shards to become duplicated.
2017-09-05 13:49:00 +01:00
Paweł Dziepak
b7c27d73d8 counters: add more comparison operators 2017-09-05 13:49:00 +01:00
Vlad Zolotarov
bdc0ca7064 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 09:33:33 +02:00
Calle Wilund
34260ce471 utils::UUID: operator< should behave as comparison of hex strings/bytes
I.e. need to be unsigned comparison.
Message-Id: <1487683665-23426-1-git-send-email-calle@scylladb.com>

(cherry picked from commit 0d87f3dd7d)
2017-08-24 14:18:55 +01:00
Avi Kivity
cffe57bcc7 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 09:45:54 +03:00
Paweł Dziepak
adb9ce7f38 lsa: avoid unnecessary segment migrations during reclaim
segment_zone::migrate_all_segments() was trying to migrate all segments
inside a zone to the other one hoping that the original one could be
completely freed. This was an attempt to optimise for throughput.

However, this may unnecesairly hurt latency if the zone is large, but
only few segments are required to satisfy reclaimer's demands.
Message-Id: <20170410171912.26821-1-pdziepak@scylladb.com>

(cherry picked from commit 0318dccafd)
2017-08-22 09:29:05 +02:00
Tomasz Grabiec
5f1fd7a0b1 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)
2017-08-17 17:15:12 +02:00
Avi Kivity
d1f06633e0 Update seastar submodule
* seastar a4d924e...949b710 (1):
  > fstream: do not ignore unresolved future

Fixes #2697.
2017-08-16 15:12:45 +03:00
Avi Kivity
b54ea3f6cf dist: use correct repository for third-party RPMs 2017-08-16 11:24:42 +03:00
Avi Kivity
63fd65414a Update seastar submodule
* seastar e5825b5...a4d924e (1):
  > Merge "Fix crash in rpc due to access to already destroyed server socket" from Gleb

Fixes #2690
2017-08-14 16:25:03 +03:00
Avi Kivity
9790c2d229 Update seastar submodule
* seastar 8d9fd92...e5825b5 (1):
  > tls: Only recurse once in shutdown code

Fixes #2691
2017-08-14 15:12:01 +03:00
Raphael S. Carvalho
7728a8dec5 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 09:59:10 +03:00
Duarte Nunes
1fd4a3ed34 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 09:46:33 +03:00
Avi Kivity
0b48863a7e 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 18:13:19 +03:00
Gleb Natapov
aec94b926c 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 17:07:55 +03:00
Tomasz Grabiec
0ac2c388b6 row_cache: Avoid deadlock/timeout due to sstable read concurrency limit
database::make_sstable_reader() creates a reader which will need to
obtain a semaphore permit when invoked, so that there is a limit on
sstable read concurrency (edeef03). Therefore, each read may create at
most one such reader in order to be guaranteed to make
progress. Otherwise, the creation of the second reader may deadlock
(in case of system tables) or timeout (non-system tables), if enough
number of such readers tries to do the same thing at the same time.

One instance of the problem fixed by this patch is in cache populating
reader (98c12dc) when we reach partition size limit
(max_cached_partition_size_in_kb). In that case population is
abandoned and a second read is created, while still keeping the old
one alive. We saw this causing deadlocks during schema tables parsing
when system.schema_columns contained large partitions. Fixes #2623.

Another case when this can potentially happen is when populating
readers are recreated by cache. We replace the reader there, but using
assignment, so the old reader is still alive when the new one is
created. This patch fixes two out of three of such cases. The third
one (in a scanning read) is not that easy to fix. That problem doesn't
exist in version 2.0 and master, where the cache is reworked for row
granularity.

Refs #2644.

Message-Id: <1501160300-18097-1-git-send-email-tgrabiec@scylladb.com>
2017-08-01 12:10:39 +03:00
Takuya ASADA
09ac5b57aa 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 14:22:06 +03:00
Shlomi Livne
ff643e3e40 release: prepare for 1.7.4
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2017-07-26 17:26:33 +03:00
Asias He
a7b8d89de8 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 16:49:11 +03:00
Duarte Nunes
013fa3da14 schema: Calculate default validator
Fixes #2605

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170719105131.21455-3-duarte@scylladb.com>
2017-07-20 10:58:29 +02:00
Duarte Nunes
259cfaf8f9 thrift: Set default validator for static CFs
Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170719105131.21455-2-duarte@scylladb.com>
2017-07-20 10:58:29 +02:00
Duarte Nunes
6501bf8e54 schema_tables: Recover comparator type
Fixes #2573

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170718125450.3727-1-duarte@scylladb.com>
2017-07-19 10:58:43 +02:00
Pekka Enberg
41b4055911 release: prepare for 1.7.3 2017-07-18 17:34:46 +03:00
Nadav Har'El
b594f21f91 Allow reading exactly desired byte ranges and fast_forward_to
Allow reading exactly desired byte ranges and fast_forward_to

In commit c63e88d556, support was added for
fast_forward_to() in data_consume_rows(). Because an input stream's end
cannot be changed after creation, that patch ignores the specified end
byte, and uses the end of file as the end position of the stream.

As result of this, even when we want to read a specific byte range (e.g.,
in the repair code to checksum the partitions in a given range), the code
reads an entire 128K buffer around the end byte, or significantly more, with
read-ahead enabled. This causes repair to do more than 10 times the amount
of I/O it really has to do in the checksumming phase (which in the current
implementation, reads small ranges of partitions at a time).

This patch has two levels:

1. In the lower level, sstable::data_consume_rows(), which reads all
   partitions in a given disk byte range, now gets another byte position,
   "last_end". That can be the range's end, the end of the file, or anything
   in between the two. It opens the disk stream until last_end, which means
   1. we will never read-ahead beyond last_end, and 2. fast_fordward_to() is
   not allowed beyond last_end.

2. In the upper level, we add to the various layers of sstable readers,
   mutation readers, etc., a boolean flag mutation_reader::forwarding, which
   says whether fast_forward_to() is allowed on the stream of mutations to
   move the stream to a different partition range.

   Note that this flag is separate from the existing boolean flag
   streamed_mutation::fowarding - that one talks about skipping inside a
   single partition, while the flag we are adding is about switching the
   partition range being read. Most of the functions that previously
   accepted streamed_mutation::forwarding now accept *also* the option
   mutation_reader::forwarding. The exception are functions which are known
   to read only a single partition, and not support fast_forward_to() a
   different partition range.

   We note that if mutation_reader::forwarding::no is requested, and
   fast_forward_to() is forbidden, there is no point in reading anything
   beyond the range's end, so data_consume_rows() is called with last_end as
   the range's end. But if forwarding::yes is requested, we use the end of the
   file as last_end, exactly like the code before this patch did.

Importantly, we note that the repair's partition reading code,
column_family::make_streaming_reader, uses mutation_reader::forwarding::no,
while the other existing reading code will use the default forwarding::yes.

In the future, we can further optimize the amount of bytes read from disk
by replacing forwarding::yes by an actual last partition that may ever be
read, and use its byte position as the last_end passed to data_consume_rows.
But we don't do this yet, and it's not a regression from the existing code,
which also opened the file input stream until the end of the file, and not
until the end of the range query. Moreover, such an improvement will not
improve of anything if the overall range is always very large, in which
case not over-reading at its end will not improve perforance.

Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Message-Id: <20170718110643.8667-1-nyh@scylladb.com>
2017-07-18 16:54:11 +03:00
Avi Kivity
bcd2e6249f 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 15:47:10 +03:00
Takuya ASADA
4c79add7b0 dist/debian: skip tunables when kernel = 3.13.0-*-generic, to prevent kernel panic bug
There is kernel panic bug on kernel = 3.13.0-*-generic(Ubuntu 14.04), we have to skip tunables.

Fixes #1724

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1493196636-25645-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit abf65cb485)
2017-07-18 15:47:03 +03:00
Asias He
00f6ccb75d 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 13:30:34 +03:00
Avi Kivity
77ac5a63db Update seastar submodule
* seastar fc69677...8d9fd92 (1):
  > rpc: start server's send loop only after protocol negotiation

Fixes #2600.
2017-07-17 10:43:12 +03:00
Pekka Enberg
eb9de1a807 Merge "Repair backport for 1.7 branch" from Asias
"This series backports all the repair related fixes to enterprise branch and
 updates the scylla_repair to send ranges to repair to all the shards in
 parallel, indepedently.

 With this series, repair can utilize all the CPUs and is much more efficent."

* tag 'asias/repair-backport-branch-1.7.3-v1' 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
  repair: further limit parallelism of checksum calculation
  repair: Do not store the failed ranges
  repair: Prefer nodes in local dc when streaming
  repair: Repair on all shards
  repair: Allow one stream plan in flight
2017-07-14 13:02:26 +03:00
Duarte Nunes
643a777067 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 12:12:09 +03:00
Avi Kivity
6f91939650 Update seastar submodule
* seastar 8e2f629...fc69677 (1):
  > tls: Wrap all IO in semaphore (Fixes #2575)
2017-07-12 10:24:04 +03:00
Gleb Natapov
15da71266d 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 17:16:58 +03:00
Botond Dénes
9cd36ade00 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 17:16:01 +03:00
Asias He
6f58a1372e repair: Use selective_token_range_sharder
With this change, we ask all the shard to handle the ranges provided by
user and we use selective_token_range_sharder to split the ranges and
ignore the ranges do not belong to the current shard.

(cherry picked from commit b10e961a64)

 Conflicts:
	repair/repair.cc
2017-07-11 08:40:49 +08:00
Asias He
0a9d26de4a tests: Add test_selective_token_range_sharder
(cherry picked from commit 2a794db61b)
2017-07-11 08:40:49 +08:00
Asias He
35cd63e1f7 dht: Add selective_token_range_sharder
It is like ring_position_range_sharder but it works with
dht::token_range. This sharder will return the ranges belong to a
selected shard.

(cherry picked from commit d835cf2748)
2017-07-11 08:40:49 +08:00
Nadav Har'El
2ada799e07 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)
2017-07-11 08:40:49 +08:00
Asias He
b71037ac55 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)

 Conflicts:
	repair/repair.cc
2017-07-11 08:40:49 +08:00
Asias He
8639f32efd repair: Prefer nodes in local dc when streaming
When peer nodes have the same partition data, i.e., with the same
checksum, we currently choose to stream from any of them randomly.
To improve streaming performance, select the peer within the same DC.
This patch is supposed to improve repair perforamnce with multiple DC.

Message-Id: <c6a345b6e8ed2b59f485e53c865241e463b44507.1498490831.git.asias@scylladb.com>
(cherry picked from commit cc02a62756)
2017-07-11 08:40:48 +08:00
Asias He
a0dce7c922 repair: Repair on all shards
Currently, shard zero is the coordinator of the repair. All the work of
checksuming of the local node and sending of the repair checksum rpc
verb is done on shard zero only. This causes other shards being
underutilized.

With this patch, we split the ranges need to be repaired into at least
smp::count ranges, so sizeof(ranges) / smp::count will be assigned to
each shard. For exmaple, we have 8 shards and 256 ragnes, each shard
will repair 32 ranges. Each shard will repair the 32 ranges
sequencially.  There will be at most 8 (smp::count) ranges of repair in
parallel.

(cherry picked from commit 47345078ec)

Conflicts:
	repair/repair.cc
2017-07-11 08:40:48 +08:00
Asias He
d39ff4f2ac repair: Allow one stream plan in flight
In "repair: Use more stream_plan" (commit 2043ffc064), we
switched to do stream while doing checksum instead of do stream only
after checksum pahse is completed. We take a parallelism_semaphore
before we do checksum, if there are more than sub_ranges_to_stream
(1024) ranges, we start a stream_plan and wait for the streaming to
complete (still under the parallelism_semaphore). So at most
parallelism_semaphore (100) stream_plans can be in parallel.

The parallelism_semaphore limits the parallelism of both checksum and the
streaming plan. However, it is not necessary to have the same
parallelism for both checksum and streaming, because 1) a streaming
operation itself runs in parallel (handling ranges on all shards in
prallel, sending mutaitons in parallel) , 2) and with more streaming plan
(in worse case 100) means we can write to 100 memtables at the same time
and flush 100 memtables to disk at the same time which can take a lot of
memory.

With this patch, we only allow one stream plan in flight.

(cherry picked from commit 54831a344c)
2017-07-11 08:40:48 +08:00
Avi Kivity
7cbfe0711f dist: redirect stdout/stderr to the journal on systemd systems
Fixes #2408.

Message-Id: <20170524080729.10085-1-avi@scylladb.com>
(cherry picked from commit 15af6acc8b)
2017-07-10 19:31:14 +03:00
Glauber Costa
139a2d14a1 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)
2017-07-10 19:25:12 +03:00
Asias He
6fff331698 gossip: Use vector for _live_endpoints
To speed up the random access in get_random_node. Switch to use vector
instead of set.

(cherry picked from commit e31d4a3940)
Message-Id: <fea90eaa5273fac50d0013b3778d9a4f2562e0b7.1499394330.git.asias@scylladb.com>
2017-07-10 14:42:26 +03:00
Asias He
43ae64cd47 gossip: Talk to more live nodes in each gossip round
In large clusters with multiple DC deployment, it is observed that it
takes long delay for gossip update to disseminate in the cluster.

To speed up, talk to more live nodes in each gossip round.

Fixes #2528

(cherry picked from commit 437899909d)
Message-Id: <9bcdaf1fb5637d14a7fda9188ba76ced8f1afaaf.1499394330.git.asias@scylladb.com>
2017-07-10 14:40:40 +03:00
Tomasz Grabiec
f306b47a88 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)
2017-07-10 12:41:33 +03:00
Tomasz Grabiec
47b1e39410 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)
2017-07-10 12:40:43 +03:00
Botond Dénes
0f4d5cde8e 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 18:19:59 +03:00
Avi Kivity
a24dcf1a19 Update seastar submodule
* seastar 18a82e2...8e2f629 (1):
  > future-utils: fix do_for_each exception reporting

Fixes bug during a failed repair.
2017-07-06 17:32:37 +03:00
Raphael S. Carvalho
611c25234e 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 12:49:34 +03:00
Amos Kong
f64e3e24d4 common/scripts: fix node_exporter url
Commit ff3d83bc2f updated node_exporter
from 0.12.0 to 0.14.0, and it introduced a bug to download install file.

node_exporter started to add 'v' prefix in release tags[1] from 0.13.0,
so we need to fix the url.

[1] https://github.com/prometheus/node_exporter/tags

Fixes #2509

Signed-off-by: Amos Kong <amos@scylladb.com>
Message-Id: <42b0a7612539a34034896d404d63a0a31ce79e10.1497919368.git.amos@scylladb.com>
(cherry picked from commit 92731eff4f)
2017-06-22 08:51:35 +03:00
Shlomi Livne
f6034c717d release: prepare 1.7.2
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2017-06-21 22:09:31 +03:00
Amos Kong
b6f4df3cc8 scylla_setup: fix deadloop in inputting invalid option
example: # scylla_setup --invalid-opt

Fixes #2305

Signed-off-by: Amos Kong <amos@scylladb.com>
Message-Id: <9a4f631b126d8eaaae479fa99137db7a61a7c869.1493135357.git.amos@scylladb.com>
(cherry picked from commit f655639e5a)
2017-06-19 22:32:38 +03:00
Amnon Heiman
af028360d7 node_exporter_install script update version to 0.14
Fixes #2097

Signed-off-by: Amnon Heiman <amnon@scylladb.com>
Message-Id: <20170612125724.7287-1-amnon@scylladb.com>
(cherry picked from commit ff3d83bc2f)
2017-06-18 12:28:19 +03:00
Duarte Nunes
60af7eab10 udt: Don't check a type is unused after applying the schema mutations
This patch is based on 6c8b5fc. It moves the check whether a dropped
type is still used by other types or tables from schema_tables to
the drop_type_statement, as delaying this check to after applying the
mutations can leave the keyspace in a broken state.

Fixes #2490

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <1497466736-28841-1-git-send-email-duarte@scylladb.com>
2017-06-15 10:35:01 +03:00
Calle Wilund
665d14584c database: Fix assert in truncate to handle empty memtables+sstables
If we do two truncates in a row, the second will have neither memtable
nor sstable data. Thus we will not write/remove sstables, and thus
get no resulting truncation replay position.

Fixes #2489

Message-Id: <1497378469-6063-1-git-send-email-calle@scylladb.com>

(cherry picked from commit 525730e135)
2017-06-14 16:25:57 +03:00
Gleb Natapov
bb56e7682c Fix use after free in nonwrapping_range::intersection
end_bound() returns temporary object (end_bound_ref), so it cannot be
taken by reference here and used later. Copy instead.

Message-Id: <20170612132328.GJ21915@scylladb.com>

(cherry picked from commit 21197981a)

Fixes #2482
2017-06-14 12:08:06 +01:00
Avi Kivity
a4bd56ce40 tests: fix partitioner_test build on gcc 5 2017-06-13 21:56:02 +03:00
Calle Wilund
6340fe61af commitlog_test: Fix test_commitlog_delete_when_over_disk_limit
Test should
a.) Wait for the flush semaphore
b.) Only compare segement sets between start and end, not start,
    end and inbetwen. I.e. the test sort of assumed we started
    with < 2 (or so) segments. Not always the case (timing)

Message-Id: <1496828317-14375-1-git-send-email-calle@scylladb.com>
(cherry picked from commit 0c598e5645)
2017-06-13 19:53:13 +03:00
Asias He
f2317a6f3f repair: Fix range use after free
Capture it by value.

scylla:  [shard 0] repair - repair's stream failed: streaming::stream_exception (Stream failed)
scylla:  [shard 0] repair - Failed sync of range ==<runtime_exception
(runtime error: Invalid token. Should have size 8, has size 0#012)>: streaming::stream_exception (Stream failed)

Message-Id: <7fda4432e54365f64b556e7e4c26e36d3a9bb1b7.1497238229.git.asias@scylladb.com>
(cherry picked from commit 2bcb368a13)
2017-06-13 11:03:14 +03:00
Paweł Dziepak
7bb41b50f9 commitlog: avoid copying column_mapping
It is safe to copy column_mapping accros shards. Such guarantee comes at
the cost of performance.

This patch makes commitlog_entry_writer use IDL generated writer to
serialise commitlog_entry so that column_mapping is not copied. This
also simplifies commitlog_entry itself.

Performance difference tested with:
perf_simple_query -c4 --write --duration 60
(medians)
          before       after      diff
write   79434.35    89247.54    +12.3%

(cherry picked from commit 374c8a56ac)

Also: Fixes #2468.
2017-06-11 15:44:20 +03:00
Paweł Dziepak
57d602fdd6 idl: fix generated writers when member functions are used
When using member name in an idetifer of generated class or method
idl compiler should strip the trailing '()'.

(cherry picked from commit 4df4994b71)

(part of #2468)
2017-06-11 15:43:53 +03:00
Paweł Dziepak
cd14b83192 idl: add start_frame() overload for seastar::simple_output_stream
(cherry picked from commit 018d16d315)

(part of #2468)
2017-06-11 15:43:11 +03:00
Avi Kivity
a85b70d846 Merge "repair memory usage fix" from Asias
"This series switches repair to use more stream plans to stream the mismatched
sub ranges and use a range generator to produce sub ranges.

Test shows no huge memory is used for repair with large data set.

In addition, we now have a progress reporter in the log how many ranges are processed.

   Jun 06 14:18:22  [shard 0] repair - Repair 512 out of 529 ranges, id=1, keyspace=myks, cf=mytable, range=(8526136029525195375, 8549482295083869942]
   Jun 06 14:19:55  [shard 0] repair - Repair 513 out of 529 ranges, id=1, keyspace=myks, cf=mytable, range=(8526136029525195375, 8549482295083869942]

Fixes #2430."

* tag 'asias/fix-repair-2430-branch-master-v1' of github.com:cloudius-systems/seastar-dev:
  repair: Remove unused sub_ranges_max
  repair: Reduce parallelism in repair_ranges
  repair: Tweak the log a bit
  repair: Use more stream_plan
  repair: iterator over subranges instead of list

(cherry picked from commit 419ad9d6cb)
2017-06-08 14:52:28 +03:00
Avi Kivity
f44ea5335b Update seastar submodule
* seastar 812e232...18a82e2 (1):
  > scripts: posix_net_conf.sh: fix bash syntax causing a failure during bonding iface configuration

Fixes #2269
2017-06-07 18:23:02 +03:00
Pekka Enberg
a95c045b48 Merge "Fixes to thrift/server" from Duarte
"This series fixes some issues with the thrift_server, namely
ensuring that streams and sockets are properly closed.

Fixes #499
Fixes #2437"

* 'thrift-server-fixes/v1' of github.com:duarten/scylla:
  thrift/server: Close connections when stopping server
  thrift/server: Move connection class to header
  thrift/server: Shutdown connection
  thrift/server: Close output_stream when connection is done

(cherry picked from commit a6dc21615b)
2017-06-07 16:08:28 +03:00
Avi Kivity
eb396d2795 Update seastar submodule
* seastar 328fdbc...812e232 (1):
  > rpc: handle messages larger than memory limit

Fixes #2453.
2017-06-07 12:29:59 +03:00
Takuya ASADA
dbbf99d7fa dist/debian: install gdebi when it's not exist
Since we started to use gdebi for install build-dep metapackage that generated by
mk-build-dep, we need to install gdebi on build_deb.sh too.

Fixes #2451

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1496819209-30318-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 7fe63c539a)
2017-06-07 10:25:02 +03:00
Raphael S. Carvalho
f7a143e7be sstables: fix report of disk space used by bloom filter
After change in boot, read_filter is called by distributed loader,
so its update to _filter_file_size is lost. The load variant
which receives foreign components that must do it. We were also
not updating it for newly created sstables.

Fixes #2449.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20170606151129.5477-1-raphaelsc@scylladb.com>
(cherry picked from commit 0ca1e5cca3)
2017-06-06 19:00:00 +03:00
Takuya ASADA
562102cc76 dist/debian: use gdebi instead of mk-build-deps -i
At least on Debian8, mk-build-deps -i silently finishes with return code 0
even it fails to install dependencies.
To prevent this, we should manually install the metapackage generated by
mk-build-deps using gdebi.

Fixes #2445

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1496737502-10737-2-git-send-email-syuu@scylladb.com>
(cherry picked from commit a4c392c113)
2017-06-06 14:18:14 +03:00
Takuya ASADA
d4b444418a dist/debian/dep: install texlive from jessie-backports to prevent gdb build fail on jessie
Installing openjdk-8-jre-headless from jessie-backports breaks texlive on
jessie main repo.
It causes 'Unmet build dependencies' error when building gdb package.
To prevent this, force insatlling texlive from jessie-backports before start
building gdb.

Fixes #2444

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1496737502-10737-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 5608842e96)
2017-06-06 14:18:08 +03:00
Raphael S. Carvalho
befd4c9819 db: fix computation of live disk usage stat after compaction
sstable::data_size() is used by rebuild_statistics() which only
returns uncompressed data size, and the function called by it
expects actual disk space used by all components.
Boot uses add_sstable() which correctly updates the stat with
sstable::bytes_on_disk(). That's what needs to be used by
r__s() too.

Fixes #1592

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20170525210055.6391-1-raphaelsc@scylladb.com>
(cherry picked from commit 3b5ad23532)
2017-05-28 10:39:14 +03:00
Avi Kivity
eb2fe0fbd3 Merge "reduce memory requirement for loading sstables" from Rapahel
"fixes a problem in which memory requirement for loading in-memory
components of sstables is very high due to unlimited parallelism."

* 'mem_requirement_sstable_load_v2_2' of github.com:raphaelsc/scylla:
  database: fix indentation of distributed_loader::open_sstable
  database: reduce memory requirement to load sstables
  sstables: loads components for a sstable in parallel
  sstables: enable read ahead for read of in-memory components
  sstables: make random_access_reader work with read ahead

(cherry picked from commit ef428d008c)
2017-05-25 12:59:55 +03:00
Raphael S. Carvalho
eb6b0b1267 db: remove partial sstable created by memtable flush which failed
partial sstable files aren't being removed after each failed attempt
to flush memtable, which happens periodically. If the cause of the
failure is ENOSPC, memtable flush will be attempted forever, and
as a result, column family may be left with a huge amount of partial
files which will overwhelm subsequent boot when removing temporary
TOC. In the past, it led to OOM because removal of temporary TOC
took place in parallel.

Fixes #2407.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20170525015455.23776-1-raphaelsc@scylladb.com>
(cherry picked from commit b7e1575ad4)
2017-05-25 11:50:17 +03:00
Asias He
7836600ded streaming: Do not abort session too early in idle detection
Streaming ususally takes long time to complete. Abort it on false
positive idle detection can be very wasteful.

Increase the abort timeout from 10 minutes to a very large timeout, 300
minutes. The real idle session will be aborted eventually if other
mechanisms, e.g., streaming manager has gossip callback for on_remove
and on_restart event to abort, do not abort the session.

Fixes #2197

Message-Id: <57f81bfebfdc6f42164de5a84733097c001b394e.1494552921.git.asias@scylladb.com>
(cherry picked from commit f792c78c96)
2017-05-24 12:30:47 +03:00
Shlomi Livne
230c33da49 release: prepare for 1.7.1
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2017-05-23 22:42:52 +03:00
Raphael S. Carvalho
17d8a0c727 compaction: do not write expired cell as dead cell if it can be purged right away
When compacting a fully expired sstable, we're not allowing that sstable
to be purged because expired cell is *unconditionally* converted into a
dead cell. Why not check if the expired cell can be purged instead using
gc before and max purgeable timestamp?

Currently, we need two compactions to get rid of a fully expired sstable
which cells could have always been purged.

look at this sstable with expired cell:
  {
    "partition" : {
      "key" : [ "2" ],
      "position" : 0
    },
    "rows" : [
      {
        "type" : "row",
        "position" : 120,
        "liveness_info" : { "tstamp" : "2017-04-09T17:07:12.702597Z",
"ttl" : 20, "expires_at" : "2017-04-09T17:07:32Z", "expired" : true },
        "cells" : [
          { "name" : "country", "value" : "1" },
        ]

now this sstable data after first compaction:
[shard 0] compaction - Compacted 1 sstables to [...]. 120 bytes to 79
(~65% of original) in 229ms = 0.000328997MB/s.

  {
    ...
    "rows" : [
      {
        "type" : "row",
        "position" : 79,
        "cells" : [
          { "name" : "country", "deletion_info" :
{ "local_delete_time" : "2017-04-09T17:07:12Z" },
            "tstamp" : "2017-04-09T17:07:12.702597Z"
          },
        ]

now another compaction will actually get rid of data:
compaction - Compacted 1 sstables to []. 79 bytes to 0 (~0% of original)
in 1ms = 0MB/s. ~2 total partitions merged to 0

NOTE:
It's a waste of time to wait for second compaction because the expired
cell could have been purged at first compaction because it satisfied
gc_before and max purgeable timestamp.

Fixes #2249, #2253

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20170413001049.9663-1-raphaelsc@scylladb.com>
(cherry picked from commit a6f8f4fe24)
2017-05-23 20:57:54 +03:00
Tomasz Grabiec
064de6f8de row_cache: Fix undefined behavior in read_wide()
_underlying is created with _range, which is captured by
reference. But range_and_underlyig_reader is moved after being
constructed by do_with(), so _range reference is invalidated.

Fixes #2377.
Message-Id: <1494492025-18091-1-git-send-email-tgrabiec@scylladb.com>

(cherry picked from commit 0351ab8bc6)
2017-05-21 19:09:03 +03:00
Gleb Natapov
df56c108b7 database: remove temporary sstables sequentially
The code that removes each sstable runs in a thread. Parallel
removing of a lot of sstables may start a lot of threads each of which
is taking 128k for its stack. There is no much benefit in running
deletion in parallel anyway, so fix it by deleting sstables sequentially.

Fixes #2384

Message-Id: <20170516103018.GQ3874@scylladb.com>
(cherry picked from commit c7ad3b9959)
2017-05-21 18:56:22 +03:00
Tomasz Grabiec
25607ab9df range: Fix SFINAE rule for picking the best do_lower_bound()/do_upper_bound() overload
mutation_partition has a slicing constructor which is supposed to copy
only the rows from the query range. The rows are located using
nonwrapping_range::lower_bound() and
nonwrapping_range::lower_bound(). Those two have two different
implementations chosen with SFINAE. One is using std::lower_bound(),
and one is using container's built in lower_bound() should it
exist. We're using intrusive tree in mutation_partition, so
container's lower_bound() is preferred. It's O(log N) whereas
std::lower_bound() is O(N), because tree's iterator is not random
access.

However, the current rule for picking container's lower_bound() never
triggers, because lower_bound() has two overloads in the container:

  ./range.hh:618:14: error: decltype cannot resolve address of overloaded function
              typename = decltype(&std::remove_reference<Range>::type::upper_bound)>
              ^~~~~~~~

As a result, the overload which uses std::lower_bound() is used.

Spotted when running perf_fast_forward with wide partition limit in
cache lifted off. It's so slow that I timeouted waiting for the result
(> 16 min).

Fixes #2395.

Message-Id: <1495048614-9913-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 3fc1703ccf)
2017-05-18 17:12:00 +03:00
Avi Kivity
b26bd8bbeb tests: fix partitioner_test for g++ 5
It can't make the leap from dht::ring_position to
stdx::optional<range_bound<dht::ring_position>> for some reason.

(cherry picked from commit ba31619594)
2017-05-18 13:10:48 +03:00
Avi Kivity
1ca7f5458b Update seastar submodule
> tls: make shutdown/close do "clean" handshake shutdown in background
  > tls: Make sink/source (i.e. streams) first class channel owners
  > native-stack: Make sink/source (i.e. streams) first class channel owners

More close() fixes, pointed out by Tomek.
2017-05-17 19:01:44 +03:00
Calle Wilund
50c8a08e91 scylla: fix compilation errors on gcc 5
Message-Id: <1495030581-2138-1-git-send-email-calle@scylladb.com>
(cherry picked from commit 6ca07f16c1)
2017-05-17 18:04:58 +03:00
Avi Kivity
9d1b9084ed Update seastar submodule
* seastar bfa1cb2...774c09c (1):
  > posix-stack: Make sink/source (i.e. streams) first class channel owners
2017-05-17 16:44:34 +03:00
Tomasz Grabiec
e2c75d8532 Merge "Fix performance problems with high shard counts tag" from Avi
From http://github.com/avikivity/scylla exponential-sharder/v3.

The sharder, which takes a range of tokens and splits it among shards, is
slow with large shard count and the default
murmur3_partitioner_ignore_msb_bits.

This patchset fixes excessive iteration in sstable sharding metadata writer and
nonsignular range scans.

Without this patchset, sealing a memtable takes > 60 ms on a 48-shard
system.  With the patchset, it drops below the latency tracker threshold I
used (5 ms).

Fixes #2392.

(cherry picked from commit 84648f73ef)
2017-05-17 16:19:24 +03:00
Duarte Nunes
59063f4891 tests: Add test case for nonwrapping_range::intersection()
Signed-off-by: Duarte Nunes <duarte@scylladb.com>
(cherry picked from commit f365b7f1f7)
2017-05-17 15:59:06 +03:00
Duarte Nunes
de79792373 nonwrapping_range: Add intersection() function
intersection() returns an optional range with the intersection of the
this range and the other, specified range.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
(cherry picked from commit 1f9359efba)
2017-05-17 15:58:55 +03:00
Avi Kivity
3557b449ac Merge "Adding private repository to housekeeping" from Amnon
"This series adds private repository support to scylla-housekeeping"

* 'amnon/housekeeping_private_repo_v3' of github.com:cloudius-systems/seastar-dev:
  scylla-housekeeping service: Support private repositories
  scylla-housekeeping-upstart: Use repository id, when checking for version
  scylla-housekeeping: support private repositories

(cherry picked from commit eb69fe78a4)
2017-05-17 15:58:29 +03:00
Pekka Enberg
a8e89d624a cql3: Fix variable_specifications class get_partition_key_bind_indexes()
The "_specs" array contains column specifications that have the bind
marker name if there is one. That results in
get_partition_key_bind_indices() not being able to look up a column
definition for such columns. Fix the issue by keeping track of the
actual column specifications passed to add() like Cassandra does.

Fixes #2369

(cherry picked from commit a45e656efb4c6478d80e4dfc18de99b94712eeba)
2017-05-10 10:00:47 +03:00
Pekka Enberg
31cd6914a8 cql3: Move variable_specifications implementation to source file
Move the class implementation to source file to reduce the need to
recompile everything when the implementation changes...

Message-Id: <1494312003-8428-1-git-send-email-penberg@scylladb.com>
(cherry picked from commit 5b931268d4)
2017-05-10 10:00:31 +03:00
Pekka Enberg
a441f889c3 cql3: Fix partition key bind indices for prepared statements
Fix the CQL front-end to populate the partition key bind index array in
result message prepared metadata, which is needed for CQL binary
protocol v4 to function correctly.

Fixes #2355.

(cherry picked from commit ebd76617276e660c590cec0a07e97e82422111df)

Tested-by: Shlomi Livne <shlomi@scylladb.com>
Message-Id: <1494257274-1189-1-git-send-email-penberg@scylladb.com>
2017-05-10 10:00:21 +03:00
Pekka Enberg
91b7cb8576 Merge "gossip mark alive fixes" from Asias
"This series fixes the user after free issue in gossip and elimates the
duplicated / unnecessary mark alive operations.

Fixes #2341"

* tag 'asias/gossip_fix_mark_alive/v1' of github.com:cloudius-systems/seastar-dev:
  gossip: Ignore callbacks and mark alive operation in shadow round
  gossip: Ingore the duplicated mark alive operation
  gossip: Fix user after free in mark_alive

(cherry picked from commit 1e04731fa0)
2017-05-09 01:57:23 +03:00
Avi Kivity
2b17c4aacf Merge "Fix update of counter in static rows" from Paweł
"The logic responsible for converting counter updates to counter shards was
not covered by unit tests and didn't transform counter cells inside static
rows.

This series fixes the problem and makes sure that the tests cover both
static rows and transformation logic.

Fixes #2334."

* tag 'pdziepak/static-counter-updates-1.7/v1' of github.com:cloudius-systems/seastar-dev:
  tests/counter: test transform_counter_updates_to_shards
  tests/counter: test static columns
  counters: transform static rows from updates to shards
2017-05-06 15:54:20 +03:00
Pekka Enberg
f61d9ac632 release: prepare for 1.7.0 2017-05-04 15:28:28 +03:00
Asias He
fc9db8bb03 repair: Fix partition estimation
We estimate number of partitions for a given range of a column familiy
and split the range into sub ranges contains fewer partitions as a
checksum unit.

The estimation is wrong, because we need to count the partitions on all
the shards, instead of only counting the local shard.

Fixes #2299

Message-Id: <7876285bd26cfaf65563d6e03ec541626814118a.1493817339.git.asias@scylladb.com>
(cherry picked from commit 66e3b73b9c)
2017-05-03 16:26:01 +03:00
Paweł Dziepak
bd67d23927 tests/counter: test transform_counter_updates_to_shards 2017-05-02 13:49:43 +01:00
Paweł Dziepak
bdeeebbd74 tests/counter: test static columns 2017-05-02 13:49:43 +01:00
Paweł Dziepak
a1cb29e7ec counters: transform static rows from updates to shards 2017-05-02 13:49:43 +01:00
Amnon Heiman
e8369644fd scylla_setup: Fix conditional when checking for newer version
During the changes in the way the housekeeping check for newer version
and warn about it in the installation the UUID part was removed but kept
in the sarounding if.

Signed-off-by: Amnon Heiman <amnon@scylladb.com>
Message-Id: <20170426075724.7132-1-amnon@scylladb.com>
(cherry picked from commit b59c95359d)
2017-05-01 12:14:04 +03:00
Glauber Costa
a36cabdb30 reduce kernel scheduler wakeup granularity
We set the scheduler wakeup granularity to 500usec, because that is the
difference in runtime we want to see from a waking task before it
preempts the running task (which will usually be Scylla). Scheduling
other processes less often is usually good for Scylla, but in this case,
one of the "other processes" is also a Scylla thread, the one we have
been using for marking ticks after we have abandoned signals.

However, there is an artifact from the Linux scheduler that causes those
preemption to be missed if the wakeup granularity is exactly twice as
small as the sched_latency. Our sched_latency is set to 1ms, which
represents the maximum time period in which we will run all runnable
tasks.

We want to keep the sched_latency at 1ms, so we will reduce the wakeup
granularity so to something slightly lower than 500usec, to make sure
that such artifact won't affect the scheduler calculations. 499.99usec
will do - according to my tests, but we will reduce it to a round
number.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
Message-Id: <20170427135039.8350-1-glauber@scylladb.com>
(cherry picked from commit 14b9aa2285)
2017-05-01 11:13:51 +03:00
Raphael S. Carvalho
1d26fab73e sstables: add method to export ancestors
Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
2017-05-01 11:09:42 +03:00
Shlomi Livne
5f0c635da7 release: prepare for 1.7.rc3
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2017-05-01 09:53:20 +03:00
Raphael S. Carvalho
82cc3d7aa5 dtcs: do not compact fully expired sstable which ancestor is not deleted yet
Currently, fully expired sstable[1] is unconditionally chosen for compaction
by DTCS, but that may lead to a compaction loop under certain conditions.

Let's consider that an almost expired sstable is compacted, and it's not
deleted yet, and that the new sstable becomes expired before its ancestor is
deleted.
Because this new sstable is expired, it will be chosen by DTCS, but it will
not be purged because 'compacted undeleted' sstables are taken into account
by calculation of max purgeable timestamp and prevents expired data from
being purged. The problem is that this sequence of events can keep happening
forever as reported by issue #2260.
NOTE: This problem was easier to reproduce before improvement on compaction
of expired cells, because fully expired sstable was being converted into a
sstable full of tombstones, which is also considered fully expired.

Fixes #2260.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20170428233554.13744-1-raphaelsc@scylladb.com>
(cherry picked from commit 687a4bb0c2)
2017-04-30 19:36:00 +03:00
Paweł Dziepak
98d782cfe1 db: make virtual dirty soft limit configurable
Message-Id: <20170428150005.28454-1-pdziepak@scylladb.com>
(cherry picked from commit 24f4dcf9e4)
2017-04-30 19:17:55 +03:00
Avi Kivity
ea0591ad3d Merge "] Fix problems with slicing using sstable's promoted index" from Tomasz
"Fixes #2327.
Fixes #2326."

* 'tgrabiec/fix-promoted-index-parsing-1.7' of github.com:cloudius-systems/seastar-dev:
  sstables: Fix incorrect parsing of cell names in promoted index
  sstables: Fix find_disk_ranges() to not miss relevant range tombstones
2017-04-30 14:48:54 +03:00
Paweł Dziepak
7eedd743bf lsa: introduce upper bound on zone size
Attempting to create huge zones may introduce significant latency. This
patch introduces the maximum allowed zone size so that the time spent
trying to allocate and initialising zone is bounded.

Fixes #2335.

Message-Id: <20170428145916.28093-1-pdziepak@scylladb.com>
(cherry picked from commit f5cf86484e)
2017-04-30 10:58:34 +03:00
Tomasz Grabiec
8a21961ec9 sstables: Fix incorrect parsing of cell names in promoted index
Range tombstones are serialized to cell names in this place:

  _sst.maybe_flush_pi_block(_out, start, {});

Note that the column set is empty. This is correct. A range tombstone
only has a clustering part. The cell name is deserialized by promoted
index reader using mp_row_consumer::column, like this:

   mp_row_consumer::column col(schema, std::move(col_name),
      api::max_timestamp); return std::move(col.clustering);

The problem is, column constructor assumes that there is always a
component corresponding to a cell name if the table is not dense, and
will pop it from the set of components (the clustering field):

  , cell(!schema.is_dense() ? pop_back(clustering) : (*(schema.regular_begin())).name())

promoted index block which starts or ends with a range tombstone will
appear as having incorrect bounds. This may result in an incorrect
value for data file range start to be calculated.

Fixes #2327.
2017-04-27 18:30:00 +02:00
Tomasz Grabiec
08698d9030 sstables: Fix find_disk_ranges() to not miss relevant range tombstones
Suppose the promoted index looks like this:

block0: start=1 end=2
block1: start=4 end=5

start and end are cell names of the first and last cell in the block.

If there is a range tombstone covering [2,3], it will be only in
block0, because it is no longer in effect when block1 starts. However,
slicing the index for [3, +inf], which intersects with the tombstone,
will yield block1. That's because the slicing looks for a block with
an end which is greater than or equal to the start of the slice:

 if (!found_range_start) {
    if (!range_start || cmp(range_start->value(), end_ck) <= 0) {
       range_start_pos = ie.position() + offset;

We should take into account that any given block may actually contain
information for anything up to the start of the next block, so instead
of using end_ck, effectively use next block's start_ck (exclusive).

Fixes #2326.
2017-04-27 18:30:00 +02:00
Tomasz Grabiec
df5a291c63 sstables: Fix usage of wrong comparator in find_disk_ranges()
This made a difference if clustering restriction bounds were not full
keys but prefixes.

Fixes #2272.

Message-Id: <1493058357-24156-1-git-send-email-tgrabiec@scylladb.com>
2017-04-24 21:56:07 +03:00
Avi Kivity
1a77312aec Merge "Reduce memory reclamation latency" from Tomasz
"Currently eviction is performed until occupancy of the whole region
drops below the 85% threshold. This may take a while if region had
high occupancy and is large. We could improve the situation by only
evicting until occupancy of the sparsest segment drops below the
threshold, as is done by this change.

I tested this using a c-s read workload in which the condition
triggers in the cache region, with 1G per shard:

 lsa-timing - Reclamation cycle took 12.934 us.
 lsa-timing - Reclamation cycle took 47.771 us.
 lsa-timing - Reclamation cycle took 125.946 us.
 lsa-timing - Reclamation cycle took 144356 us.
 lsa-timing - Reclamation cycle took 655.765 us.
 lsa-timing - Reclamation cycle took 693.418 us.
 lsa-timing - Reclamation cycle took 509.869 us.
 lsa-timing - Reclamation cycle took 1139.15 us.

The 144ms pause is when large eviction is necessary.

Statistics for reclamation pauses for a read workload over
larger-than-memory data set:

Before:

 avg = 865.796362
 stdev = 10253.498038
 min = 93.891000
 max = 264078.000000
 sum = 574022.988000
 samples = 663

After:

 avg = 513.685650
 stdev = 275.270157
 min = 212.286000
 max = 1089.670000
 sum = 340573.586000
 samples = 663

Refs #1634."

* tag 'tgrabiec/lsa-reduce-reclaim-latency-v3' of github.com:cloudius-systems/seastar-dev:
  lsa: Reduce reclamation latency
  tests: Add test for log_histogram
  log_histogram: Allow non-power-of-two minimum values
  lsa: Use regular compaction threshold in on-idle compaction
  tests: row_cache_test: Induce update failure more reliably
  lsa: Add getter for region's eviction function

(cherry picked from commit fccbf2c51f)

[avi: adjustments for 1.7's heap vs. master's log_histogram]
2017-04-21 22:12:52 +03:00
Duarte Nunes
ea684c9a3e alter_type_statement: Fix signed to unsigned conversion
This could allow us to alter a non-existing field of an UDT.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20170419114254.5582-1-duarte@scylladb.com>
(cherry picked from commit e06bafdc6c)
2017-04-19 14:48:27 +03:00
Raphael S. Carvalho
2df7c80c66 compaction_manager: fix crash when dropping a resharding column family
Problem is that column family field of task wasn't being set for resharding,
so column family wasn't being properly removed from compaction manager.
In addition to fixing this issue, we'll also interrupt ongoing compactions
when dropping a column family, exactly like we do with shutdown.

Fixes #2291.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20170418125807.7712-1-raphaelsc@scylladb.com>
(cherry picked from commit e78db43b79)
2017-04-18 17:40:09 +03:00
Raphael S. Carvalho
193b5d1782 partitioned_sstable_set: fix quadratic space complexity
streaming generates lots of small sstables with large token range,
which triggers O(N^2) in space in interval map.
level 0 sstables will now be stored in a structure that has O(N)
in space complexity and which will be included for every read.

Fixes #2287.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20170417185509.6633-1-raphaelsc@scylladb.com>
(cherry picked from commit 11b74050a1)
2017-04-18 13:05:00 +03:00
Asias He
6609c9accb gossip: Fix possible use-after-free of entry in endpoint_state_map
We take a reference of endpoint_state entry in endpoint_state_map. We
access it again after code which defers, the reference can be invalid
after the defer if someone deletes the entry during the defer.

Fix this by checking take the reference again after the defering code.

I also audited the code to remove unsafe reference to endpoint_state_map entry
as much as possible.

Fixes the following SIGSEGV:

Core was generated by `/usr/bin/scylla --log-to-syslog 1 --log-to-stdout
0 --default-log-level info --'.
Program terminated with signal SIGSEGV, Segmentation fault.
(this=<optimized out>) at /usr/include/c++/5/bits/stl_pair.h:127
127     in /usr/include/c++/5/bits/stl_pair.h
[Current thread is 1 (Thread 0x7f1448f39bc0 (LWP 107308))]

Fixes #2271

Message-Id: <529ec8ede6da884e844bc81d408b93044610afd2.1491960061.git.asias@scylladb.com>
(cherry picked from commit d27b47595b)
2017-04-13 13:18:41 +03:00
Pekka Enberg
2f107d3f61 Update seastar submodule
* seastar 211ab4a...bfa1cb2 (1):
  > resource: reduce default_reserve_memory size to fit low memory environment

Fixes #2186
2017-04-12 08:41:40 +03:00
Takuya ASADA
dd9afa4c93 dist/debian/debian/scylla-server.upstart: export SCYLLA_CONF, SCYLLA_HOME
We are sourcing sysconfig file on upstart, but forgot to load them as
environment variables.
So export them.

Fixes #2236

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1491209505-32293-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit b087616a6c)
2017-04-04 11:00:33 +03:00
Pekka Enberg
4021e2befb Update seastar submodule
* seastar f391f9e...211ab4a (1):
  > http: catch and count errors in read and respond

Fixes #2242
2017-04-03 12:02:43 +03:00
Calle Wilund
9b26a57288 commitlog/replayer: Bugfix: minimum rp broken, and cl reader offset too
The previous fix removed the additional insertion of "min rp" per source
shard based on whether we had processed existing CF:s or not (i.e. if
a CF does not exist as sstable at all, we must tag it as zero-rp, and
make whole shard for it start at same zero.

This is bad in itself, because it can cause data loss. It does not cause
crashing however. But it did uncover another, old old lingering bug,
namely the commitlog reader initiating its stream wrongly when reading
from an actual offset (i.e. not processing the whole file).
We opened the file stream from the file offset, then tried
to read the file header and magic number from there -> boom, error.

