Compare commits

..

167 Commits

Author SHA1 Message Date
Pekka Enberg
1915521974 release: prepare for 1.0.4 2016-05-29 10:41:38 +03:00
Tomasz Grabiec
ef9974e723 tests: Add unit tests for schema_registry
(cherry picked from commit 90c31701e3)
2016-05-18 14:52:45 +03:00
Tomasz Grabiec
93ac6a584a schema_registry: Fix possible hang in maybe_sync() if syncer doesn't defer
Spotted during code review.

If it doesn't defer, we may execute then_wrapped() body before we
change the state. Fix by moving then_wrapped() body after state changes.

(cherry picked from commit 443e5aef5a)
2016-05-18 13:53:14 +03:00
Tomasz Grabiec
2457a16d23 migration_manager: Fix schema syncing with older version
The problem was that "s" would not be marked as synced-with if it came from
shard != 0.

As a result, mutation using that schema would fail to apply with an exception:

  "attempted to mutate using not synced schema of ..."

The problem could surface when altering schema without changing
columns and restarting one of the nodes so that it forgets past
versions.

Fixes #1258.

Will be covered by dtest:

  SchemaManagementTest.test_prepared_statements_work_after_node_restart_after_altering_schema_without_changing_columns

(cherry picked from commit 8703136a4f)
2016-05-18 13:52:24 +03:00
Tomasz Grabiec
daabc8777d migration_manager: Invalidate prepared statements on every schema change
Currently we only do that when column set changes. When prepared
statements are executed, paramaters like read repair chance are read
from schema version stored in the statement. Not invalidating prepared
statements on changes of such parameters will appear as if alter took
no effect.

Fixes #1255.
Message-Id: <1462985495-9767-1-git-send-email-tgrabiec@scylladb.com>

(cherry picked from commit 13d8cd0ae9)
(cherry picked from commit 734cfa949a)
2016-05-15 13:36:39 +03:00
Raphael S. Carvalho
b259e1b0bc tests: test that leveled strategy was fixed
L1 wasn't being compacted into L2.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <1a357896a448eafa7da4d28bc56fa02b89d4193e.1460508373.git.raphaelsc@scylladb.com>
(cherry picked from commit beaacbda2e)
2016-05-09 08:17:59 +03:00
Raphael S. Carvalho
322f194032 sstables: Fix leveled compaction strategy
There is a problem in the implementation of leveled compaction strategy that
prevents level 1 from being compacted into level 2, and so forth. As a result,
all sstables will only belong to either level 0 or 1. One of the consequences
is level 1 being overwhelmed by a huge amount of sstables.

The root of the problem is a conditional statement in the code that prevents a
single sstable, with level > 0, from being compacted into a subsequent level
that is empty or has no overlapping sstables.

Fixes #1180.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <9a4bffdb0368dea77b49c23687015ff5832299ab.1460508373.git.raphaelsc@scylladb.com>
(cherry picked from commit c7b728e716)
2016-05-09 08:17:39 +03:00
Glauber Costa
c51b05efb3 throttle: always release at least one request if we are below the limit
Our current throttling code releases one requests per 1MB of memory available
that we have. If we are below the memory limit, but not by 1MB or more, then
we will keep getting to unthrottle, but never really do anything.

If another memtable is close to the flushing point, those requests may be
exactly the ones that would make it flush. Without them, we'll freeze the
database.

In general, we need to always release at least one request to make sure that
progress is always achieved.

This fixes #1144

Signed-off-by: Glauber Costa <glauber@scylladb.com>
(cherry picked from commit 9c87ae3496)
2016-05-09 08:14:37 +03:00
Glauber Costa
2e41a09631 memtable_list: make sure at least two memtables are available
This is usually not a problem for the main memtable list - although it can be,
depending on settings, but shows up easily for the streaming memtables list.

We would like to have at least two memtables, even if we have to cut it short.
If we don't do that, one memtable will have use all available memory and we'll
force throttling until the memtable gets totally flushed.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
(cherry picked from commit 2c5dfe08c1)
2016-05-09 08:14:37 +03:00
Glauber Costa
44cfbc15d0 unnest throttle_state
throttle_state is currently a nested member of database, but there is no
particular reason - aside from the fact that it is currently only ever
referenced by the database for us to do so.

We'll soon want to have some interaction between this and the column family, to
allow us to flush during throttle. To make that easier, let's unnest it.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
(cherry picked from commit 1daede7396)
2016-05-09 08:14:37 +03:00
Glauber Costa
c9bd954237 move information about memtables' region group inside memtable list
This is a preparation patch so we can move the throttling infrastructure inside
the memtable_list. To do that, the region group will have to be passed to the
throttler so let's just go ahead and store it.

In consequence of that, all that the CF has to tell us is what is the current
schema - no longer how to create a new memtable.

Also, with a new parameter to be passed to the memtable_list the creation code
gets quite big and hard to follow. So let's move the creation functions to a
helper.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
(cherry picked from commit 39def369ce)
2016-05-09 08:14:37 +03:00
Calle Wilund
6c4d7223fe database.cc: Fix compilation error with boost 1.55
Message-Id: <1461067254-526-1-git-send-email-calle@scylladb.com>
(cherry picked from commit 9130b0de16)
2016-05-04 08:42:21 +03:00
Calle Wilund
c1a5488993 sstables: Fix compilation error on boost 1.55
Message-Id: <1461067254-526-2-git-send-email-calle@scylladb.com>
(cherry picked from commit 49d3d79dfe)
2016-05-04 08:42:15 +03:00
Pekka Enberg
9c9f62e30b release: prepare for 1.0.3 2016-05-02 14:29:15 +03:00
Pekka Enberg
c147676ccb dist/docker/redhat: Make sure image builds against latest Scylla
Use "yum clean expire-cache" to make sure we build against the latest
Scylla release.
Message-Id: <1460374418-27315-1-git-send-email-penberg@scylladb.com>

(cherry picked from commit 355c3ea331)
2016-04-27 15:07:38 +03:00
Raphael S. Carvalho
07adedf28a tests: fix use-after-free in sstable test
After commit a843aea547, a gate was introduced to make sure that
an asynchronous operation is finished before column family is
destroyed. A sstable testcase was not stopping column family,
instead it just removed column family from compaction manager.
That could cause an user-after-free if column family is destroyed
while the asynchronous operation is running. Let's fix it by
stopping column family in the test.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <ed910ec459c1752148099e6dc503e7f3adee54da.1461177411.git.raphaelsc@scylladb.com>
(cherry picked from commit eb51c93a5a)
2016-04-26 10:37:40 +03:00
Pekka Enberg
8ca530b6d3 Merge "Backport atomic sstable deletion to 1.0" from Avi
"This patchset is a backport of the atomic sstable deletion patchset, which
 waits until all shards agree to delete an sstable set before deleting it,
 avoiding the resurrecting data problem.