Also, rp-to-file mapping was potentially suboptimal due to using
bucket iterator instead of actual range.

I.e. three fixes:
* Reinstate min position guarding for unencoutered CF:s
* Fix stream creating in CL reader
* Fix segment map iterator use.

v2:
* Fix typo
Message-Id: <1490611637-12220-1-git-send-email-calle@scylladb.com>

(cherry picked from commit b12b65db92)
2017-03-28 10:35:04 +02:00
Pekka Enberg
31b5ef13c2 release: prepare for 1.7.rc2 2017-03-23 13:22:59 +02:00
Takuya ASADA
4bbee01288 dist/common/scripts/scylla_raid_setup: don't discard blocks at mkfs time
Discarding blocks on large RAID volume takes too much time, user may suspects
the script doesn't works correctly, so it's better to skip, do discard directly on each volume instead.

Fixes #1896

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1489533460-30127-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit b65d58e90e)
2017-03-23 09:42:51 +02:00
Calle Wilund
3cc03f88fd commitlog_replayer: Do proper const-loopup of min positions for shards
Fixes #2173

Per-shard min positions can be unset if we never collected any
sstable/truncation info for it, yet replay segments of that id.

Wrap the lookups to handle "missing data -> default", which should have been
there in the first place.

Message-Id: <1490185101-12482-1-git-send-email-calle@scylladb.com>
(cherry picked from commit c3a510a08d)
2017-03-22 17:57:30 +02:00
Vlad Zolotarov
4179d8f7c4 Don't report a Tracing session ID unless the current query had a Tracing bit in its flags
Although the current master's behaviour is legal it's suboptimal and some Clients are sensitive to that.
Let's fix that.

Fixes #2179

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
Message-Id: <1490115157-4657-1-git-send-email-vladz@scylladb.com>
2017-03-22 14:55:39 +02:00
Pekka Enberg
c20ddaf5af dist/docker: Use Scylla 1.7 RPM repository 2017-03-21 15:07:27 +02:00
Pekka Enberg
29dd48621b dist/docker: Expose Prometheus port by default
This patch exposes Scylla's Prometheus port by default. You can now use
the Scylla Monitoring project with the Docker image:

  https://github.com/scylladb/scylla-grafana-monitoring

To configure the IP addresses, use the 'docker inspect' command to
determine Scylla's IP address (assuming your running container is called
'some-scylla'):

  docker inspect --format='{{ .NetworkSettings.IPAddress }}' some-scylla

and then use that IP address in the prometheus/scylla_servers.yml
configuration file.

Fixes #1827

Message-Id: <1490008357-19627-1-git-send-email-penberg@scylladb.com>
(cherry picked from commit 85a127bc78)
2017-03-20 15:30:15 +02:00
Amos Kong
87de77a5ea scylla_setup: match '-p' option of lsblk with strict pattern
On Ubuntu 14.04, the lsblk doesn't have '-p' option, but
`scylla_setup` try to get block list by `lsblk -pnr` and
trigger error.

Current simple pattern will match all help content, it might
match wrong options.
  scylla-test@amos-ubuntu-1404:~$ lsblk --help | grep -e -p
   -m, --perms          output info about permissions
   -P, --pairs          use key="value" output format

Let's use strict pattern to only match option at the head. Example:
  scylla-test@amos-ubuntu-1404:~$ lsblk --help | grep -e '^\s*-D'
   -D, --discard        print discard capabilities

Signed-off-by: Amos Kong <amos@scylladb.com>
Message-Id: <4f0f318353a43664e27da8a66855f5831457f061.1489712867.git.amos@scylladb.com>
(cherry picked from commit 468df7dd5f)
2017-03-20 08:11:57 +02:00
Raphael S. Carvalho
66c4dcba8e database: serialize sstable cleanup
We're cleaning up sstables in parallel. That means cleanup may need
almost twice the disk space used by all sstables being cleaned up,
if almost all sstables need cleanup and every one will discard an
insignificant portion of its whole data.
Given that cleanup is frequently issued when node is running out of
disk space, we should serialize cleanups in every shard to decrease
the disk space requirement.

Fixes #192.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20170317022911.10306-1-raphaelsc@scylladb.com>
(cherry picked from commit 7deeffc953)
2017-03-19 17:16:33 +02:00
Pekka Enberg
7cfdc08af9 cql3: Wire up functions for floating-point types
Fixes #2168
Message-Id: <1489661748-13924-1-git-send-email-penberg@scylladb.com>

(cherry picked from commit 3afd7f39b5)
2017-03-17 11:14:51 +02:00
Pekka Enberg
fdbe5caf41 Update scylla-ami submodule
* dist/ami/files/scylla-ami eedd12f...407e8f3 (1):
  > scylla_create_devices: check block device is exists

Fixes #2171
2017-03-17 11:14:17 +02:00
Tomasz Grabiec
522e62089b lsa: Fix debug-mode compilation error
By moving definitions of setters out of #ifdef

(cherry picked from commit 3609665b19)
2017-03-16 18:24:27 +01:00
Avi Kivity
699648d5a1 Merge "tests: Use allocating_section in lsa_async_eviction_test" from Tomasz
"The test allocates objects in batches (allocation is always under a reclaim
lock) of ~3MiB and assumes that it will always succeed because if we cross the
low water mark for free memory (20MiB) in seastar, reclamation will be
performed between the batches, asynchronously.

Unfortunately that's prevented by can_allocate_more_memory(), which fails
segment allocation when we're below the low water mark. LSA currently doesn't
allow allocating below the low water mark.

The solution which is employed across the code base is to use allocating_section,
so use it here as well.

Exposed by recent consistent failures on branch-1.7."

* 'tgrabiec/fix-lsa-async-eviction-test' of github.com:cloudius-systems/seastar-dev:
  tests: lsa_async_eviction_test: Allocate objects under allocating section
  lsa: Allow adjusting reserves in allocating_section

(cherry picked from commit 434a4fee28)
2017-03-16 12:44:54 +02:00
Calle Wilund
698a4e62d9 commitlog_replayer: Make replay parallel per shard
Fixes #2098

Replay previously did all segments in parallel on shard 0, which
caused heavy memory load. To reduce this and spread footprint
across shards, instead do X segments per shard, sequential per shard.

v2:
* Fixed whitespace errors

Message-Id: <1489503382-830-1-git-send-email-calle@scylladb.com>
(cherry picked from commit 078589c508)
2017-03-15 13:07:45 +02:00
Amnon Heiman
63bec22d28 database: requests_blocked_memory metric should be unique
Metrics name should be unique per type.

requests_blocked_memory was registered twice, one as a gauge and one as
derived.

This is not allowed.

Fixes #2165

Signed-off-by: Amnon Heiman <amnon@scylladb.com>
Message-Id: <20170314162826.25521-1-amnon@scylladb.com>
(cherry picked from commit 0a2eba1b94)
2017-03-15 12:43:01 +02:00
Amnon Heiman
3d14e6e802 storage_proxy: metrics should have unique name
Metrics should have their unique name. This patch changes
throttled_writes of the queu lenght to current_throttled_writes.

Without it, metrics will be reported twice under the same name, which
may cause errors in the prometheus server.

This could be related to scylladb/seastar#250

Fixes #2163.

Signed-off-by: Amnon Heiman <amnon@scylladb.com>
Message-Id: <20170314081456.6392-1-amnon@scylladb.com>
(cherry picked from commit 295a981c61)
2017-03-15 12:43:01 +02:00
Glauber Costa
ea4a2dad96 raid script: improve test for mounted filesystem
The current test for whether or not the filesystem is mounted is weak
and will fail if multiple pieces of the hierarchy are mounted.

util-linux ships with a mountpoint command that does exactly that,
so we'll use that instead.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
Message-Id: <1488742801-4907-1-git-send-email-glauber@scylladb.com>
(cherry picked from commit 2d620a25fb)
2017-03-13 17:04:58 +02:00
Glauber Costa
655e6197cb setup: support mount points in raid script
By default behavior is kept the same. There are deployments in which we
would like to mount data and commitlog to different places - as much as
we have avoided this up until this moment.

One example is EC2, where users may want to have the commitlog mounted
in the SSD drives for faster writes but keep the data in larger, less
expensive and durable EBS volumes.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
Message-Id: <1488258215-2592-1-git-send-email-glauber@scylladb.com>
(cherry picked from commit 9e61a73654)
2017-03-13 16:51:15 +02:00
Asias He
1a1370d33e repair: Fix midpoint is not contained in the split range assertion in split_and_add
We have:

  auto halves = range.split(midpoint, dht::token_comparator());

We saw a case where midpoint == range.start, as a result, range.split
will assert becasue the range.start is marked non-inclusive, so the
midpoint doesn't appear to be contain()ed in the range - hence the
assertion failure.

Fixes #2148

Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Signed-off-by: Asias He <asias@scylladb.com>
Message-Id: <93af2697637c28fbca261ddfb8375a790824df65.1489023933.git.asias@scylladb.com>
(cherry picked from commit 39d2e59e7e)
2017-03-09 09:16:57 +01:00
Paweł Dziepak
7f17424a4e Merge "Avoid loosing changes to keyspace parameters of system_auth and tracing keyspaces" form Tomek
"If a node is bootstrapped with auto_boostrap disabled, it will not
wait for schema sync before creating global keyspaces for auth and
tracing. When such schema changes are then reconciled with schema on
other nodes, they may overwrite changes made by the user before the
node was started, because they will have higher timestamp.

To prevent that, let's use minimum timestamp so that default schema
always looses with manual modifications. This is what Cassandra does.

Fixes #2129."

* tag 'tgrabiec/prevent-keyspace-metadata-loss-v1' of github.com:scylladb/seastar-dev:
  db: Create default auth and tracing keyspaces using lowest timestamp
  migration_manager: Append actual keyspace mutations with schema notifications

(cherry picked from commit 6db6d25f66)
2017-03-08 16:31:41 +02:00
Nadav Har'El
dd56f1bec7 sstable decompression: fix skip() to end of file
The skip() implementation for the compressed file input stream incorrectly
handled the case of skipping to the end of file: In that case we just need
to update the file pointer, but not skip anywhere in the compressed disk
file; In particular, we must NOT call locate() to find the relevant on-disk
compressed chunk, because there is none - locate() can only be called on
actual positions of bytes, not on the one-past-end-of-file position.

Fixes #2143

Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Message-Id: <20170308100057.23316-1-nyh@scylladb.com>
(cherry picked from commit 506e074ba4)
2017-03-08 12:35:39 +02:00
Pekka Enberg
5df61797d6 release: prepare for 1.7.rc1 2017-03-08 12:25:34 +02:00
Paweł Dziepak
b6db9e3d51 db: make do_apply_counter_update() propagate timeout to db_apply()
db_apply() expects to be given a time point at which the request will
time out. Originally, do_apply_counter_update() passed 0, which meant
that all requests were timed out if do_apply() needed to wait. The
caller of do_apply_counter_update() is already given a correct timeout
time point so the only thing needed to fix this problem it to propagate
it properly inside do_apply_counter_update() to the call to do_apply().

Fixes #2119.
Message-Id: <20170307104405.5843-1-pdziepak@scylladb.com>
2017-03-07 12:44:11 +01:00
Gleb Natapov
f2595bea85 memtable: do not open code logalloc::reclaim_lock use
logalloc::reclaim_lock prevents reclaim from running which may cause
regular allocation to fail although there is enough of free memory.
To solve that there is an allocation_section which acquire reclaim_lock
and if allocation fails it run reclaimer outside of a lock and retries
the allocation. The patch make use of allocation_section instead of
direct use of reclaim_lock in memtable code.

Fixes #2138.

Message-Id: <20170306160050.GC5902@scylladb.com>
(cherry picked from commit d7bdf16a16)
2017-03-07 11:16:15 +02:00
Gleb Natapov
e930ef0ee0 memtable: do not yield while holding reclaim_lock
Holding reclaim_lock while yielding may cause memory allocations to
fail.

Fixes #2139

Message-Id: <20170306153151.GA5902@scylladb.com>
(cherry picked from commit 5c4158daac)
2017-03-06 18:35:46 +02:00
Takuya ASADA
4cf0f88724 dist/redhat: enables discard on CentOS/RHEL RAID0
Since CentOS/RHEL raid module disables discard by default, we need enable it
again to use.

Fixes #2033

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1488407037-4795-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 6602221442)
2017-03-06 12:22:17 +02:00
Avi Kivity
372f07b06e Update scylla-ami submodule
* dist/ami/files/scylla-ami d5a4397...eedd12f (3):
  > Rewrite disk discovery to handle EBS and NVMEs.
  > add --developer-mode option
  > trivial cleanup: replace tab in indent
2017-03-04 13:31:08 +02:00
Tomasz Grabiec
0ccc6630a8 db: Fix overflow of gc_clock time point
If query_time is time_point::min(), which is used by
to_data_query_result(), the result of subtraction of
gc_grace_seconds() from query_time will overflow.

I don't think this bug would currently have user-perceivable
effects. This affects which tombstones are dropped, but in case of
to_data_query_result() uses, tombstones are not present in the final
data query result, and mutation_partition::do_compact() takes
tombstones into consideration while compacting before expiring them.

Fixes the following UBSAN report:

  /usr/include/c++/5.3.1/chrono:399:55: runtime error: signed integer overflow: -2147483648 - 604800 cannot be represented in type 'int'

Message-Id: <1488385429-14276-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 4b6e77e97e)
2017-03-01 18:50:19 +02:00
Takuya ASADA
b95a2338be dist/debian/dep: fix broken link of gcc-5, update it to 5.4.1-5
Since gcc-5/stretch=5.4.1-2 removed from apt repository, we nolonger able to
build gcc-5.

To avoid dead link, use launchpad.net archives instead of using apt-get source.

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1488189378-5607-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit ba323e2074)
2017-03-01 17:13:42 +02:00
Tomasz Grabiec
f2d0ac9994 query: Fix invalid initialization of _memory_tracker by moving-from-self
Fixes the following UBSAN warning:

  core/semaphore.hh:293:74: runtime error: reference binding to misaligned address 0x0000006c55d7 for type 'struct basic_semaphore', which requires 8 byte alignment

Since the field was not initialied properly, probably also fixes some
user-visible bug.
Message-Id: <1488368222-32009-1-git-send-email-tgrabiec@scylladb.com>

(cherry picked from commit 0c84f00b16)
2017-03-01 11:56:49 +00:00
Gleb Natapov
56725de0db sstable: close sstable_writer's file if writing of sstable fails.
Failing to close a file properly before destroying file's object causes
crashes.

[tgrabiec: fixed typo]

Fixes #2122.

Message-Id: <20170221144858.GG11471@scylladb.com>
(cherry picked from commit 0977f4fdf8)
2017-02-28 11:04:26 +02:00
Avi Kivity
6f479c8999 Update seastar submodule
* seastar b14373b...f391f9e (1):
  > fix append_challenged_posix_file_impl::process_queue() to handle recursion

Fixes #2121.
2017-02-28 10:55:54 +02:00
Calle Wilund
8c0488bce9 messaging_service: Move log printout to actual listen start
Fixes  #1845
Log printout was before we actually had evaluated endpoint
to create, thus never included SSL info.
Message-Id: <1487766738-27797-1-git-send-email-calle@scylladb.com>

(cherry picked from commit d5f57bd047)
2017-02-23 13:18:33 +02:00
Avi Kivity
68dd11e275 config: enable new sharding algorithm for new deployments
Set murmur3_partitioner_ignore_msb_bits to 12 (enabling the new sharding
algorithm), but do this in scylla.yaml rather than the built-in defaults.
This avoids changing the configuration for existing clusters, as their
scylla.yaml file will not be updated during the upgrade.
Message-Id: <20170214123253.3933-1-avi@scylladb.com>

(cherry picked from commit 9b113ffd3e)
2017-02-22 11:23:46 +01:00
Tomasz Grabiec
a64c53d05f Update seastar submodule
* seastar fc27cec...b14373b (1):
  > reactor utilization should return the utilization in 0-1 range
2017-02-22 09:38:17 +01:00
Paweł Dziepak
42e7a59cca tests/cql_test_env: wait for storage service initialization
Message-Id: <20170221121130.14064-1-pdziepak@scylladb.com>
(cherry picked from commit 274bcd415a)
2017-02-21 17:06:10 +02:00
Avi Kivity
2cd019ee47 Merge "Fixes for counter cell locking" from Paweł
"This series contains some fixes and a unit test for the logic responsible
for locking counter cells."

* 'pdziepak/cell-locking-fixes/v1' of github.com:cloudius-systems/seastar-dev:
  tests: add test for counter cell locker
  cell_locking: fix schema upgrades
  cell_locker: make locker non-movable
  cell_locking: allow to be included by anyone

(cherry picked from commit b8c4b35b57)
2017-02-15 17:37:38 +02:00
Takuya ASADA
bc8b553bec dist/redhat: stop backporting ninja-build from Fedora, install it from EPEL instead
ninja-build-1.6.0-2.fc23.src.rpm on fedora web site deleted for some
reason, but there is ninja-build-1.7.2-2 on EPEL, so we don't need to
backport from Fedora anymore.

Fixes #2087

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1487155729-13257-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 9c8515eeed)
2017-02-15 12:58:44 +02:00
Avi Kivity
0ba98be899 Update seastar submodule
* seastar bff963a...fc27cec (1):
  > collectd: send double correctly for gauge
2017-02-14 16:09:22 +02:00
Avi Kivity
d6899134a7 Update seastar submodule
* seastar f07f8ed...bff963a (1):
  > prometheus: send one MetricFamily per unique metric name
2017-02-13 11:50:43 +02:00
Avi Kivity
5253031110 seastar: point submodule at scylla-seastar.git
Allows backporting seastar patches independently of master.
2017-02-13 11:49:54 +02:00
Avi Kivity
a203c87f0d Merge "Disallow mixed schemas" fro Paweł
"This series makes sure that schemas containing both counter and non-counter
regular or static columns are not allowed."

* 'pdziepak/disallow-mixed-schemas/v1' of github.com:cloudius-systems/seastar-dev:
  schema: verify that there are no both counter and non-counter columns
  test/mutation_source: specify whether to generate counter mutations
  tests/canonical_mutation: don't try to upgrade incompatible schemas

(cherry picked from commit 9e4ae0763d)
2017-02-07 18:04:24 +02:00
Gleb Natapov
37fc0e6840 storage_proxy: use storage_proxy clock instead of explicit lowres_clock
Merge commit 45b6070832 used butchered version of storage_proxy
patch to adjust to rpc timer change instead the one I've sent. This
patch fixes the differences.

Message-Id: <20170206095237.GA7691@scylladb.com>
(cherry picked from commit 3c372525ed)
2017-02-06 12:51:52 +02:00
Avi Kivity
0429e5d8ea cell_locking: work around for missing boost::container::small_vector
small_vector doesn't exist on Ubuntu 14.04's boost, use std::vector
instead.

(cherry picked from commit 6e9e28d5a3)
2017-02-05 20:49:43 +02:00
Avi Kivity
3c147437ac dist: add build dependency on automake
Needed by seastar's c-ares.

(cherry picked from commit 2510b756fc)
2017-02-05 20:17:27 +02:00
Takuya ASADA
e4b3f02286 dist/common/systemd: introduce scylla-housekeeping restart mode
scylla-housekeeping requires to run 'restart mode' for check the version during
scylla-server restart, which wasn't called on systemd timer so added it.

Existing scylla-housekeeping.timer renamed to scylla-housekeeping-daily.timer,
since it is running 'daily mode'.

Fixes #1953

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1486180031-18093-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit e82932b774)
2017-02-05 11:28:03 +02:00
Avi Kivity
5a8013e155 dist: add libtool build dependency for seastar/c-ares
(cherry picked from commit 4175f40da1)
2017-02-05 11:27:38 +02:00
Pekka Enberg
fdba5b8eac release: prepare for 1.7.rc0 2017-02-04 11:04:32 +02:00
Paweł Dziepak
558a52802a cell_locking: fix parititon_entry::equal_compare
The comparator constructor took schema by value instead of const l-ref
and, consequently, later tried to access object that has been destroyed
long time ago.
Message-Id: <20170202135853.8190-1-pdziepak@scylladb.com>

(cherry picked from commit 37b0c71f1d)
2017-02-03 21:28:42 +02:00
Avi Kivity
4f416c7272 Merge "Avoid avalanche of tasks after memtable flush" from Tomasz
"Before, the logic for releasing writes blocked on dirty worked like this:

  1) When region group size changes and it is not under pressure and there
     are some requests blocked, then schedule request releasing task

  2) request releasing task, if no pressure, runs one request and if there are
     still blocked requests, schedules next request releasing task

If requests don't change the size of the region group, then either some request
executes or there is a request releasing task scheduled. The amount of scheduled
tasks is at most 1, there is a single releasing thread.

However, if requests themselves would change the size of the group, then each
such change would schedule yet another request releasing thread, growing the task
queue size by one.

The group size can also change when memory is reclaimed from the groups (e.g.
when contains sparse segments). Compaction may start many request releasing
threads due to group size updates.

Such behavior is detrimental for performance and stability if there are a lot
of blocked requests. This can happen on 1.5 even with modest concurrency
because timed out requests stay in the queue. This is less likely on 1.6 where
they are dropped from the queue.

The releasing of tasks may start to dominate over other processes in the
system. When the amount of scheduled tasks reaches 1000, polling stops and
server becomes unresponsive until all of the released requests are done, which
is either when they start to block on dirty memory again or run out of blocked
requests. It may take a while to reach pressure condition after memtable flush
if it brings virtual dirty much below the threshold, which is currently the
case for workloads with overwrites producing sparse regions.

I saw this happening in a write workload from issue #2021 where the number of
request releasing threads grew into thousands.

Fix by ensuring there is at most one request releasing thread at a time. There
will be one releasing fiber per region group which is woken up when pressure is
lifted. It executes blocked requests until pressure occurs."

* tag 'tgrabiec/lsa-single-threaded-releasing-v2' of github.com:cloudius-systems/seastar-dev:
  tests: lsa: Add test for reclaimer starting and stopping
  tests: lsa: Add request releasing stress test
  lsa: Avoid avalanche releasing of requests
  lsa: Move definitions to .cc
  lsa: Simplify hard pressure notification management
  lsa: Do not start or stop reclaiming on hard pressure
  tests: lsa: Adjust to take into account that reclaimers are run synchronously
  lsa: Document and annotate reclaimer notification callbacks
  tests: lsa: Use with_timeout() in quiesce()

(cherry picked from commit 7a00dd6985)
2017-02-03 09:47:50 +01:00
1418 changed files with 37791 additions and 118507 deletions

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:

View File

@@ -1,4 +0,0 @@
Scylla doesn't use pull-requests, please send a patch to the [mailing list](mailto:scylladb-dev@googlegroups.com) instead.
See our [contributing guidelines](../CONTRIBUTING.md) and our [Scylla development guidelines](../HACKING.md) for more information.
If you have any questions please don't hesitate to send a mail to the [dev list](mailto:scylladb-dev@googlegroups.com).

10
.gitignore vendored
View File

@@ -9,13 +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

5
.gitmodules vendored
View File

@@ -1,6 +1,6 @@
[submodule "seastar"]
path = seastar
url = ../seastar
url = ../scylla-seastar
ignore = dirty
[submodule "swagger-ui"]
path = swagger-ui
@@ -9,6 +9,3 @@
[submodule "dist/ami/files/scylla-ami"]
path = dist/ami/files/scylla-ami
url = ../scylla-ami
[submodule "xxHash"]
path = xxHash
url = ../xxHash

View File

@@ -1,141 +0,0 @@
##
## For best results, first compile the project using the Ninja build-system.
##
cmake_minimum_required(VERSION 3.7)
project(scylla)
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).
set(SEASTAR_DPDK_INCLUDE_DIRS
seastar/dpdk/lib/librte_eal/common/include
seastar/dpdk/lib/librte_eal/common/include/generic
seastar/dpdk/lib/librte_eal/common/include/x86
seastar/dpdk/lib/librte_ether)
find_package(PkgConfig REQUIRED)
set(ENV{PKG_CONFIG_PATH} "${CMAKE_SOURCE_DIR}/seastar/build/release:$ENV{PKG_CONFIG_PATH}")
pkg_check_modules(SEASTAR seastar)
find_package(Boost COMPONENTS filesystem program_options system thread)
##
## Populate the names of all source and header files in the indicated paths in a designated variable.
##
## When RECURSIVE is specified, directories are traversed recursively.
##
## Use: scan_scylla_source_directories(VAR my_result_var [RECURSIVE] PATHS [path1 path2 ...])
##
function (scan_scylla_source_directories)
set(options RECURSIVE)
set(oneValueArgs VAR)
set(multiValueArgs PATHS)
cmake_parse_arguments(args "${options}" "${oneValueArgs}" "${multiValueArgs}" "${ARGN}")
set(globs "")
foreach (dir ${args_PATHS})
list(APPEND globs "${dir}/*.cc" "${dir}/*.hh")
endforeach()
if (args_RECURSIVE)
set(glob_kind GLOB_RECURSE)
else()
set(glob_kind GLOB)
endif()
file(${glob_kind} var
${globs})
set(${args_VAR} ${var} PARENT_SCOPE)
endfunction()
## Although Seastar is an external project, it is common enough to explore the sources while doing
## Scylla development that we'll treat the Seastar sources as part of this project for easier navigation.
scan_scylla_source_directories(
VAR SEASTAR_SOURCE_FILES
RECURSIVE
PATHS
seastar/core
seastar/http
seastar/json
seastar/net
seastar/rpc
seastar/tests
seastar/util)
scan_scylla_source_directories(
VAR SCYLLA_ROOT_SOURCE_FILES
PATHS .)
scan_scylla_source_directories(
VAR SCYLLA_SUB_SOURCE_FILES
RECURSIVE
PATHS
api
auth
cql3
db
dht
exceptions
gms
index
io
locator
message
repair
service
sstables
streaming
tests
thrift
tracing
transport
utils)
scan_scylla_source_directories(
VAR SCYLLA_GEN_SOURCE_FILES
RECURSIVE
PATHS build/release/gen)
set(SCYLLA_SOURCE_FILES
${SCYLLA_ROOT_SOURCE_FILES}
${SCYLLA_GEN_SOURCE_FILES}
${SCYLLA_SUB_SOURCE_FILES})
add_executable(scylla
${SEASTAR_SOURCE_FILES}
${SCYLLA_SOURCE_FILES})
# Note that since CLion does not undestand GCC6 concepts, we always disable them (even if users configure otherwise).
# CLion seems to have trouble with `-U` (macro undefinition), so we do it this way instead.
list(REMOVE_ITEM SEASTAR_CFLAGS "-DHAVE_GCC6_CONCEPTS")
# If the Seastar pkg-config information is available, append to the default flags.
#
# For ease of browsing the source code, we always pretend that DPDK is enabled.
target_compile_options(scylla PUBLIC
-std=gnu++1z
-DHAVE_DPDK
-DHAVE_HWLOC
"${SEASTAR_CFLAGS}")
# The order matters here: prefer the "static" DPDK directories to any dynamic paths from pkg-config. Some files are only
# available dynamically, though.
target_include_directories(scylla PUBLIC
.
${SEASTAR_DPDK_INCLUDE_DIRS}
${SEASTAR_INCLUDE_DIRS}
${Boost_INCLUDE_DIRS}
xxhash
build/release/gen)

View File

@@ -1,279 +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 depends on the system package manager for its development dependencies.
Running `./install_dependencies.sh` (as root) installs the appropriate packages based on your Linux distribution.
### Build system
**Note**: Compiling Scylla requires, conservatively, 2 GB of memory per native thread, and up to 3 GB per native thread while linking.
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 options are:
- `--mode={release,debug,all}`: Debug mode enables [AddressSanitizer](https://github.com/google/sanitizers/wiki/AddressSanitizer) and allows for debugging with tools like GDB. Debugging builds are generally slower and generate much larger object files than release builds.
- `--{enable,disable}-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
```
### 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. 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 (release)", 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.
### 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
```
### 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 section 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
```
### 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
```

View File

@@ -1,131 +0,0 @@
M: Maintainer with commit access
R: Reviewer with subsystem expertise
F: Filename, directory, or pattern for the subsystem
---
AUTH
M: Paweł Dziepak <pdziepak@scylladb.com>
M: Duarte Nunes <duarte@scylladb.com>
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>
M: Paweł Dziepak <pdziepak@scylladb.com>
R: Piotr Jastrzebski <piotr@scylladb.com>
F: row_cache*
F: *mutation*
F: tests/mvcc*
COMMITLOG / BATCHLOGa
M: Paweł Dziepak <pdziepak@scylladb.com>
M: Duarte Nunes <duarte@scylladb.com>
R: Calle Wilund <calle@scylladb.com>
F: db/commitlog/*
F: db/batch*
COORDINATOR
M: Paweł Dziepak <pdziepak@scylladb.com>
M: Duarte Nunes <duarte@scylladb.com>
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
M: Paweł Dziepak <pdziepak@scylladb.com>
F: counters*
F: tests/counter_test*
GOSSIP
M: Duarte Nunes <duarte@scylladb.com>
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>
M: Paweł Dziepak <pdziepak@scylladb.com>
F: utils/logalloc*
MATERIALIZED VIEWS
M: Duarte Nunes <duarte@scylladb.com>
M: Pekka Enberg <penberg@scylladb.com>
R: Nadav Har'El <nyh@scylladb.com>
R: Duarte Nunes <duarte@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>
M: Duarte Nunes <duarte@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: Duarte Nunes <duarte@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: Duarte Nunes <duarte@scylladb.com>
R: 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>
M: Duarte Nunes <duarte@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>
M: Duarte Nunes <duarte@scylladb.com>
R: Asias He <asias@scylladb.com>
F: streaming/*
F: service/storage_service.*
THRIFT TRANSPORT LAYER
M: Duarte Nunes <duarte@scylladb.com>
F: thrift/*
THE REST
M: Avi Kivity <avi@scylladb.com>
M: Paweł Dziepak <pdziepak@scylladb.com>
M: Duarte Nunes <duarte@scylladb.com>
M: Tomasz Grabiec <tgrabiec@scylladb.com>
F: *

View File

@@ -1,5 +1,2 @@
This project includes code developed by the Apache Software Foundation (http://www.apache.org/),
especially Apache Cassandra.
It also 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.