 The first four patches are identical to master, the last patch is new.

 Fixes #1181"
2016-04-25 14:12:33 +03:00
Avi Kivity
e5a123ea80 sstables: avoid long-duration smp calls in delete_atomically()
Since seastar is limited to 128 cross-shard calls per shard-pair,
long-duration smp calls can lead to deadlocks.

Prevent such calls by returning immediately from shard 0 (which manages
the deletions), and calling back to the requesting shard when the deletion
completes.
2016-04-25 13:21:00 +03:00
Avi Kivity
9bfce3255a db: delete compacted sstables atomically
If sstables A, B are compacted, A and B must be deleted atomically.
Otherwise, if A has data that is covered by a tombstone in B, and that
tombstone is deleted, and if B is deleted while A is not, then the data
in A is resurrected.

Fixes #1181.

(cherry picked from commit a843aea547)
2016-04-25 11:41:50 +03:00
Avi Kivity
d2251199b2 sstables: convert sstable::mark_for_deletion() to atomic deletion infrastructure
All deletions must go through the same data structure, or some atomic
deletions will never be satisified.

(cherry picked from commit 3798d04ae8)
2016-04-25 11:41:39 +03:00
Avi Kivity
bed6437b38 main: cancel pending atomic deletions on shutdown
A shared sstable must be compacted by all shards before it can be deleted.
Since we're stoping, that's not going to happen.  Cancel those pending
deletions to let anyone waiting on them to continue.

(cherry picked from commit e43dbac836)
2016-04-25 11:41:28 +03:00
Avi Kivity
70508734a5 sstables: add delete_atomically(), for atomically deleting multiple sstables
When we compact a set of sstables, we have to remove the set atomically,
otherwise we can resurrect data if the following happens:

 insert data to sstable A
 insert tombstone to sstable B
 compact A+B -> C (removing both data and tombstone)
 delete B only
 read data from A

Since an sstable may be shared by multiple shard, and each shard performs
compaction at a different time, we need to defer deletion of an sstable
set until all shards agree that the set can be deleted.

An additional atomicity issue exists because posix does not provide a way
to atomically delete multiple files.  This issue is not addressed by this
patch.

(cherry picked from commit 2ba584db8d)
2016-04-25 11:41:20 +03:00
Pekka Enberg
60307f62fe release: prepare for 1.0.2 2016-04-20 22:10:57 +03:00
Gleb Natapov
8006a15e3b udt: fix error generation if accessed type is not udt
Fixes #1198
Message-Id: <1460884314-3717-2-git-send-email-gleb@scylladb.com>

(cherry picked from commit f3b515052b)
2016-04-19 11:28:53 +03:00
Duarte Nunes
1cfbc29f01 udt: Implement to_string() for selectable
Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <1460884314-3717-1-git-send-email-gleb@scylladb.com>
(cherry picked from commit ece89069dd)
2016-04-19 11:28:46 +03:00
Tomasz Grabiec
c665455b71 tests: Add test for query of collection with deleted item
(cherry picked from commit 89bc32b020)
2016-04-18 11:30:28 +03:00
Tomasz Grabiec
b09c91d1c8 mutation_partition: Fix collection emptiness check
Broken by f15c380a4f.

This resulted in empty collection being returned in the results
instead of no collection.

Fixes org.apache.cassandra.cql3.validation.entities.CollectionsTest
from cassandra-unit-tests.

(cherry picked from commit c69d0a8e87)
2016-04-18 11:30:22 +03:00
Tomasz Grabiec
776ae831e6 types: Add default argument values to is_any_live()
(cherry picked from commit b0d4782016)
2016-04-18 11:30:16 +03:00
Pekka Enberg
2ad3c7532f Merge "Summary backport" from Glauber
This series contains 1.0 backports of the following series:

 * Commit 9b98278 ("Merge "Be able to boot without a Summary" from Glauber")
 * Commit 60352f8 ("Merge "Fixes for the reading of missing Summary" from Glauber")

The backport was done by Glauber because the original commits don't work
as-is due to I/O error handling differences in master and 1.0.

Fixes #1170
2016-04-13 22:02:40 +03:00
Glauber Costa
91c35c3e19 sstable_tests: make sure the generation of the Summary is sane
When we recreate the summary from a missing Summary, we should make
sure it is generated sanely, and that it resembles the Summary that
would have otherwise been there.

In this tests we'll grab one of the Summary tests we've been doing,
and just apply them to the non-existent Summary file. We expect
the same results on those cases. Plus, a new test is added with some
sanity checking.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
2016-04-13 14:18:03 -04:00
Glauber Costa
4f0cc195dc be robust against broken summary files
Now that we can boot without a Summary file, we can just as easily boot
with a broken one.

Suggested by Nadav, and it is actually very easy to do, so do it.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
2016-04-13 14:17:54 -04:00
Glauber Costa
c9f7986be4 review fixes for generate_summary
Spotted by Avi post-merge
1) Need to close the file
2) Should be using the parameter pc instead of the default_class

1.0 backport: general_disk_error is non-existent. Replace it with just
propagating the exception

Signed-off-by: Glauber Costa <glauber@scylladb.com>
2016-04-13 14:17:15 -04:00
Glauber Costa
4feaf1372b clear components if reading toc fail
This shouldn't be a problem in practice, because if read_toc() fails,
the users will just tend to discard the sstable object altogether, and
not insist on using it.

However, if somebody does try to keep using it, a subsequent read_toc() could
theoretically have some components filled up leading the new reader to believe
the toc was populated successfully.

It is easier to just clear the _components set and never worry about it, than
trying to reason about whether or not that could happen.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
2016-04-13 14:14:04 -04:00
Glauber Costa
3ebfecc88e index_reader: avoid misleading parent name
Also add comments about the expected signature of IndexConsumer

Signed-off-by: Glauber Costa <glauber@scylladb.com>
2016-04-13 14:13:56 -04:00
Glauber Costa
c841d87fe3 summary: generate one if it is not present
There are cases in which a Summary file will not be present, and imported
SSTables will have just the Index and Data files. In earlier versions of
Cassandra, a Summary didn't exist, so one may not be generated when migrating.

In Issue #1170, we can see an example of tables generated by CQLSSTableWriter,
and they lack a Summary. Cassandra is robust against this and can cope
perfectly with the Summary not existing. I will argue that we should do the
same.

1.0 backport: open_checked_file_dma -> open_file_dma

Signed-off-by: Glauber Costa <glauber@scylladb.com>
2016-04-13 14:13:11 -04:00
Glauber Costa
7a887ea2ea sstables: allow read_toc to be called more than once
We do that by bailing immediately if we detect that the components
map is already populated. This allow us to call read_toc() earlier
if we need to - for instance, to inquire about the existence of the
Summary - without the need to re-read the components again later.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
2016-04-13 14:10:52 -04:00
Glauber Costa
bc4d63c802 sstables: avoid passing schema unnecessarily
for prepare_summary we can just pass the min interval as a parameter and
avoid having the schema do yet another hop. For sealing the summary, it
is completely unused and we can do away with it.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
2016-04-13 14:10:41 -04:00
Glauber Costa
616196b543 index reader: make index_consumer a template parameter
This is done so we can use other consumers. An example of that, is regeneration
of the Summary from an existing Index.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
2016-04-13 14:10:32 -04:00
Glauber Costa
a04f462904 make get_sstable_key_range an instance method
Because just creating an SSTable object does not generate any I/O,
get_sstable_key_range should be an instance method. The main advantage
of doing that is that we won't have to read the summary twice. The way
we're doing it currently, if happens to be a shard-relevant table we'll
call load() - which reads the summary again.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
2016-04-13 14:10:18 -04:00
Glauber Costa
ebf8fb802e do not re-read the summary
There are times in which we read the Summary file twice. That actually happens
every time during normal boot (it doesn't during refresh). First during
get_sstable_key_range and then again during load().

Every summary will have at least one entry, so we can easily test for whether
or not this is properly initialized.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
2016-04-13 14:10:00 -04:00
Avi Kivity
8d1374e911 sstables: filter sstables single-row read using first_key/last_key
Using leveled compaction strategy, only a few sstables will contain a
given key, so we need to filter out the rest.  Using the summary entries
to filter keys works if the key is before the first summary entry,
but does not work if it is after the last summary entry, because the last
summary entry does not represent the last key; so sstables that are
are towards the beginning of the ring are read even if they do not contain
the key, greatly reducing read performance.

Fix by consulting the summary's first_key/last_key entries before consulting
the summary entry array.

(cherry picked from commit 715794cce6)
2016-04-13 09:25:07 +03:00
Avi Kivity
bacc769328 Update seastar submodule (branch-1.0)
* seastar aa281bd...0225940 (10):
  > memory: avoid exercising the reclaimers for oversized requests
  > memory: fix live objects counter underflow due to cross-cpu free
  > core/reactor: Don't abort in allocate_aligned_buffer() on allocation failure
  > scripts/posix_net_conf.sh: added a support for bonding interfaces
  > scripts/posix_net_conf.sh: move the NIC configuration code into a separate function
  > scripts/posix_net_conf.sh: implement the logic for selecting default MQ mode
  > scripts/posix_net_conf.sh: forward the interface name as a parameter
  > http/routes: Remove request failure logging to stderr
  > lowres_clock: Initialize _now when the clock is created
  > apps/iotune: fix broken URL
2016-04-11 09:18:47 +03:00
Avi Kivity
241eb9e199 Update seastar submodule to point to scylla-seastar
This allows us to cherry-pick seastar fixes.
2016-04-10 18:25:31 +03:00
Pekka Enberg
58fdfe5bc9 release: prepare for 1.0.1 2016-04-09 19:21:21 +03:00
Tomasz Grabiec
f45cc1b229 tests: cql_query_test: Add test for slicing in reverse
(cherry picked from commit 3e0c24934b)
2016-04-09 18:42:53 +03:00
Tomasz Grabiec
14f9eeaafd mutation_partition: Fix static row being returned when paginating
Reproduced by dtest paging_test.py:TestPagingData.static_columns_paging_test.

Broken by f15c380a4f, where the
calcualtion of has_ck_selector got broken, in such a way that present
clustering restrictions were treated as if not present, which resulted
in static row being returned when it shouldn't.

While at it, unify the check between query_compacted() and
do_compact() by extracting it to a function.

(cherry picked from commit c2b955d40b)
2016-04-09 18:42:53 +03:00
Tomasz Grabiec
05df90ad4b mutation_partition: Fix reversed trim_rows()
The first erase_and_dispose(), which removes rows between last
position and beginning of the next range, can invalidate end()
iterator of the range. Fix by looking up end after erasing.

mutation_partition::range() was split into lower_bound() and
upper_bound() to allow for that.

This affects for example queries with descending order where the
selected clustering range is empty and falls before all rows.

Exposed by f15c380a4f, which is now
calling do_compact() during query.

Reproduced by dtest paging_test.py:TestPagingData.static_columns_paging_test

(cherry picked from commit a1539fed95)
2016-04-09 18:42:53 +03:00
Tomasz Grabiec
5646faba18 tests: Add test for query digest calculation
(cherry picked from commit 474a35ba6b)
2016-04-09 18:42:52 +03:00
Tomasz Grabiec
814df06245 tests: mutation_source: Include random mutations in generate_mutation_sets() result
Probably increases coverage.

(cherry picked from commit 4418da77e6)
2016-04-09 18:42:52 +03:00
Tomasz Grabiec
5ac9e2501c tests: mutation_test: Move mutation generator to mutation_source_test.hh
So that it can be reused.