View File

@@ -1,19 +1,29 @@
# Scylla
## Quick-start
## Building Scylla
```bash
$ git submodule update --init --recursive
$ sudo ./install-dependencies.sh
$ ./configure.py --mode=release
$ ninja-build -j4 # Assuming 4 system threads.
$ ./build/release/scylla
$ # Rejoice!
In addition to required packages by Seastar, the following packages are required by Scylla.
### Submodules
Scylla uses submodules, so make sure you pull the submodules first by doing:
```
git submodule init
git submodule update --init --recursive
```
Please see [HACKING.md](HACKING.md) for detailed information on building and developing Scylla.
### Building and Running Scylla on Fedora
* Installing required packages:
## Running Scylla
```
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
```

View File

@@ -1,6 +1,6 @@
#!/bin/sh
VERSION=666.development
VERSION=1.7.5
if test -f version
then

View File

@@ -455,7 +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"
@@ -475,7 +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",

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

@@ -792,24 +792,6 @@
}
]
},
{
"path":"/storage_service/active_repair/",
"operations":[
{
"method":"GET",
"summary":"Return an array with the ids of the currently active repairs",
"type":"array",
"items":{
"type":"int"
},
"nickname":"get_active_repair_async",
"produces":[
"application/json"
],
"parameters":[]
}
]
},
{
"path":"/storage_service/repair_async/{keyspace}",
"operations":[
@@ -970,22 +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":[
@@ -2129,41 +2095,6 @@
]
}
]
},
{
"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"
}
]
}
]
}
],
"models":{

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

@@ -39,7 +39,6 @@
#include "http/exception.hh"
#include "stream_manager.hh"
#include "system.hh"
#include "api/config.hh"
namespace api {
@@ -50,23 +49,19 @@ 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");
set_config(rb02, ctx, r);
rb->register_function(r, "system",
"The system related API");
set_system(ctx, r);
@@ -117,11 +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);
@@ -129,6 +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);
});
}

View File

@@ -29,7 +29,6 @@
#include "utils/histogram.hh"
#include "http/exception.hh"
#include "api_init.hh"
#include "seastarx.hh"
namespace api {

View File

@@ -46,7 +46,7 @@ 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

@@ -252,13 +252,13 @@ void set_cache_service(http_context& ctx, routes& r) {
// In origin row size is the weighted size.
// We currently do not support weights, so we use num entries instead
return map_reduce_cf(ctx, 0, [](const column_family& cf) {
return cf.get_row_cache().partitions();
return cf.get_row_cache().num_entries();
}, std::plus<uint64_t>());
});
cs::get_row_entries.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, 0, [](const column_family& cf) {
return cf.get_row_cache().partitions();
return cf.get_row_cache().num_entries();
}, std::plus<uint64_t>());
});

View File

@@ -182,6 +182,15 @@ static int64_t max_row_size(column_family& cf) {
return res;
}
static double update_ratio(double acc, double f, double total) {
if (f && !total) {
throw bad_param_exception("total should include all elements");
} else if (total) {
acc += f / total;
}
return acc;
}
static integral_ratio_holder mean_row_size(column_family& cf) {
integral_ratio_holder res;
for (auto i: *cf.get_sstables() ) {
@@ -274,16 +283,6 @@ static std::vector<uint64_t> concat_sstable_count_per_level(std::vector<uint64_t
return a;
}
ratio_holder filter_false_positive_as_ratio_holder(const sstables::shared_sstable& sst) {
double f = sst->filter_get_false_positive();
return ratio_holder(f + sst->filter_get_true_positive(), f);
}
ratio_holder filter_recent_false_positive_as_ratio_holder(const sstables::shared_sstable& sst) {
double f = sst->filter_get_recent_false_positive();
return ratio_holder(f + sst->filter_get_recent_true_positive(), f);
}
void set_column_family(http_context& ctx, routes& r) {
cf::get_column_family_name.set(r, [&ctx] (const_req req){
vector<sstring> res;
@@ -429,7 +428,7 @@ 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;
},
@@ -605,27 +604,39 @@ void set_column_family(http_context& ctx, routes& r) {
});
cf::get_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], ratio_holder(), [] (column_family& cf) {
return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_false_positive_as_ratio_holder), ratio_holder());
}, std::plus<>());
return map_reduce_cf(ctx, req->param["name"], double(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), double(0), [](double s, auto& sst) {
double f = sst->filter_get_false_positive();
return update_ratio(s, f, f + sst->filter_get_true_positive());
});
}, std::plus<double>());
});
cf::get_all_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, ratio_holder(), [] (column_family& cf) {
return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_false_positive_as_ratio_holder), ratio_holder());
}, std::plus<>());
return map_reduce_cf(ctx, double(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), double(0), [](double s, auto& sst) {
double f = sst->filter_get_false_positive();
return update_ratio(s, f, f + sst->filter_get_true_positive());
});
}, std::plus<double>());
});
cf::get_recent_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], ratio_holder(), [] (column_family& cf) {
return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_recent_false_positive_as_ratio_holder), ratio_holder());
}, std::plus<>());
return map_reduce_cf(ctx, req->param["name"], double(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), double(0), [](double s, auto& sst) {
double f = sst->filter_get_recent_false_positive();
return update_ratio(s, f, f + sst->filter_get_recent_true_positive());
});
}, std::plus<double>());
});
cf::get_all_recent_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, ratio_holder(), [] (column_family& cf) {
return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_recent_false_positive_as_ratio_holder), ratio_holder());
}, std::plus<>());
return map_reduce_cf(ctx, double(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), double(0), [](double s, auto& sst) {
double f = sst->filter_get_recent_false_positive();
return update_ratio(s, f, f + sst->filter_get_recent_true_positive());
});
}, std::plus<double>());
});
cf::get_bloom_filter_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -905,20 +916,5 @@ 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));
});
});
}
}

View File

@@ -24,7 +24,6 @@
#include "api.hh"
#include "api/api-doc/column_family.json.hh"
#include "database.hh"
#include <any>
namespace api {
@@ -38,15 +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::any (database&)>;
using reducer_type = std::function<std::any (std::any, std::any)>;
return ctx.db.map_reduce0(mapper_type([mapper, uuid](database& db) {
return I(mapper(db.find_column_family(uuid)));
}), std::any(std::move(init)), reducer_type([reducer = std::move(reducer)] (std::any a, std::any b) mutable {
return I(reducer(std::any_cast<I>(std::move(a)), std::any_cast<I>(std::move(b))));
})).then([] (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);
}
@@ -58,42 +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::any (column_family&)> mapper;
std::function<std::any (std::any, std::any)> reducer;
std::any operator()(database& db) const {
template<class Mapper, class I, class Reducer>
future<I> map_reduce_cf_raw(http_context& ctx, I init,
Mapper mapper, Reducer reducer) {
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;
}
};
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::any (column_family&)>;
using reducer_type = std::function<std::any (std::any, std::any)>;
auto wrapped_mapper = mapper_type([mapper = std::move(mapper)] (column_family& cf) mutable {
return I(mapper(cf));
});
auto wrapped_reducer = reducer_type([reducer = std::move(reducer)] (std::any a, std::any b) mutable {
return 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::any(init), wrapped_reducer).then([] (std::any res) {
return std::any_cast<I>(std::move(res));
});
}, init, reducer);
}

View File

@@ -20,13 +20,13 @@
*/
#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"
namespace api {
using namespace scollectd;
namespace cm = httpd::compaction_manager_json;
using namespace json;

View File

@@ -1,112 +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 <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 format_type(const std::string& type) {
if (type == "int") {
return "integer";
}
return type;
}
future<> get_config_swagger_entry(const std::string& name, const std::string& description, const std::string& 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;
#define _get_config_value(name, type, deflt, status, desc, ...) if (id == #name) {return get_json_return_type(ctx.db.local().get_config().name());}
#define _get_config_description(name, type, deflt, status, desc, ...) f = f.then([&os, &first] {return get_config_swagger_entry(#name, desc, #type, first, os);});
void set_config(std::shared_ptr < api_registry_builder20 > rb, http_context& ctx, routes& r) {
rb->register_function(r, [] (output_stream<char>& os) {
return do_with(true, [&os] (bool& first) {
auto f = make_ready_future();
_make_config_values(_get_config_description)
return f;
});
});
cs::find_config_id.set(r, [&ctx] (const_req r) {
auto id = r.param["id"];
_make_config_values(_get_config_value)
throw bad_param_exception(sstring("No such config entry: ") + id);
});
}
}

View File

@@ -24,6 +24,7 @@
namespace api {
using namespace scollectd;
using namespace json;
namespace hh = httpd::hinted_handoff_json;

View File

@@ -29,11 +29,11 @@
namespace api {
static logging::logger alogger("lsa-api");
static logging::logger logger("lsa-api");
void set_lsa(http_context& ctx, routes& r) {
httpd::lsa_json::lsa_compact.set(r, [&ctx](std::unique_ptr<request> req) {
alogger.info("Triggering compaction");
logger.info("Triggering compaction");
return ctx.db.invoke_on_all([] (database&) {
logalloc::shard_tracker().reclaim(std::numeric_limits<size_t>::max());
}).then([] {

View File

@@ -27,7 +27,7 @@
#include <sstream>
using namespace httpd::messaging_service_json;
using namespace netw;
using namespace net;
namespace api {
@@ -120,13 +120,13 @@ void set_messaging_service(http_context& ctx, routes& r) {
}));
get_version.set(r, [](const_req req) {
return netw::get_local_messaging_service().get_raw_version(req.get_query_param("addr"));
return net::get_local_messaging_service().get_raw_version(req.get_query_param("addr"));
});
get_dropped_messages_by_ver.set(r, [](std::unique_ptr<request> req) {
shared_ptr<std::vector<uint64_t>> map = make_shared<std::vector<uint64_t>>(num_verb);
return netw::get_messaging_service().map_reduce([map](const uint64_t* local_map) mutable {
return net::get_messaging_service().map_reduce([map](const uint64_t* local_map) mutable {
for (auto i = 0; i < num_verb; i++) {
(*map)[i]+= local_map[i];
}

View File

@@ -397,7 +397,7 @@ void set_storage_proxy(http_context& ctx, routes& r) {
});
sp::get_range_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timer_stats(ctx.sp, &proxy::stats::range);
return sum_timer_stats(ctx.sp, &proxy::stats::read);
});
sp::get_range_latency.set(r, [&ctx](std::unique_ptr<request> req) {

View File

@@ -34,7 +34,6 @@
#include "column_family.hh"
#include "log.hh"
#include "release.hh"
#include "sstables/compaction_manager.hh"
namespace api {
@@ -93,13 +92,10 @@ void set_storage_service(http_context& ctx, routes& r) {
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, [](const_req req) {
@@ -358,12 +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) {
@@ -371,22 +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) {
@@ -818,8 +802,10 @@ void set_storage_service(http_context& ctx, routes& r) {
return make_ready_future<json::json_return_type>(json_void());
});
ss::get_metrics_load.set(r, [&ctx](std::unique_ptr<request> req) {
return get_cf_stats(ctx, &column_family::stats::live_disk_space_used);
ss::get_metrics_load.set(r, [](std::unique_ptr<request> req) {
//TBD
unimplemented();
return make_ready_future<json::json_return_type>(0);
});
ss::get_exceptions.set(r, [](const_req req) {
@@ -852,15 +838,6 @@ 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));
});
});
}
}

View File

@@ -1,239 +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 "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, 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_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()))
{
}
static collection_mutation_view get_collection_mutation_view(const uint8_t* ptr)
{
auto f = data::cell::structure::get_member<data::cell::tags::flags>(ptr);
auto ti = data::type_info::make_collection();
data::cell::context ctx(f, ti);
auto view = data::cell::structure::get_member<data::cell::tags::cell>(ptr).as<data::cell::tags::collection>(ctx);
auto dv = data::cell::variable_value::make_view(view, f.get<data::cell::tags::external_data>());
return collection_mutation_view { dv };
}
collection_mutation_view atomic_cell_or_collection::as_collection_mutation() const {
return get_collection_mutation_view(_data.get());
}
collection_mutation::collection_mutation(const collection_type_impl& type, collection_mutation_view v)
: _data(imr_object_type::make(data::cell::make_collection(v.data), &type.imr_state().lsa_migrator()))
{
}
collection_mutation::collection_mutation(const collection_type_impl& type, bytes_view v)
: _data(imr_object_type::make(data::cell::make_collection(v), &type.imr_state().lsa_migrator()))
{
}
collection_mutation::operator collection_mutation_view() const
{
return get_collection_mutation_view(_data.get());
}
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()) {
if (!b.is_live()) {
return false;
}
if (a.is_counter_update()) {
if (!b.is_counter_update()) {
return false;
}
return a.counter_update_value() == b.counter_update_value();
}
if (a.is_live_and_has_ttl()) {
if (!b.is_live_and_has_ttl()) {
return false;
}
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 = get_collection_mutation_view(_data.get()).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_or_collection& c) {
if (!c._data.get()) {
return os << "{ null atomic_cell_or_collection }";
}
using dc = data::cell;
os << "{ ";
if (dc::structure::get_member<dc::tags::flags>(c._data.get()).get<dc::tags::collection>()) {
os << "collection";
} else {
os << "atomic cell";
}
return os << " @" << static_cast<const void*>(c._data.get()) << " }";
}

View File

@@ -29,51 +29,146 @@
#include "net/byteorder.hh"
#include <cstdint>
#include <iosfwd>
#include <seastar/util/gcc6-concepts.hh>
#include "data/cell.hh"
#include "data/schema_info.hh"
#include "imr/utils.hh"
#include "serializer.hh"
template<typename T>
static inline
void set_field(managed_bytes& 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;
/*
* 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 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;
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;
}
template<typename BytesContainer>
static void set_revert(BytesContainer& cell, bool revert) {
cell[0] = (cell[0] & ~REVERT_FLAG) | (revert * REVERT_FLAG);
}
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);
}
// Can be called on live cells only
static bytes_view value(bytes_view 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;
}
// 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, 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 | COUNTER_UPDATE_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(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;
}
template<typename ByteContainer>
friend class atomic_cell_base;
friend class atomic_cell;
public:
using pointer_type = std::conditional_t<is_mutable == mutable_view::no, const uint8_t*, uint8_t*>;
};
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_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);
@@ -82,136 +177,106 @@ 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();
}
void set_timestamp(api::timestamp_type ts) {
_view.set_timestamp(ts);
return atomic_cell_type::timestamp(_data);
}
// 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();
}
// Can be called on live counter update cells only
int64_t counter_update_value() const {
return _view.counter_update_value();
bytes_view value() const {
return atomic_cell_type::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);
}
};
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 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_ref final : public atomic_cell_base<managed_bytes&> {
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());
}
friend class atomic_cell;
atomic_cell_ref(managed_bytes& buf) : atomic_cell_base(buf) {}
};
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 final : public atomic_cell_base<managed_bytes> {
atomic_cell(managed_bytes b) : atomic_cell_base(std::move(b)) {}
public:
class collection_member_tag;
using collection_member = bool_class<collection_member_tag>;
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 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& 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, bytes_view value) {
return atomic_cell_type::make_live_counter_update(timestamp, value);
}
static atomic_cell make_live_counter_update(api::timestamp_type timestamp, const bytes& value) {
return atomic_cell_type::make_live_counter_update(timestamp, bytes_view(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);
friend class atomic_cell_or_collection;
friend std::ostream& operator<<(std::ostream& os, const atomic_cell& ac);
};
@@ -225,24 +290,38 @@ class collection_mutation_view;
// list: tbd, probably ugly
class collection_mutation {
public:
using imr_object_type = imr::utils::object<data::cell::structure>;
imr_object_type _data;
managed_bytes data;
collection_mutation() {}
collection_mutation(const collection_type_impl&, collection_mutation_view v);
collection_mutation(const collection_type_impl&, bytes_view bv);
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:
atomic_cell_value_view data;
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 };
}
namespace db {
template<typename T>
class serializer;
}
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

@@ -25,7 +25,6 @@
#include "types.hh"
#include "atomic_cell.hh"
#include "atomic_cell_or_collection.hh"
#include "hashing.hh"
#include "counters.hh"
@@ -33,15 +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.data.with_linearized([&] (bytes_view cell_bv) {
auto ctype = static_pointer_cast<const collection_type_impl>(cdef.type);
auto m_view = ctype->deserialize_mutation_form(cell_bv);
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);
}
});
}
};
@@ -53,9 +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()) {
@@ -84,15 +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

@@ -25,56 +25,46 @@
#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_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;
static atomic_cell_or_collection from_collection_mutation(collection_mutation data) {
return std::move(data.data);
}
void swap(atomic_cell_or_collection& other) noexcept {
_data.swap(other._data);
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();
}
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;
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 const sstring& 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(stdx::string_view, const authentication_options& options) const override {
return make_ready_future();
}
virtual future<> alter(stdx::string_view, const authentication_options& options) const override {
return make_ready_future();
}
virtual future<> drop(stdx::string_view) const override {
return make_ready_future();
}
virtual future<custom_options> query_custom_options(stdx::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

@@ -1,93 +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"
#include "stdx.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 const sstring& 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(stdx::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(stdx::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(stdx::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;
}
};
}

387
auth/auth.cc Normal file
View File

@@ -0,0 +1,387 @@
/*
* 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 logger("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::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(), expiry(cfg),
std::chrono::milliseconds(
cfg.permissions_validity_in_ms()),
[](const key_type& k) {
logger.debug("Refreshing permissions for {}", k.first.name());
return authorizer::get().authorize(::make_shared<authenticated_user>(k.first), k.second);
}) {
}
static std::chrono::milliseconds expiry(const db::config& cfg) {
auto exp = cfg.permissions_update_interval_in_ms();
if (exp == 0 || exp == std::numeric_limits<uint32_t>::max()) {
exp = cfg.permissions_validity_in_ms();
}
return std::chrono::milliseconds(exp);
}
future<> stop() {
return make_ready_future<>();
}
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;
};
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"));
}
logger.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) {
logger.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)] {
logger.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) {
logger.info("Created default superuser '{}'", DEFAULT_SUPERUSER_NAME);
}).handle_exception([](auto ep) {
try {
std::rethrow_exception(ep);
} catch (exceptions::request_execution_exception&) {
logger.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)
throw (exceptions::request_execution_exception) {
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) throw(exceptions::request_execution_exception) {
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());
});
});
});
}

124
auth/auth.hh Normal file
View File

@@ -0,0 +1,124 @@
/*
* 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"
namespace auth {
class authenticated_user;
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) throw(exceptions::request_execution_exception);
/**
* Deletes the user from AUTH_KS.USERS_CF.
*
* @param username Username to delete.
* @throws RequestExecutionException
*/
static future<> delete_user(const sstring& username) throw(exceptions::request_execution_exception);
/**
* 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);
};
}

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(stdx::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

@@ -41,63 +41,42 @@
#pragma once
#include <experimental/string_view>
#include <functional>
#include <iosfwd>
#include <optional>
#include <seastar/core/sstring.hh>
#include "seastarx.hh"
#include "stdx.hh"
#include <seastar/core/future.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(stdx::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

@@ -1,64 +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(sprint("The %s option is not supported.", k)) {
}
};
}

View File

@@ -39,14 +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 "authenticator.hh"
#include "authenticated_user.hh"
#include "password_authenticator.hh"
#include "auth.hh"
#include "db/config.hh"
#include "utils/class_registrator.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) throw (exceptions::configuration_exception) {
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 throw(exceptions::authentication_exception) override {
return make_ready_future<::shared_ptr<authenticated_user>>(::make_shared<authenticated_user>());
}
future<> create(sstring username, const option_map& options) throw(exceptions::request_validation_exception, exceptions::request_execution_exception) override {
return make_ready_future();
}
future<> alter(sstring username, const option_map& options) throw(exceptions::request_validation_exception, exceptions::request_execution_exception) override {
return make_ready_future();
}
future<> drop(sstring username) throw(exceptions::request_validation_exception, exceptions::request_execution_exception) 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

@@ -41,24 +41,21 @@
#pragma once
#include <experimental/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 <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"
#include "stdx.hh"
namespace db {
class config;
@@ -68,104 +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;
using credentials_map = std::unordered_map<sstring, sstring>;
virtual ~authenticator() = default;
virtual future<> start() = 0;
virtual future<> stop() = 0;
///
/// A fully-qualified (class with package) Java-like name for this implementation.
///
virtual const sstring& qualified_java_name() const = 0;
virtual bool require_authentication() const = 0;
virtual authentication_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;
///
/// 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;
///
/// 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(stdx::string_view role_name, const authentication_options& options) const = 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(stdx::string_view role_name, const authentication_options& options) const = 0;
///
/// Delete the authentication record for a user. This will disallow the user from logging in.
///
virtual future<> drop(stdx::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(stdx::string_view role_name) 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;
///
/// A stateful SASL challenge which supports many authentication schemes (depending on the implementation).
///
class sasl_challenge {
public:
virtual ~sasl_challenge() = default;
virtual bytes evaluate_response(bytes_view client_response) = 0;
virtual bool is_complete() const = 0;
virtual future<authenticated_user> get_authenticated_user() const = 0;
/**
* 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>;
/**
* 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) throw(exceptions::configuration_exception);
/**
* Returns the system authenticator. Must have called setup before calling this.
*/
static authenticator& get();
virtual ~authenticator()
{}
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;
/**
* 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;
/**
* 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;
/**
* 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 throw(exceptions::authentication_exception) = 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) throw(exceptions::request_validation_exception, exceptions::request_execution_exception) = 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) throw(exceptions::request_validation_exception, exceptions::request_execution_exception) = 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) throw(exceptions::request_validation_exception, exceptions::request_execution_exception) = 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) throw(exceptions::authentication_exception) = 0;
virtual bool is_complete() const = 0;
virtual future<::shared_ptr<authenticated_user>> get_authenticated_user() const throw(exceptions::authentication_exception) = 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

@@ -41,116 +41,131 @@
#pragma once
#include <experimental/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 "seastarx.hh"
#include "stdx.hh"
#include "permission.hh"
#include "data_resource.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 const sstring& 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(stdx::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(stdx::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(stdx::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

@@ -1,97 +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"
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) -> stdx::optional<empty_state> {
if (f.failed()) {
auth_log.info("Auth task failed with error, rescheduling: {}", f.get_exception());
return { };
}
return { empty_state() };
});
});
}).discard_result();
}
future<> create_metadata_table_if_missing(
stdx::string_view table_name,
cql3::query_processor& qp,
stdx::string_view cql,
::service::migration_manager& mm) {
auto& db = qp.db().local();
if (db.has_schema(meta::AUTH_KS, sstring(table_name))) {
return make_ready_future<>();
}
auto parsed_statement = static_pointer_cast<cql3::statements::raw::cf_statement>(
cql3::query_processor::parse_statement(cql));
parsed_statement->prepare_keyspace(meta::AUTH_KS);
auto statement = static_pointer_cast<cql3::statements::create_table_statement>(
parsed_statement->prepare(db, qp.get_cql_stats())->statement);
const auto schema = statement->get_cf_meta_data(qp.db().local());
const auto uuid = generate_legacy_id(schema->ks_name(), schema->cf_name());
schema_builder b(schema);
b.set_uuid(uuid);
return mm.announce_new_column_family(b.build(), false);
}
future<> wait_for_schema_agreement(::service::migration_manager& mm, const database& db) {
static const auto pause = [] { return sleep(std::chrono::milliseconds(500)); };
return do_until([&db] { return db.get_version() != database::empty_version; }, pause).then([&mm] {
return do_until([&mm] { return mm.have_schema_agreement(); }, pause);
});
}
}

View File

@@ -1,85 +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 <experimental/string_view>
#include <seastar/core/future.hh>
#include <seastar/core/abort_source.hh>
#include <seastar/util/noncopyable_function.hh>
#include <seastar/core/reactor.hh>
#include <seastar/core/resource.hh>
#include <seastar/core/sstring.hh>
#include "log.hh"
#include "seastarx.hh"
#include "utils/exponential_backoff_retry.hh"
using namespace std::chrono_literals;
class database;
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 (engine().cpu_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(
stdx::string_view table_name,
cql3::query_processor&,
stdx::string_view cql,
::service::migration_manager&);
future<> wait_for_schema_agreement(::service::migration_manager&, const database&);
}

173
auth/data_resource.cc Normal file
View File

@@ -0,0 +1,173 @@
/*
* 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
throw (std::invalid_argument) {
if (is_root_level()) {
throw std::invalid_argument("ROOT data resource has no keyspace");
}
return _ks;
}
const sstring& auth::data_resource::column_family() const
throw (std::invalid_argument) {
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();
}

158
auth/data_resource.hh Normal file
View File

@@ -0,0 +1,158 @@
/*
* 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>
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 throw(std::invalid_argument);
/**
* @return column family of the resource.
* @throws std::invalid_argument if it's not a cf-level resource.
*/
const sstring& column_family() const throw(std::invalid_argument);
/**
* @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

@@ -39,309 +39,202 @@
* 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/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"
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");
static logging::logger logger("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().local().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 = sprint("SELECT * FROM %s.%s 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.process(
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 = sprint("SELECT * FROM %s.%s", meta::AUTH_KS, legacy_table_name);
return _qp.process(
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().local()).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) {
logger.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&) {});
#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 = sprint(
"SELECT %s FROM %s.%s WHERE %s = ? AND %s = ?",
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.process(
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(
stdx::string_view role_name,
permission_set set,
const resource& resource,
stdx::string_view op) const {
return do_with(
sprint(
"UPDATE %s.%s SET %s = %s %s ? WHERE %s = ? AND %s = ?",
meta::AUTH_KS,
PERMISSIONS_CF,
PERMISSIONS_NAME,
PERMISSIONS_NAME,
op,
ROLE_NAME,
RESOURCE_NAME),
[this, &role_name, set, &resource](const auto& query) {
return _qp.process(
query,
db::consistency_level::ONE,
infinite_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(stdx::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(stdx::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 = sprint(
"SELECT %s, %s, %s FROM %s.%s",
ROLE_NAME,
RESOURCE_NAME,
PERMISSIONS_NAME,
meta::AUTH_KS,
PERMISSIONS_CF);
return _qp.process(
query,
db::consistency_level::ONE,
infinite_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(stdx::string_view role_name) const {
static const sstring query = sprint(
"DELETE FROM %s.%s WHERE %s = ?",
meta::AUTH_KS,
PERMISSIONS_CF,
ROLE_NAME);
return _qp.process(
query,
db::consistency_level::ONE,
infinite_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) {
logger.warn("CassandraAuthorizer failed to revoke all permissions of {}: {}", dropped_user, e);
}
});
}
future<> default_authorizer::revoke_all(const resource& resource) const {
static const sstring query = sprint(
"SELECT %s FROM %s.%s WHERE %s = ? ALLOW FILTERING",
ROLE_NAME,
meta::AUTH_KS,
PERMISSIONS_CF,
RESOURCE_NAME);
return _qp.process(
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 = sprint(
"DELETE FROM %s.%s WHERE %s = ? AND %s = ?",
meta::AUTH_KS,
PERMISSIONS_CF,
ROLE_NAME,
RESOURCE_NAME);
return _qp.process(
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) {
alogger.warn("CassandraAuthorizer failed to revoke all permissions on {}: {}", resource, e);
logger.warn("CassandraAuthorizer failed to revoke all permissions on {}: {}", resource, e);
}
});
});
} catch (exceptions::request_execution_exception& e) {
alogger.warn("CassandraAuthorizer failed to revoke all permissions on {}: {}", resource, e);
logger.warn("CassandraAuthorizer failed to revoke all permissions on {}: {}", resource, e);
return make_ready_future();
}
});
}
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 const sstring& 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(stdx::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( stdx::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(stdx::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(stdx::string_view, permission_set, const resource&, stdx::string_view) const;
future<> modify(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring, sstring);
};
} /* namespace auth */

View File

@@ -39,57 +39,35 @@
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "auth/password_authenticator.hh"
extern "C" {
#include <crypt.h>
#include <unistd.h>
}
#include <algorithm>
#include <chrono>
#include <crypt.h>
#include <random>
#include <chrono>
#include <boost/algorithm/cxx11/all_of.hpp>
#include <seastar/core/reactor.hh>
#include "auth/authenticated_user.hh"
#include "auth/common.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"
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");
static logging::logger logger("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()
{}
password_authenticator::~password_authenticator() {
}
password_authenticator::password_authenticator(cql3::query_processor& qp, ::service::migration_manager& mm)
: _qp(qp)
, _migration_manager(mm)
, _stopped(make_ready_future<>()) {
}
auth::password_authenticator::password_authenticator()
{}
// TODO: blowfish
// Origin uses Java bcrypt library, i.e. blowfish salt
@@ -110,10 +88,12 @@ password_authenticator::password_authenticator(cql3::query_processor& qp, ::serv
// and some old-fashioned random salt generation.
static constexpr size_t rand_bytes = 16;
static thread_local crypt_data tlcrypt = { 0, };
static sstring hashpw(const sstring& pass, const sstring& salt) {
auto res = crypt_r(pass.c_str(), salt.c_str(), &tlcrypt);
// 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());
}
@@ -142,14 +122,17 @@ static sstring gensalt() {
sstring salt;
if (!prefix.empty()) {
return prefix + input;
return prefix + salt;
}
auto tmp = std::make_unique<crypt_data>();
tmp->initialized = 0;
// 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(), &tlcrypt)) {
if (crypt_r("fisk", salt.c_str(), tmp.get())) {
prefix = pfx;
return salt;
}
@@ -161,129 +144,65 @@ static sstring hashpw(const sstring& pass) {
return hashpw(pass, gensalt());
}
static bool has_salted_hash(const cql3::untyped_result_set_row& row) {
return !row.get_or<sstring>(SALTED_HASH, "").empty();
}
future<> auth::password_authenticator::init() {
gensalt(); // do this once to determine usable hashing
static const sstring update_row_query = sprint(
"UPDATE %s SET %s = ? WHERE %s = ?",
meta::roles_table::qualified_name(),
SALTED_HASH,
meta::roles_table::role_col_name);
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.
static const sstring legacy_table_name{"credentials"};
bool password_authenticator::legacy_metadata_exists() const {
return _qp.db().local().has_schema(meta::AUTH_KS, legacy_table_name);
}
future<> password_authenticator::migrate_legacy_metadata() const {
plogger.info("Starting migration of legacy authentication metadata.");
static const sstring query = sprint("SELECT * FROM %s.%s", meta::AUTH_KS, legacy_table_name);
return _qp.process(
query,
db::consistency_level::QUORUM,
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) {
auto username = row.get_as<sstring>("username");
auto salted_hash = row.get_as<sstring>(SALTED_HASH);
return _qp.process(
update_row_query,
consistency_for_user(username),
infinite_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);
});
}
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.process(
update_row_query,
db::consistency_level::QUORUM,
infinite_timeout_config,
{hashpw(DEFAULT_USER_PASSWORD), DEFAULT_USER_NAME}).then([](auto&&) {
plogger.info("Created default superuser authentication record.");
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) {
logger.info("Created default user '{}'", DEFAULT_USER_NAME);
});
}
});
}
return make_ready_future<>();
});
});
}
future<> password_authenticator::start() {
return once_among_shards([this] {
gensalt(); // do this once to determine usable hashing
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().local()).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&) { });
}
db::consistency_level password_authenticator::consistency_for_user(stdx::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;
}
const sstring& 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(
const credentials_map& credentials) const {
future<::shared_ptr<auth::authenticated_user> > auth::password_authenticator::authenticate(
const credentials_map& credentials) const
throw (exceptions::authentication_exception) {
if (!credentials.count(USERNAME_KEY)) {
throw exceptions::authentication_exception(sprint("Required key '%s' is missing", USERNAME_KEY));
}
@@ -300,25 +219,17 @@ future<authenticated_user> password_authenticator::authenticate(
// Rely on query processing caching statements instead, and lets assume
// that a map lookup string->statement is not gonna kill us much.
return futurize_apply([this, username, password] {
static const sstring query = sprint(
"SELECT %s FROM %s WHERE %s = ?",
SALTED_HASH,
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.process(
query,
consistency_for_user(username),
infinite_timeout_config,
{username},
true);
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();
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) {
@@ -329,62 +240,60 @@ future<authenticated_user> password_authenticator::authenticate(
});
}
future<> password_authenticator::create(stdx::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)
throw (exceptions::request_validation_exception,
exceptions::request_execution_exception) {
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.process(
update_row_query,
consistency_for_user(role_name),
infinite_timeout_config,
{hashpw(*options.password), sstring(role_name)}).discard_result();
}
future<> password_authenticator::alter(stdx::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)
throw (exceptions::request_validation_exception,
exceptions::request_execution_exception) {
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 = sprint(
"UPDATE %s SET %s = ? WHERE %s = ?",
meta::roles_table::qualified_name(),
SALTED_HASH,
meta::roles_table::role_col_name);
return _qp.process(
query,
consistency_for_user(role_name),
infinite_timeout_config,
{hashpw(*options.password), sstring(role_name)}).discard_result();
}
future<> password_authenticator::drop(stdx::string_view name) const {
static const sstring query = sprint(
"DELETE %s FROM %s WHERE %s = ?",
SALTED_HASH,
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.process(query, consistency_for_user(name), infinite_timeout_config, {sstring(name)}).discard_result();
future<> auth::password_authenticator::drop(sstring username)
throw (exceptions::request_validation_exception,
exceptions::request_execution_exception) {
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(stdx::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<authenticator::sasl_challenge> password_authenticator::new_sasl_challenge() const {
class plain_text_password_challenge : public sasl_challenge {
const password_authenticator& _self;
::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& self) : _self(self) {
}
plain_text_password_challenge(const password_authenticator& a)
: _authenticator(a)
{}
/**
* SASL PLAIN mechanism specifies that credentials are encoded in a
@@ -399,8 +308,9 @@ const resource_set& password_authenticator::protected_resources() const {
* would expect
* @throws javax.security.sasl.SaslException
*/
bytes evaluate_response(bytes_view client_response) override {
plogger.debug("Decoding credentials from client token");
bytes evaluate_response(bytes_view client_response)
throw (exceptions::authentication_exception) override {
logger.debug("Decoding credentials from client token");
sstring username, password;
@@ -434,19 +344,17 @@ const resource_set& password_authenticator::protected_resources() const {
_complete = true;
return {};
}
bool is_complete() const override {
return _complete;
}
future<authenticated_user> get_authenticated_user() const override {
return _self.authenticate(_credentials);
future<::shared_ptr<authenticated_user>> get_authenticated_user() const
throw (exceptions::authentication_exception) 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(stdx::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 throw(exceptions::authentication_exception) override;
future<> create(sstring username, const option_map& options) throw(exceptions::request_validation_exception, exceptions::request_execution_exception) override;
future<> alter(sstring username, const option_map& options) throw(exceptions::request_validation_exception, exceptions::request_execution_exception) override;
future<> drop(sstring username) throw(exceptions::request_validation_exception, exceptions::request_execution_exception) override;
const resource_ids& protected_resources() const override;
::shared_ptr<sasl_challenge> new_sasl_challenge() const override;
virtual const sstring& 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(stdx::string_view role_name, const authentication_options& options) const override;
virtual future<> alter(stdx::string_view role_name, const authentication_options& options) const override;
virtual future<> drop(stdx::string_view role_name) const override;
virtual future<custom_options> query_custom_options(stdx::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

@@ -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) {

View File

@@ -42,11 +42,9 @@
#pragma once
#include <unordered_set>
#include <seastar/core/sstring.hh>
#include "enum_set.hh"
#include "seastarx.hh"
namespace auth {
@@ -67,13 +65,9 @@ enum class permission {
// permission management
AUTHORIZE, // required for GRANT and REVOKE.
DESCRIBE, // required on the root-level role resource to list all roles.
};
typedef enum_set<
super_enum<
permission,
typedef enum_set<super_enum<permission,
permission::READ,
permission::WRITE,
permission::CREATE,
@@ -81,15 +75,16 @@ typedef enum_set<
permission::DROP,
permission::SELECT,
permission::MODIFY,
permission::AUTHORIZE,
permission::DESCRIBE>> permission_set;
permission::AUTHORIZE>> permission_set;
bool operator<(const permission_set&, const permission_set&);
namespace permissions {
extern const permission_set ALL_DATA;
extern const permission_set ALL;
extern const permission_set NONE;
extern const permission_set ALTERATIONS;
const sstring& to_string(permission);
permission from_string(const sstring&);
@@ -97,6 +92,7 @@ permission from_string(const sstring&);
std::unordered_set<sstring> to_strings(const permission_set&);
permission_set from_strings(const std::unordered_set<sstring>&);
}
}

View File

@@ -1,53 +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/permissions_cache.hh"
#include "auth/authorizer.hh"
#include "auth/common.hh"
#include "auth/service.hh"
#include "db/config.hh"
namespace auth {
permissions_cache_config permissions_cache_config::from_db_config(const db::config& dc) {
permissions_cache_config c;
c.max_entries = dc.permissions_cache_max_entries();
c.validity_period = std::chrono::milliseconds(dc.permissions_validity_in_ms());
c.update_period = std::chrono::milliseconds(dc.permissions_update_interval_in_ms());
return c;
}
permissions_cache::permissions_cache(const permissions_cache_config& c, service& ser, logging::logger& log)
: _cache(c.max_entries, c.validity_period, c.update_period, log, [&ser, &log](const key_type& k) {
log.debug("Refreshing permissions for {}", k.first);
return ser.get_uncached_permissions(k.first, k.second);
}) {
}
future<permission_set> permissions_cache::get(const role_or_anonymous& maybe_role, const resource& r) {
return do_with(key_type(maybe_role, r), [this](const auto& k) {
return _cache.get(k);
});
}
}

View File

@@ -1,91 +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 <experimental/string_view>
#include <functional>
#include <iostream>
#include <optional>
#include <utility>
#include <seastar/core/future.hh>
#include <seastar/core/shared_ptr.hh>
#include <seastar/core/sstring.hh>
#include "auth/authenticated_user.hh"
#include "auth/permission.hh"
#include "auth/resource.hh"
#include "auth/role_or_anonymous.hh"
#include "log.hh"
#include "stdx.hh"
#include "utils/hash.hh"
#include "utils/loading_cache.hh"
namespace std {
inline std::ostream& operator<<(std::ostream& os, const pair<auth::role_or_anonymous, auth::resource>& p) {
os << "{role: " << p.first << ", resource: " << p.second << "}";
return os;
}
}
namespace db {
class config;
}
namespace auth {
class service;
struct permissions_cache_config final {
static permissions_cache_config from_db_config(const db::config&);
std::size_t max_entries;
std::chrono::milliseconds validity_period;
std::chrono::milliseconds update_period;
};
class permissions_cache final {
using cache_type = utils::loading_cache<
std::pair<role_or_anonymous, resource>,
permission_set,
utils::loading_cache_reload_enabled::yes,
utils::simple_entry_size<permission_set>,
utils::tuple_hash>;
using key_type = typename cache_type::key_type;
cache_type _cache;
public:
explicit permissions_cache(const permissions_cache_config&, service&, logging::logger&);
future <> stop() {
return _cache.stop();
}
future<permission_set> get(const role_or_anonymous&, const resource&);
};
}

View File

@@ -1,296 +0,0 @@
/*
* 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 "auth/resource.hh"
#include <algorithm>
#include <iterator>
#include <unordered_map>
#include <boost/algorithm/string/join.hpp>
#include <boost/algorithm/string/split.hpp>
#include "service/storage_proxy.hh"
namespace auth {
std::ostream& operator<<(std::ostream& os, resource_kind kind) {
switch (kind) {
case resource_kind::data: os << "data"; break;
case resource_kind::role: os << "role"; break;
}
return os;
}
static const std::unordered_map<resource_kind, stdx::string_view> roots{
{resource_kind::data, "data"},
{resource_kind::role, "roles"}};
static const std::unordered_map<resource_kind, std::size_t> max_parts{
{resource_kind::data, 2},
{resource_kind::role, 1}};
static permission_set applicable_permissions(const data_resource_view& dv) {
if (dv.table()) {
return permission_set::of<
permission::ALTER,
permission::DROP,
permission::SELECT,
permission::MODIFY,
permission::AUTHORIZE>();
}
return permission_set::of<
permission::CREATE,
permission::ALTER,
permission::DROP,
permission::SELECT,
permission::MODIFY,
permission::AUTHORIZE>();
}
static permission_set applicable_permissions(const role_resource_view& rv) {
if (rv.role()) {
return permission_set::of<permission::ALTER, permission::DROP, permission::AUTHORIZE>();
}