(cherry picked from commit 5d768d0681)
2016-04-09 18:42:52 +03:00
Tomasz Grabiec
34ddfb4498 tests: mutation_test: Add test case for querying of expired cells
(cherry picked from commit 30d25bc47a)
2016-04-09 18:42:52 +03:00
Tomasz Grabiec
e4d4d0b31c partition_slice_builder: Add new setters
(cherry picked from commit 58bbd4203f)
2016-04-09 18:42:52 +03:00
Tomasz Grabiec
4125f279c0 tests: result_set_assertions: Add and_only_that()
(cherry picked from commit 7cd8e61429)
2016-04-09 18:42:52 +03:00
Tomasz Grabiec
e276e7b1e3 database: Compact mutations when executing data queries
Currently data query digest includes cells and tombstones which may have
expired or be covered by higher-level tombstones. This causes digest
mismatch between replicas if some elements are compacted on one of the
nodes and not on others. This mismatch triggers read-repair which doesn't
resolve because mutations received by mutation queries are not differing,
they are compacted already.

The fix adds compacting step before writing and digesting query results by
reusing the algorithm used by mutation query. This is not the most optimal
way to fix this. The compaction step could be folded with the query writing,
there is redundancy in both steps. However such change carries more risk,
and thus was postponed.

perf_simple_query test (cassandra-stress-like partitions) shows regression
from 83k to 77k (7%) ops/s.

Fixes #1165.

(cherry picked from commit f15c380a4f)
2016-04-09 18:42:52 +03:00
Tomasz Grabiec
a516b24111 mutation_query: Extract main part of mutation_query() into more generic querying_reader
So that it can be reused in query()

(cherry picked from commit e4e8acc946)
2016-04-09 18:42:52 +03:00
Gleb Natapov
4642c706c1 commitlog, sstables: enlarge XFS extent allocation for large files
With big rows I see contention in XFS allocations which cause reactor
thread to sleep. Commitlog is a main offender, so enlarge extent to
commitlog segment size for big files (commitlog and sstable Data files).

Message-Id: <20160404110952.GP20957@scylladb.com>
(cherry picked from commit 70575699e4)
2016-04-07 09:52:15 +03:00
Nadav Har'El
4666c095bc sstables: overhaul range tombstone reading
Until recently, we believed that range tombstones we read from sstables will
always be for entire rows (or more generalized clustering-key prefixes),
not for arbitrary ranges. But as we found out, because Cassandra insists
that range tombstones do not overlap, it may take two overlapping row
tombstones and convert them into three range tombstones which look like
general ranges (see the patch for a more detailed example).

Not only do we need to accept such "split" range tombstones, we also need
to convert them back to our internal representation which, in the above
example, involves two overlapping tombstones. This is what this patch does.

This patch also contains a test for this case: We created in Cassandra
an sstable with two overlapping deletions, and verify that when we read
it to Scylla, we get these two overlapping deletions - despite the
sstable file actually having contained three non-overlapping tombstones.

Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Message-Id: <b7c07466074bf0db6457323af8622bb5210bb86a.1459399004.git.glauber@scylladb.com>
(cherry picked from commit 99ecda3c96)
2016-03-31 12:58:07 +03:00
Nadav Har'El
507e6ec75a sstables: merge range tombstones if possible
This is a rewrite of Glauber's earlier patch to do the same thing, taking
into account Avi's comments (do not use a class, do not throw from the
constructor, etc.). I also verified that the actual use case which was
broken in #1136 was fixed by this patch.

Currently, we have no support for range tombstones because CQL will not
generate them as of version 2.x. Thrift will, but we can safely leave this for
the future.

However, we have seen cases during a real migration in which a pure-CQL
Cassandra would generate range tombstones in its SSTables.

Although we are not sure how and why, those range tombstones were of a special
kind: their end and next's start range were adjacent, which means that in
reality, they could very well have been written as a single range tombstone for
an entire clustering key - which we support just fine.

This code will attempt to fix this problem temporarily by merging such ranges
if possible. Care must be taken so that we don't end up accepting a true
generic range tombstone by accident.

Fixes #1136

Signed-off-by: Glauber Costa <glauber@scylladb.com>
Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Message-Id: <1459333972-20345-1-git-send-email-nyh@scylladb.com>
(cherry picked from commit 0fc9a5ee4d)
2016-03-31 12:57:56 +03:00
Glauber Costa
29d6952ddd sstables: fix exception printouts in check_marker
As Nadav noticed in his bug report, check_marker is creating its error messages
using characters instead of numbers - which is what we intended here in the
first place.

That happens because sprint(), when faced with an 8-byte type, interprets this
as a character.  To avoid that we'll use uint16_t types, taking care not to
sign-extend them.

The bug also noted that one of the error messages is missing a parameter, and
that is also fixed.

Fixes #1122

Signed-off-by: Glauber Costa <glauber@scylladb.com>
Message-Id: <74f825bbff8488ffeb1911e626db51eed88629b1.1459266115.git.glauber@scylladb.com>
(cherry picked from commit 23808ba184)
2016-03-31 12:56:02 +03:00
Pekka Enberg
9fae641099 release: prepare for 1.0.0 2016-03-30 12:19:12 +03:00
Pekka Enberg
ccd1fe4348 Revert "sanity check Seastar's I/O queue configuration"
This reverts commit 7b88ba8882, it's too
late for it.
2016-03-29 16:44:55 +03:00
Glauber Costa
7b88ba8882 sanity check Seastar's I/O queue configuration
While Seastar in general can accept any parameter for its I/O queues, Scylla
in particular shouldn't run with them disabled. Such will be the status when
the max-io-requests parameter is not enabled.

On top of that, we would like to have enough depth per I/O queue not to allow
for shard-local parallelism. Therefore, we will require a minimum per-queue
capacity of 4. In machines where the disk iodepth is not enough to allow for 4
concurrent requests per shard, one should reduce the number of I/O queues.

For --max-io-requests, we will check the parameter itself. However, the
--num-io-queues parameter is not mandatory, and given enough concurrent
requests, Seastar's default configuration can very well just be doing the right
thing. So for that, we will check the final result of each I/O queue.

As it is the case with other checks of the sorts, this can be overridden by
the --developer-mode switch.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
Message-Id: <63bf7e91ac10c95810351815bb8f5e94d75592a5.1458836000.git.glauber@scylladb.com>
(cherry picked from commit e750a94300)
2016-03-29 16:37:16 +03:00
Pekka Enberg
46825a5e07 release: prepare for 1.0.rc3 2016-03-29 16:22:31 +03:00
Benoît Canet
740d98901f collectd: Write to the network to get rid of spurious log messages
Closes #1018

Suggested-by: Avi Kivity <avi@scylladb.com>
Signed-of-by: Benoît Canet <benoit@scylladb.com>
Message-Id: <1458759378-4935-1-git-send-email-benoit@scylladb.com>
(cherry picked from commit 4ac1126677)
2016-03-29 11:47:19 +03:00
Tomasz Grabiec
ceff8b9b41 schema_tables: Wait for notifications to be processed.
Listeners may defer since:

 93015bcc54 "migration_manager: Make the migration callbacks runs inside seastar thread"

Not all places were adjusted to wait for them. Fix that.