return permission_set::of<
permission::CREATE,
permission::ALTER,
permission::DROP,
permission::AUTHORIZE,
permission::DESCRIBE>();
}
resource::resource(resource_kind kind) : _kind(kind), _parts{sstring(roots.at(kind))} {
}
resource::resource(resource_kind kind, std::vector<sstring> parts) : resource(kind) {
_parts.reserve(parts.size() + 1);
_parts.insert(_parts.end(), std::make_move_iterator(parts.begin()), std::make_move_iterator(parts.end()));
}
resource::resource(data_resource_t, stdx::string_view keyspace)
: resource(resource_kind::data, std::vector<sstring>{sstring(keyspace)}) {
}
resource::resource(data_resource_t, stdx::string_view keyspace, stdx::string_view table)
: resource(resource_kind::data, std::vector<sstring>{sstring(keyspace), sstring(table)}) {
}
resource::resource(role_resource_t, stdx::string_view role)
: resource(resource_kind::role, std::vector<sstring>{sstring(role)}) {
}
sstring resource::name() const {
return boost::algorithm::join(_parts, "/");
}
std::optional<resource> resource::parent() const {
if (_parts.size() == 1) {
return {};
}
resource copy = *this;
copy._parts.pop_back();
return copy;
}
permission_set resource::applicable_permissions() const {
permission_set ps;
switch (_kind) {
case resource_kind::data: ps = ::auth::applicable_permissions(data_resource_view(*this)); break;
case resource_kind::role: ps = ::auth::applicable_permissions(role_resource_view(*this)); break;
}
return ps;
}
bool operator<(const resource& r1, const resource& r2) {
if (r1._kind != r2._kind) {
return r1._kind < r2._kind;
}
return std::lexicographical_compare(
r1._parts.cbegin() + 1,
r1._parts.cend(),
r2._parts.cbegin() + 1,
r2._parts.cend());
}
std::ostream& operator<<(std::ostream& os, const resource& r) {
switch (r.kind()) {
case resource_kind::data: return os << data_resource_view(r);
case resource_kind::role: return os << role_resource_view(r);
}
return os;
}
data_resource_view::data_resource_view(const resource& r) : _resource(r) {
if (r._kind != resource_kind::data) {
throw resource_kind_mismatch(resource_kind::data, r._kind);
}
}
std::optional<stdx::string_view> data_resource_view::keyspace() const {
if (_resource._parts.size() == 1) {
return {};
}
return _resource._parts[1];
}
std::optional<stdx::string_view> data_resource_view::table() const {
if (_resource._parts.size() <= 2) {
return {};
}
return _resource._parts[2];
}
std::ostream& operator<<(std::ostream& os, const data_resource_view& v) {
const auto keyspace = v.keyspace();
const auto table = v.table();
if (!keyspace) {
os << "<all keyspaces>";
} else if (!table) {
os << "<keyspace " << *keyspace << '>';
} else {
os << "<table " << *keyspace << '.' << *table << '>';
}
return os;
}
role_resource_view::role_resource_view(const resource& r) : _resource(r) {
if (r._kind != resource_kind::role) {
throw resource_kind_mismatch(resource_kind::role, r._kind);
}
}
std::optional<stdx::string_view> role_resource_view::role() const {
if (_resource._parts.size() == 1) {
return {};
}
return _resource._parts[1];
}
std::ostream& operator<<(std::ostream& os, const role_resource_view& v) {
const auto role = v.role();
if (!role) {
os << "<all roles>";
} else {
os << "<role " << *role << '>';
}
return os;
}
resource parse_resource(stdx::string_view name) {
static const std::unordered_map<stdx::string_view, resource_kind> reverse_roots = [] {
std::unordered_map<stdx::string_view, resource_kind> result;
for (const auto& pair : roots) {
result.emplace(pair.second, pair.first);
}
return result;
}();
std::vector<sstring> parts;
boost::split(parts, name, [](char ch) { return ch == '/'; });
if (parts.empty()) {
throw invalid_resource_name(name);
}
const auto iter = reverse_roots.find(parts[0]);
if (iter == reverse_roots.end()) {
throw invalid_resource_name(name);
}
const auto kind = iter->second;
parts.erase(parts.begin());
if (parts.size() > max_parts.at(kind)) {
throw invalid_resource_name(name);
}
return resource(kind, std::move(parts));
}
static const resource the_root_data_resource{resource_kind::data};
const resource& root_data_resource() {
return the_root_data_resource;
}
static const resource the_root_role_resource{resource_kind::role};
const resource& root_role_resource() {
return the_root_role_resource;
}
resource_set expand_resource_family(const resource& rr) {
resource r = rr;
resource_set rs;
while (true) {
const auto pr = r.parent();
rs.insert(std::move(r));
if (!pr) {
break;
}
r = std::move(*pr);
}
return rs;
}
}

View File

@@ -1,254 +0,0 @@
/*
* 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 <experimental/string_view>
#include <iostream>
#include <optional>
#include <stdexcept>
#include <tuple>
#include <vector>
#include <unordered_set>
#include <seastar/core/print.hh>
#include <seastar/core/sstring.hh>
#include "auth/permission.hh"
#include "seastarx.hh"
#include "stdx.hh"
#include "utils/hash.hh"
namespace auth {
class invalid_resource_name : public std::invalid_argument {
public:
explicit invalid_resource_name(stdx::string_view name)
: std::invalid_argument(sprint("The resource name '%s' is invalid.", name)) {
}
};
enum class resource_kind {
data, role
};
std::ostream& operator<<(std::ostream&, resource_kind);
///
/// Type tag for constructing data resources.
///
struct data_resource_t final {};
///
/// Type tag for constructing role resources.
///
struct role_resource_t final {};
///
/// Resources are entities that users can be granted permissions on.
///
/// There are data (keyspaces and tables) and role resources. There may be other kinds of resources in the future.
///
/// When they are stored as system metadata, resources have the form `root/part_0/part_1/.../part_n`. Each kind of
/// resource has a specific root prefix, followed by a maximum of `n` parts (where `n` is distinct for each kind of
/// resource as well). In this code, this form is called the "name".
///
/// Since all resources have this same structure, all the different kinds are stored in instances of the same class:
/// \ref resource. When we wish to query a resource for kind-specific data (like the table of a "data" resource), we
/// create a kind-specific "view" of the resource.
///
class resource final {
resource_kind _kind;
std::vector<sstring> _parts;
public:
///
/// A root resource of a particular kind.
///
explicit resource(resource_kind);
resource(data_resource_t, stdx::string_view keyspace);
resource(data_resource_t, stdx::string_view keyspace, stdx::string_view table);
resource(role_resource_t, stdx::string_view role);
resource_kind kind() const noexcept {
return _kind;
}
///
/// A machine-friendly identifier unique to each resource.
///
sstring name() const;
std::optional<resource> parent() const;
permission_set applicable_permissions() const;
private:
resource(resource_kind, std::vector<sstring> parts);
friend class std::hash<resource>;
friend class data_resource_view;
friend class role_resource_view;
friend bool operator<(const resource&, const resource&);
friend bool operator==(const resource&, const resource&);
friend resource parse_resource(stdx::string_view);
};
bool operator<(const resource&, const resource&);
inline bool operator==(const resource& r1, const resource& r2) {
return (r1._kind == r2._kind) && (r1._parts == r2._parts);
}
inline bool operator!=(const resource& r1, const resource& r2) {
return !(r1 == r2);
}
std::ostream& operator<<(std::ostream&, const resource&);
class resource_kind_mismatch : public std::invalid_argument {
public:
explicit resource_kind_mismatch(resource_kind expected, resource_kind actual)
: std::invalid_argument(
sprint("This resource has kind '%s', but was expected to have kind '%s'.", actual, expected)) {
}
};
/// A "data" view of \ref resource.
///
/// If neither `keyspace` nor `table` is present, this is the root resource.
class data_resource_view final {
const resource& _resource;
public:
///
/// \throws `resource_kind_mismatch` if the argument is not a `data` resource.
///
explicit data_resource_view(const resource& r);
std::optional<stdx::string_view> keyspace() const;
std::optional<stdx::string_view> table() const;
};
std::ostream& operator<<(std::ostream&, const data_resource_view&);
///
/// A "role" view of \ref resource.
///
/// If `role` is not present, this is the root resource.
///
class role_resource_view final {
const resource& _resource;
public:
///
/// \throws \ref resource_kind_mismatch if the argument is not a "role" resource.
///
explicit role_resource_view(const resource&);
std::optional<stdx::string_view> role() const;
};
std::ostream& operator<<(std::ostream&, const role_resource_view&);
///
/// Parse a resource from its name.
///
/// \throws \ref invalid_resource_name when the name is malformed.
///
resource parse_resource(stdx::string_view name);
const resource& root_data_resource();
inline resource make_data_resource(stdx::string_view keyspace) {
return resource(data_resource_t{}, keyspace);
}
inline resource make_data_resource(stdx::string_view keyspace, stdx::string_view table) {
return resource(data_resource_t{}, keyspace, table);
}
const resource& root_role_resource();
inline resource make_role_resource(stdx::string_view role) {
return resource(role_resource_t{}, role);
}
}
namespace std {
template <>
struct hash<auth::resource> {
static size_t hash_data(const auth::data_resource_view& dv) {
return utils::tuple_hash()(std::make_tuple(auth::resource_kind::data, dv.keyspace(), dv.table()));
}
static size_t hash_role(const auth::role_resource_view& rv) {
return utils::tuple_hash()(std::make_tuple(auth::resource_kind::role, rv.role()));
}
size_t operator()(const auth::resource& r) const {
std::size_t value;
switch (r._kind) {
case auth::resource_kind::data: value = hash_data(auth::data_resource_view(r)); break;
case auth::resource_kind::role: value = hash_role(auth::role_resource_view(r)); break;
}
return value;
}
};
}
namespace auth {
using resource_set = std::unordered_set<resource>;
//
// A resource and all of its parents.
//
resource_set expand_resource_family(const resource&);
}

View File

@@ -1,169 +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 <experimental/string_view>
#include <memory>
#include <optional>
#include <stdexcept>
#include <unordered_set>
#include <seastar/core/future.hh>
#include <seastar/core/print.hh>
#include <seastar/core/sstring.hh>
#include "auth/resource.hh"
#include "seastarx.hh"
#include "stdx.hh"
namespace auth {
struct role_config final {
bool is_superuser{false};
bool can_login{false};
};
///
/// Differential update for altering existing roles.
///
struct role_config_update final {
std::optional<bool> is_superuser{};
std::optional<bool> can_login{};
};
///
/// A logical argument error for a role-management operation.
///
class roles_argument_exception : public std::invalid_argument {
public:
using std::invalid_argument::invalid_argument;
};
class role_already_exists : public roles_argument_exception {
public:
explicit role_already_exists(stdx::string_view role_name)
: roles_argument_exception(sprint("Role %s already exists.", role_name)) {
}
};
class nonexistant_role : public roles_argument_exception {
public:
explicit nonexistant_role(stdx::string_view role_name)
: roles_argument_exception(sprint("Role %s doesn't exist.", role_name)) {
}
};
class role_already_included : public roles_argument_exception {
public:
role_already_included(stdx::string_view grantee_name, stdx::string_view role_name)
: roles_argument_exception(
sprint("%s already includes role %s.", grantee_name, role_name)) {
}
};
class revoke_ungranted_role : public roles_argument_exception {
public:
revoke_ungranted_role(stdx::string_view revokee_name, stdx::string_view role_name)
: roles_argument_exception(
sprint("%s was not granted role %s, so it cannot be revoked.", revokee_name, role_name)) {
}
};
using role_set = std::unordered_set<sstring>;
enum class recursive_role_query { yes, no };
///
/// Abstract client for managing roles.
///
/// All state necessary for managing roles is stored externally to the client instance.
///
/// All implementations should throw role-related exceptions as documented. Authorization is not addressed here, and
/// access-control should never be enforced in implementations.
///
class role_manager {
public:
virtual ~role_manager() = default;
virtual stdx::string_view qualified_java_name() const noexcept = 0;
virtual const resource_set& protected_resources() const = 0;
virtual future<> start() = 0;
virtual future<> stop() = 0;
///
/// \returns an exceptional future with \ref role_already_exists for a role that has previously been created.
///
virtual future<> create(stdx::string_view role_name, const role_config&) const = 0;
///
/// \returns an exceptional future with \ref nonexistant_role if the role does not exist.
///
virtual future<> drop(stdx::string_view role_name) const = 0;
///
/// \returns an exceptional future with \ref nonexistant_role if the role does not exist.
///
virtual future<> alter(stdx::string_view role_name, const role_config_update&) const = 0;
///
/// Grant `role_name` to `grantee_name`.
///
/// \returns an exceptional future with \ref nonexistant_role if either the role or the grantee do not exist.
///
/// \returns an exceptional future with \ref role_already_included if granting the role would be redundant, or
/// create a cycle.
///
virtual future<> grant(stdx::string_view grantee_name, stdx::string_view role_name) const = 0;
///
/// Revoke `role_name` from `revokee_name`.
///
/// \returns an exceptional future with \ref nonexistant_role if either the role or the revokee do not exist.
///
/// \returns an exceptional future with \ref revoke_ungranted_role if the role was not granted.
///
virtual future<> revoke(stdx::string_view revokee_name, stdx::string_view role_name) const = 0;
///
/// \returns an exceptional future with \ref nonexistant_role if the role does not exist.
///
virtual future<role_set> query_granted(stdx::string_view grantee, recursive_role_query) const = 0;
virtual future<role_set> query_all() const = 0;
virtual future<bool> exists(stdx::string_view role_name) const = 0;
///
/// \returns an exceptional future with \ref nonexistant_role if the role does not exist.
///
virtual future<bool> is_superuser(stdx::string_view role_name) const = 0;
///
/// \returns an exceptional future with \ref nonexistant_role if the role does not exist.
///
virtual future<bool> can_login(stdx::string_view role_name) const = 0;
};
}

View File

@@ -1,41 +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/role_or_anonymous.hh"
#include <iostream>
namespace auth {
std::ostream& operator<<(std::ostream& os, const role_or_anonymous& mr) {
os << mr.name.value_or("<anonymous>");
return os;
}
bool operator==(const role_or_anonymous& mr1, const role_or_anonymous& mr2) noexcept {
return mr1.name == mr2.name;
}
bool is_anonymous(const role_or_anonymous& mr) noexcept {
return !mr.name.has_value();
}
}

View File

@@ -1,66 +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 <experimental/string_view>
#include <functional>
#include <iosfwd>
#include <optional>
#include <seastar/core/sstring.hh>
#include "seastarx.hh"
#include "stdx.hh"
namespace auth {
class role_or_anonymous final {
public:
std::optional<sstring> name{};
role_or_anonymous() = default;
role_or_anonymous(stdx::string_view name) : name(name) {
}
};
std::ostream& operator<<(std::ostream&, const role_or_anonymous&);
bool operator==(const role_or_anonymous&, const role_or_anonymous&) noexcept;
inline bool operator!=(const role_or_anonymous& mr1, const role_or_anonymous& mr2) noexcept {
return !(mr1 == mr2);
}
bool is_anonymous(const role_or_anonymous&) noexcept;
}
namespace std {
template <>
struct hash<auth::role_or_anonymous> {
size_t operator()(const auth::role_or_anonymous& mr) const {
return hash<std::optional<sstring>>()(mr.name);
}
};
}

View File

@@ -1,122 +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/roles-metadata.hh"
#include <boost/algorithm/cxx11/any_of.hpp>
#include <seastar/core/print.hh>
#include <seastar/core/shared_ptr.hh>
#include <seastar/core/sstring.hh>
#include "auth/common.hh"
#include "cql3/query_processor.hh"
#include "cql3/untyped_result_set.hh"
namespace auth {
namespace meta {
namespace roles_table {
stdx::string_view creation_query() {
static const sstring instance = sprint(
"CREATE TABLE %s ("
" %s text PRIMARY KEY,"
" can_login boolean,"
" is_superuser boolean,"
" member_of set<text>,"
" salted_hash text"
")",
qualified_name(),
role_col_name);
return instance;
}
stdx::string_view qualified_name() noexcept {
static const sstring instance = AUTH_KS + "." + sstring(name);
return instance;
}
}
}
future<bool> default_role_row_satisfies(
cql3::query_processor& qp,
std::function<bool(const cql3::untyped_result_set_row&)> p) {
static const sstring query = sprint(
"SELECT * FROM %s WHERE %s = ?",
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return do_with(std::move(p), [&qp](const auto& p) {
return qp.process(
query,
db::consistency_level::ONE,
infinite_timeout_config,
{meta::DEFAULT_SUPERUSER_NAME},
true).then([&qp, &p](::shared_ptr<cql3::untyped_result_set> results) {
if (results->empty()) {
return qp.process(
query,
db::consistency_level::QUORUM,
infinite_timeout_config,
{meta::DEFAULT_SUPERUSER_NAME},
true).then([&p](::shared_ptr<cql3::untyped_result_set> results) {
if (results->empty()) {
return make_ready_future<bool>(false);
}
return make_ready_future<bool>(p(results->one()));
});
}
return make_ready_future<bool>(p(results->one()));
});
});
}
future<bool> any_nondefault_role_row_satisfies(
cql3::query_processor& qp,
std::function<bool(const cql3::untyped_result_set_row&)> p) {
static const sstring query = sprint("SELECT * FROM %s", meta::roles_table::qualified_name());
return do_with(std::move(p), [&qp](const auto& p) {
return qp.process(
query,
db::consistency_level::QUORUM,
infinite_timeout_config).then([&p](::shared_ptr<cql3::untyped_result_set> results) {
if (results->empty()) {
return false;
}
static const sstring col_name = sstring(meta::roles_table::role_col_name);
return boost::algorithm::any_of(*results, [&p](const cql3::untyped_result_set_row& row) {
const bool is_nondefault = row.get_as<sstring>(col_name) != meta::DEFAULT_SUPERUSER_NAME;
return is_nondefault && p(row);
});
});
});
}
}

View File

@@ -1,69 +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 <experimental/string_view>
#include <functional>
#include <seastar/core/future.hh>
#include "seastarx.hh"
#include "stdx.hh"
namespace cql3 {
class query_processor;
class untyped_result_set_row;
}
namespace auth {
namespace meta {
namespace roles_table {
stdx::string_view creation_query();
constexpr stdx::string_view name{"roles", 5};
stdx::string_view qualified_name() noexcept;
constexpr stdx::string_view role_col_name{"role", 4};
}
}
///
/// Check that the default role satisfies a predicate, or `false` if the default role does not exist.
///
future<bool> default_role_row_satisfies(
cql3::query_processor&,
std::function<bool(const cql3::untyped_result_set_row&)>);
///
/// Check that any nondefault role satisfies a predicate. `false` if no nondefault roles exist.
///
future<bool> any_nondefault_role_row_satisfies(
cql3::query_processor&,
std::function<bool(const cql3::untyped_result_set_row&)>);
}

View File

@@ -1,583 +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/service.hh"
#include <algorithm>
#include <map>
#include <seastar/core/future-util.hh>
#include <seastar/core/sharded.hh>
#include <seastar/core/shared_ptr.hh>
#include "auth/allow_all_authenticator.hh"
#include "auth/allow_all_authorizer.hh"
#include "auth/common.hh"
#include "auth/password_authenticator.hh"
#include "auth/role_or_anonymous.hh"
#include "auth/standard_role_manager.hh"
#include "cql3/query_processor.hh"
#include "cql3/untyped_result_set.hh"
#include "db/config.hh"
#include "db/consistency_level_type.hh"
#include "exceptions/exceptions.hh"
#include "log.hh"
#include "service/migration_listener.hh"
#include "utils/class_registrator.hh"
namespace auth {
namespace meta {
static const sstring user_name_col_name("name");
static const sstring superuser_col_name("super");
}
static logging::logger log("auth_service");
class auth_migration_listener final : public ::service::migration_listener {
authorizer& _authorizer;
public:
explicit auth_migration_listener(authorizer& a) : _authorizer(a) {
}
private:
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 {
_authorizer.revoke_all(
auth::make_data_resource(ks_name)).handle_exception_type([](const unsupported_authorization_operation&) {
// Nothing.
});
}
void on_drop_column_family(const sstring& ks_name, const sstring& cf_name) override {
_authorizer.revoke_all(
auth::make_data_resource(
ks_name, cf_name)).handle_exception_type([](const unsupported_authorization_operation&) {
// Nothing.
});
}
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 future<> validate_role_exists(const service& ser, stdx::string_view role_name) {
return ser.underlying_role_manager().exists(role_name).then([role_name](bool exists) {
if (!exists) {
throw nonexistant_role(role_name);
}
});
}
service_config service_config::from_db_config(const db::config& dc) {
const qualified_name qualified_authorizer_name(meta::AUTH_PACKAGE_NAME, dc.authorizer());
const qualified_name qualified_authenticator_name(meta::AUTH_PACKAGE_NAME, dc.authenticator());
const qualified_name qualified_role_manager_name(meta::AUTH_PACKAGE_NAME, dc.role_manager());
service_config c;
c.authorizer_java_name = qualified_authorizer_name;
c.authenticator_java_name = qualified_authenticator_name;
c.role_manager_java_name = qualified_role_manager_name;
return c;
}
service::service(
permissions_cache_config c,
cql3::query_processor& qp,
::service::migration_manager& mm,
std::unique_ptr<authorizer> z,
std::unique_ptr<authenticator> a,
std::unique_ptr<role_manager> r)
: _permissions_cache_config(std::move(c))
, _permissions_cache(nullptr)
, _qp(qp)
, _migration_manager(mm)
, _authorizer(std::move(z))
, _authenticator(std::move(a))
, _role_manager(std::move(r))
, _migration_listener(std::make_unique<auth_migration_listener>(*_authorizer)) {
// The password authenticator requires that the `standard_role_manager` is running so that the roles metadata table
// it manages is created and updated. This cross-module dependency is rather gross, but we have to maintain it for
// the sake of compatibility with Apache Cassandra and its choice of auth. schema.
if ((_authenticator->qualified_java_name() == password_authenticator_name())
&& (_role_manager->qualified_java_name() != standard_role_manager_name())) {
throw incompatible_module_combination(
sprint(
"The %s authenticator must be loaded alongside the %s role-manager.",
password_authenticator_name(),
standard_role_manager_name()));
}
}
service::service(
permissions_cache_config c,
cql3::query_processor& qp,
::service::migration_manager& mm,
const service_config& sc)
: service(
std::move(c),
qp,
mm,
create_object<authorizer>(sc.authorizer_java_name, qp, mm),
create_object<authenticator>(sc.authenticator_java_name, qp, mm),
create_object<role_manager>(sc.role_manager_java_name, qp, mm)) {
}
future<> service::create_keyspace_if_missing() const {
auto& db = _qp.db().local();
if (!db.has_keyspace(meta::AUTH_KS)) {
std::map<sstring, sstring> opts{{"replication_factor", "1"}};
auto ksm = keyspace_metadata::new_keyspace(
meta::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.
return _migration_manager.announce_new_keyspace(ksm, api::min_timestamp, false);
}
return make_ready_future<>();
}
future<> service::start() {
return once_among_shards([this] {
return create_keyspace_if_missing();
}).then([this] {
return when_all_succeed(_role_manager->start(), _authorizer->start(), _authenticator->start());
}).then([this] {
_permissions_cache = std::make_unique<permissions_cache>(_permissions_cache_config, *this, log);
}).then([this] {
return once_among_shards([this] {
_migration_manager.register_listener(_migration_listener.get());
return make_ready_future<>();
});
});
}
future<> service::stop() {
return _permissions_cache->stop().then([this] {
return when_all_succeed(_role_manager->stop(), _authorizer->stop(), _authenticator->stop());
});
}
future<bool> service::has_existing_legacy_users() const {
if (!_qp.db().local().has_schema(meta::AUTH_KS, meta::USERS_CF)) {
return make_ready_future<bool>(false);
}
static const sstring default_user_query = sprint(
"SELECT * FROM %s.%s WHERE %s = ?",
meta::AUTH_KS,
meta::USERS_CF,
meta::user_name_col_name);
static const sstring all_users_query = sprint(
"SELECT * FROM %s.%s LIMIT 1",
meta::AUTH_KS,
meta::USERS_CF);
// This logic is borrowed directly from Apache Cassandra. By first checking for the presence of the default user, we
// can potentially avoid doing a range query with a high consistency level.
return _qp.process(
default_user_query,
db::consistency_level::ONE,
infinite_timeout_config,
{meta::DEFAULT_SUPERUSER_NAME},
true).then([this](auto results) {
if (!results->empty()) {
return make_ready_future<bool>(true);
}
return _qp.process(
default_user_query,
db::consistency_level::QUORUM,
infinite_timeout_config,
{meta::DEFAULT_SUPERUSER_NAME},
true).then([this](auto results) {
if (!results->empty()) {
return make_ready_future<bool>(true);
}
return _qp.process(
all_users_query,
db::consistency_level::QUORUM,
infinite_timeout_config).then([](auto results) {
return make_ready_future<bool>(!results->empty());
});
});
});
}
future<permission_set>
service::get_uncached_permissions(const role_or_anonymous& maybe_role, const resource& r) const {
if (is_anonymous(maybe_role)) {
return _authorizer->authorize(maybe_role, r);
}
const stdx::string_view role_name = *maybe_role.name;
return has_superuser(role_name).then([this, role_name, &r](bool superuser) {
if (superuser) {
return make_ready_future<permission_set>(r.applicable_permissions());
}
//
// Aggregate the permissions from all granted roles.
//
return do_with(permission_set(), [this, role_name, &r](auto& all_perms) {
return get_roles(role_name).then([this, &r, &all_perms](role_set all_roles) {
return do_with(std::move(all_roles), [this, &r, &all_perms](const auto& all_roles) {
return parallel_for_each(all_roles, [this, &r, &all_perms](stdx::string_view role_name) {
return _authorizer->authorize(role_name, r).then([&all_perms](permission_set perms) {
all_perms = permission_set::from_mask(all_perms.mask() | perms.mask());
});
});
});
}).then([&all_perms] {
return all_perms;
});
});
});
}
future<permission_set> service::get_permissions(const role_or_anonymous& maybe_role, const resource& r) const {
return _permissions_cache->get(maybe_role, r);
}
future<bool> service::has_superuser(stdx::string_view role_name) const {
return this->get_roles(std::move(role_name)).then([this](role_set roles) {
return do_with(std::move(roles), [this](const role_set& roles) {
return do_with(false, roles.begin(), [this, &roles](bool& any_super, auto& iter) {
return do_until(
[&roles, &any_super, &iter] { return any_super || (iter == roles.end()); },
[this, &any_super, &iter] {
return _role_manager->is_superuser(*iter++).then([&any_super](bool super) {
any_super = super;
});
}).then([&any_super] {
return any_super;
});
});
});
});
}
future<role_set> service::get_roles(stdx::string_view role_name) const {
//
// We may wish to cache this information in the future (as Apache Cassandra does).
//
return _role_manager->query_granted(role_name, recursive_role_query::yes);
}
future<bool> service::exists(const resource& r) const {
switch (r.kind()) {
case resource_kind::data: {
const auto& db = _qp.db().local();
data_resource_view v(r);
const auto keyspace = v.keyspace();
const auto table = v.table();
if (table) {
return make_ready_future<bool>(db.has_schema(sstring(*keyspace), sstring(*table)));
}
if (keyspace) {
return make_ready_future<bool>(db.has_keyspace(sstring(*keyspace)));
}
return make_ready_future<bool>(true);
}
case resource_kind::role: {
role_resource_view v(r);
const auto role = v.role();
if (role) {
return _role_manager->exists(*role);
}
return make_ready_future<bool>(true);
}
}
return make_ready_future<bool>(false);
}
//
// Free functions.
//
future<bool> has_superuser(const service& ser, const authenticated_user& u) {
if (is_anonymous(u)) {
return make_ready_future<bool>(false);
}
return ser.has_superuser(*u.name);
}
future<role_set> get_roles(const service& ser, const authenticated_user& u) {
if (is_anonymous(u)) {
return make_ready_future<role_set>();
}
return ser.get_roles(*u.name);
}
future<permission_set> get_permissions(const service& ser, const authenticated_user& u, const resource& r) {
return do_with(role_or_anonymous(), [&ser, &u, &r](auto& maybe_role) {
maybe_role.name = u.name;
return ser.get_permissions(maybe_role, r);
});
}
bool is_enforcing(const service& ser) {
const bool enforcing_authorizer = ser.underlying_authorizer().qualified_java_name() != allow_all_authorizer_name();
const bool enforcing_authenticator = ser.underlying_authenticator().qualified_java_name()
!= allow_all_authenticator_name();
return enforcing_authorizer || enforcing_authenticator;
}
bool is_protected(const service& ser, const resource& r) noexcept {
return ser.underlying_role_manager().protected_resources().count(r)
|| ser.underlying_authenticator().protected_resources().count(r)
|| ser.underlying_authorizer().protected_resources().count(r);
}
static void validate_authentication_options_are_supported(
const authentication_options& options,
const authentication_option_set& supported) {
const auto check = [&supported](authentication_option k) {
if (supported.count(k) == 0) {
throw unsupported_authentication_option(k);
}
};
if (options.password) {
check(authentication_option::password);
}
if (options.options) {
check(authentication_option::options);
}
}
future<> create_role(
const service& ser,
stdx::string_view name,
const role_config& config,
const authentication_options& options) {
return ser.underlying_role_manager().create(name, config).then([&ser, name, &options] {
if (!auth::any_authentication_options(options)) {
return make_ready_future<>();
}
return futurize_apply(
&validate_authentication_options_are_supported,
options,
ser.underlying_authenticator().supported_options()).then([&ser, name, &options] {
return ser.underlying_authenticator().create(name, options);
}).handle_exception([&ser, &name](std::exception_ptr ep) {
// Roll-back.
return ser.underlying_role_manager().drop(name).then([ep = std::move(ep)] {
std::rethrow_exception(ep);
});
});
});
}
future<> alter_role(
const service& ser,
stdx::string_view name,
const role_config_update& config_update,
const authentication_options& options) {
return ser.underlying_role_manager().alter(name, config_update).then([&ser, name, &options] {
if (!any_authentication_options(options)) {
return make_ready_future<>();
}
return futurize_apply(
&validate_authentication_options_are_supported,
options,
ser.underlying_authenticator().supported_options()).then([&ser, name, &options] {
return ser.underlying_authenticator().alter(name, options);
});
});
}
future<> drop_role(const service& ser, stdx::string_view name) {
return do_with(make_role_resource(name), [&ser, name](const resource& r) {
auto& a = ser.underlying_authorizer();
return when_all_succeed(
a.revoke_all(name),
a.revoke_all(r)).handle_exception_type([](const unsupported_authorization_operation&) {
// Nothing.
});
}).then([&ser, name] {
return ser.underlying_authenticator().drop(name);
}).then([&ser, name] {
return ser.underlying_role_manager().drop(name);
});
}
future<bool> has_role(const service& ser, stdx::string_view grantee, stdx::string_view name) {
return when_all_succeed(
validate_role_exists(ser, name),
ser.get_roles(grantee)).then([name](role_set all_roles) {
return make_ready_future<bool>(all_roles.count(sstring(name)) != 0);
});
}
future<bool> has_role(const service& ser, const authenticated_user& u, stdx::string_view name) {
if (is_anonymous(u)) {
return make_ready_future<bool>(false);
}
return has_role(ser, *u.name, name);
}
future<> grant_permissions(
const service& ser,
stdx::string_view role_name,
permission_set perms,
const resource& r) {
return validate_role_exists(ser, role_name).then([&ser, role_name, perms, &r] {
return ser.underlying_authorizer().grant(role_name, perms, r);
});
}
future<> grant_applicable_permissions(const service& ser, stdx::string_view role_name, const resource& r) {
return grant_permissions(ser, role_name, r.applicable_permissions(), r);
}
future<> grant_applicable_permissions(const service& ser, const authenticated_user& u, const resource& r) {
if (is_anonymous(u)) {
return make_ready_future<>();
}
return grant_applicable_permissions(ser, *u.name, r);
}
future<> revoke_permissions(
const service& ser,
stdx::string_view role_name,
permission_set perms,
const resource& r) {
return validate_role_exists(ser, role_name).then([&ser, role_name, perms, &r] {
return ser.underlying_authorizer().revoke(role_name, perms, r);
});
}
future<std::vector<permission_details>> list_filtered_permissions(
const service& ser,
permission_set perms,
std::optional<stdx::string_view> role_name,
const std::optional<std::pair<resource, recursive_permissions>>& resource_filter) {
return ser.underlying_authorizer().list_all().then([&ser, perms, role_name, &resource_filter](
std::vector<permission_details> all_details) {
if (resource_filter) {
const resource r = resource_filter->first;
const auto resources = resource_filter->second
? auth::expand_resource_family(r)
: auth::resource_set{r};
all_details.erase(
std::remove_if(
all_details.begin(),
all_details.end(),
[&resources](const permission_details& pd) {
return resources.count(pd.resource) == 0;
}),
all_details.end());
}
std::transform(
std::make_move_iterator(all_details.begin()),
std::make_move_iterator(all_details.end()),
all_details.begin(),
[perms](permission_details pd) {
pd.permissions = permission_set::from_mask(pd.permissions.mask() & perms.mask());
return pd;
});
// Eliminate rows with an empty permission set.
all_details.erase(
std::remove_if(all_details.begin(), all_details.end(), [](const permission_details& pd) {
return pd.permissions.mask() == 0;
}),
all_details.end());
if (!role_name) {
return make_ready_future<std::vector<permission_details>>(std::move(all_details));
}
//
// Filter out rows based on whether permissions have been granted to this role (directly or indirectly).
//
return do_with(std::move(all_details), [&ser, role_name](auto& all_details) {
return ser.get_roles(*role_name).then([&all_details](role_set all_roles) {
all_details.erase(
std::remove_if(
all_details.begin(),
all_details.end(),
[&all_roles](const permission_details& pd) {
return all_roles.count(pd.role_name) == 0;
}),
all_details.end());
return make_ready_future<std::vector<permission_details>>(std::move(all_details));
});
});
});
}
}

View File

@@ -1,296 +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 <experimental/string_view>
#include <memory>
#include <optional>
#include <seastar/core/future.hh>
#include <seastar/core/sstring.hh>
#include <seastar/util/bool_class.hh>
#include "auth/authenticator.hh"
#include "auth/authorizer.hh"
#include "auth/permission.hh"
#include "auth/permissions_cache.hh"
#include "auth/role_manager.hh"
#include "seastarx.hh"
#include "stdx.hh"
namespace cql3 {
class query_processor;
}
namespace db {
class config;
}
namespace service {
class migration_manager;
class migration_listener;
}
namespace auth {
class role_or_anonymous;
struct service_config final {
static service_config from_db_config(const db::config&);
sstring authorizer_java_name;
sstring authenticator_java_name;
sstring role_manager_java_name;
};
///
/// Due to poor (in this author's opinion) decisions of Apache Cassandra, certain choices of one role-manager,
/// authenticator, or authorizer imply restrictions on the rest.
///
/// This exception is thrown when an invalid combination of modules is selected, with a message explaining the
/// incompatibility.
///
class incompatible_module_combination : public std::invalid_argument {
public:
using std::invalid_argument::invalid_argument;
};
///
/// Client for access-control in the system.
///
/// Access control encompasses user/role management, authentication, and authorization. This client provides access to
/// the dynamically-loaded implementations of these modules (through the `underlying_*` member functions), but also
/// builds on their functionality with caching and abstractions for common operations.
///
/// All state associated with access-control is stored externally to any particular instance of this class.
///
class service final {
permissions_cache_config _permissions_cache_config;
std::unique_ptr<permissions_cache> _permissions_cache;
cql3::query_processor& _qp;
::service::migration_manager& _migration_manager;
std::unique_ptr<authorizer> _authorizer;
std::unique_ptr<authenticator> _authenticator;
std::unique_ptr<role_manager> _role_manager;
// Only one of these should be registered, so we end up with some unused instances. Not the end of the world.
std::unique_ptr<::service::migration_listener> _migration_listener;
public:
service(
permissions_cache_config,
cql3::query_processor&,
::service::migration_manager&,
std::unique_ptr<authorizer>,
std::unique_ptr<authenticator>,
std::unique_ptr<role_manager>);
///
/// This constructor is intended to be used when the class is sharded via \ref seastar::sharded. In that case, the
/// arguments must be copyable, which is why we delay construction with instance-construction instructions instead
/// of the instances themselves.
///
service(
permissions_cache_config,
cql3::query_processor&,
::service::migration_manager&,
const service_config&);
future<> start();
future<> stop();
///
/// \returns an exceptional future with \ref nonexistant_role if the named role does not exist.
///
future<permission_set> get_permissions(const role_or_anonymous&, const resource&) const;
///
/// Like \ref get_permissions, but never returns cached permissions.
///
future<permission_set> get_uncached_permissions(const role_or_anonymous&, const resource&) const;
///
/// Query whether the named role has been granted a role that is a superuser.
///
/// A role is always granted to itself. Therefore, a role that "is" a superuser also "has" superuser.
///
/// \returns an exceptional future with \ref nonexistant_role if the role does not exist.
///
future<bool> has_superuser(stdx::string_view role_name) const;
///
/// Return the set of all roles granted to the given role, including itself and roles granted through other roles.
///
/// \returns an exceptional future with \ref nonexistent_role if the role does not exist.
future<role_set> get_roles(stdx::string_view role_name) const;
future<bool> exists(const resource&) const;
const authenticator& underlying_authenticator() const {
return *_authenticator;
}
const authorizer& underlying_authorizer() const {
return *_authorizer;
}
const role_manager& underlying_role_manager() const {
return *_role_manager;
}
private:
future<bool> has_existing_legacy_users() const;
future<> create_keyspace_if_missing() const;
};
future<bool> has_superuser(const service&, const authenticated_user&);
future<role_set> get_roles(const service&, const authenticated_user&);
future<permission_set> get_permissions(const service&, const authenticated_user&, const resource&);
///
/// Access-control is "enforcing" when either the authenticator or the authorizer are not their "allow-all" variants.
///
/// Put differently, when access control is not enforcing, all operations on resources will be allowed and users do not
/// need to authenticate themselves.
///
bool is_enforcing(const service&);
///
/// Protected resources cannot be modified even if the performer has permissions to do so.
///
bool is_protected(const service&, const resource&) noexcept;
///
/// Create a role with optional authentication information.
///
/// \returns an exceptional future with \ref role_already_exists if the user or role exists.
///
/// \returns an exceptional future with \ref unsupported_authentication_option if an unsupported option is included.
///
future<> create_role(
const service&,
stdx::string_view name,
const role_config&,
const authentication_options&);
///
/// Alter an existing role and its authentication information.
///
/// \returns an exceptional future with \ref nonexistant_role if the named role does not exist.
///
/// \returns an exceptional future with \ref unsupported_authentication_option if an unsupported option is included.
///
future<> alter_role(
const service&,
stdx::string_view name,
const role_config_update&,
const authentication_options&);
///
/// Drop a role from the system, including all permissions and authentication information.
///
/// \returns an exceptional future with \ref nonexistant_role if the named role does not exist.
///
future<> drop_role(const service&, stdx::string_view name);
///
/// Check if `grantee` has been granted the named role.
///
/// \returns an exceptional future with \ref nonexistent_role if `grantee` or `name` do not exist.
///
future<bool> has_role(const service&, stdx::string_view grantee, stdx::string_view name);
///
/// Check if the authenticated user has been granted the named role.
///
/// \returns an exceptional future with \ref nonexistent_role if the user or `name` do not exist.
///
future<bool> has_role(const service&, const authenticated_user&, stdx::string_view name);
///
/// \returns an exceptional future with \ref nonexistent_role if the named role does not exist.
///
/// \returns an exceptional future with \ref unsupported_authorization_operation if granting permissions is not
/// supported.
///
future<> grant_permissions(
const service&,
stdx::string_view role_name,
permission_set,
const resource&);
///
/// Like \ref grant_permissions, but grants all applicable permissions on the resource.
///
/// \returns an exceptional future with \ref nonexistent_role if the named role does not exist.
///
/// \returns an exceptional future with \ref unsupported_authorization_operation if granting permissions is not
/// supported.
///
future<> grant_applicable_permissions(const service&, stdx::string_view role_name, const resource&);
future<> grant_applicable_permissions(const service&, const authenticated_user&, const resource&);
///
/// \returns an exceptional future with \ref nonexistent_role if the named role does not exist.
///
/// \returns an exceptional future with \ref unsupported_authorization_operation if revoking permissions is not
/// supported.
///
future<> revoke_permissions(
const service&,
stdx::string_view role_name,
permission_set,
const resource&);
using recursive_permissions = bool_class<struct recursive_permissions_tag>;
///
/// Query for all granted permissions according to filtering criteria.
///
/// Only permissions included in the provided set are included.
///
/// If a role name is provided, only permissions granted (directly or recursively) to the role are included.
///
/// If a resource filter is provided, only permissions granted on the resource are included. When \ref
/// recursive_permissions is `true`, permissions on a parent resource are included.
///
/// \returns an exceptional future with \ref nonexistent_role if a role name is included which refers to a role that
/// does not exist.
///
/// \returns an exceptional future with \ref unsupported_authorization_operation if listing permissions is not
/// supported.
///
future<std::vector<permission_details>> list_filtered_permissions(
const service&,
permission_set,
std::optional<stdx::string_view> role_name,
const std::optional<std::pair<resource, recursive_permissions>>& resource_filter);
}

View File

@@ -1,552 +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/standard_role_manager.hh"
#include <experimental/optional>
#include <unordered_set>
#include <vector>
#include <boost/algorithm/string/join.hpp>
#include <seastar/core/future-util.hh>
#include <seastar/core/print.hh>
#include <seastar/core/sleep.hh>
#include <seastar/core/sstring.hh>
#include <seastar/core/thread.hh>
#include "auth/common.hh"
#include "auth/roles-metadata.hh"
#include "cql3/query_processor.hh"
#include "db/consistency_level_type.hh"
#include "exceptions/exceptions.hh"
#include "log.hh"
#include "utils/class_registrator.hh"
namespace auth {
namespace meta {
namespace role_members_table {
constexpr stdx::string_view name{"role_members" , 12};
static stdx::string_view qualified_name() noexcept {
static const sstring instance = AUTH_KS + "." + sstring(name);
return instance;
}
}
}
static logging::logger log("standard_role_manager");
static const class_registrator<
role_manager,
standard_role_manager,
cql3::query_processor&,
::service::migration_manager&> registration("org.apache.cassandra.auth.CassandraRoleManager");
struct record final {
sstring name;
bool is_superuser;
bool can_login;
role_set member_of;
};
static db::consistency_level consistency_for_role(stdx::string_view role_name) noexcept {
if (role_name == meta::DEFAULT_SUPERUSER_NAME) {
return db::consistency_level::QUORUM;
}
return db::consistency_level::LOCAL_ONE;
}
static future<stdx::optional<record>> find_record(cql3::query_processor& qp, stdx::string_view role_name) {
static const sstring query = sprint(
"SELECT * FROM %s WHERE %s = ?",
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return qp.process(
query,
consistency_for_role(role_name),
infinite_timeout_config,
{sstring(role_name)},
true).then([](::shared_ptr<cql3::untyped_result_set> results) {
if (results->empty()) {
return stdx::optional<record>();
}
const cql3::untyped_result_set_row& row = results->one();
return stdx::make_optional(
record{
row.get_as<sstring>(sstring(meta::roles_table::role_col_name)),
row.get_as<bool>("is_superuser"),
row.get_as<bool>("can_login"),
(row.has("member_of")
? row.get_set<sstring>("member_of")
: role_set())});
});
}
static future<record> require_record(cql3::query_processor& qp, stdx::string_view role_name) {
return find_record(qp, role_name).then([role_name](stdx::optional<record> mr) {
if (!mr) {
throw nonexistant_role(role_name);
}
return make_ready_future<record>(*mr);
});
}
static bool has_can_login(const cql3::untyped_result_set_row& row) {
return row.has("can_login") && !(boolean_type->deserialize(row.get_blob("can_login")).is_null());
}
stdx::string_view standard_role_manager_name() noexcept {
static const sstring instance = meta::AUTH_PACKAGE_NAME + "CassandraRoleManager";
return instance;
}
stdx::string_view standard_role_manager::qualified_java_name() const noexcept {
return standard_role_manager_name();
}
const resource_set& standard_role_manager::protected_resources() const {
static const resource_set resources({
make_data_resource(meta::AUTH_KS, meta::roles_table::name),
make_data_resource(meta::AUTH_KS, meta::role_members_table::name)});
return resources;
}
future<> standard_role_manager::create_metadata_tables_if_missing() const {
static const sstring create_role_members_query = sprint(
"CREATE TABLE %s ("
" role text,"
" member text,"
" PRIMARY KEY (role, member)"
")",
meta::role_members_table::qualified_name());
return when_all_succeed(
create_metadata_table_if_missing(
meta::roles_table::name,
_qp,
meta::roles_table::creation_query(),
_migration_manager),
create_metadata_table_if_missing(
meta::role_members_table::name,
_qp,
create_role_members_query,
_migration_manager));
}
future<> standard_role_manager::create_default_role_if_missing() const {
return default_role_row_satisfies(_qp, &has_can_login).then([this](bool exists) {
if (!exists) {
static const sstring query = sprint(
"INSERT INTO %s (%s, is_superuser, can_login) VALUES (?, true, true)",
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.process(
query,
db::consistency_level::QUORUM,
infinite_timeout_config,
{meta::DEFAULT_SUPERUSER_NAME}).then([](auto&&) {
log.info("Created default superuser role '{}'.", meta::DEFAULT_SUPERUSER_NAME);
return make_ready_future<>();
});
}
return make_ready_future<>();
}).handle_exception_type([](const exceptions::unavailable_exception& e) {
log.warn("Skipped default role setup: some nodes were not ready; will retry");
return make_exception_future<>(e);
});
}
static const sstring legacy_table_name{"users"};
bool standard_role_manager::legacy_metadata_exists() const {
return _qp.db().local().has_schema(meta::AUTH_KS, legacy_table_name);
}
future<> standard_role_manager::migrate_legacy_metadata() const {
log.info("Starting migration of legacy user metadata.");
static const sstring query = sprint("SELECT * FROM %s.%s", meta::AUTH_KS, legacy_table_name);
return _qp.process(
query,
db::consistency_level::QUORUM,
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) {
role_config config;
config.is_superuser = row.get_as<bool>("super");
config.can_login = true;