Message-Id: <1458837613-27616-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 53bbcf4a1e)
2016-03-29 11:18:32 +03:00
Gleb Natapov
1b2dbcc26e config: enable truncate_request_timeout_in_ms option
Option truncate_request_timeout_in_ms is used by truncate. Mark it as
used.

Message-Id: <20160323162649.GH2282@scylladb.com>
(cherry picked from commit 0afd1c6f0a)
2016-03-29 11:16:53 +03:00
Raphael Carvalho
75b2db7862 sstables: fix deletion of sstable with temporary TOC
After 4e52b41a4, remove_by_toc_name() became aware of temporary TOC
files, however, it doesn't consider that some components may be
missing if temporary TOC is present.
When creating a new sstable, the first thing we do is to write all
components into temporary TOC, so content of a temporary TOC isn't
reliable until it is renamed.

Solution is about implementing the following flow (described by Avi):
"Flow should be:

  - remove all components in parallel
  - forgive ENOENT, since the compoent may not have been written;
otherwise deletion error should be raised
  - fsync the directory
  - delete the temporary TOC
"

This problem can be reproduced by running compaction without disk
space, so compaction would fail and leave a partial sstable that would
be marked for deletion. Afterwards, remove_by_toc_name() would try to
delete a component that doesn't exist because it looked at the content
of temporary TOC.

Fixes #1095.

Signed-off-by: Raphael Carvalho <raphaelsc@scylladb.com>
Message-Id: <0cfcaacb43cc5bad3a8a7ea6c1fa6f325c5de97d.1459194263.git.raphaelsc@scylladb.com>
(cherry picked from commit d515a7fd85)
2016-03-29 10:56:49 +03:00
Tomasz Grabiec
789c1297dd storage_service: Fix typos
Message-Id: <1458837390-26634-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit d1db23e353)
2016-03-29 10:29:28 +03:00
Pekka Enberg
afeaaab034 Update scylla-ami submodule
* dist/ami/files/scylla-ami 89e7436...7019088 (1):
  > Re-enable clocksource=tsc on AMI
2016-03-29 09:59:34 +03:00
Takuya ASADA
80242ff443 dist: re-enable clocksource=tsc on AMI
clocksource=tsc on boot parameter mistakenly dropped on b3c85aea89, need to re-enable.

[ penberg: Manual backport of commit 050fb911d5 to 1.0. ]
Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1459180643-4389-1-git-send-email-syuu@scylladb.com>
2016-03-29 09:56:10 +03:00
Nadav Har'El
0b456578c0 sstable: fix read failure of certain sstables
We had a problem reading certain existing Cassandra sstables into
Scylla.

Our consume_range_tombstone() function assumes that the start and end
columns have a certain "end of component" markers, and want to verify
that assumption. But because of bugs in older versions of Cassandra,
see https://issues.apache.org/jira/browse/CASSANDRA-7593, sometimes the
"end of component" was missing (set to 0). CASSANDRA-7593 suggested
this problem might exist on the start column, so we allowed for that,
but now we discovered a case where also the end column is set to 0 -
causing the test in consume_range_tombstone() to fail and the sstable
read to fail - causing Scylla to no be able to import that sstable from
Cassandra. Allowing for an 0 also on the end column made it possible
to read that sstable, compact it, and so on.

Fixes #1125.

Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Message-Id: <1459173964-23242-1-git-send-email-nyh@scylladb.com>
(cherry picked from commit a05577ca41)
2016-03-28 17:10:10 +03:00
Pekka Enberg
3b5a55c6fc release: prepare for 1.0.rc2 2016-03-27 10:19:53 +03:00
Raphael Carvalho
4f1d37c3c9 Fix corner-case in refresh
Problem found by dtest which loads sstables with generation 1 and 2 into an
empty column family. The root of the problem is that reshuffle procedure
changes new sstables to start from generation 2 at least. So reshuffle could
try to set generation 1 to 2 when generation 2 exists.
This problem can be fixed by starting from generation 1 instead, so reshuffle
would handle this case properly.

Fixes #1099.

Signed-off-by: Raphael Carvalho <raphaelsc@scylladb.com>
Message-Id: <88c51fbda9557a506ad99395aeb0a91cd550ede4.1458917237.git.raphaelsc@scylladb.com>
(cherry picked from commit e6e5999282)
2016-03-27 10:04:28 +03:00
Avi Kivity
8422a42381 dist: ami: fix AMI_OPT receiving no value
We assign AMI=0 and AMI_OPT=1, so in the true case, AMI_OPT has no value,
and a later compare fails.

(cherry picked from commit 077c0d1022)
2016-03-26 21:17:49 +03:00
Takuya ASADA
c0f31fac48 dist/ami: use tilde for release candidate builds
Sync with ubuntu package versioning rule

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1458882718-29317-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 2582dbe4a0)
2016-03-26 16:51:24 +02:00
Calle Wilund
6fe88a663f database: Use disk-marking delete function in discard_sstables
Fixes #797

To make sure an inopportune crash after truncate does not leave
sstables on disk to be considered live, and thus resurrect data,
after a truncate, use delete function that renames the TOC file to
make sure we've marked sstables as dead on disk when we finish
this discard call.
Message-Id: <1458575440-505-2-git-send-email-calle@scylladb.com>

Rebase to 1.0:
Signed-off-by: Glauber Costa <glauber@scylladb.com>
2016-03-24 09:16:24 -04:00
Calle Wilund
5f76f3d445 sstables: Add delete func to rename TOC ensuring table is marked dead
Note: "normal" remove_by_toc_name must now be prepared for and check
if the TOC of the sstable is already moved to temp file when we
get to the juicy delete parts.
Message-Id: <1458575440-505-1-git-send-email-calle@scylladb.com>

For the rebase to 1.0:

Signed-off-by: Glauber Costa <glauber@scylladb.com>
2016-03-24 09:05:03 -04:00
Asias He
6676d126aa streaming: Complete receive task after the flush
A STREAM_MUTATION_DONE message will signal the receiver that the sender
has completed the sending of streams mutations. When the receiver finds
it has zero task to send and zero task to receive, it will finish the
stream_session, and in turn finish the stream_plan if all the
stream_sessions are finished. We should call receive_task_completed only
after the flush finishes so that when stream_plan is finshed all the
data is on disk.

Fixes repair_disjoint_data_test issue with Glauber's "[PATCH v4 0/9] Make
sure repairs do not cripple incoming load" serries

======================================================================
FAIL: repair_disjoint_data_test
(repair_additional_test.RepairAdditionalTest)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "scylla-dtest/repair_additional_test.py",
line 102, in repair_disjoint_data_test
    self.check_rows_on_node(node1, 3000)
  File "scylla-dtest/repair_additional_test.py",
line 33, in check_rows_on_node
    self.assertEqual(len(result), rows, len(result))
AssertionError: 2461

(cherry picked from commit c2eff7e824)
2016-03-24 10:26:00 +02:00
Glauber Costa
38343ccbfe repair: rework repair code so we can limit parallelism
The repair code as it is right now is a bit convoluted: it resorts to detached
continuations + do_for_each when calling sync_ranges, and deals with the
problem of excessive parallelism by employing a semaphore inside that range.

Still, even by doing that, we still generate a great number of
checksum requests because the ranges themselves are processed in parallel.

It would be better to have a single-semaphore to limit the overall parallelism
for all requests.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
(cherry picked from commit f49e965d78)
2016-03-24 10:26:00 +02:00
Glauber Costa
f1272933fd database: keep streaming memtables in their own region group
Theoretically, because we can have a lot of pending streaming memtables, we can
have the database start throttling and incoming connections slowing down during
streaming.

Turns out this is actually a very easy condition to trigger. That is basically
because the other side of the wire in this case is quite efficient in sending
us work. This situation is alleviated a bit by reducing parallelism, but not
only it does't go away completely, once we have the tools to start increasing
parallelism again it will become common place.

The solution for this is to limit the streaming memtables to a fraction of the
total allowed dirty memory. Using the nesting capability built in in the LSA
regions, we will make the streaming region group a child of the main region
group.  With that, we can throttle streaming requests separately, while at the
same time being able to control the total amount of dirty memory as well.

Because of the property, it can still be the case that incoming requests will
throttle earlier due to streaming - unless we allow for more dirty memory to be
used during repairs - but at least that effect will be limited.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
(cherry picked from commit 34a9fc106f)
2016-03-24 10:26:00 +02:00
Glauber Costa
ccd623aa87 streaming memtables: coalesce incoming writes
The repair process will potentially send ranges containing few mutations,
definitely not enough to fill a memtable. It wants to know whether or not each
of those ranges individually succeeded or failed, so we need a future for each.

Small memtables being flushed are bad, and we would like to write bigger
memtables so we can better utilize our disks.

One of the ways to fix that, is changing the repair itself to send more
mutations at a single batch. But relying on that is a bad idea for two reasons:

First, the goals of the SSTable writer and the repair sender are at odds. The
SSTable writer wants to write as few SSTables as possible, while the repair
sender wants to break down the range in pieces as small as it can and checksum
them individually, so it doesn't have to send a lot of mutations for no reason.

Second, even if the repair process wants to process larger ranges at once, some
ranges themselves may be small. So while most ranges would be large, we would
still have potentially some fairly small SSTables lying around.

The best course of action in this case is to coalesce the incoming streams
write-side.  repair can now choose whatever strategy - small or big ranges - it
wants, resting assure that the incoming memtables will be coalesced together.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
(cherry picked from commit 455d5a57d2)
2016-03-24 10:26:00 +02:00
Glauber Costa
8176fa8379 streaming: add incoming streaming mutations to a different sstable
Keeping the mutations coming from the streaming process as mutations like any
other have a number of advantages - and that's why we do it.

However, this makes it impossible for Seastar's I/O scheduler to differentiate
between incoming requests from clients, and those who are arriving from peers
in the streaming process.

As a result, if the streaming mutations consume a significant fraction of the
total mutations, and we happen to be using the disk at its limits, we are in no
position to provide any guarantees - defeating the whole purpose of the
scheduler.

To implement that, we'll keep a separate set of memtables that will contain
only streaming mutations. We don't have to do it this way, but doing so
makes life a lot easier. In particular, to write an SSTable, our API requires
(because the filter requires), that a good estimate on the number of partitions
is informed in advance. The partitions also need to be sorted.

We could write mutations directly to disk, but the above conditions couldn't be
met without significant effort. In particular, because mutations can be
arriving from multiple peer nodes, we can't really sort them without keeping a
staging area anyway.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
(cherry picked from commit 5fa866223d)
2016-03-24 10:26:00 +02:00
Glauber Costa
d03910f46d priority manager: separate streaming reads from writes
Streaming has currently one class, that can be used to contain the read
operations being generated by the streaming process. Those reads come from two
places:

- checksums (if doing repair)
- reading mutations to be sent over the wire.

Depending on the amount of data we're dealing with, that can generate a
significant chunk of data, with seconds worth of backlog, and if we need to
have the incoming writes intertwined with those reads, those can take a long
time.

Even if one node is only acting as a receiver, it may still read a lot for the
checksums - if we're talking about repairs, those are coming from the
checksums.

However, in more complicated failure scenarios, it is not hard to imagine a
node that will be both sending and receiving a lot of data.

The best way to guarantee progress on both fronts, is to put both kinds of
operations into different classes.

This patch introduces a new write class, and rename the old read class so it
can have a more meaningful name.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
(cherry picked from commit 10c8ca6ace)
2016-03-24 10:26:00 +02:00
Glauber Costa
0c75700d8c database: make seal_on_overflow a method of the memtable_list
Signed-off-by: Glauber Costa <glauber@scylladb.com>
(cherry picked from commit 78189de57f)
2016-03-24 10:26:00 +02:00
Glauber Costa
478975b3fa database: move add_memtable as a method of the memtable_list
The column family still has to teach the memtable list how to allocate a new memtable,
since it uses CF parameters to do so.