return do_with(
row.get_as<sstring>("name"),
std::move(config),
[this](const auto& name, const auto& config) {
return this->create_or_replace(name, config);
});
}).finally([results] {});
}).then([] {
log.info("Finished migrating legacy user metadata.");
}).handle_exception([](std::exception_ptr ep) {
log.error("Encountered an error during migration!");
std::rethrow_exception(ep);
});
}
future<> standard_role_manager::start() {
return once_among_shards([this] {
return this->create_metadata_tables_if_missing().then([this] {
_stopped = auth::do_after_system_ready(_as, [this] {
return seastar::async([this] {
wait_for_schema_agreement(_migration_manager, _qp.db().local()).get0();
if (any_nondefault_role_row_satisfies(_qp, &has_can_login).get0()) {
if (this->legacy_metadata_exists()) {
log.warn("Ignoring legacy user metadata since nondefault roles already exist.");
}
return;
}
if (this->legacy_metadata_exists()) {
this->migrate_legacy_metadata().get0();
return;
}
create_default_role_if_missing().get0();
});
});
});
});
}
future<> standard_role_manager::stop() {
_as.request_abort();
return _stopped.handle_exception_type([] (const sleep_aborted&) { });
}
future<> standard_role_manager::create_or_replace(stdx::string_view role_name, const role_config& c) const {
static const sstring query = sprint(
"INSERT INTO %s (%s, is_superuser, can_login) VALUES (?, ?, ?)",
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.process(
query,
consistency_for_role(role_name),
infinite_timeout_config,
{sstring(role_name), c.is_superuser, c.can_login},
true).discard_result();
}
future<>
standard_role_manager::create(stdx::string_view role_name, const role_config& c) const {
return this->exists(role_name).then([this, role_name, &c](bool role_exists) {
if (role_exists) {
throw role_already_exists(role_name);
}
return this->create_or_replace(role_name, c);
});
}
future<>
standard_role_manager::alter(stdx::string_view role_name, const role_config_update& u) const {
static const auto build_column_assignments = [](const role_config_update& u) -> sstring {
std::vector<sstring> assignments;
if (u.is_superuser) {
assignments.push_back(sstring("is_superuser = ") + (*u.is_superuser ? "true" : "false"));
}
if (u.can_login) {
assignments.push_back(sstring("can_login = ") + (*u.can_login ? "true" : "false"));
}
return boost::algorithm::join(assignments, ", ");
};
return require_record(_qp, role_name).then([this, role_name, &u](record) {
if (!u.is_superuser && !u.can_login) {
return make_ready_future<>();
}
return _qp.process(
sprint(
"UPDATE %s SET %s WHERE %s = ?",
meta::roles_table::qualified_name(),
build_column_assignments(u),
meta::roles_table::role_col_name),
consistency_for_role(role_name),
infinite_timeout_config,
{sstring(role_name)}).discard_result();
});
}
future<> standard_role_manager::drop(stdx::string_view role_name) const {
return this->exists(role_name).then([this, role_name](bool role_exists) {
if (!role_exists) {
throw nonexistant_role(role_name);
}
// First, revoke this role from all roles that are members of it.
const auto revoke_from_members = [this, role_name] {
static const sstring query = sprint(
"SELECT member FROM %s WHERE role = ?",
meta::role_members_table::qualified_name());
return _qp.process(
query,
consistency_for_role(role_name),
infinite_timeout_config,
{sstring(role_name)}).then([this, role_name](::shared_ptr<cql3::untyped_result_set> members) {
return parallel_for_each(
members->begin(),
members->end(),
[this, role_name](const cql3::untyped_result_set_row& member_row) {
const sstring member = member_row.template get_as<sstring>("member");
return this->modify_membership(member, role_name, membership_change::remove);
}).finally([members] {});
});
};
// In parallel, revoke all roles that this role is members of.
const auto revoke_members_of = [this, grantee = role_name] {
return this->query_granted(
grantee,
recursive_role_query::no).then([this, grantee](role_set granted_roles) {
return do_with(
std::move(granted_roles),
[this, grantee](const role_set& granted_roles) {
return parallel_for_each(
granted_roles.begin(),
granted_roles.end(),
[this, grantee](const sstring& role_name) {
return this->modify_membership(grantee, role_name, membership_change::remove);
});
});
});
};
// Finally, delete the role itself.
auto delete_role = [this, role_name] {
static const sstring query = sprint(
"DELETE FROM %s WHERE %s = ?",
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.process(
query,
consistency_for_role(role_name),
infinite_timeout_config,
{sstring(role_name)}).discard_result();
};
return when_all_succeed(revoke_from_members(), revoke_members_of()).then([delete_role = std::move(delete_role)] {
return delete_role();
});
});
}
future<>
standard_role_manager::modify_membership(
stdx::string_view grantee_name,
stdx::string_view role_name,
membership_change ch) const {
const auto modify_roles = [this, role_name, grantee_name, ch] {
const auto query = sprint(
"UPDATE %s SET member_of = member_of %s ? WHERE %s = ?",
meta::roles_table::qualified_name(),
(ch == membership_change::add ? '+' : '-'),
meta::roles_table::role_col_name);
return _qp.process(
query,
consistency_for_role(grantee_name),
infinite_timeout_config,
{role_set{sstring(role_name)}, sstring(grantee_name)}).discard_result();
};
const auto modify_role_members = [this, role_name, grantee_name, ch] {
switch (ch) {
case membership_change::add:
return _qp.process(
sprint(
"INSERT INTO %s (role, member) VALUES (?, ?)",
meta::role_members_table::qualified_name()),
consistency_for_role(role_name),
infinite_timeout_config,
{sstring(role_name), sstring(grantee_name)}).discard_result();
case membership_change::remove:
return _qp.process(
sprint(
"DELETE FROM %s WHERE role = ? AND member = ?",
meta::role_members_table::qualified_name()),
consistency_for_role(role_name),
infinite_timeout_config,
{sstring(role_name), sstring(grantee_name)}).discard_result();
}
return make_ready_future<>();
};
return when_all_succeed(modify_roles(), modify_role_members());
}
future<>
standard_role_manager::grant(stdx::string_view grantee_name, stdx::string_view role_name) const {
const auto check_redundant = [this, role_name, grantee_name] {
return this->query_granted(
grantee_name,
recursive_role_query::yes).then([role_name, grantee_name](role_set roles) {
if (roles.count(sstring(role_name)) != 0) {
throw role_already_included(grantee_name, role_name);
}
return make_ready_future<>();
});
};
const auto check_cycle = [this, role_name, grantee_name] {
return this->query_granted(
role_name,
recursive_role_query::yes).then([role_name, grantee_name](role_set roles) {
if (roles.count(sstring(grantee_name)) != 0) {
throw role_already_included(role_name, grantee_name);
}
return make_ready_future<>();
});
};
return when_all_succeed(check_redundant(), check_cycle()).then([this, role_name, grantee_name] {
return this->modify_membership(grantee_name, role_name, membership_change::add);
});
}
future<>
standard_role_manager::revoke(stdx::string_view revokee_name, stdx::string_view role_name) const {
return this->exists(role_name).then([this, revokee_name, role_name](bool role_exists) {
if (!role_exists) {
throw nonexistant_role(sstring(role_name));
}
}).then([this, revokee_name, role_name] {
return this->query_granted(
revokee_name,
recursive_role_query::no).then([revokee_name, role_name](role_set roles) {
if (roles.count(sstring(role_name)) == 0) {
throw revoke_ungranted_role(revokee_name, role_name);
}
return make_ready_future<>();
}).then([this, revokee_name, role_name] {
return this->modify_membership(revokee_name, role_name, membership_change::remove);
});
});
}
static future<> collect_roles(
cql3::query_processor& qp,
stdx::string_view grantee_name,
bool recurse,
role_set& roles) {
return require_record(qp, grantee_name).then([&qp, &roles, recurse](record r) {
return do_with(std::move(r.member_of), [&qp, &roles, recurse](const role_set& memberships) {
return do_for_each(memberships.begin(), memberships.end(), [&qp, &roles, recurse](const sstring& role_name) {
roles.insert(role_name);
if (recurse) {
return collect_roles(qp, role_name, true, roles);
}
return make_ready_future<>();
});
});
});
}
future<role_set> standard_role_manager::query_granted(stdx::string_view grantee_name, recursive_role_query m) const {
const bool recurse = (m == recursive_role_query::yes);
return do_with(
role_set{sstring(grantee_name)},
[this, grantee_name, recurse](role_set& roles) {
return collect_roles(_qp, grantee_name, recurse, roles).then([&roles] { return roles; });
});
}
future<role_set> standard_role_manager::query_all() const {
static const sstring query = sprint(
"SELECT %s FROM %s",
meta::roles_table::role_col_name,
meta::roles_table::qualified_name());
// To avoid many copies of a view.
static const auto role_col_name_string = sstring(meta::roles_table::role_col_name);
return _qp.process(query, db::consistency_level::QUORUM, infinite_timeout_config).then([](::shared_ptr<cql3::untyped_result_set> results) {
role_set roles;
std::transform(
results->begin(),
results->end(),
std::inserter(roles, roles.begin()),
[](const cql3::untyped_result_set_row& row) {
return row.get_as<sstring>(role_col_name_string);
});
return roles;
});
}
future<bool> standard_role_manager::exists(stdx::string_view role_name) const {
return find_record(_qp, role_name).then([](stdx::optional<record> mr) {
return static_cast<bool>(mr);
});
}
future<bool> standard_role_manager::is_superuser(stdx::string_view role_name) const {
return require_record(_qp, role_name).then([](record r) {
return r.is_superuser;
});
}
future<bool> standard_role_manager::can_login(stdx::string_view role_name) const {
return require_record(_qp, role_name).then([](record r) {
return r.can_login;
});
}
}

View File

@@ -1,105 +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/role_manager.hh"
#include <experimental/string_view>
#include <unordered_set>
#include <seastar/core/abort_source.hh>
#include <seastar/core/future.hh>
#include <seastar/core/sstring.hh>
#include "stdx.hh"
#include "seastarx.hh"
namespace cql3 {
class query_processor;
}
namespace service {
class migration_manager;
}
namespace auth {
stdx::string_view standard_role_manager_name() noexcept;
class standard_role_manager final : public role_manager {
cql3::query_processor& _qp;
::service::migration_manager& _migration_manager;
future<> _stopped;
seastar::abort_source _as;
public:
standard_role_manager(cql3::query_processor& qp, ::service::migration_manager& mm)
: _qp(qp)
, _migration_manager(mm)
, _stopped(make_ready_future<>()) {
}
virtual stdx::string_view qualified_java_name() const noexcept override;
virtual const resource_set& protected_resources() const override;
virtual future<> start() override;
virtual future<> stop() override;
virtual future<> create(stdx::string_view role_name, const role_config&) const override;
virtual future<> drop(stdx::string_view role_name) const override;
virtual future<> alter(stdx::string_view role_name, const role_config_update&) const override;
virtual future<> grant(stdx::string_view grantee_name, stdx::string_view role_name) const override;
virtual future<> revoke(stdx::string_view revokee_name, stdx::string_view role_name) const override;
virtual future<role_set> query_granted(stdx::string_view grantee_name, recursive_role_query) const override;
virtual future<role_set> query_all() const override;
virtual future<bool> exists(stdx::string_view role_name) const override;
virtual future<bool> is_superuser(stdx::string_view role_name) const override;
virtual future<bool> can_login(stdx::string_view role_name) const override;
private:
enum class membership_change { add, remove };
future<> create_metadata_tables_if_missing() const;
bool legacy_metadata_exists() const;
future<> migrate_legacy_metadata() const;
future<> create_default_role_if_missing() const;
future<> create_or_replace(stdx::string_view role_name, const role_config&) const;
future<> modify_membership(stdx::string_view role_name, stdx::string_view grantee_name, membership_change) const;
};
}

View File

@@ -1,262 +0,0 @@
/*
* 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) 2017 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 "auth/authenticated_user.hh"
#include "auth/authenticator.hh"
#include "auth/authorizer.hh"
#include "auth/default_authorizer.hh"
#include "auth/password_authenticator.hh"
#include "auth/permission.hh"
#include "db/config.hh"
#include "utils/class_registrator.hh"
namespace auth {
static const sstring PACKAGE_NAME("com.scylladb.auth.");
static const sstring& transitional_authenticator_name() {
static const sstring name = PACKAGE_NAME + "TransitionalAuthenticator";
return name;
}
static const sstring& transitional_authorizer_name() {
static const sstring name = PACKAGE_NAME + "TransitionalAuthorizer";
return name;
}
class transitional_authenticator : public authenticator {
std::unique_ptr<authenticator> _authenticator;
public:
static const sstring PASSWORD_AUTHENTICATOR_NAME;
transitional_authenticator(cql3::query_processor& qp, ::service::migration_manager& mm)
: transitional_authenticator(std::make_unique<password_authenticator>(qp, mm)) {
}
transitional_authenticator(std::unique_ptr<authenticator> a)
: _authenticator(std::move(a)) {
}
virtual future<> start() override {
return _authenticator->start();
}
virtual future<> stop() override {
return _authenticator->stop();
}
virtual const sstring& qualified_java_name() const override {
return transitional_authenticator_name();
}
virtual bool require_authentication() const override {
return true;
}
virtual authentication_option_set supported_options() const override {
return _authenticator->supported_options();
}
virtual authentication_option_set alterable_options() const override {
return _authenticator->alterable_options();
}
virtual future<authenticated_user> authenticate(const credentials_map& credentials) const override {
auto i = credentials.find(authenticator::USERNAME_KEY);
if ((i == credentials.end() || i->second.empty())
&& (!credentials.count(PASSWORD_KEY) || credentials.at(PASSWORD_KEY).empty())) {
// return anon user
return make_ready_future<authenticated_user>(anonymous_user());
}
return make_ready_future().then([this, &credentials] {
return _authenticator->authenticate(credentials);
}).handle_exception([](auto ep) {
try {
std::rethrow_exception(ep);
} catch (exceptions::authentication_exception&) {
// return anon user
return make_ready_future<authenticated_user>(anonymous_user());
}
});
}
virtual future<> create(stdx::string_view role_name, const authentication_options& options) const override {
return _authenticator->create(role_name, options);
}
virtual future<> alter(stdx::string_view role_name, const authentication_options& options) const override {
return _authenticator->alter(role_name, options);
}
virtual future<> drop(stdx::string_view role_name) const override {
return _authenticator->drop(role_name);
}
virtual future<custom_options> query_custom_options(stdx::string_view role_name) const override {
return _authenticator->query_custom_options(role_name);
}
virtual const resource_set& protected_resources() const override {
return _authenticator->protected_resources();
}
virtual ::shared_ptr<sasl_challenge> new_sasl_challenge() const override {
class sasl_wrapper : public sasl_challenge {
public:
sasl_wrapper(::shared_ptr<sasl_challenge> sasl)
: _sasl(std::move(sasl)) {
}
virtual bytes evaluate_response(bytes_view client_response) override {
try {
return _sasl->evaluate_response(client_response);
} catch (exceptions::authentication_exception&) {
_complete = true;
return {};
}
}
virtual bool is_complete() const override {
return _complete || _sasl->is_complete();
}
virtual future<authenticated_user> get_authenticated_user() const {
return futurize_apply([this] {
return _sasl->get_authenticated_user().handle_exception([](auto ep) {
try {
std::rethrow_exception(ep);
} catch (exceptions::authentication_exception&) {
// return anon user
return make_ready_future<authenticated_user>(anonymous_user());
}
});
});
}
private:
::shared_ptr<sasl_challenge> _sasl;
bool _complete = false;
};
return ::make_shared<sasl_wrapper>(_authenticator->new_sasl_challenge());
}
};
class transitional_authorizer : public authorizer {
std::unique_ptr<authorizer> _authorizer;
public:
transitional_authorizer(cql3::query_processor& qp, ::service::migration_manager& mm)
: transitional_authorizer(std::make_unique<default_authorizer>(qp, mm)) {
}
transitional_authorizer(std::unique_ptr<authorizer> a)
: _authorizer(std::move(a)) {
}
~transitional_authorizer() {
}
virtual future<> start() override {
return _authorizer->start();
}
virtual future<> stop() override {
return _authorizer->stop();
}
virtual const sstring& qualified_java_name() const override {
return transitional_authorizer_name();
}
virtual future<permission_set> authorize(const role_or_anonymous&, const resource&) const override {
static const permission_set transitional_permissions =
permission_set::of<
permission::CREATE,
permission::ALTER,
permission::DROP,
permission::SELECT,
permission::MODIFY>();
return make_ready_future<permission_set>(transitional_permissions);
}
virtual future<> grant(stdx::string_view s, permission_set ps, const resource& r) const override {
return _authorizer->grant(s, std::move(ps), r);
}
virtual future<> revoke(stdx::string_view s, permission_set ps, const resource& r) const override {
return _authorizer->revoke(s, std::move(ps), r);
}
virtual future<std::vector<permission_details>> list_all() const override {
return _authorizer->list_all();
}
virtual future<> revoke_all(stdx::string_view s) const override {
return _authorizer->revoke_all(s);
}
virtual future<> revoke_all(const resource& r) const override {
return _authorizer->revoke_all(r);
}
virtual const resource_set& protected_resources() const override {
return _authorizer->protected_resources();
}
};
}
//
// To ensure correct initialization order, we unfortunately need to use string literals.
//
static const class_registrator<
auth::authenticator,
auth::transitional_authenticator,
cql3::query_processor&,
::service::migration_manager&> transitional_authenticator_reg(auth::PACKAGE_NAME + "TransitionalAuthenticator");
static const class_registrator<
auth::authorizer,
auth::transitional_authorizer,
cql3::query_processor&,
::service::migration_manager&> transitional_authorizer_reg(auth::PACKAGE_NAME + "TransitionalAuthorizer");

View File

@@ -1,146 +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 <seastar/core/scheduling.hh>
#include <seastar/core/timer.hh>
#include <seastar/core/gate.hh>
#include <chrono>
// Simple proportional controller to adjust shares for processes for which a backlog can be clearly
// defined.
//
// Goal is to consume the backlog as fast as we can, but not so fast that we steal all the CPU from
// incoming requests, and at the same time minimize user-visible fluctuations in the quota.
//
// What that translates to is we'll try to keep the backlog's firt derivative at 0 (IOW, we keep
// backlog constant). As the backlog grows we increase CPU usage, decreasing CPU usage as the
// backlog diminishes.
//
// The exact point at which the controller stops determines the desired CPU usage. As the backlog
// grows and approach a maximum desired, we need to be more aggressive. We will therefore define two
// thresholds, and increase the constant as we cross them.
//
// Doing that divides the range in three (before the first, between first and second, and after
// second threshold), and we'll be slow to grow in the first region, grow normally in the second
// region, and aggressively in the third region.
//
// The constants q1 and q2 are used to determine the proportional factor at each stage.
class backlog_controller {
public:
future<> shutdown() {
_update_timer.cancel();
return std::move(_inflight_update);
}
protected:
struct control_point {
float input;
float output;
};
seastar::scheduling_group _scheduling_group;
const ::io_priority_class& _io_priority;
std::chrono::milliseconds _interval;
timer<> _update_timer;
std::vector<control_point> _control_points;
std::function<float()> _current_backlog;
// updating shares for an I/O class may contact another shard and returns a future.
future<> _inflight_update;
virtual void update_controller(float quota);
void adjust();
backlog_controller(seastar::scheduling_group sg, const ::io_priority_class& iop, std::chrono::milliseconds interval,
std::vector<control_point> control_points, std::function<float()> backlog)
: _scheduling_group(sg)
, _io_priority(iop)
, _interval(interval)
, _update_timer([this] { adjust(); })
, _control_points({{0,0}})
, _current_backlog(std::move(backlog))
, _inflight_update(make_ready_future<>())
{
_control_points.insert(_control_points.end(), control_points.begin(), control_points.end());
_update_timer.arm_periodic(_interval);
}
// Used when the controllers are disabled and a static share is used
// When that option is deprecated we should remove this.
backlog_controller(seastar::scheduling_group sg, const ::io_priority_class& iop, float static_shares)
: _scheduling_group(sg)
, _io_priority(iop)
, _inflight_update(make_ready_future<>())
{
update_controller(static_shares);
}
virtual ~backlog_controller() {}
public:
backlog_controller(backlog_controller&&) = default;
float backlog_of_shares(float shares) const;
seastar::scheduling_group sg() {
return _scheduling_group;
}
};
// memtable flush CPU controller.
//
// - First threshold is the soft limit line,
// - Maximum is the point in which we'd stop consuming request,
// - Second threshold is halfway between them.
//
// Below the soft limit, we are in no particular hurry to flush, since it means we're set to
// complete flushing before we a new memtable is ready. The quota is dirty * q1, and q1 is set to a
// low number.
//
// The first half of the virtual dirty region is where we expect to be usually, so we have a low
// slope corresponding to a sluggish response between q1 * soft_limit and q2.
//
// In the second half, we're getting close to the hard dirty limit so we increase the slope and
// become more responsive, up to a maximum quota of qmax.
class flush_controller : public backlog_controller {
static constexpr float hard_dirty_limit = 1.0f;
public:
flush_controller(seastar::scheduling_group sg, const ::io_priority_class& iop, float static_shares) : backlog_controller(sg, iop, static_shares) {}
flush_controller(seastar::scheduling_group sg, const ::io_priority_class& iop, std::chrono::milliseconds interval, float soft_limit, std::function<float()> current_dirty)
: backlog_controller(sg, iop, std::move(interval),
std::vector<backlog_controller::control_point>({{soft_limit, 10}, {soft_limit + (hard_dirty_limit - soft_limit) / 2, 200} , {hard_dirty_limit, 1000}}),
std::move(current_dirty)
)
{}
};
class compaction_controller : public backlog_controller {
public:
static constexpr unsigned normalization_factor = 30;
static constexpr float disable_backlog = std::numeric_limits<double>::infinity();
static constexpr float backlog_disabled(float backlog) { return std::isinf(backlog); }
compaction_controller(seastar::scheduling_group sg, const ::io_priority_class& iop, float static_shares) : backlog_controller(sg, iop, static_shares) {}
compaction_controller(seastar::scheduling_group sg, const ::io_priority_class& iop, std::chrono::milliseconds interval, std::function<float()> current_backlog)
: backlog_controller(sg, iop, std::move(interval),
std::vector<backlog_controller::control_point>({{0.5, 10}, {1.5, 100} , {normalization_factor, 1000}}),
std::move(current_backlog)
)
{}
};

View File

@@ -21,17 +21,14 @@
#pragma once
#include "seastarx.hh"
#include "core/sstring.hh"
#include "hashing.hh"
#include <experimental/optional>
#include <iosfwd>
#include <functional>
#include "utils/mutable_view.hh"
using bytes = basic_sstring<int8_t, uint32_t, 31, false>;
using bytes = basic_sstring<int8_t, uint32_t, 31>;
using bytes_view = std::experimental::basic_string_view<int8_t>;
using bytes_mutable_view = basic_mutable_view<bytes_view::value_type>;
using bytes_opt = std::experimental::optional<bytes>;
using sstring_view = std::experimental::string_view;
@@ -78,11 +75,3 @@ struct appending_hash<bytes_view> {
h.update(reinterpret_cast<const char*>(v.begin()), v.size() * sizeof(bytes_view::value_type));
}
};
inline int32_t compare_unsigned(bytes_view v1, bytes_view v2) {
auto n = memcmp(v1.begin(), v2.begin(), std::min(v1.size(), v2.size()));
if (n) {
return n;
}
return (int32_t) (v1.size() - v2.size());
}

View File

@@ -65,9 +65,8 @@ private:
size_type _size;
public:
class fragment_iterator : public std::iterator<std::input_iterator_tag, bytes_view> {
chunk* _current = nullptr;
chunk* _current;
public:
fragment_iterator() = default;
fragment_iterator(chunk* current) : _current(current) {}
fragment_iterator(const fragment_iterator&) = default;
fragment_iterator& operator=(const fragment_iterator&) = default;
@@ -290,24 +289,6 @@ public:
}
}
// Removes n bytes from the end of the bytes_ostream.
// Beware of O(n) algorithm.
void remove_suffix(size_t n) {
_size -= n;
auto left = _size;
auto current = _begin.get();
while (current) {
if (current->offset >= left) {
current->offset = left;
_current = current;
current->next.reset();
return;
}
left -= current->offset;
current = current->next.get();
}
}
// begin() and end() form an input range to bytes_view representing fragments.
// Any modification of this instance invalidates iterators.
fragment_iterator begin() const { return { _begin.get() }; }

View File

@@ -1,671 +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 <vector>
#include "row_cache.hh"
#include "mutation_reader.hh"
#include "mutation_fragment.hh"
#include "partition_version.hh"
#include "utils/logalloc.hh"
#include "query-request.hh"
#include "partition_snapshot_reader.hh"
#include "partition_snapshot_row_cursor.hh"
#include "read_context.hh"
#include "flat_mutation_reader.hh"
namespace cache {
extern logging::logger clogger;
class cache_flat_mutation_reader final : public flat_mutation_reader::impl {
enum class state {
before_static_row,
// Invariants:
// - position_range(_lower_bound, _upper_bound) covers all not yet emitted positions from current range
// - if _next_row has valid iterators:
// - _next_row points to the nearest row in cache >= _lower_bound
// - _next_row_in_range = _next.position() < _upper_bound
// - if _next_row doesn't have valid iterators, it has no meaning.
reading_from_cache,
// Starts reading from underlying reader.
// The range to read is position_range(_lower_bound, min(_next_row.position(), _upper_bound)).
// Invariants:
// - _next_row_in_range = _next.position() < _upper_bound
move_to_underlying,
// Invariants:
// - Upper bound of the read is min(_next_row.position(), _upper_bound)
// - _next_row_in_range = _next.position() < _upper_bound
// - _last_row points at a direct predecessor of the next row which is going to be read.
// Used for populating continuity.
reading_from_underlying,
end_of_stream
};
partition_snapshot_ptr _snp;
position_in_partition::tri_compare _position_cmp;
query::clustering_key_filter_ranges _ck_ranges;
query::clustering_row_ranges::const_iterator _ck_ranges_curr;
query::clustering_row_ranges::const_iterator _ck_ranges_end;
lsa_manager _lsa_manager;
partition_snapshot_row_weakref _last_row;
// Holds the lower bound of a position range which hasn't been processed yet.
// Only rows with positions < _lower_bound have been emitted, and only
// range_tombstones with positions <= _lower_bound.
position_in_partition _lower_bound;
position_in_partition_view _upper_bound;
state _state = state::before_static_row;
lw_shared_ptr<read_context> _read_context;
partition_snapshot_row_cursor _next_row;
bool _next_row_in_range = false;
// Whether _lower_bound was changed within current fill_buffer().
// If it did not then we cannot break out of it (e.g. on preemption) because
// forward progress is not guaranteed in case iterators are getting constantly invalidated.
bool _lower_bound_changed = false;
future<> do_fill_buffer(db::timeout_clock::time_point);
void copy_from_cache_to_buffer();
future<> process_static_row(db::timeout_clock::time_point);
void move_to_end();
void move_to_next_range();
void move_to_range(query::clustering_row_ranges::const_iterator);
void move_to_next_entry();
void add_to_buffer(const partition_snapshot_row_cursor&);
void add_clustering_row_to_buffer(mutation_fragment&&);
void add_to_buffer(range_tombstone&&);
void add_to_buffer(mutation_fragment&&);
future<> read_from_underlying(db::timeout_clock::time_point);
void start_reading_from_underlying();
bool after_current_range(position_in_partition_view position);
bool can_populate() const;
// Marks the range between _last_row (exclusive) and _next_row (exclusive) as continuous,
// provided that the underlying reader still matches the latest version of the partition.
void maybe_update_continuity();
// Tries to ensure that the lower bound of the current population range exists.
// Returns false if it failed and range cannot be populated.
// Assumes can_populate().
bool ensure_population_lower_bound();
void maybe_add_to_cache(const mutation_fragment& mf);
void maybe_add_to_cache(const clustering_row& cr);
void maybe_add_to_cache(const range_tombstone& rt);
void maybe_add_to_cache(const static_row& sr);
void maybe_set_static_row_continuous();
void finish_reader() {
push_mutation_fragment(partition_end());
_end_of_stream = true;
_state = state::end_of_stream;
}
void touch_partition();
public:
cache_flat_mutation_reader(schema_ptr s,
dht::decorated_key dk,
query::clustering_key_filter_ranges&& crr,
lw_shared_ptr<read_context> ctx,
partition_snapshot_ptr snp,
row_cache& cache)
: flat_mutation_reader::impl(std::move(s))
, _snp(std::move(snp))
, _position_cmp(*_schema)
, _ck_ranges(std::move(crr))
, _ck_ranges_curr(_ck_ranges.begin())
, _ck_ranges_end(_ck_ranges.end())
, _lsa_manager(cache)
, _lower_bound(position_in_partition::before_all_clustered_rows())
, _upper_bound(position_in_partition_view::before_all_clustered_rows())
, _read_context(std::move(ctx))
, _next_row(*_schema, *_snp)
{
clogger.trace("csm {}: table={}.{}", this, _schema->ks_name(), _schema->cf_name());
push_mutation_fragment(partition_start(std::move(dk), _snp->partition_tombstone()));
}
cache_flat_mutation_reader(const cache_flat_mutation_reader&) = delete;
cache_flat_mutation_reader(cache_flat_mutation_reader&&) = delete;
virtual future<> fill_buffer(db::timeout_clock::time_point timeout) override;
virtual void next_partition() override {
clear_buffer_to_next_partition();
if (is_buffer_empty()) {
_end_of_stream = true;
}
}
virtual future<> fast_forward_to(const dht::partition_range&, db::timeout_clock::time_point timeout) override {
clear_buffer();
_end_of_stream = true;
return make_ready_future<>();
}
virtual future<> fast_forward_to(position_range pr, db::timeout_clock::time_point timeout) override {
throw std::bad_function_call();
}
};
inline
future<> cache_flat_mutation_reader::process_static_row(db::timeout_clock::time_point timeout) {
if (_snp->static_row_continuous()) {
_read_context->cache().on_row_hit();
static_row sr = _lsa_manager.run_in_read_section([this] {
return _snp->static_row(_read_context->digest_requested());
});
if (!sr.empty()) {
push_mutation_fragment(mutation_fragment(std::move(sr)));
}
return make_ready_future<>();
} else {
_read_context->cache().on_row_miss();
return _read_context->get_next_fragment(timeout).then([this] (mutation_fragment_opt&& sr) {
if (sr) {
assert(sr->is_static_row());
maybe_add_to_cache(sr->as_static_row());
push_mutation_fragment(std::move(*sr));
}
maybe_set_static_row_continuous();
});
}
}
inline
void cache_flat_mutation_reader::touch_partition() {
if (_snp->at_latest_version()) {
rows_entry& last_dummy = *_snp->version()->partition().clustered_rows().rbegin();
_snp->tracker()->touch(last_dummy);
}
}
inline
future<> cache_flat_mutation_reader::fill_buffer(db::timeout_clock::time_point timeout) {
if (_state == state::before_static_row) {
auto after_static_row = [this, timeout] {
if (_ck_ranges_curr == _ck_ranges_end) {
touch_partition();
finish_reader();
return make_ready_future<>();
}
_state = state::reading_from_cache;
_lsa_manager.run_in_read_section([this] {
move_to_range(_ck_ranges_curr);
});
return fill_buffer(timeout);
};
if (_schema->has_static_columns()) {
return process_static_row(timeout).then(std::move(after_static_row));
} else {
return after_static_row();
}
}
clogger.trace("csm {}: fill_buffer(), range={}, lb={}", this, *_ck_ranges_curr, _lower_bound);
return do_until([this] { return _end_of_stream || is_buffer_full(); }, [this, timeout] {
return do_fill_buffer(timeout);
});
}
inline
future<> cache_flat_mutation_reader::do_fill_buffer(db::timeout_clock::time_point timeout) {
if (_state == state::move_to_underlying) {
_state = state::reading_from_underlying;
auto end = _next_row_in_range ? position_in_partition(_next_row.position())
: position_in_partition(_upper_bound);
return _read_context->fast_forward_to(position_range{_lower_bound, std::move(end)}, timeout).then([this, timeout] {
return read_from_underlying(timeout);
});
}
if (_state == state::reading_from_underlying) {
return read_from_underlying(timeout);
}
// assert(_state == state::reading_from_cache)
return _lsa_manager.run_in_read_section([this] {
auto next_valid = _next_row.iterators_valid();
clogger.trace("csm {}: reading_from_cache, range=[{}, {}), next={}, valid={}", this, _lower_bound,
_upper_bound, _next_row.position(), next_valid);
// We assume that if there was eviction, and thus the range may
// no longer be continuous, the cursor was invalidated.
if (!next_valid) {
auto adjacent = _next_row.advance_to(_lower_bound);
_next_row_in_range = !after_current_range(_next_row.position());
if (!adjacent && !_next_row.continuous()) {
_last_row = nullptr; // We could insert a dummy here, but this path is unlikely.
start_reading_from_underlying();
return make_ready_future<>();
}
}
_next_row.maybe_refresh();
clogger.trace("csm {}: next={}, cont={}", this, _next_row.position(), _next_row.continuous());
_lower_bound_changed = false;
while (_state == state::reading_from_cache) {
copy_from_cache_to_buffer();
// We need to check _lower_bound_changed even if is_buffer_full() because
// we may have emitted only a range tombstone which overlapped with _lower_bound
// and thus didn't cause _lower_bound to change.
if ((need_preempt() || is_buffer_full()) && _lower_bound_changed) {
break;
}
}
return make_ready_future<>();
});
}
inline
future<> cache_flat_mutation_reader::read_from_underlying(db::timeout_clock::time_point timeout) {
return consume_mutation_fragments_until(_read_context->underlying().underlying(),
[this] { return _state != state::reading_from_underlying || is_buffer_full(); },
[this] (mutation_fragment mf) {
_read_context->cache().on_row_miss();
maybe_add_to_cache(mf);
add_to_buffer(std::move(mf));
},
[this] {
_state = state::reading_from_cache;
_lsa_manager.run_in_update_section([this] {
auto same_pos = _next_row.maybe_refresh();
if (!same_pos) {
_read_context->cache().on_mispopulate(); // FIXME: Insert dummy entry at _upper_bound.
_next_row_in_range = !after_current_range(_next_row.position());
if (!_next_row.continuous()) {
start_reading_from_underlying();
}
return;
}
if (_next_row_in_range) {
maybe_update_continuity();
_last_row = _next_row;
add_to_buffer(_next_row);
try {
move_to_next_entry();
} catch (const std::bad_alloc&) {
// We cannot reenter the section, since we may have moved to the new range, and
// because add_to_buffer() should not be repeated.
_snp->region().allocator().invalidate_references(); // Invalidates _next_row
}
} else {
if (no_clustering_row_between(*_schema, _upper_bound, _next_row.position())) {
this->maybe_update_continuity();
} else if (can_populate()) {
rows_entry::compare less(*_schema);
auto& rows = _snp->version()->partition().clustered_rows();
if (query::is_single_row(*_schema, *_ck_ranges_curr)) {
with_allocator(_snp->region().allocator(), [&] {
auto e = alloc_strategy_unique_ptr<rows_entry>(
current_allocator().construct<rows_entry>(_ck_ranges_curr->start()->value()));
// Use _next_row iterator only as a hint, because there could be insertions after _upper_bound.
auto insert_result = rows.insert_check(_next_row.get_iterator_in_latest_version(), *e, less);
auto inserted = insert_result.second;
auto it = insert_result.first;
if (inserted) {
_snp->tracker()->insert(*e);
e.release();
auto next = std::next(it);
it->set_continuous(next->continuous());
clogger.trace("csm {}: inserted dummy at {}, cont={}", this, it->position(), it->continuous());
}
});
} else if (ensure_population_lower_bound()) {
with_allocator(_snp->region().allocator(), [&] {
auto e = alloc_strategy_unique_ptr<rows_entry>(
current_allocator().construct<rows_entry>(*_schema, _upper_bound, is_dummy::yes, is_continuous::yes));
// Use _next_row iterator only as a hint, because there could be insertions after _upper_bound.
auto insert_result = rows.insert_check(_next_row.get_iterator_in_latest_version(), *e, less);
auto inserted = insert_result.second;
if (inserted) {
clogger.trace("csm {}: inserted dummy at {}", this, _upper_bound);
_snp->tracker()->insert(*e);
e.release();
} else {
clogger.trace("csm {}: mark {} as continuous", this, insert_result.first->position());
insert_result.first->set_continuous(true);
}
});
}
} else {
_read_context->cache().on_mispopulate();
}
try {
move_to_next_range();
} catch (const std::bad_alloc&) {
// We cannot reenter the section, since we may have moved to the new range
_snp->region().allocator().invalidate_references(); // Invalidates _next_row
}
}
});
return make_ready_future<>();
});
}
inline
bool cache_flat_mutation_reader::ensure_population_lower_bound() {
if (!_ck_ranges_curr->start()) {
return true;
}
if (!_last_row.refresh(*_snp)) {
return false;
}
// Continuity flag we will later set for the upper bound extends to the previous row in the same version,
// so we need to ensure we have an entry in the latest version.
if (!_last_row.is_in_latest_version()) {
with_allocator(_snp->region().allocator(), [&] {
auto& rows = _snp->version()->partition().clustered_rows();
rows_entry::compare less(*_schema);
// FIXME: Avoid the copy by inserting an incomplete clustering row
auto e = alloc_strategy_unique_ptr<rows_entry>(
current_allocator().construct<rows_entry>(*_schema, *_last_row));
e->set_continuous(false);
auto insert_result = rows.insert_check(rows.end(), *e, less);
auto inserted = insert_result.second;
if (inserted) {
clogger.trace("csm {}: inserted lower bound dummy at {}", this, e->position());
_snp->tracker()->insert(*e);
e.release();
}
});
}
return true;
}
inline
void cache_flat_mutation_reader::maybe_update_continuity() {
if (can_populate() && ensure_population_lower_bound()) {
with_allocator(_snp->region().allocator(), [&] {
rows_entry& e = _next_row.ensure_entry_in_latest().row;
e.set_continuous(true);
});
} else {
_read_context->cache().on_mispopulate();
}
}
inline
void cache_flat_mutation_reader::maybe_add_to_cache(const mutation_fragment& mf) {
if (mf.is_range_tombstone()) {
maybe_add_to_cache(mf.as_range_tombstone());
} else {
assert(mf.is_clustering_row());
const clustering_row& cr = mf.as_clustering_row();
maybe_add_to_cache(cr);
}
}
inline
void cache_flat_mutation_reader::maybe_add_to_cache(const clustering_row& cr) {
if (!can_populate()) {
_last_row = nullptr;
_read_context->cache().on_mispopulate();
return;
}
clogger.trace("csm {}: populate({})", this, cr);
_lsa_manager.run_in_update_section_with_allocator([this, &cr] {
mutation_partition& mp = _snp->version()->partition();
rows_entry::compare less(*_schema);
if (_read_context->digest_requested()) {
cr.cells().prepare_hash(*_schema, column_kind::regular_column);
}
auto new_entry = alloc_strategy_unique_ptr<rows_entry>(
current_allocator().construct<rows_entry>(*_schema, cr.key(), cr.tomb(), cr.marker(), cr.cells()));
new_entry->set_continuous(false);
auto it = _next_row.iterators_valid() ? _next_row.get_iterator_in_latest_version()
: mp.clustered_rows().lower_bound(cr.key(), less);
auto insert_result = mp.clustered_rows().insert_check(it, *new_entry, less);
if (insert_result.second) {
_snp->tracker()->insert(*new_entry);
new_entry.release();
}
it = insert_result.first;
rows_entry& e = *it;
if (ensure_population_lower_bound()) {
clogger.trace("csm {}: set_continuous({})", this, e.position());
e.set_continuous(true);
} else {
_read_context->cache().on_mispopulate();
}
with_allocator(standard_allocator(), [&] {
_last_row = partition_snapshot_row_weakref(*_snp, it, true);
});
});
}
inline
bool cache_flat_mutation_reader::after_current_range(position_in_partition_view p) {
return _position_cmp(p, _upper_bound) >= 0;
}
inline
void cache_flat_mutation_reader::start_reading_from_underlying() {
clogger.trace("csm {}: start_reading_from_underlying(), range=[{}, {})", this, _lower_bound, _next_row_in_range ? _next_row.position() : _upper_bound);
_state = state::move_to_underlying;
_next_row.touch();
}
inline
void cache_flat_mutation_reader::copy_from_cache_to_buffer() {
clogger.trace("csm {}: copy_from_cache, next={}, next_row_in_range={}", this, _next_row.position(), _next_row_in_range);
_next_row.touch();
position_in_partition_view next_lower_bound = _next_row.dummy() ? _next_row.position() : position_in_partition_view::after_key(_next_row.key());
for (auto &&rts : _snp->range_tombstones(_lower_bound, _next_row_in_range ? next_lower_bound : _upper_bound)) {
position_in_partition::less_compare less(*_schema);
// This guarantees that rts starts after any emitted clustering_row
// and not before any emitted range tombstone.
if (!less(_lower_bound, rts.position())) {
rts.set_start(*_schema, _lower_bound);
} else {
_lower_bound = position_in_partition(rts.position());
_lower_bound_changed = true;
if (is_buffer_full()) {
return;
}
}
push_mutation_fragment(std::move(rts));
}
// We add the row to the buffer even when it's full.
// This simplifies the code. For more info see #3139.
if (_next_row_in_range) {
_last_row = _next_row;
add_to_buffer(_next_row);
move_to_next_entry();
} else {
move_to_next_range();
}
}
inline
void cache_flat_mutation_reader::move_to_end() {
finish_reader();
clogger.trace("csm {}: eos", this);
}
inline
void cache_flat_mutation_reader::move_to_next_range() {
auto next_it = std::next(_ck_ranges_curr);
if (next_it == _ck_ranges_end) {
move_to_end();
_ck_ranges_curr = next_it;
} else {
move_to_range(next_it);
}
}
inline
void cache_flat_mutation_reader::move_to_range(query::clustering_row_ranges::const_iterator next_it) {
auto lb = position_in_partition::for_range_start(*next_it);
auto ub = position_in_partition_view::for_range_end(*next_it);
_last_row = nullptr;
_lower_bound = std::move(lb);
_upper_bound = std::move(ub);
_lower_bound_changed = true;
_ck_ranges_curr = next_it;
auto adjacent = _next_row.advance_to(_lower_bound);
_next_row_in_range = !after_current_range(_next_row.position());
clogger.trace("csm {}: move_to_range(), range={}, lb={}, ub={}, next={}", this, *_ck_ranges_curr, _lower_bound, _upper_bound, _next_row.position());
if (!adjacent && !_next_row.continuous()) {
// FIXME: We don't insert a dummy for singular range to avoid allocating 3 entries
// for a hit (before, at and after). If we supported the concept of an incomplete row,
// we could insert such a row for the lower bound if it's full instead, for both singular and
// non-singular ranges.
if (_ck_ranges_curr->start() && !query::is_single_row(*_schema, *_ck_ranges_curr)) {
// Insert dummy for lower bound
if (can_populate()) {
// FIXME: _lower_bound could be adjacent to the previous row, in which case we could skip this
clogger.trace("csm {}: insert dummy at {}", this, _lower_bound);
auto it = with_allocator(_lsa_manager.region().allocator(), [&] {
auto& rows = _snp->version()->partition().clustered_rows();
auto new_entry = current_allocator().construct<rows_entry>(*_schema, _lower_bound, is_dummy::yes, is_continuous::no);
return rows.insert_before(_next_row.get_iterator_in_latest_version(), *new_entry);
});
_snp->tracker()->insert(*it);
_last_row = partition_snapshot_row_weakref(*_snp, it, true);
} else {
_read_context->cache().on_mispopulate();
}
}
start_reading_from_underlying();
}
}
// _next_row must be inside the range.
inline
void cache_flat_mutation_reader::move_to_next_entry() {
clogger.trace("csm {}: move_to_next_entry(), curr={}", this, _next_row.position());
if (no_clustering_row_between(*_schema, _next_row.position(), _upper_bound)) {
move_to_next_range();
} else {
if (!_next_row.next()) {
move_to_end();
return;
}
_next_row_in_range = !after_current_range(_next_row.position());
clogger.trace("csm {}: next={}, cont={}, in_range={}", this, _next_row.position(), _next_row.continuous(), _next_row_in_range);
if (!_next_row.continuous()) {
start_reading_from_underlying();
}
}
}
inline
void cache_flat_mutation_reader::add_to_buffer(mutation_fragment&& mf) {
clogger.trace("csm {}: add_to_buffer({})", this, mf);
if (mf.is_clustering_row()) {
add_clustering_row_to_buffer(std::move(mf));
} else {
assert(mf.is_range_tombstone());
add_to_buffer(std::move(mf).as_range_tombstone());
}
}
inline
void cache_flat_mutation_reader::add_to_buffer(const partition_snapshot_row_cursor& row) {
if (!row.dummy()) {
_read_context->cache().on_row_hit();
add_clustering_row_to_buffer(row.row(_read_context->digest_requested()));
}
}
// Maintains the following invariants, also in case of exception:
// (1) no fragment with position >= _lower_bound was pushed yet
// (2) If _lower_bound > mf.position(), mf was emitted
inline
void cache_flat_mutation_reader::add_clustering_row_to_buffer(mutation_fragment&& mf) {
clogger.trace("csm {}: add_clustering_row_to_buffer({})", this, mf);
auto& row = mf.as_clustering_row();
auto new_lower_bound = position_in_partition::after_key(row.key());
push_mutation_fragment(std::move(mf));
_lower_bound = std::move(new_lower_bound);
_lower_bound_changed = true;
}
inline
void cache_flat_mutation_reader::add_to_buffer(range_tombstone&& rt) {
clogger.trace("csm {}: add_to_buffer({})", this, rt);
// This guarantees that rt starts after any emitted clustering_row
// and not before any emitted range tombstone.
position_in_partition::less_compare less(*_schema);
if (!less(_lower_bound, rt.end_position())) {
return;
}
if (!less(_lower_bound, rt.position())) {
rt.set_start(*_schema, _lower_bound);
} else {
_lower_bound = position_in_partition(rt.position());
_lower_bound_changed = true;
}
push_mutation_fragment(std::move(rt));
}
inline
void cache_flat_mutation_reader::maybe_add_to_cache(const range_tombstone& rt) {
if (can_populate()) {
clogger.trace("csm {}: maybe_add_to_cache({})", this, rt);
_lsa_manager.run_in_update_section_with_allocator([&] {
_snp->version()->partition().row_tombstones().apply_monotonically(*_schema, rt);
});
} else {
_read_context->cache().on_mispopulate();
}
}
inline
void cache_flat_mutation_reader::maybe_add_to_cache(const static_row& sr) {
if (can_populate()) {
clogger.trace("csm {}: populate({})", this, sr);
_read_context->cache().on_static_row_insert();
_lsa_manager.run_in_update_section_with_allocator([&] {
if (_read_context->digest_requested()) {
sr.cells().prepare_hash(*_schema, column_kind::static_column);
}
_snp->version()->partition().static_row().apply(*_schema, column_kind::static_column, sr.cells());
});
} else {
_read_context->cache().on_mispopulate();
}
}
inline
void cache_flat_mutation_reader::maybe_set_static_row_continuous() {
if (can_populate()) {
clogger.trace("csm {}: set static row continuous", this);
_snp->version()->partition().set_static_row_continuous(true);
} else {
_read_context->cache().on_mispopulate();
}
}
inline
bool cache_flat_mutation_reader::can_populate() const {
return _snp->at_latest_version() && _read_context->cache().phase_of(_read_context->key()) == _read_context->phase();
}
} // namespace cache
inline flat_mutation_reader make_cache_flat_mutation_reader(schema_ptr s,
dht::decorated_key dk,
query::clustering_key_filter_ranges crr,
row_cache& cache,
lw_shared_ptr<cache::read_context> ctx,
partition_snapshot_ptr snp)
{
return make_flat_mutation_reader<cache::cache_flat_mutation_reader>(
std::move(s), std::move(dk), std::move(crr), std::move(ctx), std::move(snp), cache);
}

View File

@@ -24,7 +24,6 @@
#include <boost/lexical_cast.hpp>
#include "exceptions/exceptions.hh"
#include "json.hh"
#include "seastarx.hh"
class schema;
@@ -59,34 +58,30 @@ class caching_options {
caching_options() : _key_cache(default_key), _row_cache(default_row) {}
public:
std::map<sstring, sstring> to_map() const {
return {{ "keys", _key_cache }, { "rows_per_partition", _row_cache }};
}
sstring to_sstring() const {
return json::to_json(to_map());
return json::to_json(std::map<sstring, sstring>({{ "keys", _key_cache }, { "rows_per_partition", _row_cache }}));
}
template<typename Map>
static caching_options from_map(const Map & map) {
sstring k = default_key;
sstring r = default_row;
static caching_options from_sstring(const sstring& str) {
auto map = json::to_map(str);
if (map.size() > 2) {
throw exceptions::configuration_exception("Invalid map: " + str);
}
sstring k;
sstring r;
if (map.count("keys")) {
k = map.at("keys");
} else {
k = default_key;
}
for (auto& p : map) {
if (p.first == "keys") {
k = p.second;
} else if (p.first == "rows_per_partition") {
r = p.second;
} else {
throw exceptions::configuration_exception("Invalid caching option: " + p.first);
}
if (map.count("rows_per_partition")) {
r = map.at("rows_per_partition");
} else {
r = default_row;
}
return caching_options(k, r);
}
static caching_options from_sstring(const sstring& str) {
return from_map(json::to_map(str));
}
bool operator==(const caching_options& other) const {
return _key_cache == other._key_cache && _row_cache == other._row_cache;
}

View File

@@ -75,7 +75,7 @@ mutation canonical_mutation::to_mutation(schema_ptr s) const {
auto version = mv.schema_version();
auto pk = mv.key();
mutation m(std::move(s), std::move(pk));
mutation m(std::move(pk), std::move(s));
if (version == m.schema()->version()) {
auto partition_view = mutation_partition_view::from_view(mv.partition());

View File

@@ -23,15 +23,27 @@
#include <boost/intrusive/unordered_set.hpp>
#include "utils/small_vector.hh"
#if __has_include(<boost/container/small_vector.hpp>)
#include <boost/container/small_vector.hpp>
template <typename T, size_t N>
using small_vector = boost::container::small_vector<T, N>;
#else
#include <vector>
template <typename T, size_t N>
using small_vector = std::vector<T>;
#endif
#include "fnv1a_hasher.hh"
#include "mutation_fragment.hh"
#include "streamed_mutation.hh"
#include "mutation_partition.hh"
#include "db/timeout_clock.hh"
class cells_range {
using ids_vector_type = utils::small_vector<column_id, 5>;
using ids_vector_type = small_vector<column_id, 5>;
position_in_partition_view _position;
ids_vector_type _ids;
@@ -124,13 +136,7 @@ public:
class locked_cell;
struct cell_locker_stats {
uint64_t lock_acquisitions = 0;
uint64_t operations_waiting_for_lock = 0;
};
class cell_locker {
private:
class partition_entry;
struct cell_address {
@@ -142,7 +148,7 @@ private:
public enable_lw_shared_from_this<cell_entry> {
partition_entry& _parent;
cell_address _address;
db::timeout_semaphore _semaphore { 0 };
semaphore _semaphore { 0 };
friend class cell_locker;
public:
@@ -171,8 +177,8 @@ private:
return _address.position;
}
future<> lock(db::timeout_clock::time_point _timeout) {
return _semaphore.wait(_timeout);
future<> lock() {
return _semaphore.wait();
}
void unlock() {
_semaphore.signal();
@@ -230,14 +236,14 @@ private:
bi::hash<cell_entry::hasher>,
bi::constant_time_size<false>>;
static constexpr size_t initial_bucket_count = 16;
static constexpr size_t initial_bucket_count = 64;
using max_load_factor = std::ratio<3, 4>;
dht::decorated_key _key;
cell_locker& _parent;
size_t _rehash_at_size = compute_rehash_at_size(initial_bucket_count);
std::unique_ptr<cells_type::bucket_type[]> _buckets; // TODO: start with internal storage?
size_t _cell_count = 0; // cells_type::empty() is not O(1) if the hook is auto-unlink
cells_type::bucket_type _internal_buckets[initial_bucket_count];
cells_type _cells;
schema_ptr _schema;
@@ -261,7 +267,8 @@ private:
partition_entry(schema_ptr s, cell_locker& parent, const dht::decorated_key& dk)
: _key(dk)
, _parent(parent)
, _cells(cells_type::bucket_traits(_internal_buckets, initial_bucket_count),
, _buckets(std::make_unique<cells_type::bucket_type[]>(initial_bucket_count))
, _cells(cells_type::bucket_traits(_buckets.get(), initial_bucket_count),
cell_entry::hasher(*s), cell_entry::equal_compare(*s))
, _schema(s)
{ }
@@ -328,7 +335,6 @@ private:
// partitions_type uses equality comparator which keeps a reference to the
// original schema, we must ensure that it doesn't die.
schema_ptr _original_schema;
cell_locker_stats& _stats;
friend class locked_cell;
private:
@@ -349,13 +355,12 @@ private:
}
}
public:
explicit cell_locker(schema_ptr s, cell_locker_stats& stats)
explicit cell_locker(schema_ptr s)
: _buckets(std::make_unique<partitions_type::bucket_type[]>(initial_bucket_count))
, _partitions(partitions_type::bucket_traits(_buckets.get(), initial_bucket_count),
partition_entry::hasher(), partition_entry::equal_compare(*s))
, _schema(s)
, _original_schema(std::move(s))
, _stats(stats)
{ }
~cell_locker() {
@@ -370,8 +375,7 @@ public:
}
// partition_cells_range is required to be in cell_locker::schema()
future<std::vector<locked_cell>> lock_cells(const dht::decorated_key& dk, partition_cells_range&& range,
db::timeout_clock::time_point timeout);
future<std::vector<locked_cell>> lock_cells(const dht::decorated_key& dk, partition_cells_range&& range);
};
@@ -400,9 +404,7 @@ struct cell_locker::locker {
partition_cells_range::iterator _current_ck;
cells_range::const_iterator _current_cell;
db::timeout_clock::time_point _timeout;
std::vector<locked_cell> _locks;
cell_locker_stats& _stats;
private:
void update_ck() {
if (!is_done()) {
@@ -414,14 +416,12 @@ private:
bool is_done() const { return _current_ck == _range.end(); }
public:
explicit locker(const ::schema& s, cell_locker_stats& st, partition_entry& pe, partition_cells_range&& range, db::timeout_clock::time_point timeout)
explicit locker(const ::schema& s, partition_entry& pe, partition_cells_range&& range)
: _hasher(s)
, _eq_cmp(s)
, _partition_entry(pe)
, _range(std::move(range))
, _current_ck(_range.begin())
, _timeout(timeout)
, _stats(st)
{
update_ck();
}
@@ -442,7 +442,7 @@ public:
};
inline
future<std::vector<locked_cell>> cell_locker::lock_cells(const dht::decorated_key& dk, partition_cells_range&& range, db::timeout_clock::time_point timeout) {
future<std::vector<locked_cell>> cell_locker::lock_cells(const dht::decorated_key& dk, partition_cells_range&& range) {
partition_entry::hasher pe_hash;
partition_entry::equal_compare pe_eq(*_schema);
@@ -464,7 +464,6 @@ future<std::vector<locked_cell>> cell_locker::lock_cells(const dht::decorated_ke
}
for (auto&& c : r) {
auto cell = make_lw_shared<cell_entry>(*partition, position_in_partition(r.position()), c);
_stats.lock_acquisitions++;
partition->insert(cell);
locks.emplace_back(std::move(cell));
}
@@ -478,7 +477,7 @@ future<std::vector<locked_cell>> cell_locker::lock_cells(const dht::decorated_ke
return make_ready_future<std::vector<locked_cell>>(std::move(locks));
}
auto l = std::make_unique<locker>(*_schema, _stats, *it, std::move(range), timeout);
auto l = std::make_unique<locker>(*_schema, *it, std::move(range));
auto f = l->lock_all();
return f.then([l = std::move(l)] {
return std::move(*l).get();
@@ -499,16 +498,12 @@ future<> cell_locker::locker::lock_next() {
cell_address ca { position_in_partition(_current_ck->position()), cid };
auto it = _partition_entry.cells().find(ca, _hasher, _eq_cmp);
if (it != _partition_entry.cells().end()) {
_stats.operations_waiting_for_lock++;
return it->lock(_timeout).then([this, ce = it->shared_from_this()] () mutable {
_stats.operations_waiting_for_lock--;
_stats.lock_acquisitions++;
return it->lock().then([this, ce = it->shared_from_this()] () mutable {
_locks.emplace_back(std::move(ce));
});
}
auto cell = make_lw_shared<cell_entry>(_partition_entry, position_in_partition(_current_ck->position()), cid);
_stats.lock_acquisitions++;
_partition_entry.insert(cell);
_locks.emplace_back(std::move(cell));
}

View File

@@ -112,11 +112,6 @@ public:
});
}
virtual future<temporary_buffer<uint8_t>> dma_read_bulk(uint64_t offset, size_t range_size, const io_priority_class& pc) override {
return do_io_check(_error_handler, [&] {
return get_file_impl(_file)->dma_read_bulk(offset, range_size, pc);
});
}
private:
const io_error_handler& _error_handler;
file _file;
@@ -130,7 +125,7 @@ inline file make_checked_file(const io_error_handler& error_handler, file f)
future<file>
inline open_checked_file_dma(const io_error_handler& error_handler,
sstring name, open_flags flags,
file_open_options options = {})
file_open_options options)
{
return do_io_check(error_handler, [&] {
return open_file_dma(name, flags, options).then([&] (file f) {
@@ -139,6 +134,17 @@ inline open_checked_file_dma(const io_error_handler& error_handler,
});
}
future<file>
inline open_checked_file_dma(const io_error_handler& error_handler,
sstring name, open_flags flags)
{
return do_io_check(error_handler, [&] {
return open_file_dma(name, flags).then([&] (file f) {
return make_ready_future<file>(make_checked_file(error_handler, f));
});
});
}
future<file>
inline open_checked_directory(const io_error_handler& error_handler,
sstring name)

View File

@@ -1,49 +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 <algorithm>
#include <atomic>
#include <chrono>
#include <cstdint>
extern std::atomic<int64_t> clocks_offset;
template<typename Duration>
static inline void forward_jump_clocks(Duration delta)
{
auto d = std::chrono::duration_cast<std::chrono::seconds>(delta).count();
clocks_offset.fetch_add(d, std::memory_order_relaxed);
}
static inline std::chrono::seconds get_clocks_offset()
{
auto off = clocks_offset.load(std::memory_order_relaxed);
return std::chrono::seconds(off);
}
// Returns a time point which is earlier from t by d, or minimum time point if it cannot be represented.
template<typename Clock, typename Duration, typename Rep, typename Period>
inline
auto saturating_subtract(std::chrono::time_point<Clock, Duration> t, std::chrono::duration<Rep, Period> d) -> decltype(t) {
return std::max(t, decltype(t)::min() + d) - d;
}

View File

@@ -22,7 +22,6 @@
#pragma once
#include <functional>
#include "keys.hh"
#include "schema.hh"
#include "range.hh"
@@ -43,21 +42,34 @@ std::ostream& operator<<(std::ostream& out, const bound_kind k);
bound_kind invert_kind(bound_kind k);
int32_t weight(bound_kind k);
static inline bound_kind flip_bound_kind(bound_kind bk)
{
switch (bk) {
case bound_kind::excl_end: return bound_kind::excl_start;
case bound_kind::incl_end: return bound_kind::incl_start;
case bound_kind::excl_start: return bound_kind::excl_end;
case bound_kind::incl_start: return bound_kind::incl_end;
}
abort();
}
class bound_view {
const static thread_local clustering_key _empty_prefix;
std::reference_wrapper<const clustering_key_prefix> _prefix;
bound_kind _kind;
const static thread_local clustering_key empty_prefix;
public:
const clustering_key_prefix& prefix;
bound_kind kind;
bound_view(const clustering_key_prefix& prefix, bound_kind kind)
: _prefix(prefix)
, _kind(kind)
: prefix(prefix)
, kind(kind)
{ }
bound_view(const bound_view& other) noexcept = default;
bound_view& operator=(const bound_view& other) noexcept = default;
bound_kind kind() const { return _kind; }
const clustering_key_prefix& prefix() const { return _prefix; }
bound_view& operator=(const bound_view& other) noexcept {
if (this != &other) {
this->~bound_view();
new (this) bound_view(other);
}
return *this;
}
struct tri_compare {
// To make it assignable and to avoid taking a schema_ptr, we
// wrap the schema reference.
@@ -81,13 +93,13 @@ public:
return d1 < d2 ? w1 - (w1 <= 0) : -(w2 - (w2 <= 0));
}
int operator()(const bound_view b, const clustering_key_prefix& p) const {
return operator()(b._prefix, weight(b._kind), p, 0);
return operator()(b.prefix, weight(b.kind), p, 0);
}
int operator()(const clustering_key_prefix& p, const bound_view b) const {
return operator()(p, 0, b._prefix, weight(b._kind));
return operator()(p, 0, b.prefix, weight(b.kind));
}
int operator()(const bound_view b1, const bound_view b2) const {
return operator()(b1._prefix, weight(b1._kind), b2._prefix, weight(b2._kind));
return operator()(b1.prefix, weight(b1.kind), b2.prefix, weight(b2.kind));
}
};
struct compare {
@@ -100,56 +112,43 @@ public:
return _cmp(p1, w1, p2, w2) < 0;
}
bool operator()(const bound_view b, const clustering_key_prefix& p) const {
return operator()(b._prefix, weight(b._kind), p, 0);
return operator()(b.prefix, weight(b.kind), p, 0);
}
bool operator()(const clustering_key_prefix& p, const bound_view b) const {
return operator()(p, 0, b._prefix, weight(b._kind));
return operator()(p, 0, b.prefix, weight(b.kind));
}
bool operator()(const bound_view b1, const bound_view b2) const {
return operator()(b1._prefix, weight(b1._kind), b2._prefix, weight(b2._kind));
return operator()(b1.prefix, weight(b1.kind), b2.prefix, weight(b2.kind));
}
};
bool equal(const schema& s, const bound_view other) const {
return _kind == other._kind && _prefix.get().equal(s, other._prefix.get());
return kind == other.kind && prefix.equal(s, other.prefix);
}
bool adjacent(const schema& s, const bound_view other) const {
return invert_kind(other._kind) == _kind && _prefix.get().equal(s, other._prefix.get());
return invert_kind(other.kind) == kind && prefix.equal(s, other.prefix);
}
static bound_view bottom() {
return {_empty_prefix, bound_kind::incl_start};
return {empty_prefix, bound_kind::incl_start};
}
static bound_view top() {
return {_empty_prefix, bound_kind::incl_end};
return {empty_prefix, bound_kind::incl_end};
}
template<template<typename> typename R>
GCC6_CONCEPT( requires Range<R, clustering_key_prefix_view> )
static bound_view from_range_start(const R<clustering_key_prefix>& range) {
return range.start()
? bound_view(range.start()->value(), range.start()->is_inclusive() ? bound_kind::incl_start : bound_kind::excl_start)
: bottom();
}
template<template<typename> typename R>
GCC6_CONCEPT( requires Range<R, clustering_key_prefix> )
static bound_view from_range_end(const R<clustering_key_prefix>& range) {
return range.end()
? bound_view(range.end()->value(), range.end()->is_inclusive() ? bound_kind::incl_end : bound_kind::excl_end)
: top();
}
template<template<typename> typename R>
GCC6_CONCEPT( requires Range<R, clustering_key_prefix> )
static std::pair<bound_view, bound_view> from_range(const R<clustering_key_prefix>& range) {
return {from_range_start(range), from_range_end(range)};
}
template<template<typename> typename R>
GCC6_CONCEPT( requires Range<R, clustering_key_prefix_view> )
static stdx::optional<typename R<clustering_key_prefix_view>::bound> to_range_bound(const bound_view& bv) {
if (&bv._prefix.get() == &_empty_prefix) {
return {};
}
bool inclusive = bv._kind != bound_kind::excl_end && bv._kind != bound_kind::excl_start;
return {typename R<clustering_key_prefix_view>::bound(bv._prefix.get().view(), inclusive)};
/*
template<template<typename> typename T, typename U>
concept bool Range() {
return requires (T<U> range) {
{ range.start() } -> stdx::optional<U>;
{ range.end() } -> stdx::optional<U>;
};
};*/
template<template<typename> typename Range>
static std::pair<bound_view, bound_view> from_range(const Range<clustering_key_prefix>& range) {
return {
range.start() ? bound_view(range.start()->value(), range.start()->is_inclusive() ? bound_kind::incl_start : bound_kind::excl_start) : bottom(),
range.end() ? bound_view(range.end()->value(), range.end()->is_inclusive() ? bound_kind::incl_end : bound_kind::excl_end) : top(),
};
}
friend std::ostream& operator<<(std::ostream& out, const bound_view& b) {
return out << "{bound: prefix=" << b._prefix.get() << ", kind=" << b._kind << "}";
return out << "{bound: prefix=" << b.prefix << ", kind=" << b.kind << "}";
}
};

View File

@@ -54,7 +54,6 @@ public:
auto end() const { return _ref.end(); }
bool empty() const { return _ref.empty(); }
size_t size() const { return _ref.size(); }
const clustering_row_ranges& ranges() const { return _ref; }
static clustering_key_filter_ranges get_ranges(const schema& schema, const query::partition_slice& slice, const partition_key& key) {
const query::clustering_row_ranges& ranges = slice.row_ranges(schema, key);

View File

@@ -1,219 +0,0 @@
/*
* Copyright (C) 2017 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 "schema.hh"
#include "query-request.hh"
#include "mutation_fragment.hh"
// Utility for in-order checking of overlap with position ranges.
class clustering_ranges_walker {
const schema& _schema;
const query::clustering_row_ranges& _ranges;
query::clustering_row_ranges::const_iterator _current;
query::clustering_row_ranges::const_iterator _end;
bool _in_current; // next position is known to be >= _current_start
bool _with_static_row;
position_in_partition_view _current_start;
position_in_partition_view _current_end;
stdx::optional<position_in_partition> _trim;
size_t _change_counter = 1;
private:
bool advance_to_next_range() {
_in_current = false;
if (!_current_start.is_static_row()) {
if (_current == _end) {
return false;
}
++_current;
}
++_change_counter;
if (_current == _end) {
_current_end = _current_start = position_in_partition_view::after_all_clustered_rows();
return false;
}
_current_start = position_in_partition_view::for_range_start(*_current);
_current_end = position_in_partition_view::for_range_end(*_current);
return true;
}
public:
clustering_ranges_walker(const schema& s, const query::clustering_row_ranges& ranges, bool with_static_row = true)
: _schema(s)
, _ranges(ranges)
, _current(ranges.begin())
, _end(ranges.end())
, _in_current(with_static_row)
, _with_static_row(with_static_row)
, _current_start(position_in_partition_view::for_static_row())
, _current_end(position_in_partition_view::before_all_clustered_rows())
{
if (!with_static_row) {
if (_current == _end) {
_current_start = position_in_partition_view::before_all_clustered_rows();
} else {
_current_start = position_in_partition_view::for_range_start(*_current);
_current_end = position_in_partition_view::for_range_end(*_current);
}
}
}
clustering_ranges_walker(clustering_ranges_walker&& o) noexcept
: _schema(o._schema)
, _ranges(o._ranges)
, _current(o._current)
, _end(o._end)
, _in_current(o._in_current)
, _with_static_row(o._with_static_row)
, _current_start(o._current_start)
, _current_end(o._current_end)
, _trim(std::move(o._trim))
, _change_counter(o._change_counter)
{ }
clustering_ranges_walker& operator=(clustering_ranges_walker&& o) {
if (this != &o) {
this->~clustering_ranges_walker();
new (this) clustering_ranges_walker(std::move(o));
}
return *this;
}
// Excludes positions smaller than pos from the ranges.
// pos should be monotonic.
// No constraints between pos and positions passed to advance_to().
//
// After the invocation, when !out_of_range(), lower_bound() returns the smallest position still contained.
void trim_front(position_in_partition pos) {
position_in_partition::less_compare less(_schema);
do {
if (!less(_current_start, pos)) {
break;
}
if (less(pos, _current_end)) {
_trim = std::move(pos);
_current_start = *_trim;
_in_current = false;
++_change_counter;
break;
}
} while (advance_to_next_range());
}
// Returns true if given position is contained.
// Must be called with monotonic positions.
// Idempotent.
bool advance_to(position_in_partition_view pos) {
position_in_partition::less_compare less(_schema);
do {
if (!_in_current && less(pos, _current_start)) {
break;
}
// All subsequent clustering keys are larger than the start of this
// range so there is no need to check that again.
_in_current = true;
if (less(pos, _current_end)) {
return true;
}
} while (advance_to_next_range());
return false;
}
// Returns true if the range expressed by start and end (as in position_range) overlaps
// with clustering ranges.
// Must be called with monotonic start position. That position must also be greater than
// the last position passed to the other advance_to() overload.
// Idempotent.
bool advance_to(position_in_partition_view start, position_in_partition_view end) {
position_in_partition::less_compare less(_schema);
do {
if (!less(_current_start, end)) {
break;
}
if (less(start, _current_end)) {
return true;
}
} while (advance_to_next_range());
return false;
}
// Returns true if the range tombstone expressed by start and end (as in position_range) overlaps
// with clustering ranges.
// No monotonicity restrictions on argument values across calls.
// Does not affect lower_bound().
// Idempotent.
bool contains_tombstone(position_in_partition_view start, position_in_partition_view end) const {
position_in_partition::less_compare less(_schema);
if (_trim && !less(*_trim, end)) {
return false;
}
auto i = _current;
while (i != _end) {
auto range_start = position_in_partition_view::for_range_start(*i);
if (!less(range_start, end)) {
return false;
}
auto range_end = position_in_partition_view::for_range_end(*i);
if (less(start, range_end)) {
return true;
}
++i;
}
return false;
}
// Returns true if advanced past all contained positions. Any later advance_to() until reset() will return false.
bool out_of_range() const {
return !_in_current && _current == _end;
}
// Resets the state of the walker so that advance_to() can be now called for new sequence of positions.
// Any range trimmings still hold after this.
void reset() {
auto trim = std::move(_trim);
auto ctr = _change_counter;
*this = clustering_ranges_walker(_schema, _ranges, _with_static_row);
_change_counter = ctr + 1;
if (trim) {
trim_front(std::move(*trim));
}
}
// Can be called only when !out_of_range()
position_in_partition_view lower_bound() const {
return _current_start;
}
// When lower_bound() changes, this also does
// Always > 0.
size_t lower_bound_change_counter() const {
return _change_counter;
}
};

View File

@@ -1,3 +0,0 @@
# Scylla Coding Style
Please see the [Seastar style document](https://github.com/scylladb/seastar/blob/master/coding-style.md).

View File

@@ -21,12 +21,7 @@
#pragma once
#include "sstables/shared_sstable.hh"
#include "exceptions/exceptions.hh"
#include "sstables/compaction_backlog_manager.hh"
class table;
using column_family = table;
class column_family;
class schema;
using schema_ptr = lw_shared_ptr<const schema>;
@@ -38,14 +33,12 @@ enum class compaction_strategy_type {
size_tiered,
leveled,
date_tiered,
time_window,
};
class compaction_strategy_impl;
class sstable;
class sstable_set;
struct compaction_descriptor;
struct resharding_descriptor;
class compaction_strategy {
::shared_ptr<compaction_strategy_impl> _compaction_strategy_impl;
@@ -59,13 +52,11 @@ public:
compaction_strategy& operator=(compaction_strategy&&);
// Return a list of sstables to be compacted after applying the strategy.
compaction_descriptor get_sstables_for_compaction(column_family& cfs, std::vector<shared_sstable> candidates);
std::vector<resharding_descriptor> get_resharding_jobs(column_family& cf, std::vector<shared_sstable> candidates);
compaction_descriptor get_sstables_for_compaction(column_family& cfs, std::vector<lw_shared_ptr<sstable>> candidates);
// Some strategies may look at the compacted and resulting sstables to
// get some useful information for subsequent compactions.
void notify_completion(const std::vector<shared_sstable>& removed, const std::vector<shared_sstable>& added);
void notify_completion(const std::vector<lw_shared_ptr<sstable>>& removed, const std::vector<lw_shared_ptr<sstable>>& added);
// Return if parallel compaction is allowed by strategy.
bool parallel_compaction() const;
@@ -88,8 +79,6 @@ public:
return "LeveledCompactionStrategy";
case compaction_strategy_type::date_tiered:
return "DateTieredCompactionStrategy";
case compaction_strategy_type::time_window:
return "TimeWindowCompactionStrategy";
default:
throw std::runtime_error("Invalid Compaction Strategy");
}
@@ -108,8 +97,6 @@ public:
return compaction_strategy_type::leveled;
} else if (short_name == "DateTieredCompactionStrategy") {
return compaction_strategy_type::date_tiered;
} else if (short_name == "TimeWindowCompactionStrategy") {
return compaction_strategy_type::time_window;
} else {
throw exceptions::configuration_exception(sprint("Unable to find compaction strategy class '%s'", name));
}
@@ -122,8 +109,6 @@ public:
}
sstable_set make_sstable_set(schema_ptr schema) const;
compaction_backlog_tracker& get_backlog_tracker();
};
// Creates a compaction_strategy object from one of the strategies available.

View File

@@ -0,0 +1,67 @@
/*
* Copyright (C) 2016 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 "query-request.hh"
#include <experimental/optional>
// Wraps ring_position so it is compatible with old-style C++: default constructor,
// stateless comparators, yada yada
class compatible_ring_position {
const schema* _schema = nullptr;
// optional to supply a default constructor, no more
std::experimental::optional<dht::ring_position> _rp;
public:
compatible_ring_position() noexcept = default;
compatible_ring_position(const schema& s, const dht::ring_position& rp)
: _schema(&s), _rp(rp) {
}
compatible_ring_position(const schema& s, dht::ring_position&& rp)
: _schema(&s), _rp(std::move(rp)) {
}
const dht::token& token() const {
return _rp->token();
}
friend int tri_compare(const compatible_ring_position& x, const compatible_ring_position& y) {
return x._rp->tri_compare(*x._schema, *y._rp);
}
friend bool operator<(const compatible_ring_position& x, const compatible_ring_position& y) {
return tri_compare(x, y) < 0;
}
friend bool operator<=(const compatible_ring_position& x, const compatible_ring_position& y) {
return tri_compare(x, y) <= 0;
}
friend bool operator>(const compatible_ring_position& x, const compatible_ring_position& y) {
return tri_compare(x, y) > 0;
}
friend bool operator>=(const compatible_ring_position& x, const compatible_ring_position& y) {
return tri_compare(x, y) >= 0;
}
friend bool operator==(const compatible_ring_position& x, const compatible_ring_position& y) {
return tri_compare(x, y) == 0;
}
friend bool operator!=(const compatible_ring_position& x, const compatible_ring_position& y) {
return tri_compare(x, y) != 0;
}
};

View File

@@ -1,64 +0,0 @@
/*
* Copyright (C) 2016 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 "query-request.hh"
#include <optional>
// Wraps ring_position_view so it is compatible with old-style C++: default
// constructor, stateless comparators, yada yada.
class compatible_ring_position_view {
const schema* _schema = nullptr;
// Optional to supply a default constructor, no more.
std::optional<dht::ring_position_view> _rpv;
public:
constexpr compatible_ring_position_view() = default;
compatible_ring_position_view(const schema& s, dht::ring_position_view rpv)
: _schema(&s), _rpv(rpv) {
}
const dht::ring_position_view& position() const {
return *_rpv;
}
friend int tri_compare(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
return dht::ring_position_tri_compare(*x._schema, *x._rpv, *y._rpv);
}
friend bool operator<(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
return tri_compare(x, y) < 0;
}
friend bool operator<=(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
return tri_compare(x, y) <= 0;
}
friend bool operator>(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
return tri_compare(x, y) > 0;
}
friend bool operator>=(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
return tri_compare(x, y) >= 0;
}
friend bool operator==(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
return tri_compare(x, y) == 0;
}
friend bool operator!=(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
return tri_compare(x, y) != 0;
}
};

View File

@@ -28,7 +28,6 @@
#include <boost/range/iterator_range.hpp>
#include <boost/range/adaptor/transformed.hpp>
#include "utils/serialization.hh"
#include "util/backtrace.hh"
#include "unimplemented.hh"
enum class allow_prefixes { no, yes };
@@ -131,10 +130,10 @@ public:
bytes decompose_value(const value_type& values) {
return serialize_value(values);
}
class iterator : public std::iterator<std::input_iterator_tag, const bytes_view> {
class iterator : public std::iterator<std::input_iterator_tag, bytes_view> {
private:
bytes_view _v;
bytes_view _current;
value_type _current;
private:
void read_current() {
size_type len;
@@ -145,7 +144,7 @@ public:
}
len = read_simple<size_type>(_v);
if (_v.size() < len) {
throw_with_backtrace<marshal_exception>(sprint("compound_type iterator - not enough bytes, expected %d, got %d", len, _v.size()));
throw marshal_exception();
}
}
_current = bytes_view(_v.begin(), len);
@@ -221,9 +220,6 @@ public:
assert(AllowPrefixes == allow_prefixes::yes);
return std::distance(begin(v), end(v)) == (ssize_t)_types.size();
}
bool is_empty(bytes_view v) const {
return begin(v) == end(v);
}
void validate(bytes_view v) {
// FIXME: implement
warn(unimplemented::cause::VALIDATION);

View File

@@ -25,7 +25,6 @@
#include <boost/range/adaptor/transformed.hpp>
#include "compound.hh"
#include "schema.hh"
#include "sstables/version.hh"
//
// This header provides adaptors between the representation used by our compound_type<>
@@ -185,8 +184,6 @@ bytes to_legacy(CompoundType& type, bytes_view packed) {
return legacy_form;
}
class composite_view;
// Represents a value serialized according to Origin's CompositeType.
// If is_compound is true, then the value is one or more components encoded as:
//
@@ -205,7 +202,7 @@ public:
, _is_compound(is_compound)
{ }
explicit composite(bytes&& b)
composite(bytes&& b)
: _bytes(std::move(b))
, _is_compound(true)
{ }
@@ -242,7 +239,7 @@ public:
using component_view = std::pair<bytes_view, eoc>;
private:
template<typename Value, typename = std::enable_if_t<!std::is_same<const data_value, std::decay_t<Value>>::value>>
static size_t size(const Value& val) {
static size_t size(Value& val) {
return val.size();
}
static size_t size(const data_value& val) {
@@ -303,40 +300,27 @@ private:
}
public:
template <typename Describer>
auto describe_type(sstables::sstable_version_types v, Describer f) const {
auto describe_type(Describer f) const {
return f(const_cast<bytes&>(_bytes));
}
// marker is ignored if !is_compound
template<typename RangeOfSerializedComponents>
static composite serialize_value(RangeOfSerializedComponents&& values, bool is_compound = true, eoc marker = eoc::none) {
static bytes serialize_value(RangeOfSerializedComponents&& values, bool is_compound = true) {
auto size = serialized_size(values, is_compound);
bytes b(bytes::initialized_later(), size);
auto i = b.begin();
serialize_value(std::forward<decltype(values)>(values), i, is_compound);
if (is_compound && !b.empty()) {
b.back() = eoc_type(marker);
}
return composite(std::move(b), is_compound);
}
template<typename RangeOfSerializedComponents>
static composite serialize_static(const schema& s, RangeOfSerializedComponents&& values) {
// FIXME: Optimize
auto b = bytes(size_t(2), bytes::value_type(0xff));
std::vector<bytes_view> sv(s.clustering_key_size());
b += composite::serialize_value(boost::range::join(sv, std::forward<RangeOfSerializedComponents>(values)), true).release_bytes();
return composite(std::move(b));
}
static eoc to_eoc(int8_t eoc_byte) {
return eoc_byte == 0 ? eoc::none : (eoc_byte < 0 ? eoc::start : eoc::end);
return b;
}
class iterator : public std::iterator<std::input_iterator_tag, const component_view> {
bytes_view _v;
component_view _current;
private:
eoc to_eoc(int8_t eoc_byte) {
return eoc_byte == 0 ? eoc::none : (eoc_byte < 0 ? eoc::start : eoc::end);
}
void read_current() {
size_type len;
{
@@ -346,7 +330,7 @@ public:
}
len = read_simple<size_type>(_v);
if (_v.size() < len) {
throw_with_backtrace<marshal_exception>(sprint("composite iterator - not enough bytes, expected %d, got %d", len, _v.size()));
throw marshal_exception();
}
}
auto value = bytes_view(_v.begin(), len);
@@ -422,10 +406,6 @@ public:
return _bytes;
}
bytes release_bytes() && {
return std::move(_bytes);
}
size_t size() const {
return _bytes.size();
}
@@ -446,20 +426,26 @@ public:
return _is_compound;
}
// The following factory functions assume this composite is a compound value.
template <typename ClusteringElement>
static composite from_clustering_element(const schema& s, const ClusteringElement& ce) {
return serialize_value(ce.components(s), s.is_compound());
return serialize_value(ce.components(s));
}
static composite from_exploded(const std::vector<bytes_view>& v, bool is_compound, eoc marker = eoc::none) {
static composite from_exploded(const std::vector<bytes_view>& v, eoc marker = eoc::none) {
if (v.size() == 0) {
return composite(bytes(size_t(1), bytes::value_type(marker)), is_compound);
return bytes(size_t(1), bytes::value_type(marker));
}
return serialize_value(v, is_compound, marker);
auto b = serialize_value(v);
b.back() = eoc_type(marker);
return composite(std::move(b));
}
static composite static_prefix(const schema& s) {
return serialize_static(s, std::vector<bytes_view>());
static bytes static_marker(size_t(2), bytes::value_type(0xff));
std::vector<bytes_view> sv(s.clustering_key_size());
return static_marker + serialize_value(sv);
}
explicit operator bytes_view() const {
@@ -470,15 +456,6 @@ public:
friend inline std::ostream& operator<<(std::ostream& os, const std::pair<Component, eoc>& c) {
return os << "{value=" << c.first << "; eoc=" << sprint("0x%02x", eoc_type(c.second) & 0xff) << "}";
}
friend std::ostream& operator<<(std::ostream& os, const composite& v);
struct tri_compare {
const std::vector<data_type>& _types;
tri_compare(const std::vector<data_type>& types) : _types(types) {}
int operator()(const composite&, const composite&) const;
int operator()(composite_view, composite_view) const;
};
};
class composite_view final {
@@ -499,15 +476,14 @@ public:
, _is_compound(true)
{ }
std::vector<bytes_view> explode() const {
std::vector<bytes> explode() const {
if (!_is_compound) {
return { _bytes };
return { to_bytes(_bytes) };
}
std::vector<bytes_view> ret;
ret.reserve(8);
std::vector<bytes> ret;
for (auto it = begin(), e = end(); it != e; ) {
ret.push_back(it->first);
ret.push_back(to_bytes(it->first));
auto marker = it->second;
++it;
if (it != e && marker != composite::eoc::none) {
@@ -529,15 +505,6 @@ public:
return { begin(), end() };
}
composite::eoc last_eoc() const {
if (!_is_compound || _bytes.empty()) {
return composite::eoc::none;
}
bytes_view v(_bytes);
v.remove_prefix(v.size() - 1);
return composite::to_eoc(read_simple<composite::eoc_type>(v));
}
auto values() const {
return components() | boost::adaptors::transformed([](auto&& c) { return c.first; });
}
@@ -560,46 +527,4 @@ public:
bool operator==(const composite_view& k) const { return k._bytes == _bytes && k._is_compound == _is_compound; }
bool operator!=(const composite_view& k) const { return !(k == *this); }
friend inline std::ostream& operator<<(std::ostream& os, composite_view v) {
return os << "{" << ::join(", ", v.components()) << ", compound=" << v._is_compound << ", static=" << v.is_static() << "}";
}
};
inline
std::ostream& operator<<(std::ostream& os, const composite& v) {
return os << composite_view(v);
}
inline
int composite::tri_compare::operator()(const composite& v1, const composite& v2) const {
return (*this)(composite_view(v1), composite_view(v2));
}
inline
int composite::tri_compare::operator()(composite_view v1, composite_view v2) const {
// See org.apache.cassandra.db.composites.AbstractCType#compare
if (v1.empty()) {
return v2.empty() ? 0 : -1;
}
if (v2.empty()) {
return 1;
}
if (v1.is_static() != v2.is_static()) {
return v1.is_static() ? -1 : 1;
}
auto a_values = v1.components();
auto b_values = v2.components();
auto cmp = [&](const data_type& t, component_view c1, component_view c2) {
// First by value, then by EOC
auto r = t->compare(c1.first, c2.first);
if (r) {
return r;
}
return static_cast<int>(c1.second) - static_cast<int>(c2.second);
};
return lexicographical_tri_compare(_types.begin(), _types.end(),
a_values.begin(), a_values.end(),
b_values.begin(), b_values.end(),
cmp);
}

View File

@@ -1,345 +0,0 @@
/*
* Copyright (C) 2016 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 <lz4.h>
#include <zlib.h>
#include <snappy-c.h>
#include "compress.hh"
#include "utils/class_registrator.hh"
const sstring compressor::namespace_prefix = "org.apache.cassandra.io.compress.";
class lz4_processor: public compressor {
public:
using compressor::compressor;
size_t uncompress(const char* input, size_t input_len, char* output,
size_t output_len) const override;
size_t compress(const char* input, size_t input_len, char* output,
size_t output_len) const override;
size_t compress_max_size(size_t input_len) const override;
};
class snappy_processor: public compressor {
public:
using compressor::compressor;
size_t uncompress(const char* input, size_t input_len, char* output,
size_t output_len) const override;
size_t compress(const char* input, size_t input_len, char* output,
size_t output_len) const override;
size_t compress_max_size(size_t input_len) const override;
};
class deflate_processor: public compressor {
public:
using compressor::compressor;
size_t uncompress(const char* input, size_t input_len, char* output,
size_t output_len) const override;
size_t compress(const char* input, size_t input_len, char* output,
size_t output_len) const override;
size_t compress_max_size(size_t input_len) const override;
};
compressor::compressor(sstring name)
: _name(std::move(name))
{}
std::set<sstring> compressor::option_names() const {
return {};
}
std::map<sstring, sstring> compressor::options() const {
return {};
}
shared_ptr<compressor> compressor::create(const sstring& name, const opt_getter& opts) {
if (name.empty()) {
return {};
}
qualified_name qn(namespace_prefix, name);
for (auto& c : { lz4, snappy, deflate }) {
if (c->name() == qn) {
return c;
}
}
return compressor_registry::create(qn, opts);
}
shared_ptr<compressor> compressor::create(const std::map<sstring, sstring>& options) {
auto i = options.find(compression_parameters::SSTABLE_COMPRESSION);
if (i != options.end() && !i->second.empty()) {
return create(i->second, [&options](const sstring& key) -> opt_string {
auto i = options.find(key);
if (i == options.end()) {
return std::experimental::nullopt;
}
return { i->second };
});
}
return {};
}
thread_local const shared_ptr<compressor> compressor::lz4 = make_shared<lz4_processor>(namespace_prefix + "LZ4Compressor");
thread_local const shared_ptr<compressor> compressor::snappy = make_shared<snappy_processor>(namespace_prefix + "SnappyCompressor");
thread_local const shared_ptr<compressor> compressor::deflate = make_shared<deflate_processor>(namespace_prefix + "DeflateCompressor");
const sstring compression_parameters::SSTABLE_COMPRESSION = "sstable_compression";
const sstring compression_parameters::CHUNK_LENGTH_KB = "chunk_length_kb";
const sstring compression_parameters::CRC_CHECK_CHANCE = "crc_check_chance";
compression_parameters::compression_parameters()
: compression_parameters(nullptr)
{}
compression_parameters::~compression_parameters()
{}
compression_parameters::compression_parameters(compressor_ptr c)
: _compressor(std::move(c))
{}
compression_parameters::compression_parameters(const std::map<sstring, sstring>& options) {
_compressor = compressor::create(options);
validate_options(options);
auto chunk_length = options.find(CHUNK_LENGTH_KB);
if (chunk_length != options.end()) {
try {
_chunk_length = std::stoi(chunk_length->second) * 1024;
} catch (const std::exception& e) {
throw exceptions::syntax_exception(sstring("Invalid integer value ") + chunk_length->second + " for " + CHUNK_LENGTH_KB);
}
}
auto crc_chance = options.find(CRC_CHECK_CHANCE);
if (crc_chance != options.end()) {
try {
_crc_check_chance = std::stod(crc_chance->second);
} catch (const std::exception& e) {
throw exceptions::syntax_exception(sstring("Invalid double value ") + crc_chance->second + "for " + CRC_CHECK_CHANCE);
}
}
}
void compression_parameters::validate() {
if (_chunk_length) {
auto chunk_length = _chunk_length.value();
if (chunk_length <= 0) {
throw exceptions::configuration_exception(sstring("Invalid negative or null ") + CHUNK_LENGTH_KB);
}
// _chunk_length must be a power of two
if (chunk_length & (chunk_length - 1)) {
throw exceptions::configuration_exception(sstring(CHUNK_LENGTH_KB) + " must be a power of 2.");
}
}
if (_crc_check_chance && (_crc_check_chance.value() < 0.0 || _crc_check_chance.value() > 1.0)) {
throw exceptions::configuration_exception(sstring(CRC_CHECK_CHANCE) + " must be between 0.0 and 1.0.");
}
}
std::map<sstring, sstring> compression_parameters::get_options() const {
if (!_compressor) {
return std::map<sstring, sstring>();
}
auto opts = _compressor->options();
opts.emplace(compression_parameters::SSTABLE_COMPRESSION, _compressor->name());
if (_chunk_length) {
opts.emplace(sstring(CHUNK_LENGTH_KB), std::to_string(_chunk_length.value() / 1024));
}
if (_crc_check_chance) {
opts.emplace(sstring(CRC_CHECK_CHANCE), std::to_string(_crc_check_chance.value()));
}
return opts;
}
bool compression_parameters::operator==(const compression_parameters& other) const {
return _compressor == other._compressor
&& _chunk_length == other._chunk_length
&& _crc_check_chance == other._crc_check_chance;
}
bool compression_parameters::operator!=(const compression_parameters& other) const {
return !(*this == other);
}
void compression_parameters::validate_options(const std::map<sstring, sstring>& options) {
// currently, there are no options specific to a particular compressor
static std::set<sstring> keywords({
sstring(SSTABLE_COMPRESSION),
sstring(CHUNK_LENGTH_KB),
sstring(CRC_CHECK_CHANCE),
});
std::set<sstring> ckw;
if (_compressor) {
ckw = _compressor->option_names();
}
for (auto&& opt : options) {
if (!keywords.count(opt.first) && !ckw.count(opt.first)) {
throw exceptions::configuration_exception(sprint("Unknown compression option '%s'.", opt.first));
}
}
}
size_t lz4_processor::uncompress(const char* input, size_t input_len,
char* output, size_t output_len) const {
// We use LZ4_decompress_safe(). According to the documentation, the
// function LZ4_decompress_fast() is slightly faster, but maliciously
// crafted compressed data can cause it to overflow the output buffer.
// Theoretically, our compressed data is created by us so is not malicious
// (and accidental corruption is avoided by the compressed-data checksum),
// but let's not take that chance for now, until we've actually measured
// the performance benefit that LZ4_decompress_fast() would bring.
// Cassandra's LZ4Compressor prepends to the chunk its uncompressed length
// in 4 bytes little-endian (!) order. We don't need this information -
// we already know the uncompressed data is at most the given chunk size
// (and usually is exactly that, except in the last chunk). The advance
// knowledge of the uncompressed size could be useful if we used
// LZ4_decompress_fast(), but we prefer LZ4_decompress_safe() anyway...
input += 4;
input_len -= 4;
auto ret = LZ4_decompress_safe(input, output, input_len, output_len);
if (ret < 0) {
throw std::runtime_error("LZ4 uncompression failure");
}
return ret;
}
size_t lz4_processor::compress(const char* input, size_t input_len,
char* output, size_t output_len) const {
if (output_len < LZ4_COMPRESSBOUND(input_len) + 4) {
throw std::runtime_error("LZ4 compression failure: length of output is too small");
}
// Write input_len (32-bit data) to beginning of output in little-endian representation.
output[0] = input_len & 0xFF;
output[1] = (input_len >> 8) & 0xFF;
output[2] = (input_len >> 16) & 0xFF;
output[3] = (input_len >> 24) & 0xFF;
#ifdef SEASTAR_HAVE_LZ4_COMPRESS_DEFAULT
auto ret = LZ4_compress_default(input, output + 4, input_len, LZ4_compressBound(input_len));
#else
auto ret = LZ4_compress(input, output + 4, input_len);
#endif
if (ret == 0) {
throw std::runtime_error("LZ4 compression failure: LZ4_compress() failed");
}
return ret + 4;
}
size_t lz4_processor::compress_max_size(size_t input_len) const {
return LZ4_COMPRESSBOUND(input_len) + 4;
}
size_t deflate_processor::uncompress(const char* input,
size_t input_len, char* output, size_t output_len) const {
z_stream zs;
zs.zalloc = Z_NULL;
zs.zfree = Z_NULL;
zs.opaque = Z_NULL;
zs.avail_in = 0;
zs.next_in = Z_NULL;
if (inflateInit(&zs) != Z_OK) {
throw std::runtime_error("deflate uncompression init failure");
}
// yuck, zlib is not const-correct, and also uses unsigned char while we use char :-(
zs.next_in = reinterpret_cast<unsigned char*>(const_cast<char*>(input));
zs.avail_in = input_len;
zs.next_out = reinterpret_cast<unsigned char*>(output);
zs.avail_out = output_len;
auto res = inflate(&zs, Z_FINISH);
inflateEnd(&zs);
if (res == Z_STREAM_END) {
return output_len - zs.avail_out;
} else {
throw std::runtime_error("deflate uncompression failure");
}
}
size_t deflate_processor::compress(const char* input,
size_t input_len, char* output, size_t output_len) const {
z_stream zs;
zs.zalloc = Z_NULL;
zs.zfree = Z_NULL;
zs.opaque = Z_NULL;
zs.avail_in = 0;
zs.next_in = Z_NULL;
if (deflateInit(&zs, Z_DEFAULT_COMPRESSION) != Z_OK) {
throw std::runtime_error("deflate compression init failure");
}
zs.next_in = reinterpret_cast<unsigned char*>(const_cast<char*>(input));
zs.avail_in = input_len;
zs.next_out = reinterpret_cast<unsigned char*>(output);
zs.avail_out = output_len;
auto res = ::deflate(&zs, Z_FINISH);
deflateEnd(&zs);
if (res == Z_STREAM_END) {
return output_len - zs.avail_out;
} else {
throw std::runtime_error("deflate compression failure");
}
}
size_t deflate_processor::compress_max_size(size_t input_len) const {
z_stream zs;
zs.zalloc = Z_NULL;
zs.zfree = Z_NULL;
zs.opaque = Z_NULL;
zs.avail_in = 0;
zs.next_in = Z_NULL;
if (deflateInit(&zs, Z_DEFAULT_COMPRESSION) != Z_OK) {
throw std::runtime_error("deflate compression init failure");
}
auto res = deflateBound(&zs, input_len);
deflateEnd(&zs);
return res;
}
size_t snappy_processor::uncompress(const char* input, size_t input_len,
char* output, size_t output_len) const {
if (snappy_uncompress(input, input_len, output, &output_len)
== SNAPPY_OK) {
return output_len;
} else {
throw std::runtime_error("snappy uncompression failure");
}
}
size_t snappy_processor::compress(const char* input, size_t input_len,
char* output, size_t output_len) const {
auto ret = snappy_compress(input, input_len, output, &output_len);
if (ret != SNAPPY_OK) {
throw std::runtime_error("snappy compression failure: snappy_compress() failed");
}
return output_len;
}
size_t snappy_processor::compress_max_size(size_t input_len) const {
return snappy_max_compressed_length(input_len);
}

View File

@@ -21,103 +21,135 @@
#pragma once
#include <map>
#include <set>
#include <seastar/core/future.hh>
#include <seastar/core/shared_ptr.hh>
#include <seastar/core/sstring.hh>
#include "exceptions/exceptions.hh"
#include "stdx.hh"
class compressor {
sstring _name;
public:
compressor(sstring);
virtual ~compressor() {}
/**
* Unpacks data in "input" to output. If output_len is of insufficient size,
* exception is thrown. I.e. you should keep track of the uncompressed size.
*/
virtual size_t uncompress(const char* input, size_t input_len, char* output,
size_t output_len) const = 0;
/**
* Packs data in "input" to output. If output_len is of insufficient size,
* exception is thrown. Maximum required size is obtained via "compress_max_size"
*/
virtual size_t compress(const char* input, size_t input_len, char* output,
size_t output_len) const = 0;
/**
* Returns the maximum output size for compressing data on "input_len" size.
*/
virtual size_t compress_max_size(size_t input_len) const = 0;
/**
* Returns accepted option names for this compressor
*/
virtual std::set<sstring> option_names() const;
/**
* Returns original options used in instantiating this compressor
*/
virtual std::map<sstring, sstring> options() const;
/**
* Compressor class name.
*/
const sstring& name() const {
return _name;
}
// to cheaply bridge sstable compression options / maps
using opt_string = stdx::optional<sstring>;
using opt_getter = std::function<opt_string(const sstring&)>;
static shared_ptr<compressor> create(const sstring& name, const opt_getter&);
static shared_ptr<compressor> create(const std::map<sstring, sstring>&);
static thread_local const shared_ptr<compressor> lz4;
static thread_local const shared_ptr<compressor> snappy;
static thread_local const shared_ptr<compressor> deflate;
static const sstring namespace_prefix;
enum class compressor {
none,
lz4,
snappy,
deflate,
};
template<typename BaseType, typename... Args>
class class_registry;
using compressor_ptr = shared_ptr<compressor>;
using compressor_registry = class_registry<compressor_ptr, const typename compressor::opt_getter&>;
class compression_parameters {
public:
static constexpr int32_t DEFAULT_CHUNK_LENGTH = 4 * 1024;
static constexpr double DEFAULT_CRC_CHECK_CHANCE = 1.0;
static const sstring SSTABLE_COMPRESSION;
static const sstring CHUNK_LENGTH_KB;
static const sstring CRC_CHECK_CHANCE;
static constexpr auto SSTABLE_COMPRESSION = "sstable_compression";
static constexpr auto CHUNK_LENGTH_KB = "chunk_length_kb";