After that, the memtable_list's constructor takes a seal and a create function and is complete.
The copy constructor can now go, since there are no users left.
The behavior of keeping a reference to the underlying memtables can also go, since we can now
guarantee that nobody is keeping references to it (it is not even a shared pointer anymore).
Individual memtables are, and users may be keeping references to them individually.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
(cherry picked from commit 635bb942b2)
2016-03-24 10:26:00 +02:00
Glauber Costa
5ce76258c8 database: move active_memtable to memtable_list
Each list can have a different active memtable. The column family method keeps
existing, since the two separate sets of memtable are just an implementation
detail to deal with the problem of streaming QoS: *the* active memtable keeps
being the one from the main list.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
(cherry picked from commit 6ba95d450f)
2016-03-24 10:26:00 +02:00
Glauber Costa
4cf8791d56 database: create a class for memtable_list
memtable_list is currently just an alias for a vector of memtables.  Let's move
them to a class on its own, exporting the relevant methods to keep user code
unchanged as much as possible.

This will help us keeping separate lists of memtables.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
(cherry picked from commit af6c7a5192)
2016-03-24 10:26:00 +02:00
Pekka Enberg
ccd51010f1 Merge seastar upstream
* seastar 9f2b868...aa281bd (7):
  > shared_promise: Add move assignment operator
  > lowres_clock: Fix stretched time
  > scripts: Delete tap with ip instead of tunctl
  > vla: Actually be exception-safe
  > vla: Ensure memory is freed if ctor throws
  > vla: Ensure memory is correctly freed
  > net: Improve error message when parsing invalid ipv4 address
2016-03-24 10:25:42 +02:00
Shlomi Livne
8e78cbfc2d fix a collision betwen --ami command line param and env
sysconfig scylla-server includes an AMI, the script also used an AMI
variable fix this by renaming the script variable

6a18634f9f introduced this issue since it
started imported the sysconfig scylla-server

Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
Message-Id: <0bc472bb885db2f43702907e3e40d871f1385972.1458767984.git.shlomi@scylladb.com>
(cherry picked from commit d3a91e737b)
2016-03-24 08:18:45 +02:00
Shlomi Livne
c6c176b1be scylla_io_setup import scylla-server env args
scylla_io_seup requires the scylla-server env to be setup to run
correctly. previously scylla_io_setup was encapsulated in
scylla-io.service that assured this.

extracting CPUSET,SMP from SCYLLA_ARGS as CPUSET is needed for invoking
io_tune

Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
Message-Id: <d49af9cb54ae327c38e451ff76fe0322e64a5f00.1458747527.git.shlomi@scylladb.com>
(cherry picked from commit 6a18634f9f)
2016-03-23 17:55:33 +02:00
Shlomi Livne
9795edbe04 dist/ami: Use the actual number of disks instead of AWS meta service
We have seen in some cases that when using the boto api to start
instances the aws metadata service
http://169.254.169.254/latest/meta-data/block-device-mapping/ returns
incorrect number of disks - workaround that by checking the actual
number of disks using lsblk

Adding a validation at the end verifying that after all computations the
NR_IO_QUEUES will not be greater then the number of shards (we had an
issue with i2.8x)

Fixes: #1062

Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
Message-Id: <54c51cd94dd30577a3fe23aef3ce916c01e05504.1458721659.git.shlomi@scylladb.com>
(cherry picked from commit 4ecc37111f)
2016-03-23 11:22:25 +02:00
Shlomi Livne
1539c8b136 fix centos local ami creation (revert some changes)
in centos we do not have a version file created - revert this changes
introduced when adding ubuntu ami creation

Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
Message-Id: <69c80dcfa7afe4f5db66dde2893d9253a86ac430.1458578004.git.shlomi@scylladb.com>
(cherry picked from commit b7e338275b)
2016-03-23 11:22:25 +02:00
Takuya ASADA
0396a94eaf dist: allow more requests for i2 instances
i2 instances has better performance than others, so allow more requests.
Fixes #921

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1458251067-1533-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 769204d41e)
2016-03-23 11:22:25 +02:00
Raphael Carvalho
3c40c1be71 service: fix refresh
Vlad and I were working on finding the root of the problems with
refresh. We found that refresh was deleting existing sstable files
because of a bug in a function that was supposed to return the maximum
generation of a column family.
The intention of this function is to get generation from last element
of column_family::_sstables, which is of type std::map.
However, we were incorrectly using std::map::end() to get last element,
so garbage was being read instead of maximum generation.
If the garbage value is lower than the minimum generation of a column
family, then reshuffle_sstables() would set generation of all existing
sstables to a lower value. That would confuse our mechanism used to
delete sstables because sstables loaded at boot stage were touched.
Solution to this problem is about using rbegin() instead of end() to
get last element from column_family::_sstables.

The other problem is that refresh will only load generations that are
larger than or equal to X, so new sstables with lower generation will
not be loaded. Solution is about creating a set with generation of
live SSTables from all shards, and using this set to determine whether
a generation is new or not.

The last change was about providing an unused generation to reshuffle
procedure by adding one to the maximum generation. That's important to
prevent reshuffle from touching an existing SSTable.

Tested 'refresh' under the following scenarios:
1) Existing generations: 1, 2, 3, 4. New ones: 5, 6.
2) Existing generations: 3, 4, 5, 6. New ones: 1, 2.
3) Existing generations: 1, 2, 3, 4. New ones: 7, 8.
4) No existing generation. No new generation.
5) No existing generation. New ones: 1, 2.
I also had to adapt existing testcase for reshuffle procedure.

Fixes #1073.

Signed-off-by: Raphael Carvalho <raphaelsc@scylladb.com>
Message-Id: <1c7b8b7f94163d5cd00d90247598dd7d26442e70.1458694985.git.raphaelsc@scylladb.com>
(cherry picked from commit 370b1336fe)
2016-03-23 11:22:25 +02:00
Benoît Canet
de969a5d6f dist/ubuntu: Fix the init script variable sourcing
The variable sourcing was crashing the init script on ubuntu.
Fix it with the suggestion from Avi.

Signed-off-by: Benoît Canet <benoit@scylladb.com>
Message-Id: <1458685099-1160-1-git-send-email-benoit@scylladb.com>
(cherry picked from commit 1594bdd5bb)
2016-03-23 11:22:25 +02:00
Takuya ASADA
0ade2894f7 dist: stop using '-p' option on lsblk since Ubuntu doesn't supported it
On scylla_setup interactive mode we are using lsblk to list up candidate
block devices for RAID, and -p option is to print full device paths.