static constexpr auto CRC_CHECK_CHANCE = "crc_check_chance";
private:
compressor_ptr _compressor;
compressor _compressor;
std::experimental::optional<int> _chunk_length;
std::experimental::optional<double> _crc_check_chance;
public:
compression_parameters();
compression_parameters(compressor_ptr);
compression_parameters(const std::map<sstring, sstring>& options);
~compression_parameters();
compression_parameters(compressor c = compressor::lz4) : _compressor(c) { }
compression_parameters(const std::map<sstring, sstring>& options) {
validate_options(options);
compressor_ptr get_compressor() const { return _compressor; }
auto it = options.find(SSTABLE_COMPRESSION);
if (it == options.end() || it->second.empty()) {
_compressor = compressor::none;
return;
}
const auto& compressor_class = it->second;
if (is_compressor_class(compressor_class, "LZ4Compressor")) {
_compressor = compressor::lz4;
} else if (is_compressor_class(compressor_class, "SnappyCompressor")) {
_compressor = compressor::snappy;
} else if (is_compressor_class(compressor_class, "DeflateCompressor")) {
_compressor = compressor::deflate;
} else {
throw exceptions::configuration_exception(sstring("Unsupported compression class '") + compressor_class + "'.");
}
auto chunk_length = options.find(CHUNK_LENGTH_KB);
if (chunk_length != options.end()) {
try {
_chunk_length = std::stoi(chunk_length->second) * 1024;
} catch (const std::exception& e) {
throw exceptions::syntax_exception(sstring("Invalid integer value ") + chunk_length->second + " for " + CHUNK_LENGTH_KB);
}
}
auto crc_chance = options.find(CRC_CHECK_CHANCE);
if (crc_chance != options.end()) {
try {
_crc_check_chance = std::stod(crc_chance->second);
} catch (const std::exception& e) {
throw exceptions::syntax_exception(sstring("Invalid double value ") + crc_chance->second + "for " + CRC_CHECK_CHANCE);
}
}
}
compressor get_compressor() const { return _compressor; }
int32_t chunk_length() const { return _chunk_length.value_or(int(DEFAULT_CHUNK_LENGTH)); }
double crc_check_chance() const { return _crc_check_chance.value_or(double(DEFAULT_CRC_CHECK_CHANCE)); }
void validate();
std::map<sstring, sstring> get_options() const;
bool operator==(const compression_parameters& other) const;
bool operator!=(const compression_parameters& other) const;
void validate() {
if (_chunk_length) {
auto chunk_length = _chunk_length.value();
if (chunk_length <= 0) {
throw exceptions::configuration_exception(sstring("Invalid negative or null ") + CHUNK_LENGTH_KB);
}
// _chunk_length must be a power of two
if (chunk_length & (chunk_length - 1)) {
throw exceptions::configuration_exception(sstring(CHUNK_LENGTH_KB) + " must be a power of 2.");
}
}
if (_crc_check_chance && (_crc_check_chance.value() < 0.0 || _crc_check_chance.value() > 1.0)) {
throw exceptions::configuration_exception(sstring(CRC_CHECK_CHANCE) + " must be between 0.0 and 1.0.");
}
}
std::map<sstring, sstring> get_options() const {
if (_compressor == compressor::none) {
return std::map<sstring, sstring>();
}
std::map<sstring, sstring> opts;
opts.emplace(sstring(SSTABLE_COMPRESSION), compressor_name());
if (_chunk_length) {
opts.emplace(sstring(CHUNK_LENGTH_KB), std::to_string(_chunk_length.value() / 1024));
}
if (_crc_check_chance) {
opts.emplace(sstring(CRC_CHECK_CHANCE), std::to_string(_crc_check_chance.value()));
}
return opts;
}
bool operator==(const compression_parameters& other) const {
return _compressor == other._compressor
&& _chunk_length == other._chunk_length
&& _crc_check_chance == other._crc_check_chance;
}
bool operator!=(const compression_parameters& other) const {
return !(*this == other);
}
private:
void validate_options(const std::map<sstring, sstring>&);
void validate_options(const std::map<sstring, sstring>& options) {
// currently, there are no options specific to a particular compressor
static std::set<sstring> keywords({
sstring(SSTABLE_COMPRESSION),
sstring(CHUNK_LENGTH_KB),
sstring(CRC_CHECK_CHANCE),
});
for (auto&& opt : options) {
if (!keywords.count(opt.first)) {
throw exceptions::configuration_exception(sprint("Unknown compression option '%s'.", opt.first));
}
}
}
bool is_compressor_class(const sstring& value, const sstring& class_name) {
static const sstring namespace_prefix = "org.apache.cassandra.io.compress.";
return value == class_name || value == namespace_prefix + class_name;
}
sstring compressor_name() const {
switch (_compressor) {
case compressor::lz4:
return "org.apache.cassandra.io.compress.LZ4Compressor";
case compressor::snappy:
return "org.apache.cassandra.io.compress.SnappyCompressor";
case compressor::deflate:
return "org.apache.cassandra.io.compress.DeflateCompressor";
default:
abort();
}
}
};

View File

@@ -12,9 +12,7 @@
# The name of the cluster. This is mainly used to prevent machines in
# one logical cluster from joining another.
# It is recommended to change the default value when creating a new cluster.
# You can NOT modify this value for an existing cluster
#cluster_name: 'Test Cluster'
cluster_name: 'Test Cluster'
# This defines the number of tokens randomly assigned to this node on the ring
# The more tokens, relative to other nodes, the larger the proportion of data
@@ -87,25 +85,16 @@ listen_address: localhost
# Leaving this blank will set it to the same value as listen_address
# broadcast_address: 1.2.3.4
# When using multiple physical network interfaces, set this to true to listen on broadcast_address
# in addition to the listen_address, allowing nodes to communicate in both interfaces.
# Ignore this property if the network configuration automatically routes between the public and private networks such as EC2.
#
# listen_on_broadcast_address: false
# port for the CQL native transport to listen for clients on
# For security reasons, you should not expose this port to the internet. Firewall it if needed.
native_transport_port: 9042
# Enabling native transport encryption in client_encryption_options allows you to either use
# encryption for the standard port or to use a dedicated, additional port along with the unencrypted
# standard native_transport_port.
# Enabling client encryption and keeping native_transport_port_ssl disabled will use encryption
# for native_transport_port. Setting native_transport_port_ssl to a different value
# from native_transport_port will use encryption for native_transport_port_ssl while
# keeping native_transport_port unencrypted.
#native_transport_port_ssl: 9142
# Throttles all outbound streaming file transfers on this node to the
# given total throughput in Mbps. This is necessary because Scylla does
# mostly sequential IO when streaming data during bootstrap or repair, which
# can lead to saturating the network connection and degrading rpc performance.
# When unset, the default is 200 Mbps or 25 MB/s.
# stream_throughput_outbound_megabits_per_sec: 200
# How long the coordinator should wait for read operations to complete
read_request_timeout_in_ms: 5000
@@ -203,9 +192,6 @@ api_address: 127.0.0.1
# Caution should be taken on increasing the size of this threshold as it can lead to node instability.
batch_size_warn_threshold_in_kb: 5
# Fail any multiple-partition batch exceeding this value. 50kb (10x warn threshold) by default.
batch_size_fail_threshold_in_kb: 50
# Authentication backend, identifying users
# Out of the box, Scylla provides org.apache.cassandra.auth.{AllowAllAuthenticator,
# PasswordAuthenticator}.
@@ -237,11 +223,9 @@ batch_size_fail_threshold_in_kb: 50
# be set.
# broadcast_rpc_address: 1.2.3.4
# Uncomment to enable experimental features
# experimental: true
# The directory where hints files are stored if hinted handoff is enabled.
# hints_directory: /var/lib/scylla/hints
###################################################
## Not currently supported, reserved for future use
###################################################
# See http://wiki.apache.org/cassandra/HintedHandoff
# May either be "true" or "false" to enable globally, or contain a list
@@ -265,27 +249,23 @@ batch_size_fail_threshold_in_kb: 50
# cross-dc handoff tends to be slower
# max_hints_delivery_threads: 2
###################################################
## Not currently supported, reserved for future use
###################################################
# Maximum throttle in KBs per second, total. This will be
# reduced proportionally to the number of nodes in the cluster.
# batchlog_replay_throttle_in_kb: 1024
# Validity period for permissions cache (fetching permissions can be an
# expensive operation depending on the authorizer, CassandraAuthorizer is
# one example). Defaults to 10000, set to 0 to disable.
# one example). Defaults to 2000, set to 0 to disable.
# Will be disabled automatically for AllowAllAuthorizer.
# permissions_validity_in_ms: 10000
# permissions_validity_in_ms: 2000
# Refresh interval for permissions cache (if enabled).
# After this interval, cache entries become eligible for refresh. Upon next
# access, an async reload is scheduled and the old value returned until it
# completes. If permissions_validity_in_ms is non-zero, then this also must have
# a non-zero value. Defaults to 2000. It's recommended to set this value to
# be at least 3 times smaller than the permissions_validity_in_ms.
# permissions_update_interval_in_ms: 2000
# completes. If permissions_validity_in_ms is non-zero, then this must be
# also.
# Defaults to the same value as permissions_validity_in_ms.
# permissions_update_interval_in_ms: 1000
# The partitioner is responsible for distributing groups of rows (by
# partition key) across nodes in the cluster. You should leave this
@@ -299,6 +279,28 @@ batch_size_fail_threshold_in_kb: 50
#
partitioner: org.apache.cassandra.dht.Murmur3Partitioner
# policy for data disk failures:
# die: shut down gossip and Thrift and kill the JVM for any fs errors or
# single-sstable errors, so the node can be replaced.
# stop_paranoid: shut down gossip and Thrift even for single-sstable errors.
# stop: shut down gossip and Thrift, leaving the node effectively dead, but
# can still be inspected via JMX.
# best_effort: stop using the failed disk and respond to requests based on
# remaining available sstables. This means you WILL see obsolete
# data at CL.ONE!
# ignore: ignore fatal errors and let requests fail, as in pre-1.2 Scylla
# disk_failure_policy: stop
# policy for commit disk failures:
# die: shut down gossip and Thrift and kill the JVM, so the node can be replaced.
# stop: shut down gossip and Thrift, leaving the node effectively dead, but
# can still be inspected via JMX.
# stop_commit: shutdown the commit log, letting writes collect but
# continuing to service reads, as in pre-2.0.5 Scylla
# ignore: ignore fatal errors and let the batches fail
# commit_failure_policy: stop
# Maximum size of the key cache in memory.
#
# Each key cache hit saves 1 seek and each row cache hit saves 2 seeks at the
@@ -725,17 +727,22 @@ commitlog_total_space_in_mb: -1
# certificate: conf/scylla.crt
# keyfile: conf/scylla.key
# truststore: <none, use system trust>
# require_client_auth: False
# priority_string: <none, use default>
# enable or disable client/server encryption.
# client_encryption_options:
# enabled: false
# certificate: conf/scylla.crt
# keyfile: conf/scylla.key
# truststore: <none, use system trust>
# require_client_auth: False
# priority_string: <none, use default>
# require_client_auth: false
# Set trustore and truststore_password if require_client_auth is true
# truststore: conf/.truststore
# truststore_password: cassandra
# More advanced defaults below:
# protocol: TLS
# algorithm: SunX509
# store_type: JKS
# cipher_suites: [TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA,TLS_DHE_RSA_WITH_AES_128_CBC_SHA,TLS_DHE_RSA_WITH_AES_256_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA]
# internode_compression controls whether traffic between nodes is
# compressed.

View File

@@ -20,11 +20,9 @@
# along with Scylla. If not, see <http://www.gnu.org/licenses/>.
#
import os, os.path, textwrap, argparse, sys, shlex, subprocess, tempfile, re, platform
import os, os.path, textwrap, argparse, sys, shlex, subprocess, tempfile, re
from distutils.spawn import find_executable
tempfile.tempdir = "./build/tmp"
configure_args = str.join(' ', [shlex.quote(x) for x in sys.argv[1:]])
for line in open('/etc/os-release'):
@@ -85,33 +83,17 @@ def pkg_config(option, package):
return output.decode('utf-8').strip()
def try_compile(compiler, source = '', flags = []):
return try_compile_and_link(compiler, source, flags = flags + ['-c'])
def ensure_tmp_dir_exists():
if not os.path.exists(tempfile.tempdir):
os.makedirs(tempfile.tempdir)
def try_compile_and_link(compiler, source = '', flags = []):
ensure_tmp_dir_exists()
with tempfile.NamedTemporaryFile() as sfile:
ofile = tempfile.mktemp()
try:
sfile.file.write(bytes(source, 'utf-8'))
sfile.file.flush()
# We can't write to /dev/null, since in some cases (-ftest-coverage) gcc will create an auxiliary
# output file based on the name of the output file, and "/dev/null.gcsa" is not a good name
return subprocess.call([compiler, '-x', 'c++', '-o', ofile, sfile.name] + args.user_cflags.split() + flags,
stdout = subprocess.DEVNULL,
stderr = subprocess.DEVNULL) == 0
finally:
if os.path.exists(ofile):
os.unlink(ofile)
sfile.file.write(bytes(source, 'utf-8'))
sfile.file.flush()
return subprocess.call([compiler, '-x', 'c++', '-o', '/dev/null', '-c', sfile.name] + flags,
stdout = subprocess.DEVNULL,
stderr = subprocess.DEVNULL) == 0
def flag_supported(flag, compiler):
def warning_supported(warning, compiler):
# gcc ignores -Wno-x even if it is not supported
adjusted = re.sub('^-Wno-', '-W', flag)
split = adjusted.split(' ')
return try_compile(flags = ['-Werror'] + split, compiler = compiler)
adjusted = re.sub('^-Wno-', '-W', warning)
return try_compile(flags = [adjusted], compiler = compiler)
def debug_flag(compiler):
src_with_auto = textwrap.dedent('''\
@@ -126,14 +108,6 @@ def debug_flag(compiler):
print('Note: debug information disabled; upgrade your compiler')
return ''
def gold_supported(compiler):
src_main = 'int main(int argc, char **argv) { return 0; }'
if try_compile_and_link(source = src_main, flags = ['-fuse-ld=gold'], compiler = compiler):
return '-fuse-ld=gold'
else:
print('Note: gold not found; using default system linker')
return ''
def maybe_static(flag, libs):
if flag and not args.static:
libs = '-Wl,-Bstatic {} -Wl,-Bdynamic'.format(libs)
@@ -159,13 +133,6 @@ class Thrift(object):
def endswith(self, end):
return self.source.endswith(end)
def default_target_arch():
mach = platform.machine()
if platform.machine() in ['i386', 'i686', 'x86_64']:
return 'nehalem'
else:
return ''
class Antlr3Grammar(object):
def __init__(self, source):
self.source = source
@@ -187,22 +154,20 @@ modes = {
'debug': {
'sanitize': '-fsanitize=address -fsanitize=leak -fsanitize=undefined',
'sanitize_libs': '-lasan -lubsan',
'opt': '-O0 -DDEBUG -DDEBUG_SHARED_PTR -DDEFAULT_ALLOCATOR -DDEBUG_LSA_SANITIZER',
'opt': '-O0 -DDEBUG -DDEBUG_SHARED_PTR -DDEFAULT_ALLOCATOR',
'libs': '',
},
'release': {
'sanitize': '',
'sanitize_libs': '',
'opt': '-O3',
'opt': '-O2',
'libs': '',
},
}
scylla_tests = [
'tests/mutation_test',
'tests/mvcc_test',
'tests/mutation_fragment_test',
'tests/flat_mutation_reader_test',
'tests/streamed_mutation_test',
'tests/schema_registry_test',
'tests/canonical_mutation_test',
'tests/range_test',
@@ -210,9 +175,6 @@ scylla_tests = [
'tests/keys_test',
'tests/partitioner_test',
'tests/frozen_mutation_test',
'tests/serialized_action_test',
'tests/hint_test',
'tests/clustering_ranges_walker_test',
'tests/perf/perf_mutation',
'tests/lsa_async_eviction_test',
'tests/lsa_sync_eviction_test',
@@ -221,14 +183,9 @@ scylla_tests = [
'tests/perf/perf_hash',
'tests/perf/perf_cql_parser',
'tests/perf/perf_simple_query',
'tests/perf/perf_fast_forward',
'tests/perf/perf_cache_eviction',
'tests/cache_flat_mutation_reader_test',
'tests/row_cache_stress_test',
'tests/memory_footprint',
'tests/perf/perf_sstable',
'tests/cql_query_test',
'tests/secondary_index_test',
'tests/storage_proxy_test',
'tests/schema_change_test',
'tests/mutation_reader_test',
@@ -236,9 +193,7 @@ scylla_tests = [
'tests/row_cache_test',
'tests/test-serialization',
'tests/sstable_test',
'tests/sstable_3_x_test',
'tests/sstable_mutation_test',
'tests/sstable_resharding_test',
'tests/memtable_test',
'tests/commitlog_test',
'tests/cartesian_product_test',
@@ -251,7 +206,6 @@ scylla_tests = [
'tests/config_test',
'tests/gossiping_property_file_snitch_test',
'tests/ec2_snitch_test',
'tests/gce_snitch_test',
'tests/snitch_reset_test',
'tests/network_topology_strategy_test',
'tests/query_processor_test',
@@ -261,7 +215,6 @@ scylla_tests = [
'tests/murmur_hash_test',
'tests/allocation_strategy_test',
'tests/logalloc_test',
'tests/log_heap_test',
'tests/managed_vector_test',
'tests/crc_test',
'tests/flush_queue_test',
@@ -273,50 +226,18 @@ scylla_tests = [
'tests/database_test',
'tests/nonwrapping_range_test',
'tests/input_stream_test',
'tests/sstable_atomic_deletion_test',
'tests/virtual_reader_test',
'tests/view_schema_test',
'tests/view_build_test',
'tests/view_complex_test',
'tests/counter_test',
'tests/cell_locker_test',
'tests/row_locker_test',
'tests/streaming_histogram_test',
'tests/duration_test',
'tests/vint_serialization_test',
'tests/continuous_data_consumer_test',
'tests/compress_test',
'tests/chunked_vector_test',
'tests/loading_cache_test',
'tests/castas_fcts_test',
'tests/big_decimal_test',
'tests/aggregate_fcts_test',
'tests/role_manager_test',
'tests/caching_options_test',
'tests/auth_resource_test',
'tests/cql_auth_query_test',
'tests/enum_set_test',
'tests/extensions_test',
'tests/cql_auth_syntax_test',
'tests/querier_cache',
'tests/limiting_data_source_test',
'tests/meta_test',
'tests/imr_test',
'tests/partition_data_test',
'tests/reusable_buffer_test',
'tests/multishard_writer_test',
]
perf_tests = [
'tests/perf/perf_mutation_readers',
'tests/perf/perf_mutation_fragment',
'tests/perf/perf_idl',
]
apps = [
'scylla',
]
tests = scylla_tests + perf_tests
tests = scylla_tests
other = [
'iotune',
@@ -338,12 +259,8 @@ arg_parser.add_argument('--cflags', action = 'store', dest = 'user_cflags', defa
help = 'Extra flags for the C++ compiler')
arg_parser.add_argument('--ldflags', action = 'store', dest = 'user_ldflags', default = '',
help = 'Extra flags for the linker')
arg_parser.add_argument('--target', action = 'store', dest = 'target', default = default_target_arch(),
help = 'Target architecture (-march)')
arg_parser.add_argument('--compiler', action = 'store', dest = 'cxx', default = 'g++',
help = 'C++ compiler path')
arg_parser.add_argument('--c-compiler', action='store', dest='cc', default='gcc',
help='C compiler path')
arg_parser.add_argument('--with-osv', action = 'store', dest = 'with_osv', default = '',
help = 'Shortcut for compile for OSv')
arg_parser.add_argument('--enable-dpdk', action = 'store_true', dest = 'dpdk', default = False,
@@ -358,22 +275,12 @@ arg_parser.add_argument('--static-thrift', dest = 'staticthrift', action = 'stor
help = 'Link libthrift statically')
arg_parser.add_argument('--static-boost', dest = 'staticboost', action = 'store_true',
help = 'Link boost statically')
arg_parser.add_argument('--static-yaml-cpp', dest = 'staticyamlcpp', action = 'store_true',
help = 'Link libyaml-cpp statically')
arg_parser.add_argument('--tests-debuginfo', action = 'store', dest = 'tests_debuginfo', type = int, default = 0,
help = 'Enable(1)/disable(0)compiler debug information generation for tests')
arg_parser.add_argument('--python', action = 'store', dest = 'python', default = 'python3',
help = 'Python3 path')
add_tristate(arg_parser, name = 'hwloc', dest = 'hwloc', help = 'hwloc support')
add_tristate(arg_parser, name = 'xen', dest = 'xen', help = 'Xen support')
arg_parser.add_argument('--enable-gcc6-concepts', dest='gcc6_concepts', action='store_true', default=False,
help='enable experimental support for C++ Concepts as implemented in GCC 6')
arg_parser.add_argument('--enable-alloc-failure-injector', dest='alloc_failure_injector', action='store_true', default=False,
help='enable allocation failure injection')
arg_parser.add_argument('--with-antlr3', dest='antlr3_exec', action='store', default=None,
help='path to antlr3 executable')
arg_parser.add_argument('--with-ragel', dest='ragel_exec', action='store', default=None,
help='path to ragel executable')
args = arg_parser.parse_args()
defines = []
@@ -383,50 +290,41 @@ extra_cxxflags = {}
cassandra_interface = Thrift(source = 'interface/cassandra.thrift', service = 'Cassandra')
scylla_core = (['database.cc',
'atomic_cell.cc',
'schema.cc',
'frozen_schema.cc',
'schema_registry.cc',
'bytes.cc',
'mutation.cc',
'mutation_fragment.cc',
'streamed_mutation.cc',
'partition_version.cc',
'row_cache.cc',
'canonical_mutation.cc',
'frozen_mutation.cc',
'memtable.cc',
'schema_mutations.cc',
'release.cc',
'supervisor.cc',
'utils/logalloc.cc',
'utils/large_bitset.cc',
'utils/buffer_input_stream.cc',
'utils/limiting_data_source.cc',
'mutation_partition.cc',
'mutation_partition_view.cc',
'mutation_partition_serializer.cc',
'mutation_reader.cc',
'flat_mutation_reader.cc',
'mutation_query.cc',
'keys.cc',
'counters.cc',
'compress.cc',
'sstables/mp_row_consumer.cc',
'counters.cc',
'sstables/sstables.cc',
'sstables/sstable_version.cc',
'sstables/compress.cc',
'sstables/row.cc',
'sstables/partition.cc',
'sstables/filter.cc',
'sstables/compaction.cc',
'sstables/compaction_strategy.cc',
'sstables/compaction_manager.cc',
'sstables/integrity_checked_file_impl.cc',
'sstables/prepended_input_stream.cc',
'sstables/m_format_write_helpers.cc',
'sstables/m_format_read_helpers.cc',
'sstables/atomic_deletion.cc',
'transport/event.cc',
'transport/event_notifier.cc',
'transport/server.cc',
'transport/messages/result_message.cc',
'cql3/abstract_marker.cc',
'cql3/attributes.cc',
'cql3/cf_name.cc',
@@ -438,7 +336,6 @@ scylla_core = (['database.cc',
'cql3/sets.cc',
'cql3/maps.cc',
'cql3/functions/functions.cc',
'cql3/functions/castas_fcts.cc',
'cql3/statements/cf_prop_defs.cc',
'cql3/statements/cf_statement.cc',
'cql3/statements/authentication_statement.cc',
@@ -446,7 +343,7 @@ scylla_core = (['database.cc',
'cql3/statements/create_table_statement.cc',
'cql3/statements/create_view_statement.cc',
'cql3/statements/create_type_statement.cc',
'cql3/statements/drop_index_statement.cc',
'cql3/statements/create_user_statement.cc',
'cql3/statements/drop_keyspace_statement.cc',
'cql3/statements/drop_table_statement.cc',
'cql3/statements/drop_view_statement.cc',
@@ -467,6 +364,8 @@ scylla_core = (['database.cc',
'cql3/statements/truncate_statement.cc',
'cql3/statements/alter_table_statement.cc',
'cql3/statements/alter_view_statement.cc',
'cql3/statements/alter_user_statement.cc',
'cql3/statements/drop_user_statement.cc',
'cql3/statements/list_users_statement.cc',
'cql3/statements/authorization_statement.cc',
'cql3/statements/permission_altering_statement.cc',
@@ -475,10 +374,9 @@ scylla_core = (['database.cc',
'cql3/statements/revoke_statement.cc',
'cql3/statements/alter_type_statement.cc',
'cql3/statements/alter_keyspace_statement.cc',
'cql3/statements/role-management-statements.cc',
'cql3/update_parameters.cc',
'cql3/ut_name.cc',
'cql3/role_name.cc',
'cql3/user_options.cc',
'thrift/handler.cc',
'thrift/server.cc',
'thrift/thrift_validation.cc',
@@ -514,25 +412,16 @@ scylla_core = (['database.cc',
'cql3/variable_specifications.cc',
'db/consistency_level.cc',
'db/system_keyspace.cc',
'db/system_distributed_keyspace.cc',
'db/schema_tables.cc',
'db/cql_type_parser.cc',
'db/legacy_schema_migrator.cc',
'db/commitlog/commitlog.cc',
'db/commitlog/commitlog_replayer.cc',
'db/commitlog/commitlog_entry.cc',
'db/hints/manager.cc',
'db/hints/resource_manager.cc',
'db/config.cc',
'db/extensions.cc',
'db/heat_load_balance.cc',
'db/large_partition_handler.cc',
'db/index/secondary_index.cc',
'db/marshal/type_parser.cc',
'db/batchlog_manager.cc',
'db/view/view.cc',
'db/view/row_locking.cc',
'index/secondary_index_manager.cc',
'index/secondary_index.cc',
'io/io.cc',
'utils/utils.cc',
'utils/UUID_gen.cc',
'utils/i_filter.cc',
'utils/bloom_filter.cc',
@@ -542,7 +431,6 @@ scylla_core = (['database.cc',
'utils/dynamic_bitset.cc',
'utils/managed_bytes.cc',
'utils/exceptions.cc',
'utils/config_file.cc',
'gms/version_generator.cc',
'gms/versioned_value.cc',
'gms/gossiper.cc',
@@ -552,7 +440,6 @@ scylla_core = (['database.cc',
'gms/gossip_digest_ack2.cc',
'gms/endpoint_state.cc',
'gms/application_state.cc',
'gms/inet_address.cc',
'dht/i_partitioner.cc',
'dht/murmur3_partitioner.cc',
'dht/byte_ordered_partitioner.cc',
@@ -568,6 +455,7 @@ scylla_core = (['database.cc',
'locator/network_topology_strategy.cc',
'locator/everywhere_replication_strategy.cc',
'locator/token_metadata.cc',
'locator/locator.cc',
'locator/snitch_base.cc',
'locator/simple_snitch.cc',
'locator/rack_inferring_snitch.cc',
@@ -575,12 +463,11 @@ scylla_core = (['database.cc',
'locator/production_snitch_base.cc',
'locator/ec2_snitch.cc',
'locator/ec2_multi_region_snitch.cc',
'locator/gce_snitch.cc',
'message/messaging_service.cc',
'service/client_state.cc',
'service/migration_task.cc',
'service/storage_service.cc',
'service/misc_services.cc',
'service/load_broadcaster.cc',
'service/pager/paging_state.cc',
'service/pager/query_pagers.cc',
'streaming/stream_task.cc',
@@ -596,41 +483,26 @@ scylla_core = (['database.cc',
'streaming/stream_manager.cc',
'streaming/stream_result_future.cc',
'streaming/stream_session_state.cc',
'clocks-impl.cc',
'gc_clock.cc',
'partition_slice_builder.cc',
'init.cc',
'lister.cc',
'repair/repair.cc',
'exceptions/exceptions.cc',
'auth/allow_all_authenticator.cc',
'auth/allow_all_authorizer.cc',
'dns.cc',
'auth/auth.cc',
'auth/authenticated_user.cc',
'auth/authenticator.cc',
'auth/common.cc',
'auth/authorizer.cc',
'auth/default_authorizer.cc',
'auth/resource.cc',
'auth/roles-metadata.cc',
'auth/data_resource.cc',
'auth/password_authenticator.cc',
'auth/permission.cc',
'auth/permissions_cache.cc',
'auth/service.cc',
'auth/standard_role_manager.cc',
'auth/transitional.cc',
'auth/authentication_options.cc',
'auth/role_or_anonymous.cc',
'tracing/tracing.cc',
'tracing/trace_keyspace_helper.cc',
'tracing/trace_state.cc',
'table_helper.cc',
'range_tombstone.cc',
'range_tombstone_list.cc',
'disk-error-handler.cc',
'duration.cc',
'vint-serialization.cc',
'utils/arch/powerpc/crc32-vpmsum/crc32_wrapper.cc',
'querier.cc',
'data/cell.cc',
'multishard_writer.cc',
'disk-error-handler.cc'
]
+ [Antlr3Grammar('cql3/Cql.g')]
+ [Thrift('interface/cassandra.thrift', 'Cassandra')]
@@ -667,9 +539,7 @@ api = ['api/api.cc',
'api/api-doc/stream_manager.json',
'api/stream_manager.cc',
'api/api-doc/system.json',
'api/system.cc',
'api/config.cc',
'api/api-doc/config.json',
'api/system.cc'
]
idls = ['idl/gossip_digest.idl.hh',
@@ -694,10 +564,9 @@ idls = ['idl/gossip_digest.idl.hh',
'idl/commitlog.idl.hh',
'idl/tracing.idl.hh',
'idl/consistency_level.idl.hh',
'idl/cache_temperature.idl.hh',
]
scylla_tests_dependencies = scylla_core + idls + [
scylla_tests_dependencies = scylla_core + api + idls + [
'tests/cql_test_env.cc',
'tests/cql_assertions.cc',
'tests/result_set_assertions.cc',
@@ -710,7 +579,7 @@ scylla_tests_seastar_deps = [
]
deps = {
'scylla': idls + ['main.cc', 'release.cc'] + scylla_core + api,
'scylla': idls + ['main.cc'] + scylla_core + api,
}
pure_boost_tests = set([
@@ -728,20 +597,6 @@ pure_boost_tests = set([
'tests/dynamic_bitset_test',
'tests/idl_test',
'tests/cartesian_product_test',
'tests/streaming_histogram_test',
'tests/duration_test',
'tests/vint_serialization_test',
'tests/compress_test',
'tests/chunked_vector_test',
'tests/big_decimal_test',
'tests/caching_options_test',
'tests/auth_resource_test',
'tests/enum_set_test',
'tests/cql_auth_syntax_test',
'tests/meta_test',
'tests/imr_test',
'tests/partition_data_test',
'tests/reusable_buffer_test',
])
tests_not_using_seastar_test_framework = set([
@@ -754,9 +609,6 @@ tests_not_using_seastar_test_framework = set([
'tests/perf/perf_cql_parser',
'tests/message',
'tests/perf/perf_simple_query',
'tests/perf/perf_fast_forward',
'tests/perf/perf_cache_eviction',
'tests/row_cache_stress_test',
'tests/memory_footprint',
'tests/gossip',
'tests/perf/perf_sstable',
@@ -772,62 +624,27 @@ for t in scylla_tests:
deps[t] += scylla_tests_dependencies
deps[t] += scylla_tests_seastar_deps
else:
deps[t] += scylla_core + idls + ['tests/cql_test_env.cc']
deps[t] += scylla_core + api + idls + ['tests/cql_test_env.cc']
perf_tests_seastar_deps = [
'seastar/tests/perf/perf_tests.cc'
]
deps['tests/sstable_test'] += ['tests/sstable_datafile_test.cc']
for t in perf_tests:
deps[t] = [t + '.cc'] + scylla_tests_dependencies + perf_tests_seastar_deps
deps['tests/sstable_test'] += ['tests/sstable_datafile_test.cc', 'tests/sstable_utils.cc']
deps['tests/mutation_reader_test'] += ['tests/sstable_utils.cc']
deps['tests/bytes_ostream_test'] = ['tests/bytes_ostream_test.cc', 'utils/managed_bytes.cc', 'utils/logalloc.cc', 'utils/dynamic_bitset.cc']
deps['tests/bytes_ostream_test'] = ['tests/bytes_ostream_test.cc']
deps['tests/input_stream_test'] = ['tests/input_stream_test.cc']
deps['tests/UUID_test'] = ['utils/UUID_gen.cc', 'tests/UUID_test.cc', 'utils/uuid.cc', 'utils/managed_bytes.cc', 'utils/logalloc.cc', 'utils/dynamic_bitset.cc']
deps['tests/UUID_test'] = ['utils/UUID_gen.cc', 'tests/UUID_test.cc', 'utils/uuid.cc']
deps['tests/murmur_hash_test'] = ['bytes.cc', 'utils/murmur_hash.cc', 'tests/murmur_hash_test.cc']
deps['tests/allocation_strategy_test'] = ['tests/allocation_strategy_test.cc', 'utils/logalloc.cc', 'utils/dynamic_bitset.cc']
deps['tests/log_heap_test'] = ['tests/log_heap_test.cc']
deps['tests/anchorless_list_test'] = ['tests/anchorless_list_test.cc']
deps['tests/perf/perf_fast_forward'] += ['release.cc']
deps['tests/meta_test'] = ['tests/meta_test.cc']
deps['tests/imr_test'] = ['tests/imr_test.cc']
deps['tests/reusable_buffer_test'] = ['tests/reusable_buffer_test.cc']
warnings = [
'-Wno-mismatched-tags', # clang-only
'-Wno-maybe-uninitialized', # false positives on gcc 5
'-Wno-tautological-compare',
'-Wno-parentheses-equality',
'-Wno-c++11-narrowing',
'-Wno-c++1z-extensions',
'-Wno-sometimes-uninitialized',
'-Wno-return-stack-address',
'-Wno-missing-braces',
'-Wno-unused-lambda-capture',
'-Wno-misleading-indentation',
'-Wno-overflow',
'-Wno-noexcept-type',
'-Wno-nonnull-compare'
]
warnings = [w
for w in warnings
if flag_supported(flag = w, compiler = args.cxx)]
if warning_supported(warning = w, compiler = args.cxx)]
warnings = ' '.join(warnings + ['-Wno-error=deprecated-declarations'])
optimization_flags = [
'--param inline-unit-growth=300',
]
optimization_flags = [o
for o in optimization_flags
if flag_supported(flag = o, compiler = args.cxx)]
modes['release']['opt'] += ' ' + ' '.join(optimization_flags)
gold_linker_flag = gold_supported(compiler = args.cxx)
warnings = ' '.join(warnings)
dbgflag = debug_flag(args.cxx) if args.debuginfo else ''
tests_link_rule = 'link' if args.tests_debuginfo else 'link_stripped'
@@ -868,22 +685,6 @@ for pkglist in optional_packages:
alternatives = ':'.join(pkglist[1:])
print('Missing optional package {pkglist[0]} (or alteratives {alternatives})'.format(**locals()))
compiler_test_src = '''
#if __GNUC__ < 7
#error "MAJOR"
#elif __GNUC__ == 7
#if __GNUC_MINOR__ < 3
#error "MINOR"
#endif
#endif
int main() { return 0; }
'''
if not try_compile_and_link(compiler=args.cxx, source=compiler_test_src):
print('Wrong GCC version. Scylla needs GCC >= 7.3 to compile.')
sys.exit(1)
if not try_compile(compiler=args.cxx, source='#include <boost/version.hpp>'):
print('Boost not installed. Please install {}.'.format(pkgname("boost-devel")))
sys.exit(1)
@@ -897,9 +698,6 @@ if not try_compile(compiler=args.cxx, source='''\
print('Installed boost version too old. Please update {}.'.format(pkgname("boost-devel")))
sys.exit(1)
has_sanitize_address_use_after_scope = try_compile(compiler=args.cxx, flags=['-fsanitize-address-use-after-scope'], source='int f() {}')
defines = ' '.join(['-D' + d for d in defines])
globals().update(vars(args))
@@ -922,7 +720,7 @@ scylla_release = file.read().strip()
extra_cxxflags["release.cc"] = "-DSCYLLA_VERSION=\"\\\"" + scylla_version + "\\\"\" -DSCYLLA_RELEASE=\"\\\"" + scylla_release + "\\\"\""
seastar_flags = []
seastar_flags = ['--disable-xen']
if args.dpdk:
# fake dependencies on dpdk, so that it is built before anything else
seastar_flags += ['--enable-dpdk']
@@ -932,20 +730,9 @@ if args.staticcxx:
seastar_flags += ['--static-stdc++']
if args.staticboost:
seastar_flags += ['--static-boost']
if args.staticyamlcpp:
seastar_flags += ['--static-yaml-cpp']
if args.gcc6_concepts:
seastar_flags += ['--enable-gcc6-concepts']
if args.alloc_failure_injector:
seastar_flags += ['--enable-alloc-failure-injector']
seastar_cflags = args.user_cflags
if args.target != '':
seastar_cflags += ' -march=' + args.target
seastar_ldflags = args.user_ldflags
seastar_flags += ['--compiler', args.cxx, '--c-compiler', args.cc, '--cflags=%s' % (seastar_cflags), '--ldflags=%s' %(seastar_ldflags),
'--c++-dialect=gnu++1z', '--optflags=%s' % (modes['release']['opt']),
]
seastar_cflags = args.user_cflags + " -march=nehalem"
seastar_flags += ['--compiler', args.cxx, '--cflags=%s' % (seastar_cflags)]
status = subprocess.call([python, './configure.py'] + seastar_flags, cwd = 'seastar')
@@ -976,16 +763,11 @@ for mode in build_modes:
seastar_deps = 'practically_anything_can_change_so_lets_run_it_every_time_and_restat.'
args.user_cflags += " " + pkg_config("--cflags", "jsoncpp")
libs = ' '.join([maybe_static(args.staticyamlcpp, '-lyaml-cpp'), '-llz4', '-lz', '-lsnappy', pkg_config("--libs", "jsoncpp"),
maybe_static(args.staticboost, '-lboost_filesystem'), ' -lcrypt', ' -lcryptopp',
libs = ' '.join(['-lyaml-cpp', '-llz4', '-lz', '-lsnappy', pkg_config("--libs", "jsoncpp"),
maybe_static(args.staticboost, '-lboost_filesystem'), ' -lcrypt',
maybe_static(args.staticboost, '-lboost_date_time'),
])
xxhash_dir = 'xxHash'
if not os.path.exists(xxhash_dir) or not os.listdir(xxhash_dir):
raise Exception(xxhash_dir + ' is empty. Run "git submodule update --init".')
if not args.staticboost:
args.user_cflags += ' -DBOOST_TEST_DYN_LINK'
@@ -1008,31 +790,20 @@ os.makedirs(outdir, exist_ok = True)
do_sanitize = True
if args.static:
do_sanitize = False
if args.antlr3_exec:
antlr3_exec = args.antlr3_exec
else:
antlr3_exec = "antlr3"
if args.ragel_exec:
ragel_exec = args.ragel_exec
else:
ragel_exec = "ragel"
with open(buildfile, 'w') as f:
f.write(textwrap.dedent('''\
configure_args = {configure_args}
builddir = {outdir}
cxx = {cxx}
cxxflags = {user_cflags} {warnings} {defines}
ldflags = {gold_linker_flag} {user_ldflags}
ldflags = {user_ldflags}
libs = {libs}
pool link_pool
depth = {link_pool_depth}
pool seastar_pool
depth = 1
rule ragel
command = {ragel_exec} -G2 -o $out $in
command = ragel -G2 -o $out $in
description = RAGEL $out
rule gen
command = echo -e $text > $out
@@ -1054,9 +825,9 @@ with open(buildfile, 'w') as f:
for mode in build_modes:
modeval = modes[mode]
f.write(textwrap.dedent('''\
cxxflags_{mode} = {opt} -DXXH_PRIVATE_API -I. -I $builddir/{mode}/gen -I seastar -I seastar/build/{mode}/gen
cxxflags_{mode} = -I. -I $builddir/{mode}/gen -I seastar -I seastar/build/{mode}/gen
rule cxx.{mode}
command = $cxx -MD -MT $out -MF $out.d {seastar_cflags} $cxxflags $cxxflags_{mode} $obj_cxxflags -c -o $out $in
command = $cxx -MD -MT $out -MF $out.d {seastar_cflags} $cxxflags $cxxflags_{mode} -c -o $out $in
description = CXX $out
depfile = $out.d
rule link.{mode}
@@ -1074,19 +845,9 @@ with open(buildfile, 'w') as f:
command = thrift -gen cpp:cob_style -out $builddir/{mode}/gen $in
description = THRIFT $in
rule antlr3.{mode}
# We replace many local `ExceptionBaseType* ex` variables with a single function-scope one.
# Because we add such a variable to every function, and because `ExceptionBaseType` is not a global
# name, we also add a global typedef to avoid compilation errors.
command = sed -e '/^#if 0/,/^#endif/d' $in > $builddir/{mode}/gen/$in $
&& {antlr3_exec} $builddir/{mode}/gen/$in $
&& sed -i -e 's/^\\( *\)\\(ImplTraits::CommonTokenType\\* [a-zA-Z0-9_]* = NULL;\\)$$/\\1const \\2/' $
-e '1i using ExceptionBaseType = int;' $
-e 's/^{{/{{ ExceptionBaseType\* ex = nullptr;/; $
s/ExceptionBaseType\* ex = new/ex = new/; $
s/exceptions::syntax_exception e/exceptions::syntax_exception\& e/' $
build/{mode}/gen/${{stem}}Parser.cpp
command = sed -e '/^#if 0/,/^#endif/d' $in > $builddir/{mode}/gen/$in && antlr3 $builddir/{mode}/gen/$in && sed -i 's/^\\( *\)\\(ImplTraits::CommonTokenType\\* [a-zA-Z0-9_]* = NULL;\\)$$/\\1const \\2/' build/{mode}/gen/${{stem}}Parser.cpp
description = ANTLR3 $in
''').format(mode = mode, antlr3_exec = antlr3_exec, **modeval))
''').format(mode = mode, **modeval))
f.write('build {mode}: phony {artifacts}\n'.format(mode = mode,
artifacts = str.join(' ', ('$builddir/' + mode + '/' + x for x in build_artifacts))))
compiles = {}
@@ -1102,7 +863,6 @@ with open(buildfile, 'w') as f:
objs = ['$builddir/' + mode + '/' + src.replace('.cc', '.o')
for src in srcs
if src.endswith('.cc')]
objs.append('$builddir/../utils/arch/powerpc/crc32-vpmsum/crc32.S')
has_thrift = False
for dep in deps[binary]:
if isinstance(dep, Thrift):
@@ -1110,7 +870,19 @@ with open(buildfile, 'w') as f:
objs += dep.objects('$builddir/' + mode + '/gen')
if isinstance(dep, Antlr3Grammar):
objs += dep.objects('$builddir/' + mode + '/gen')
if binary.endswith('.a'):
if binary.endswith('.pc'):
vars = modeval.copy()
vars.update(globals())
pc = textwrap.dedent('''\
Name: Seastar
URL: http://seastar-project.org/
Description: Advanced C++ framework for high-performance server applications on modern hardware.
Version: 1.0
Libs: -L{srcdir}/{builddir} -Wl,--whole-archive -lseastar -Wl,--no-whole-archive {dbgflag} -Wl,--no-as-needed {static} {pie} -fvisibility=hidden -pthread {user_ldflags} {libs} {sanitize_libs}
Cflags: -std=gnu++1y {dbgflag} {fpie} -Wall -Werror -fvisibility=hidden -pthread -I{srcdir} -I{srcdir}/{builddir}/gen {user_cflags} {warnings} {defines} {sanitize} {opt}
''').format(builddir = 'build/' + mode, srcdir = os.getcwd(), **vars)
f.write('build $builddir/{}/{}: gen\n text = {}\n'.format(mode, binary, repr(pc)))
elif binary.endswith('.a'):
f.write('build $builddir/{}/{}: ar.{} {}\n'.format(mode, binary, mode, str.join(' ', objs)))
else:
if binary.startswith('tests/'):
@@ -1173,7 +945,7 @@ with open(buildfile, 'w') as f:
f.write('build {}: ragel {}\n'.format(hh, src))
for hh in swaggers:
src = swaggers[hh]
f.write('build {}: swagger {} | seastar/json/json2code.py\n'.format(hh,src))
f.write('build {}: swagger {}\n'.format(hh,src))
for hh in serializers:
src = serializers[hh]
f.write('build {}: serializer {} | idl-compiler.py\n'.format(hh,src))
@@ -1190,9 +962,6 @@ with open(buildfile, 'w') as f:
for cc in grammar.sources('$builddir/{}/gen'.format(mode)):
obj = cc.replace('.cpp', '.o')
f.write('build {}: cxx.{} {} || {}\n'.format(obj, mode, cc, ' '.join(serializers)))
if cc.endswith('Parser.cpp') and has_sanitize_address_use_after_scope:
# Parsers end up using huge amounts of stack space and overflowing their stack
f.write(' obj_cxxflags = -fno-sanitize-address-use-after-scope\n')
f.write('build seastar/build/{mode}/libseastar.a seastar/build/{mode}/apps/iotune/iotune seastar/build/{mode}/gen/http/request_parser.hh seastar/build/{mode}/gen/http/http_response_parser.hh: ninja {seastar_deps}\n'
.format(**locals()))
f.write(' pool = seastar_pool\n')
@@ -1206,7 +975,7 @@ with open(buildfile, 'w') as f:
rule configure
command = {python} configure.py $configure_args
generator = 1
build build.ninja: configure | configure.py seastar/configure.py
build build.ninja: configure | configure.py
rule cscope
command = find -name '*.[chS]' -o -name "*.cc" -o -name "*.hh" | cscope -bq -i-
description = CSCOPE

View File

@@ -22,7 +22,6 @@
#pragma once
#include "mutation_partition_view.hh"
#include "mutation_partition.hh"
#include "schema.hh"
// Mutation partition visitor which applies visited data into
@@ -38,33 +37,17 @@ private:
static bool is_compatible(const column_definition& new_def, const data_type& old_type, column_kind kind) {
return ::is_compatible(new_def.kind, kind) && new_def.type->is_value_compatible_with(*old_type);
}
static void accept_cell(row& dst, column_kind kind, const column_definition& new_def, const data_type& old_type, atomic_cell_view cell) {
if (!is_compatible(new_def, old_type, kind) || cell.timestamp() <= new_def.dropped_at()) {
return;
void accept_cell(row& dst, column_kind kind, const column_definition& new_def, const data_type& old_type, atomic_cell_view cell) {
if (is_compatible(new_def, old_type, kind) && cell.timestamp() > new_def.dropped_at()) {
dst.apply(new_def, atomic_cell_or_collection(cell));
}
auto new_cell = [&] {
if (cell.is_live() && !old_type->is_counter()) {
if (cell.is_live_and_has_ttl()) {
return atomic_cell_or_collection(
atomic_cell::make_live(*new_def.type, cell.timestamp(), cell.value().linearize(), cell.expiry(), cell.ttl())
);
}
return atomic_cell_or_collection(
atomic_cell::make_live(*new_def.type, cell.timestamp(), cell.value().linearize())
);
} else {
return atomic_cell_or_collection(*new_def.type, cell);
}
}();
dst.apply(new_def, std::move(new_cell));
}
static void accept_cell(row& dst, column_kind kind, const column_definition& new_def, const data_type& old_type, collection_mutation_view cell) {
void accept_cell(row& dst, column_kind kind, const column_definition& new_def, const data_type& old_type, collection_mutation_view cell) {
if (!is_compatible(new_def, old_type, kind)) {
return;
}
cell.data.with_linearized([&] (bytes_view cell_bv) {
auto&& ctype = static_pointer_cast<const collection_type_impl>(old_type);
auto old_view = ctype->deserialize_mutation_form(cell_bv);
auto old_view = ctype->deserialize_mutation_form(cell);
collection_type_impl::mutation_view new_view;
if (old_view.tomb.timestamp > new_def.dropped_at()) {
@@ -76,7 +59,6 @@ private:
}
}
dst.apply(new_def, ctype->serialize_mutation_form(std::move(new_view)));
});
}
public:
converting_mutation_partition_applier(
@@ -92,10 +74,6 @@ public:
_p.apply(t);
}
void accept_static_cell(column_id id, atomic_cell cell) {
return accept_static_cell(id, atomic_cell_view(cell));
}
virtual void accept_static_cell(column_id id, atomic_cell_view cell) override {
const column_mapping_entry& col = _visited_column_mapping.static_column_at(id);
const column_definition* def = _p_schema.get_column_definition(col.name());
@@ -116,17 +94,13 @@ public:
_p.apply_row_tombstone(_p_schema, rt);
}
virtual void accept_row(position_in_partition_view key, const row_tombstone& deleted_at, const row_marker& rm, is_dummy dummy, is_continuous continuous) override {
deletable_row& r = _p.clustered_row(_p_schema, key, dummy, continuous);
virtual void accept_row(clustering_key_view key, tombstone deleted_at, const row_marker& rm) override {
deletable_row& r = _p.clustered_row(_p_schema, key);
r.apply(rm);
r.apply(deleted_at);
_current_row = &r;
}
void accept_row_cell(column_id id, atomic_cell cell) {
return accept_row_cell(id, atomic_cell_view(cell));
}
virtual void accept_row_cell(column_id id, atomic_cell_view cell) override {
const column_mapping_entry& col = _visited_column_mapping.regular_column_at(id);
const column_definition* def = _p_schema.get_column_definition(col.name());
@@ -142,14 +116,4 @@ public:
accept_cell(_current_row->cells(), column_kind::regular_column, *def, col.type(), collection);
}
}
// Appends the cell to dst upgrading it to the new schema.
// Cells must have monotonic names.
static void append_cell(row& dst, column_kind kind, const column_definition& new_def, const column_definition& old_def, const atomic_cell_or_collection& cell) {
if (new_def.is_atomic()) {
accept_cell(dst, kind, new_def, old_def.type, cell.as_atomic_cell(old_def));
} else {
accept_cell(dst, kind, new_def, old_def.type, cell.as_collection_mutation());
}
}
};

View File

@@ -78,97 +78,58 @@ std::vector<counter_shard> counter_cell_view::shards_compatible_with_1_7_4() con
return sorted_shards;
}
static bool apply_in_place(const column_definition& cdef, atomic_cell_mutable_view dst, atomic_cell_mutable_view src)
bool counter_cell_view::apply_reversibly(atomic_cell_or_collection& dst, atomic_cell_or_collection& src)
{
auto dst_ccmv = counter_cell_mutable_view(dst);
auto src_ccmv = counter_cell_mutable_view(src);
auto dst_shards = dst_ccmv.shards();
auto src_shards = src_ccmv.shards();
auto dst_it = dst_shards.begin();
auto src_it = src_shards.begin();
while (src_it != src_shards.end()) {
while (dst_it != dst_shards.end() && dst_it->id() < src_it->id()) {
++dst_it;
}
if (dst_it == dst_shards.end() || dst_it->id() != src_it->id()) {
// Fast-path failed. Revert and fall back to the slow path.
if (dst_it == dst_shards.end()) {
--dst_it;
}
while (src_it != src_shards.begin()) {
--src_it;
while (dst_it->id() != src_it->id()) {
--dst_it;
}
src_it->swap_value_and_clock(*dst_it);
}
return false;
}
if (dst_it->logical_clock() < src_it->logical_clock()) {
dst_it->swap_value_and_clock(*src_it);
} else {
src_it->set_value_and_clock(*dst_it);
}
++src_it;
}
auto dst_ts = dst_ccmv.timestamp();
auto src_ts = src_ccmv.timestamp();
dst_ccmv.set_timestamp(std::max(dst_ts, src_ts));
src_ccmv.set_timestamp(dst_ts);
return true;
}
void counter_cell_view::apply(const column_definition& cdef, atomic_cell_or_collection& dst, atomic_cell_or_collection& src)
{
auto dst_ac = dst.as_atomic_cell(cdef);
auto src_ac = src.as_atomic_cell(cdef);
// TODO: optimise for single shard existing in the other
// TODO: optimise for no new shards?
auto dst_ac = dst.as_atomic_cell();
auto src_ac = src.as_atomic_cell();
if (!dst_ac.is_live() || !src_ac.is_live()) {
if (dst_ac.is_live() || (!src_ac.is_live() && compare_atomic_cell_for_merge(dst_ac, src_ac) < 0)) {
std::swap(dst, src);
return true;
}
return;
return false;
}
if (dst_ac.is_counter_update() && src_ac.is_counter_update()) {
auto src_v = src_ac.counter_update_value();
auto dst_v = dst_ac.counter_update_value();
// FIXME: store deltas just as a normal int64_t and get rid of these calls
// to long_type
auto src_v = value_cast<int64_t>(long_type->deserialize_value(src_ac.value()));
auto dst_v = value_cast<int64_t>(long_type->deserialize_value(dst_ac.value()));
dst = atomic_cell::make_live_counter_update(std::max(dst_ac.timestamp(), src_ac.timestamp()),
src_v + dst_v);
return;
long_type->decompose(src_v + dst_v));
return true;
}
assert(!dst_ac.is_counter_update());
assert(!src_ac.is_counter_update());
with_linearized(dst_ac, [&] (counter_cell_view dst_ccv) {
with_linearized(src_ac, [&] (counter_cell_view src_ccv) {
if (dst_ccv.shard_count() >= src_ccv.shard_count()) {
auto dst_amc = dst.as_mutable_atomic_cell(cdef);
auto src_amc = src.as_mutable_atomic_cell(cdef);
if (!dst_amc.is_value_fragmented() && !src_amc.is_value_fragmented()) {
if (apply_in_place(cdef, dst_amc, src_amc)) {
return;
}
}
}
auto dst_shards = dst_ccv.shards();
auto src_shards = src_ccv.shards();
auto a_shards = counter_cell_view(dst_ac).shards();
auto b_shards = counter_cell_view(src_ac).shards();
counter_cell_builder result;
combine(dst_shards.begin(), dst_shards.end(), src_shards.begin(), src_shards.end(),
combine(a_shards.begin(), a_shards.end(), b_shards.begin(), b_shards.end(),
result.inserter(), counter_shard_view::less_compare_by_id(), [] (auto& x, auto& y) {
return x.logical_clock() < y.logical_clock() ? y : x;
});
auto cell = result.build(std::max(dst_ac.timestamp(), src_ac.timestamp()));
src = std::exchange(dst, atomic_cell_or_collection(std::move(cell)));
});
});
src = std::exchange(dst, atomic_cell_or_collection(cell));
return true;
}
void counter_cell_view::revert_apply(atomic_cell_or_collection& dst, atomic_cell_or_collection& src)
{
if (dst.as_atomic_cell().is_counter_update()) {
auto src_v = value_cast<int64_t>(long_type->deserialize_value(src.as_atomic_cell().value()));
auto dst_v = value_cast<int64_t>(long_type->deserialize_value(dst.as_atomic_cell().value()));
dst = atomic_cell::make_live(dst.as_atomic_cell().timestamp(),
long_type->decompose(dst_v - src_v));
} else {
std::swap(dst, src);
}
}
stdx::optional<atomic_cell> counter_cell_view::difference(atomic_cell_view a, atomic_cell_view b)
@@ -176,17 +137,14 @@ stdx::optional<atomic_cell> counter_cell_view::difference(atomic_cell_view a, at
assert(!a.is_counter_update());
assert(!b.is_counter_update());
if (!b.is_live() || !a.is_live()) {
if (b.is_live() || (!a.is_live() && compare_atomic_cell_for_merge(b, a) < 0)) {
return atomic_cell(*counter_type, a);
}
if (!b.is_live()) {
return { };
} else if (!a.is_live()) {
return atomic_cell(a);
}
return with_linearized(a, [&] (counter_cell_view a_ccv) {
return with_linearized(b, [&] (counter_cell_view b_ccv) {
auto a_shards = a_ccv.shards();
auto b_shards = b_ccv.shards();
auto a_shards = counter_cell_view(a).shards();
auto b_shards = counter_cell_view(b).shards();
auto a_it = a_shards.begin();
auto a_end = a_shards.end();
@@ -208,60 +166,62 @@ stdx::optional<atomic_cell> counter_cell_view::difference(atomic_cell_view a, at
if (!result.empty()) {
diff = result.build(std::max(a.timestamp(), b.timestamp()));
} else if (a.timestamp() > b.timestamp()) {
diff = atomic_cell::make_live(*counter_type, a.timestamp(), bytes_view());
diff = atomic_cell::make_live(a.timestamp(), bytes_view());
}
return diff;
});
});
}
void transform_counter_updates_to_shards(mutation& m, const mutation* current_state, uint64_t clock_offset) {
// FIXME: allow current_state to be frozen_mutation
auto transform_new_row_to_shards = [&s = *m.schema(), clock_offset] (column_kind kind, auto& cells) {
cells.for_each_cell([&] (column_id id, atomic_cell_or_collection& ac_o_c) {
auto& cdef = s.column_at(kind, id);
auto acv = ac_o_c.as_atomic_cell(cdef);
auto transform_new_row_to_shards = [clock_offset] (auto& cells) {
cells.for_each_cell([clock_offset] (auto, atomic_cell_or_collection& ac_o_c) {
auto acv = ac_o_c.as_atomic_cell();
if (!acv.is_live()) {
return; // continue -- we are in lambda
}
auto delta = acv.counter_update_value();
auto cs = counter_shard(counter_id::local(), delta, clock_offset + 1);
ac_o_c = counter_cell_builder::from_single_shard(acv.timestamp(), cs);
auto delta = value_cast<int64_t>(long_type->deserialize_value(acv.value()));
counter_cell_builder ccb;
ccb.add_shard(counter_shard(counter_id::local(), delta, clock_offset + 1));
ac_o_c = ccb.build(acv.timestamp());
});
};
if (!current_state) {
transform_new_row_to_shards(column_kind::static_column, m.partition().static_row());
transform_new_row_to_shards(m.partition().static_row());
for (auto& cr : m.partition().clustered_rows()) {
transform_new_row_to_shards(column_kind::regular_column, cr.row().cells());
transform_new_row_to_shards(cr.row().cells());
}
return;
}
clustering_key::less_compare cmp(*m.schema());
auto transform_row_to_shards = [&s = *m.schema(), clock_offset] (column_kind kind, auto& transformee, auto& state) {
std::deque<std::pair<column_id, counter_shard>> shards;
auto transform_row_to_shards = [clock_offset] (auto& transformee, auto& state) {
struct counter_shard_or_tombstone {
stdx::optional<counter_shard> shard;
tombstone tomb;
};
std::deque<std::pair<column_id, counter_shard_or_tombstone>> shards;
state.for_each_cell([&] (column_id id, const atomic_cell_or_collection& ac_o_c) {
auto& cdef = s.column_at(kind, id);
auto acv = ac_o_c.as_atomic_cell(cdef);
auto acv = ac_o_c.as_atomic_cell();
if (!acv.is_live()) {
counter_shard_or_tombstone cs_o_t { { },
tombstone(acv.timestamp(), acv.deletion_time()) };
shards.emplace_back(std::make_pair(id, cs_o_t));
return; // continue -- we are in lambda
}
counter_cell_view::with_linearized(acv, [&] (counter_cell_view ccv) {
counter_cell_view ccv(acv);
auto cs = ccv.local_shard();
if (!cs) {
return; // continue
}
shards.emplace_back(std::make_pair(id, counter_shard(*cs)));
});
shards.emplace_back(std::make_pair(id, counter_shard_or_tombstone { counter_shard(*cs), tombstone() }));
});
transformee.for_each_cell([&] (column_id id, atomic_cell_or_collection& ac_o_c) {
auto& cdef = s.column_at(kind, id);
auto acv = ac_o_c.as_atomic_cell(cdef);
auto acv = ac_o_c.as_atomic_cell();
if (!acv.is_live()) {
return; // continue -- we are in lambda
}
@@ -269,21 +229,30 @@ void transform_counter_updates_to_shards(mutation& m, const mutation* current_st
shards.pop_front();
}
auto delta = acv.counter_update_value();
auto delta = value_cast<int64_t>(long_type->deserialize_value(acv.value()));
counter_cell_builder ccb;
if (shards.empty() || shards.front().first > id) {
auto cs = counter_shard(counter_id::local(), delta, clock_offset + 1);
ac_o_c = counter_cell_builder::from_single_shard(acv.timestamp(), cs);
} else {
auto& cs = shards.front().second;
ccb.add_shard(counter_shard(counter_id::local(), delta, clock_offset + 1));
} else if (shards.front().second.tomb.timestamp == api::missing_timestamp) {
auto& cs = *shards.front().second.shard;
cs.update(delta, clock_offset + 1);
ac_o_c = counter_cell_builder::from_single_shard(acv.timestamp(), cs);
ccb.add_shard(cs);
shards.pop_front();
} else {
// We are apply the tombstone that's already there second time.
// It is not necessary but there is no easy way to remove cell
// from a mutation.
tombstone t = shards.front().second.tomb;
ac_o_c = atomic_cell::make_dead(t.timestamp, t.deletion_time);
shards.pop_front();
return; // continue -- we are in lambda
}
ac_o_c = ccb.build(acv.timestamp());
});
};
transform_row_to_shards(column_kind::static_column, m.partition().static_row(), current_state->partition().static_row());
transform_row_to_shards(m.partition().static_row(), current_state->partition().static_row());
auto& cstate = current_state->partition();
auto it = cstate.clustered_rows().begin();
@@ -293,10 +262,10 @@ void transform_counter_updates_to_shards(mutation& m, const mutation* current_st
++it;
}
if (it == end || cmp(cr.key(), it->key())) {
transform_new_row_to_shards(column_kind::regular_column, cr.row().cells());
transform_new_row_to_shards(cr.row().cells());
continue;
}
transform_row_to_shards(column_kind::regular_column, cr.row().cells(), it->row().cells());
transform_row_to_shards(cr.row().cells(), it->row().cells());
}
}

View File

@@ -79,8 +79,7 @@ static_assert(std::is_pod<counter_id>::value, "counter_id should be a POD type")
std::ostream& operator<<(std::ostream& os, const counter_id& id);
template<mutable_view is_mutable>
class basic_counter_shard_view {
class counter_shard_view {
enum class offset : unsigned {
id = 0u,
value = unsigned(id) + sizeof(counter_id),
@@ -88,59 +87,40 @@ class basic_counter_shard_view {
total_size = unsigned(logical_clock) + sizeof(int64_t),
};
private:
using pointer_type = std::conditional_t<is_mutable == mutable_view::no, const signed char*, signed char*>;
pointer_type _base;
bytes_view::const_pointer _base;
private:
template<typename T>
T read(offset off) const {
T value;
std::copy_n(_base + static_cast<unsigned>(off), sizeof(T), reinterpret_cast<signed char*>(&value));
std::copy_n(_base + static_cast<unsigned>(off), sizeof(T), reinterpret_cast<char*>(&value));
return value;
}
public:
static constexpr auto size = size_t(offset::total_size);
public:
basic_counter_shard_view() = default;
explicit basic_counter_shard_view(pointer_type ptr) noexcept
counter_shard_view() = default;
explicit counter_shard_view(bytes_view::const_pointer ptr) noexcept
: _base(ptr) { }
counter_id id() const { return read<counter_id>(offset::id); }
int64_t value() const { return read<int64_t>(offset::value); }
int64_t logical_clock() const { return read<int64_t>(offset::logical_clock); }
void swap_value_and_clock(basic_counter_shard_view& other) noexcept {
static constexpr size_t off = size_t(offset::value);
static constexpr size_t size = size_t(offset::total_size) - off;
signed char tmp[size];
std::copy_n(_base + off, size, tmp);
std::copy_n(other._base + off, size, _base + off);
std::copy_n(tmp, size, other._base + off);
}
void set_value_and_clock(const basic_counter_shard_view& other) noexcept {
static constexpr size_t off = size_t(offset::value);
static constexpr size_t size = size_t(offset::total_size) - off;
std::copy_n(other._base + off, size, _base + off);
}
bool operator==(const basic_counter_shard_view& other) const {
bool operator==(const counter_shard_view& other) const {
return id() == other.id() && value() == other.value()
&& logical_clock() == other.logical_clock();
}
bool operator!=(const basic_counter_shard_view& other) const {
bool operator!=(const counter_shard_view& other) const {
return !(*this == other);
}
struct less_compare_by_id {
bool operator()(const basic_counter_shard_view& x, const basic_counter_shard_view& y) const {
bool operator()(const counter_shard_view& x, const counter_shard_view& y) const {
return x.id() < y.id();
}
};
};
using counter_shard_view = basic_counter_shard_view<mutable_view::no>;
std::ostream& operator<<(std::ostream& os, counter_shard_view csv);
class counter_shard {
@@ -150,16 +130,12 @@ class counter_shard {
private:
template<typename T>
static void write(const T& value, bytes::iterator& out) {
out = std::copy_n(reinterpret_cast<const signed char*>(&value), sizeof(T), out);
out = std::copy_n(reinterpret_cast<const char*>(&value), sizeof(T), out);
}
private:
// Shared logic for applying counter_shards and counter_shard_views.
// T is either counter_shard or basic_counter_shard_view<U>.
template<typename T>
GCC6_CONCEPT(requires requires(T shard) {
{ shard.value() } -> int64_t;
{ shard.logical_clock() } -> int64_t;
})
counter_shard& do_apply(T&& other) noexcept {
auto other_clock = other.logical_clock();
if (_logical_clock < other_clock) {
@@ -199,7 +175,7 @@ public:
return do_apply(other);
}
static constexpr size_t serialized_size() {
static size_t serialized_size() {
return counter_shard_view::size;
}
void serialize(bytes::iterator& out) const {
@@ -253,33 +229,10 @@ public:
}
atomic_cell build(api::timestamp_type timestamp) const {
// If we can assume that the counter shards never cross fragment boundaries
// the serialisation code gets much simpler.
static_assert(data::cell::maximum_external_chunk_length % counter_shard::serialized_size() == 0);
auto ac = atomic_cell::make_live_uninitialized(*counter_type, timestamp, serialized_size());
auto dst_it = ac.value().begin();
auto dst_current = *dst_it++;
for (auto&& cs : _shards) {
if (dst_current.empty()) {
dst_current = *dst_it++;
}
assert(!dst_current.empty());
auto value_dst = dst_current.data();
cs.serialize(value_dst);
dst_current.remove_prefix(counter_shard::serialized_size());
}
return ac;
}
static atomic_cell from_single_shard(api::timestamp_type timestamp, const counter_shard& cs) {
// We don't really need to bother with fragmentation here.
static_assert(data::cell::maximum_external_chunk_length >= counter_shard::serialized_size());
auto ac = atomic_cell::make_live_uninitialized(*counter_type, timestamp, counter_shard::serialized_size());
auto dst = ac.value().first_fragment().begin();
cs.serialize(dst);
return ac;
bytes b(bytes::initialized_later(), serialized_size());
auto out = b.begin();
serialize(out);
return atomic_cell::make_live(timestamp, b);
}
class inserter_iterator : public std::iterator<std::output_iterator_tag, counter_shard> {
@@ -306,32 +259,26 @@ public:
// <counter_id> := <int64_t><int64_t>
// <shard> := <counter_id><int64_t:value><int64_t:logical_clock>
// <counter_cell> := <shard>*
template<mutable_view is_mutable>
class basic_counter_cell_view {
protected:
using linearized_value_view = std::conditional_t<is_mutable == mutable_view::no,
bytes_view, bytes_mutable_view>;
using pointer_type = typename linearized_value_view::pointer;
basic_atomic_cell_view<is_mutable> _cell;
linearized_value_view _value;
class counter_cell_view {
atomic_cell_view _cell;
private:
class shard_iterator : public std::iterator<std::input_iterator_tag, basic_counter_shard_view<is_mutable>> {
pointer_type _current;
basic_counter_shard_view<is_mutable> _current_view;
class shard_iterator : public std::iterator<std::input_iterator_tag, const counter_shard_view> {
bytes_view::const_pointer _current;
counter_shard_view _current_view;
public:
shard_iterator() = default;
shard_iterator(pointer_type ptr) noexcept
shard_iterator(bytes_view::const_pointer ptr) noexcept
: _current(ptr), _current_view(ptr) { }
basic_counter_shard_view<is_mutable>& operator*() noexcept {
const counter_shard_view& operator*() const noexcept {
return _current_view;
}
basic_counter_shard_view<is_mutable>* operator->() noexcept {
const counter_shard_view* operator->() const noexcept {
return &_current_view;
}
shard_iterator& operator++() noexcept {
_current += counter_shard_view::size;
_current_view = basic_counter_shard_view<is_mutable>(_current);
_current_view = counter_shard_view(_current);
return *this;
}
shard_iterator operator++(int) noexcept {
@@ -339,16 +286,6 @@ private:
operator++();
return it;
}
shard_iterator& operator--() noexcept {
_current -= counter_shard_view::size;
_current_view = basic_counter_shard_view<is_mutable>(_current);
return *this;
}
shard_iterator operator--(int) noexcept {
auto it = *this;
operator--();
return it;
}
bool operator==(const shard_iterator& other) const noexcept {
return _current == other._current;
}
@@ -358,23 +295,22 @@ private:
};
public:
boost::iterator_range<shard_iterator> shards() const {
auto begin = shard_iterator(_value.data());
auto end = shard_iterator(_value.data() + _value.size());
auto bv = _cell.value();
auto begin = shard_iterator(bv.data());
auto end = shard_iterator(bv.data() + bv.size());
return boost::make_iterator_range(begin, end);
}
size_t shard_count() const {
return _cell.value().size_bytes() / counter_shard_view::size;
return _cell.value().size() / counter_shard_view::size;
}
protected:
public:
// ac must be a live counter cell
explicit basic_counter_cell_view(basic_atomic_cell_view<is_mutable> ac, linearized_value_view vv) noexcept
: _cell(ac), _value(vv)
{
explicit counter_cell_view(atomic_cell_view ac) noexcept : _cell(ac) {
assert(_cell.is_live());
assert(!_cell.is_counter_update());
}
public:
api::timestamp_type timestamp() const { return _cell.timestamp(); }
static data_type total_value_type() { return long_type; }
@@ -400,27 +336,19 @@ public:
return get_shard(counter_id::local());
}
bool operator==(const basic_counter_cell_view& other) const {
bool operator==(const counter_cell_view& other) const {
return timestamp() == other.timestamp() && boost::equal(shards(), other.shards());
}
};
struct counter_cell_view : basic_counter_cell_view<mutable_view::no> {
using basic_counter_cell_view::basic_counter_cell_view;
template<typename Function>
static decltype(auto) with_linearized(basic_atomic_cell_view<mutable_view::no> ac, Function&& fn) {
return ac.value().with_linearized([&] (bytes_view value_view) {
counter_cell_view ccv(ac, value_view);
return fn(ccv);
});
}
// Returns counter shards in an order that is compatible with Scylla 1.7.4.
std::vector<counter_shard> shards_compatible_with_1_7_4() const;
// Reversibly applies two counter cells, at least one of them must be live.
static void apply(const column_definition& cdef, atomic_cell_or_collection& dst, atomic_cell_or_collection& src);
// Returns true iff dst was modified.
static bool apply_reversibly(atomic_cell_or_collection& dst, atomic_cell_or_collection& src);
// Reverts apply performed by apply_reversible().
static void revert_apply(atomic_cell_or_collection& dst, atomic_cell_or_collection& src);
// Computes a counter cell containing minimal amount of data which, when
// applied to 'b' returns the same cell as 'a' and 'b' applied together.
@@ -429,18 +357,6 @@ struct counter_cell_view : basic_counter_cell_view<mutable_view::no> {
friend std::ostream& operator<<(std::ostream& os, counter_cell_view ccv);
};
struct counter_cell_mutable_view : basic_counter_cell_view<mutable_view::yes> {
using basic_counter_cell_view::basic_counter_cell_view;
explicit counter_cell_mutable_view(atomic_cell_mutable_view ac) noexcept
: basic_counter_cell_view<mutable_view::yes>(ac, ac.value().first_fragment())
{
assert(!ac.value().is_fragmented());
}
void set_timestamp(api::timestamp_type ts) { _cell.set_timestamp(ts); }
};
// Transforms mutation dst from counter updates to counter shards using state
// stored in current_state.
// If current_state is present it has to be in the same schema as dst.

View File

@@ -46,7 +46,6 @@ options {
#include "cql3/statements/drop_type_statement.hh"
#include "cql3/statements/alter_type_statement.hh"
#include "cql3/statements/property_definitions.hh"
#include "cql3/statements/drop_index_statement.hh"
#include "cql3/statements/drop_table_statement.hh"
#include "cql3/statements/drop_view_statement.hh"
#include "cql3/statements/truncate_statement.hh"
@@ -56,16 +55,13 @@ options {
#include "cql3/statements/index_prop_defs.hh"
#include "cql3/statements/raw/use_statement.hh"
#include "cql3/statements/raw/batch_statement.hh"
#include "cql3/statements/create_user_statement.hh"
#include "cql3/statements/alter_user_statement.hh"
#include "cql3/statements/drop_user_statement.hh"
#include "cql3/statements/list_users_statement.hh"
#include "cql3/statements/grant_statement.hh"
#include "cql3/statements/revoke_statement.hh"
#include "cql3/statements/list_permissions_statement.hh"
#include "cql3/statements/alter_role_statement.hh"
#include "cql3/statements/list_roles_statement.hh"
#include "cql3/statements/grant_role_statement.hh"
#include "cql3/statements/revoke_role_statement.hh"
#include "cql3/statements/drop_role_statement.hh"
#include "cql3/statements/create_role_statement.hh"
#include "cql3/statements/index_target.hh"
#include "cql3/statements/ks_prop_defs.hh"
#include "cql3/selection/raw_selector.hh"
@@ -83,8 +79,6 @@ options {
#include "cql3/maps.hh"
#include "cql3/sets.hh"
#include "cql3/lists.hh"
#include "cql3/role_name.hh"
#include "cql3/role_options.hh"
#include "cql3/type_cast.hh"
#include "cql3/tuples.hh"
#include "cql3/user_types.hh"
@@ -94,7 +88,6 @@ options {
#include "core/sstring.hh"
#include "CqlLexer.hpp"
#include <algorithm>
#include <unordered_map>
#include <map>
}
@@ -242,12 +235,6 @@ struct uninitialized {
return res;
}
bool convert_boolean_literal(stdx::string_view s) {
std::string lower_s(s.size(), '\0');
std::transform(s.cbegin(), s.cend(), lower_s.begin(), &::tolower);
return lower_s == "true";
}
void add_raw_update(std::vector<std::pair<::shared_ptr<cql3::column_identifier::raw>,::shared_ptr<cql3::operation::raw_update>>>& operations,
::shared_ptr<cql3::column_identifier::raw> key, ::shared_ptr<cql3::operation::raw_update> update)
{
@@ -331,7 +318,9 @@ cqlStatement returns [shared_ptr<raw::parsed_statement> stmt]
| st10=createIndexStatement { $stmt = st10; }
| st11=dropKeyspaceStatement { $stmt = st11; }
| st12=dropTableStatement { $stmt = st12; }
#if 0
| st13=dropIndexStatement { $stmt = st13; }
#endif
| st14=alterTableStatement { $stmt = st14; }
| st15=alterKeyspaceStatement { $stmt = st15; }
| st16=grantStatement { $stmt = st16; }
@@ -357,12 +346,6 @@ cqlStatement returns [shared_ptr<raw::parsed_statement> stmt]
| st32=createViewStatement { $stmt = st32; }
| st33=alterViewStatement { $stmt = st33; }
| st34=dropViewStatement { $stmt = st34; }
| st35=listRolesStatement { $stmt = st35; }
| st36=grantRoleStatement { $stmt = st36; }
| st37=revokeRoleStatement { $stmt = st37; }
| st38=dropRoleStatement { $stmt = st38; }
| st39=createRoleStatement { $stmt = st39; }
| st40=alterRoleStatement { $stmt = st40; }
;
/*
@@ -373,7 +356,7 @@ useStatement returns [::shared_ptr<raw::use_statement> stmt]
;
/**
* SELECT [JSON] <expression>
* SELECT <expression>
* FROM <CF>
* WHERE KEY = "key1" AND COL > 1 AND COL < 100
* LIMIT <NUMBER>;
@@ -384,12 +367,10 @@ selectStatement returns [shared_ptr<raw::select_statement> expr]
::shared_ptr<cql3::term::raw> limit;
raw::select_statement::parameters::orderings_type orderings;
bool allow_filtering = false;
bool is_json = false;
}
: K_SELECT (
( K_JSON { is_json = true; } )?
( K_DISTINCT { is_distinct = true; } )?
sclause=selectClause
: K_SELECT ( ( K_DISTINCT { is_distinct = true; } )?
sclause=selectClause
| sclause=selectCountClause
)
K_FROM cf=columnFamilyName
( K_WHERE wclause=whereClause )?
@@ -397,7 +378,7 @@ selectStatement returns [shared_ptr<raw::select_statement> expr]
( K_LIMIT rows=intValue { limit = rows; } )?
( K_ALLOW K_FILTERING { allow_filtering = true; } )?
{
auto params = ::make_shared<raw::select_statement::parameters>(std::move(orderings), is_distinct, allow_filtering, is_json);
auto params = ::make_shared<raw::select_statement::parameters>(std::move(orderings), is_distinct, allow_filtering);
$expr = ::make_shared<raw::select_statement>(std::move(cf), std::move(params),
std::move(sclause), std::move(wclause), std::move(limit));
}
@@ -416,11 +397,9 @@ selector returns [shared_ptr<raw_selector> s]
unaliasedSelector returns [shared_ptr<selectable::raw> s]
@init { shared_ptr<selectable::raw> tmp; }
: ( c=cident { tmp = c; }
| K_COUNT '(' countArgument ')' { tmp = selectable::with_function::raw::make_count_rows_function(); }
| K_WRITETIME '(' c=cident ')' { tmp = make_shared<selectable::writetime_or_ttl::raw>(c, true); }
| K_TTL '(' c=cident ')' { tmp = make_shared<selectable::writetime_or_ttl::raw>(c, false); }
| f=functionName args=selectionFunctionArgs { tmp = ::make_shared<selectable::with_function::raw>(std::move(f), std::move(args)); }
| K_CAST '(' arg=unaliasedSelector K_AS t=native_type ')' { tmp = ::make_shared<selectable::with_cast::raw>(std::move(arg), std::move(t)); }
)
( '.' fi=cident { tmp = make_shared<selectable::with_field_selection::raw>(std::move(tmp), std::move(fi)); } )*
{ $s = tmp; }
@@ -433,6 +412,16 @@ selectionFunctionArgs returns [std::vector<shared_ptr<selectable::raw>> a]
')'
;
selectCountClause returns [std::vector<shared_ptr<raw_selector>> expr]
@init{ auto alias = make_shared<cql3::column_identifier>("count", false); }
: K_COUNT '(' countArgument ')' (K_AS c=ident { alias = c; })? {
auto&& with_fn = ::make_shared<cql3::selection::selectable::with_function::raw>(
cql3::functions::function_name::native_function("countRows"),
std::vector<shared_ptr<cql3::selection::selectable::raw>>());
$expr.push_back(make_shared<cql3::selection::raw_selector>(with_fn, alias));
}
;
countArgument
: '*'
| i=INTEGER { if (i->getText() != "1") {
@@ -451,51 +440,33 @@ orderByClause[raw::select_statement::parameters::orderings_type& orderings]
: c=cident (K_ASC | K_DESC { reversed = true; })? { orderings.emplace_back(c, reversed); }
;
jsonValue returns [::shared_ptr<cql3::term::raw> value]
:
| s=STRING_LITERAL { $value = cql3::constants::literal::string(sstring{$s.text}); }
| ':' id=ident { $value = new_bind_variables(id); }
| QMARK { $value = new_bind_variables(shared_ptr<cql3::column_identifier>{}); }
;
/**
* INSERT INTO <CF> (<column>, <column>, <column>, ...)
* VALUES (<value>, <value>, <value>, ...)
* USING TIMESTAMP <long>;
*
*/
insertStatement returns [::shared_ptr<raw::modification_statement> expr]
insertStatement returns [::shared_ptr<raw::insert_statement> expr]
@init {
auto attrs = ::make_shared<cql3::attributes::raw>();
std::vector<::shared_ptr<cql3::column_identifier::raw>> column_names;
std::vector<::shared_ptr<cql3::term::raw>> values;
bool if_not_exists = false;
::shared_ptr<cql3::term::raw> json_value;
}
: K_INSERT K_INTO cf=columnFamilyName
'(' c1=cident { column_names.push_back(c1); } ( ',' cn=cident { column_names.push_back(cn); } )* ')'
( K_VALUES
'(' v1=term { values.push_back(v1); } ( ',' vn=term { values.push_back(vn); } )* ')'
( K_IF K_NOT K_EXISTS { if_not_exists = true; } )?
( usingClause[attrs] )?
{
$expr = ::make_shared<raw::insert_statement>(std::move(cf),
std::move(attrs),
std::move(column_names),
std::move(values),
if_not_exists);
}
| K_JSON
json_token=jsonValue { json_value = $json_token.value; }
( K_IF K_NOT K_EXISTS { if_not_exists = true; } )?
( usingClause[attrs] )?
{
$expr = ::make_shared<raw::insert_json_statement>(std::move(cf),
std::move(attrs),
std::move(json_value),
if_not_exists);
}
)
K_VALUES
'(' v1=term { values.push_back(v1); } ( ',' vn=term { values.push_back(vn); } )* ')'
( K_IF K_NOT K_EXISTS { if_not_exists = true; } )?
( usingClause[attrs] )?
{
$expr = ::make_shared<raw::insert_statement>(std::move(cf),
std::move(attrs),
std::move(column_names),
std::move(values),
if_not_exists);
}
;
usingClause[::shared_ptr<cql3::attributes::raw> attrs]
@@ -807,13 +778,12 @@ createIndexStatement returns [::shared_ptr<create_index_statement> expr]
auto props = make_shared<index_prop_defs>();
bool if_not_exists = false;
auto name = ::make_shared<cql3::index_name>();
std::vector<::shared_ptr<index_target::raw>> targets;
}
: K_CREATE (K_CUSTOM { props->is_custom = true; })? K_INDEX (K_IF K_NOT K_EXISTS { if_not_exists = true; } )?
(idxName[name])? K_ON cf=columnFamilyName '(' (target1=indexIdent { targets.emplace_back(target1); } (',' target2=indexIdent { targets.emplace_back(target2); } )*)? ')'
(idxName[name])? K_ON cf=columnFamilyName '(' id=indexIdent ')'
(K_USING cls=STRING_LITERAL { props->custom_class = sstring{$cls.text}; })?
(K_WITH properties[props])?
{ $expr = ::make_shared<create_index_statement>(cf, name, targets, props, if_not_exists); }
{ $expr = ::make_shared<create_index_statement>(cf, name, id, props, if_not_exists); }
;
indexIdent returns [::shared_ptr<index_target::raw> id]
@@ -987,14 +957,16 @@ dropViewStatement returns [::shared_ptr<drop_view_statement> stmt]
{ $stmt = ::make_shared<drop_view_statement>(cf, if_exists); }
;
#if 0
/**
* DROP INDEX [IF EXISTS] <INDEX_NAME>
*/
dropIndexStatement returns [::shared_ptr<drop_index_statement> expr]
@init { bool if_exists = false; }
: K_DROP K_INDEX (K_IF K_EXISTS { if_exists = true; } )? index=indexName
{ $expr = ::make_shared<drop_index_statement>(index, if_exists); }
dropIndexStatement returns [DropIndexStatement expr]
@init { boolean ifExists = false; }
: K_DROP K_INDEX (K_IF K_EXISTS { ifExists = true; } )? index=indexName
{ $expr = new DropIndexStatement(index, ifExists); }
;
#endif
/**
* TRUNCATE <CF>;
@@ -1004,7 +976,7 @@ truncateStatement returns [::shared_ptr<truncate_statement> stmt]
;
/**
* GRANT <permission> ON <resource> TO <grantee>
* GRANT <permission> ON <resource> TO <username>
*/
grantStatement returns [::shared_ptr<grant_statement> stmt]
: K_GRANT
@@ -1012,12 +984,12 @@ grantStatement returns [::shared_ptr<grant_statement> stmt]
K_ON
resource
K_TO
grantee=userOrRoleName
{ $stmt = ::make_shared<grant_statement>($permissionOrAll.perms, $resource.res, std::move(grantee)); }
username
{ $stmt = ::make_shared<grant_statement>($permissionOrAll.perms, $resource.res, $username.text); }
;
/**
* REVOKE <permission> ON <resource> FROM <revokee>
* REVOKE <permission> ON <resource> FROM <username>
*/
revokeStatement returns [::shared_ptr<revoke_statement> stmt]
: K_REVOKE
@@ -1025,104 +997,80 @@ revokeStatement returns [::shared_ptr<revoke_statement> stmt]
K_ON
resource
K_FROM
revokee=userOrRoleName
{ $stmt = ::make_shared<revoke_statement>($permissionOrAll.perms, $resource.res, std::move(revokee)); }
;
/**
* GRANT <rolename> to <grantee>
*/
grantRoleStatement returns [::shared_ptr<grant_role_statement> stmt]
: K_GRANT role=userOrRoleName K_TO grantee=userOrRoleName
{ $stmt = ::make_shared<grant_role_statement>(std::move(role), std::move(grantee)); }
;
/**
* REVOKE <rolename> FROM <revokee>
*/
revokeRoleStatement returns [::shared_ptr<revoke_role_statement> stmt]
: K_REVOKE role=userOrRoleName K_FROM revokee=userOrRoleName
{ $stmt = ::make_shared<revoke_role_statement>(std::move(role), std::move(revokee)); }
username
{ $stmt = ::make_shared<revoke_statement>($permissionOrAll.perms, $resource.res, $username.text); }
;
listPermissionsStatement returns [::shared_ptr<list_permissions_statement> stmt]
@init {
std::optional<auth::resource> r;
std::optional<sstring> role;
std::experimental::optional<auth::data_resource> r;
std::experimental::optional<sstring> u;
bool recursive = true;
}
: K_LIST
permissionOrAll
( K_ON resource { r = $resource.res; } )?
( K_OF rn=userOrRoleName { role = sstring(static_cast<cql3::role_name>(rn).to_string()); } )?
( K_OF username { u = sstring($username.text); } )?
( K_NORECURSIVE { recursive = false; } )?
{ $stmt = ::make_shared<list_permissions_statement>($permissionOrAll.perms, std::move(r), std::move(role), recursive); }
{ $stmt = ::make_shared<list_permissions_statement>($permissionOrAll.perms, std::move(r), std::move(u), recursive); }
;
permission returns [auth::permission perm]
: p=(K_CREATE | K_ALTER | K_DROP | K_SELECT | K_MODIFY | K_AUTHORIZE | K_DESCRIBE)
: p=(K_CREATE | K_ALTER | K_DROP | K_SELECT | K_MODIFY | K_AUTHORIZE)
{ $perm = auth::permissions::from_string($p.text); }
;
permissionOrAll returns [auth::permission_set perms]
: K_ALL ( K_PERMISSIONS )? { $perms = auth::permissions::ALL; }
: K_ALL ( K_PERMISSIONS )? { $perms = auth::permissions::ALL_DATA; }
| p=permission ( K_PERMISSION )? { $perms = auth::permission_set::from_mask(auth::permission_set::mask_for($p.perm)); }
;
resource returns [uninitialized<auth::resource> res]
: d=dataResource { $res = std::move(d); }
| r=roleResource { $res = std::move(r); }
resource returns [auth::data_resource res]
: r=dataResource { $res = $r.res; }
;
dataResource returns [uninitialized<auth::resource> res]
: K_ALL K_KEYSPACES { $res = auth::resource(auth::resource_kind::data); }
| K_KEYSPACE ks = keyspaceName { $res = auth::make_data_resource($ks.id); }
dataResource returns [auth::data_resource res]
: K_ALL K_KEYSPACES { $res = auth::data_resource(); }
| K_KEYSPACE ks = keyspaceName { $res = auth::data_resource($ks.id); }
| ( K_COLUMNFAMILY )? cf = columnFamilyName
{ $res = auth::make_data_resource($cf.name->get_keyspace(), $cf.name->get_column_family()); }
;
roleResource returns [uninitialized<auth::resource> res]
: K_ALL K_ROLES { $res = auth::resource(auth::resource_kind::role); }
| K_ROLE role = userOrRoleName { $res = auth::make_role_resource(static_cast<const cql3::role_name&>(role).to_string()); }
{ $res = auth::data_resource($cf.name->get_keyspace(), $cf.name->get_column_family()); }
;
/**
* CREATE USER [IF NOT EXISTS] <username> [WITH PASSWORD <password>] [SUPERUSER|NOSUPERUSER]
*/
createUserStatement returns [::shared_ptr<create_role_statement> stmt]
createUserStatement returns [::shared_ptr<create_user_statement> stmt]
@init {
cql3::role_options opts;
opts.is_superuser = false;
opts.can_login = true;
auto opts = ::make_shared<cql3::user_options>();
bool superuser = false;
bool ifNotExists = false;
}
: K_CREATE K_USER (K_IF K_NOT K_EXISTS { ifNotExists = true; })? username
( K_WITH K_PASSWORD v=STRING_LITERAL { opts.password = $v.text; })?
( K_SUPERUSER { opts.is_superuser = true; } | K_NOSUPERUSER { opts.is_superuser = false; } )?
{ $stmt = ::make_shared<create_role_statement>(cql3::role_name($username.text, cql3::preserve_role_case::yes), std::move(opts), ifNotExists); }
( K_WITH userOptions[opts] )?
( K_SUPERUSER { superuser = true; } | K_NOSUPERUSER { superuser = false; } )?
{ $stmt = ::make_shared<create_user_statement>($username.text, std::move(opts), superuser, ifNotExists); }
;
/**
* ALTER USER <username> [WITH PASSWORD <password>] [SUPERUSER|NOSUPERUSER]
*/
alterUserStatement returns [::shared_ptr<alter_role_statement> stmt]
alterUserStatement returns [::shared_ptr<alter_user_statement> stmt]
@init {
cql3::role_options opts;
auto opts = ::make_shared<cql3::user_options>();
std::experimental::optional<bool> superuser;
}
: K_ALTER K_USER username
( K_WITH K_PASSWORD v=STRING_LITERAL { opts.password = $v.text; })?
( K_SUPERUSER { opts.is_superuser = true; } | K_NOSUPERUSER { opts.is_superuser = false; } )?
{ $stmt = ::make_shared<alter_role_statement>(cql3::role_name($username.text, cql3::preserve_role_case::yes), std::move(opts)); }
( K_WITH userOptions[opts] )?
( K_SUPERUSER { superuser = true; } | K_NOSUPERUSER { superuser = false; } )?
{ $stmt = ::make_shared<alter_user_statement>($username.text, std::move(opts), std::move(superuser)); }
;
/**
* DROP USER [IF EXISTS] <username>
*/
dropUserStatement returns [::shared_ptr<drop_role_statement> stmt]
dropUserStatement returns [::shared_ptr<drop_user_statement> stmt]
@init { bool ifExists = false; }
: K_DROP K_USER (K_IF K_EXISTS { ifExists = true; })? username
{ $stmt = ::make_shared<drop_role_statement>(cql3::role_name($username.text, cql3::preserve_role_case::yes), ifExists); }
: K_DROP K_USER (K_IF K_EXISTS { ifExists = true; })? username { $stmt = ::make_shared<drop_user_statement>($username.text, ifExists); }
;
/**
@@ -1132,67 +1080,12 @@ listUsersStatement returns [::shared_ptr<list_users_statement> stmt]
: K_LIST K_USERS { $stmt = ::make_shared<list_users_statement>(); }
;
/**
* CREATE ROLE [IF NOT EXISTS] <role_name> [WITH <roleOption> [AND <roleOption>]*]
*/
createRoleStatement returns [::shared_ptr<create_role_statement> stmt]
@init {
cql3::role_options opts;
opts.is_superuser = false;
opts.can_login = false;
bool if_not_exists = false;
}
: K_CREATE K_ROLE (K_IF K_NOT K_EXISTS { if_not_exists = true; })? name=userOrRoleName
(K_WITH roleOptions[opts])?
{ $stmt = ::make_shared<create_role_statement>(name, std::move(opts), if_not_exists); }
userOptions[::shared_ptr<cql3::user_options> opts]
: userOption[opts]
;
/**
* ALTER ROLE <rolename> [WITH <roleOption> [AND <roleOption>]*]
*/
alterRoleStatement returns [::shared_ptr<alter_role_statement> stmt]
@init {
cql3::role_options opts;
}
: K_ALTER K_ROLE name=userOrRoleName
(K_WITH roleOptions[opts])?
{ $stmt = ::make_shared<alter_role_statement>(name, std::move(opts)); }
;
/**
* DROP ROLE [IF EXISTS] <rolename>
*/
dropRoleStatement returns [::shared_ptr<drop_role_statement> stmt]
@init {
bool if_exists = false;
}
: K_DROP K_ROLE (K_IF K_EXISTS { if_exists = true; })? name=userOrRoleName
{ $stmt = ::make_shared<drop_role_statement>(name, if_exists); }
;
/**
* LIST ROLES [OF <rolename>] [NORECURSIVE]
*/
listRolesStatement returns [::shared_ptr<list_roles_statement> stmt]
@init {
bool recursive = true;
std::optional<cql3::role_name> grantee;
}
: K_LIST K_ROLES
(K_OF g=userOrRoleName { grantee = std::move(g); })?
(K_NORECURSIVE { recursive = false; })?
{ $stmt = ::make_shared<list_roles_statement>(grantee, recursive); }
;
roleOptions[cql3::role_options& opts]
: roleOption[opts] (K_AND roleOption[opts])*
;
roleOption[cql3::role_options& opts]
: K_PASSWORD '=' v=STRING_LITERAL { opts.password = $v.text; }
| K_OPTIONS '=' m=mapLiteral { opts.options = convert_property_map(m); }
| K_SUPERUSER '=' b=BOOLEAN { opts.is_superuser = convert_boolean_literal($b.text); }
| K_LOGIN '=' b=BOOLEAN { opts.can_login = convert_boolean_literal($b.text); }
userOption[::shared_ptr<cql3::user_options> opts]
: k=K_PASSWORD v=STRING_LITERAL { opts->put($k.text, $v.text); }
;
/** DEFINITIONS **/
@@ -1233,13 +1126,12 @@ userTypeName returns [uninitialized<cql3::ut_name> name]
: (ks=ident '.')? ut=non_type_ident { $name = cql3::ut_name(ks, ut); }
;
userOrRoleName returns [uninitialized<cql3::role_name> name]
: t=IDENT { $name = cql3::role_name($t.text, cql3::preserve_role_case::no); }
| t=STRING_LITERAL { $name = cql3::role_name($t.text, cql3::preserve_role_case::yes); }
| t=QUOTED_NAME { $name = cql3::role_name($t.text, cql3::preserve_role_case::yes); }
| k=unreserved_keyword { $name = cql3::role_name(k, cql3::preserve_role_case::no); }
| QMARK {add_recognition_error("Bind variables cannot be used for role names");}
#if 0
userOrRoleName returns [RoleName name]
@init { $name = new RoleName(); }
: roleName[name] {return $name;}
;
#endif
ksName[::shared_ptr<cql3::keyspace_element_name> name]
: t=IDENT { $name->set_keyspace($t.text, false);}
@@ -1262,13 +1154,21 @@ idxName[::shared_ptr<cql3::index_name> name]
| QMARK {add_recognition_error("Bind variables cannot be used for index names");}
;
#if 0
roleName[RoleName name]
: t=IDENT { $name.setName($t.text, false); }
| t=QUOTED_NAME { $name.setName($t.text, true); }
| k=unreserved_keyword { $name.setName(k, false); }
| QMARK {addRecognitionError("Bind variables cannot be used for role names");}
;
#endif
constant returns [shared_ptr<cql3::constants::literal> constant]
@init{std::string sign;}
: t=STRING_LITERAL { $constant = cql3::constants::literal::string(sstring{$t.text}); }
| t=INTEGER { $constant = cql3::constants::literal::integer(sstring{$t.text}); }
| t=FLOAT { $constant = cql3::constants::literal::floating_point(sstring{$t.text}); }
| t=BOOLEAN { $constant = cql3::constants::literal::bool_(sstring{$t.text}); }
| t=DURATION { $constant = cql3::constants::literal::duration(sstring{$t.text}); }
| t=UUID { $constant = cql3::constants::literal::uuid(sstring{$t.text}); }
| t=HEXNUMBER { $constant = cql3::constants::literal::hex(sstring{$t.text}); }
| { sign=""; } ('-' {sign = "-"; } )? t=(K_NAN | K_INFINITY) { $constant = cql3::constants::literal::floating_point(sstring{sign + $t.text}); }
@@ -1403,10 +1303,6 @@ normalColumnOperation[operations_type& operations, ::shared_ptr<cql3::column_ide
}
add_raw_update(operations, key, make_shared<cql3::operation::addition>(cql3::constants::literal::integer($i.text)));
}
| K_SCYLLA_COUNTER_SHARD_LIST '(' t=term ')'
{
add_raw_update(operations, key, ::make_shared<cql3::operation::set_counter_value_from_tuple_list>(t));
}
;
specializedColumnOperation[std::vector<std::pair<shared_ptr<cql3::column_identifier::raw>,
@@ -1566,7 +1462,6 @@ native_type returns [shared_ptr<cql3_type> t]
| K_COUNTER { $t = cql3_type::counter; }
| K_DECIMAL { $t = cql3_type::decimal; }
| K_DOUBLE { $t = cql3_type::double_; }
| K_DURATION { $t = cql3_type::duration; }
| K_FLOAT { $t = cql3_type::float_; }
| K_INET { $t = cql3_type::inet; }
| K_INT { $t = cql3_type::int_; }
@@ -1606,7 +1501,6 @@ tuple_type returns [shared_ptr<cql3::cql3_type::raw> t]
username
: IDENT
| STRING_LITERAL
| QUOTED_NAME { add_recognition_error("Quoted strings are not supported for user names"); }
;
// Basically the same as cident, but we need to exlude existing CQL3 types
@@ -1645,13 +1539,8 @@ basic_unreserved_keyword returns [sstring str]
| K_ALL
| K_USER
| K_USERS
| K_ROLE
| K_ROLES
| K_SUPERUSER
| K_NOSUPERUSER
| K_LOGIN
| K_NOLOGIN
| K_OPTIONS
| K_PASSWORD
| K_EXISTS
| K_CUSTOM
@@ -1671,7 +1560,6 @@ basic_unreserved_keyword returns [sstring str]
| K_LANGUAGE
| K_NON
| K_DETERMINISTIC
| K_JSON
) { $str = $k.text; }
;
@@ -1679,7 +1567,6 @@ basic_unreserved_keyword returns [sstring str]
K_SELECT: S E L E C T;
K_FROM: F R O M;
K_AS: A S;
K_CAST: C A S T;
K_WHERE: W H E R E;
K_AND: A N D;
K_KEY: K E Y;
@@ -1744,19 +1631,13 @@ K_OF: O F;
K_REVOKE: R E V O K E;
K_MODIFY: M O D I F Y;
K_AUTHORIZE: A U T H O R I Z E;
K_DESCRIBE: D E S C R I B E;
K_NORECURSIVE: N O R E C U R S I V E;
K_USER: U S E R;
K_USERS: U S E R S;
K_ROLE: R O L E;
K_ROLES: R O L E S;
K_SUPERUSER: S U P E R U S E R;
K_NOSUPERUSER: N O S U P E R U S E R;
K_PASSWORD: P A S S W O R D;
K_LOGIN: L O G I N;
K_NOLOGIN: N O L O G I N;
K_OPTIONS: O P T I O N S;
K_CLUSTERING: C L U S T E R I N G;
K_ASCII: A S C I I;
@@ -1766,7 +1647,6 @@ K_BOOLEAN: B O O L E A N;
K_COUNTER: C O U N T E R;
K_DECIMAL: D E C I M A L;
K_DOUBLE: D O U B L E;
K_DURATION: D U R A T I O N;
K_FLOAT: F L O A T;
K_INET: I N E T;
K_INT: I N T;
@@ -1808,10 +1688,8 @@ K_NON: N O N;
K_OR: O R;
K_REPLACE: R E P L A C E;
K_DETERMINISTIC: D E T E R M I N I S T I C;
K_JSON: J S O N;
K_SCYLLA_TIMEUUID_LIST_INDEX: S C Y L L A '_' T I M E U U I D '_' L I S T '_' I N D E X;
K_SCYLLA_COUNTER_SHARD_LIST: S C Y L L A '_' C O U N T E R '_' S H A R D '_' L I S T;
// Case-insensitive alpha characters
fragment A: ('a'|'A');
@@ -1897,20 +1775,6 @@ fragment EXPONENT
: E ('+' | '-')? DIGIT+
;
fragment DURATION_UNIT
: Y
| M O
| W
| D
| H
| M
| S
| M S
| U S
| '\u00B5' S
| N S
;
INTEGER
: '-'? DIGIT+
;
@@ -1935,13 +1799,6 @@ BOOLEAN
: T R U E | F A L S E
;
DURATION
: '-'? DIGIT+ DURATION_UNIT (DIGIT+ DURATION_UNIT)*
| '-'? 'P' (DIGIT+ 'Y')? (DIGIT+ 'M')? (DIGIT+ 'D')? ('T' (DIGIT+ 'H')? (DIGIT+ 'M')? (DIGIT+ 'S')?)? // ISO 8601 "format with designators"
| '-'? 'P' DIGIT+ 'W'
| '-'? 'P' DIGIT DIGIT DIGIT DIGIT '-' DIGIT DIGIT '-' DIGIT DIGIT 'T' DIGIT DIGIT ':' DIGIT DIGIT ':' DIGIT DIGIT // ISO 8601 "alternative format"
;
IDENT
: LETTER (LETTER | DIGIT | '_')*
;

View File

@@ -79,7 +79,6 @@ abstract_marker::raw::raw(int32_t bind_index)
return ::make_shared<maps::marker>(_bind_index, receiver);
}
assert(0);
return shared_ptr<term>();
}
assignment_testable::test_result abstract_marker::raw::test_assignment(database& db, const sstring& keyspace, ::shared_ptr<column_specification> receiver) {

View File

@@ -79,7 +79,7 @@ int64_t attributes::get_timestamp(int64_t now, const query_options& options) {
}
try {
data_type_for<int64_t>()->validate(*tval);
} catch (marshal_exception& e) {
} catch (marshal_exception e) {
throw exceptions::invalid_request_exception("Invalid timestamp value");
}
return value_cast<int64_t>(data_type_for<int64_t>()->deserialize(*tval));
@@ -99,7 +99,7 @@ int32_t attributes::get_time_to_live(const query_options& options) {
try {
data_type_for<int32_t>()->validate(*tval);
}
catch (marshal_exception& e) {
catch (marshal_exception e) {
throw exceptions::invalid_request_exception("Invalid TTL value");
}

View File

@@ -1,187 +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 "cql3/prepared_statements_cache.hh"
namespace cql3 {
struct authorized_prepared_statements_cache_size {
size_t operator()(const statements::prepared_statement::checked_weak_ptr& val) {
// TODO: improve the size approximation - most of the entry is occupied by the key here.
return 100;
}
};
class authorized_prepared_statements_cache_key {
public:
using cache_key_type = std::pair<auth::authenticated_user, typename cql3::prepared_cache_key_type::cache_key_type>;
private:
cache_key_type _key;
public:
authorized_prepared_statements_cache_key(auth::authenticated_user user, cql3::prepared_cache_key_type prepared_cache_key)
: _key(std::move(user), std::move(prepared_cache_key.key())) {}
cache_key_type& key() { return _key; }
const cache_key_type& key() const { return _key; }
bool operator==(const authorized_prepared_statements_cache_key& other) const {
return _key == other._key;
}
bool operator!=(const authorized_prepared_statements_cache_key& other) const {
return !(*this == other);
}
static size_t hash(const auth::authenticated_user& user, const cql3::prepared_cache_key_type::cache_key_type& prep_cache_key) {
return utils::hash_combine(std::hash<auth::authenticated_user>()(user), utils::tuple_hash()(prep_cache_key));
}
};
/// \class authorized_prepared_statements_cache
/// \brief A cache of previously authorized statements.
///
/// Entries are inserted every time a new statement is authorized.
/// Entries are evicted in any of the following cases:
/// - When the corresponding prepared statement is not valid anymore.
/// - Periodically, with the same period as the permission cache is refreshed.
/// - If the corresponding entry hasn't been used for \ref entry_expiry.
class authorized_prepared_statements_cache {
public:
struct stats {
uint64_t authorized_prepared_statements_cache_evictions = 0;
};
static stats& shard_stats() {
static thread_local stats _stats;
return _stats;
}
struct authorized_prepared_statements_cache_stats_updater {
static void inc_hits() noexcept {}
static void inc_misses() noexcept {}
static void inc_blocks() noexcept {}
static void inc_evictions() noexcept {
++shard_stats().authorized_prepared_statements_cache_evictions;
}
};
private:
using cache_key_type = authorized_prepared_statements_cache_key;
using checked_weak_ptr = typename statements::prepared_statement::checked_weak_ptr;
using cache_type = utils::loading_cache<cache_key_type,
checked_weak_ptr,
utils::loading_cache_reload_enabled::yes,
authorized_prepared_statements_cache_size,
std::hash<cache_key_type>,
std::equal_to<cache_key_type>,
authorized_prepared_statements_cache_stats_updater>;
public:
using key_type = cache_key_type;
using value_type = checked_weak_ptr;
using entry_is_too_big = typename cache_type::entry_is_too_big;
using iterator = typename cache_type::iterator;
private:
cache_type _cache;
logging::logger& _logger;
public:
// Choose the memory budget such that would allow us ~4K entries when a shard gets 1GB of RAM
authorized_prepared_statements_cache(std::chrono::milliseconds entry_expiration, std::chrono::milliseconds entry_refresh, size_t cache_size, logging::logger& logger)
: _cache(cache_size, entry_expiration, entry_refresh, logger, [this] (const key_type& k) {
_cache.remove(k);
return make_ready_future<value_type>();
})
, _logger(logger)
{}
future<> insert(auth::authenticated_user user, cql3::prepared_cache_key_type prep_cache_key, value_type v) noexcept {
return _cache.get_ptr(key_type(std::move(user), std::move(prep_cache_key)), [v = std::move(v)] (const cache_key_type&) mutable {
return make_ready_future<value_type>(std::move(v));
}).discard_result();
}
iterator find(const auth::authenticated_user& user, const cql3::prepared_cache_key_type& prep_cache_key) {
struct key_view {
const auth::authenticated_user& user_ref;
const cql3::prepared_cache_key_type& prep_cache_key_ref;
};
struct hasher {
size_t operator()(const key_view& kv) {
return cql3::authorized_prepared_statements_cache_key::hash(kv.user_ref, kv.prep_cache_key_ref.key());
}
};
struct equal {
bool operator()(const key_type& k1, const key_view& k2) {
return k1.key().first == k2.user_ref && k1.key().second == k2.prep_cache_key_ref.key();
}
bool operator()(const key_view& k2, const key_type& k1) {
return operator()(k1, k2);
}
};
return _cache.find(key_view{user, prep_cache_key}, hasher(), equal());
}
iterator end() {
return _cache.end();
}
void remove(const auth::authenticated_user& user, const cql3::prepared_cache_key_type& prep_cache_key) {
iterator it = find(user, prep_cache_key);
_cache.remove(it);
}
size_t size() const {
return _cache.size();
}
size_t memory_footprint() const {
return _cache.memory_footprint();
}
future<> stop() {
return _cache.stop();
}
};
}
namespace std {
template <>
struct hash<cql3::authorized_prepared_statements_cache_key> final {
size_t operator()(const cql3::authorized_prepared_statements_cache_key& k) const {
return cql3::authorized_prepared_statements_cache_key::hash(k.key().first, k.key().second);
}
};
inline std::ostream& operator<<(std::ostream& out, const cql3::authorized_prepared_statements_cache_key& k) {
return out << "{ " << k.key().first << ", " << k.key().second << " }";
}
}

View File

@@ -40,29 +40,11 @@
*/
#include "cql3/column_condition.hh"
#include "statements/request_validations.hh"
#include "unimplemented.hh"
#include "lists.hh"
#include "maps.hh"
#include <boost/range/algorithm_ext/push_back.hpp>
namespace {
void validate_operation_on_durations(const abstract_type& type, const cql3::operator_type& op) {
using cql3::statements::request_validations::check_false;
if (op.is_slice() && type.references_duration()) {
check_false(type.is_collection(), "Slice conditions are not supported on collections containing durations");
check_false(type.is_tuple(), "Slice conditions are not supported on tuples containing durations");
check_false(type.is_user_type(), "Slice conditions are not supported on UDTs containing durations");
// We're a duration.
throw exceptions::invalid_request_exception(sprint("Slice conditions are not supported on durations"));
}
}
}
namespace cql3 {
bool
@@ -113,7 +95,6 @@ column_condition::raw::prepare(database& db, const sstring& keyspace, const colu
}
return column_condition::in_condition(receiver, std::move(terms));
} else {
validate_operation_on_durations(*receiver.type, _op);
return column_condition::condition(receiver, _value->prepare(db, keyspace, receiver.column_specification), _op);
}
}
@@ -148,8 +129,6 @@ column_condition::raw::prepare(database& db, const sstring& keyspace, const colu
| boost::adaptors::transformed(std::bind(&term::raw::prepare, std::placeholders::_1, std::ref(db), std::ref(keyspace), value_spec)));
return column_condition::in_condition(receiver, _collection_element->prepare(db, keyspace, element_spec), terms);
} else {
validate_operation_on_durations(*receiver.type, _op);
return column_condition::condition(receiver,
_collection_element->prepare(db, keyspace, element_spec),
_value->prepare(db, keyspace, value_spec),

View File

@@ -22,9 +22,6 @@
#include "cql3/column_identifier.hh"
#include "exceptions/exceptions.hh"
#include "cql3/selection/simple_selector.hh"
#include "cql3/util.hh"
#include <regex>
namespace cql3 {
@@ -62,14 +59,6 @@ sstring column_identifier::to_string() const {
return _text;
}
sstring column_identifier::to_cql_string() const {
return util::maybe_quote(_text);
}
sstring column_identifier::raw::to_cql_string() const {
return util::maybe_quote(_text);
}
column_identifier::raw::raw(sstring raw_text, bool keep_case)
: _raw_text{raw_text}
, _text{raw_text}

View File

@@ -80,8 +80,6 @@ public:
sstring to_string() const;
sstring to_cql_string() const;
friend std::ostream& operator<<(std::ostream& out, const column_identifier& i) {
return out << i._text;
}
@@ -123,7 +121,6 @@ public:
bool operator!=(const raw& other) const;
virtual sstring to_string() const;
sstring to_cql_string() const;
friend std::hash<column_identifier::raw>;
friend std::ostream& operator<<(std::ostream& out, const column_identifier::raw& id);

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