Since Ubuntu 14.04LTS version of lsblk doesn't supported this option, we
need to use non-full path name and complete paths before passes it to
scylla_raid_setup.

Fixes #1030

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1458325411-9870-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 6edd909b00)
2016-03-23 09:16:04 +02:00
Takuya ASADA
6b36315040 dist: allow to run 'sudo scylla_ami_setup' for Ubuntu AMI
Allows to run scylla_ami_setup from scylla-server.conf

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
(cherry picked from commit a6cd085c38)
2016-03-23 09:14:49 +02:00
Takuya ASADA
edc5f8f2f7 dist: launch scylla_ami_setup on Ubuntu AMI
Since upstart does not have same behavior as systemd, we need to run scylla_io_setup and scylla_ami_setup in scylla-server.conf's pre-start stanza.

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
(cherry picked from commit 7828023599)
2016-03-23 09:14:49 +02:00
Takuya ASADA
066149ad46 dist: fix broken scylla_install_pkg --local-pkg and --unstable on Ubuntu
--local-pkg and --unstable arguments didn't handled on Ubuntu, support it.

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
(cherry picked from commit 93bf7bff8e)
2016-03-23 09:14:49 +02:00
Takuya ASADA
1f07468195 dist: prevent to show up dialog on apt-get in scylla_raid_setup
"apt-get -y install mdadm" shows up a dialog to select install mode of postfix, this will block scylla-ami-setup.service forever since it is running as background task, we need to prevent it.

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
(cherry picked from commit 0c83b34d0c)
2016-03-23 09:14:49 +02:00
Takuya ASADA
0577ae5a61 dist: Ubuntu based AMI support
This introduces Ubuntu AMI.
Both CentOS AMI and Ubuntu AMI are need to build on same distribution, so build_ami.sh script automatically detect current distribution, and selects base AMI image.

Fixes #998

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
(cherry picked from commit b097ed6d75)
2016-03-23 09:14:49 +02:00
Pekka Enberg
054cf13cd0 Update scylla-ami submodule
* dist/ami/files/scylla-ami 84bcd0d...89e7436 (3):
  > Merge "iotune packaging fix for scylla-ami" from Takuya
  > Ubuntu AMI support on scylla_install_ami
  > scylla_ami_setup is not POSIX sh compatible, change shebang to /bin/bash
2016-03-23 09:07:07 +02:00
Takuya ASADA
71446edc97 dist: on scylla_io_setup, SMP and CPUSET should be empty when the parameter not present
Fixes #1060

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1458659928-2050-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit dac2bc3055)
2016-03-23 09:06:00 +02:00
Takuya ASADA
c1d8a62b5b dist: remove scylla-io-setup.service and make it standalone script
(cherry picked from commit 9889712d43)
2016-03-23 09:06:00 +02:00
Takuya ASADA
a3baef6b45 dist: on scylla_io_setup print out message both for stdout and syslog
(cherry picked from commit 2cedab07f2)
2016-03-23 09:06:00 +02:00
Takuya ASADA
feaba177e2 dist: introduce dev-mode.conf and scylla_dev_mode_setup
(cherry picked from commit 83112551bb)
2016-03-23 09:06:00 +02:00
Tomasz Grabiec
83a289bdcd cql3: batch_statement: Execute statements sequentially
Currently we execute all statements in parallel, but some statements
depend on order, in particular list append/prepend. Fix by executing
sequentially.

Fixes cql_additional_tests.py:TestCQL.batch_and_list_test dtest.

Fixes #1075.

Message-Id: <1458672874-4749-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 5f44afa311)
2016-03-22 21:06:21 +02:00
Tomasz Grabiec
382e7e63b3 Fix assertion in row_cache_alloc_stress
Fixes the following assertion failure:

  row_cache_alloc_stress: tests/row_cache_alloc_stress.cc:120: main(int, char**)::<lambda()>::<lambda()>: Assertion `mt->occupancy().used_space() < memory::stats().free_memory()' failed.

memory::stats()::free_memory() may be much lower than the actual
amount of reclaimable memory in the system since LSA zones will try to
keep a lot of free segments to themselves. Fix by using actual amount
of reclaimable memory in the check.

(cherry picked from commit a4e3adfbec)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
deeed904f4 logalloc: Introduce tracker::occupancy()
Returns occupancy information for all memory allocated by LSA, including
segment pools / zones.

(cherry picked from commit a0cba3c86f)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
d927053b3b logalloc: Rename tracker::occupancy() to region_occupancy()
(cherry picked from commit 529c8b8858)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
8b8923b5af managed_bytes: Make operator[] work for large blobs as well
Fixes assertion in mutation_test:

mutation_test: ./utils/managed_bytes.hh:349: blob_storage::char_type* managed_bytes::data(): Assertion `!_u.ptr->next'

Introduced in ea7c2dd085

Message-Id: <1458648786-9127-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit ca08db504b)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
48ec129595 perf_simple_query: Make duration configurable
(cherry picked from commit 6e73c3f3dc)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
a4757a6737 mutation_test: Add allocation failure stress test for apply()
The test injects allocation failures at every allocation site during
apply(). Only allocations throug allocation_strategy are instrumented,
but currently those should include all allocations in the apply() path.

The target and source mutations are randomized.

(cherry picked from commit 2fbb55929d)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
223b73849d mutation_test: Add more apply() tests
(cherry picked from commit 8ede27f9c6)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
ba4b1eac45 mutation_test: Hoist make_blob() to a function
(cherry picked from commit 36575d9f01)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
9cf5fabfdf mutation_test: Make make_blob() return different blob each time
random_bytes was constructed with the same seed each time.

(cherry picked from commit 4c85d06df7)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
5723c664ad mutation_test: Fix use-after-free
The problem was that verify_row() was returning a future which was not
waited on. Fix by running the code in a thread.

(cherry picked from commit 19b3df9f0f)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
9635a83edd mutation_partition: Fix friend declarations
Missing "class" confuses CLion IDE.

(cherry picked from commit a7966e9b71)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
24c68e48a5 mutation_partition: Make apply() atomic even in case of exception
We cannot leave partially applied mutation behind when the write
fails. It may fail if memory allocation fails in the middle of
apply(). This for example would violate write atomicity, readers
should either see the whole write or none at all.

This fix makes apply() revert partially applied data upon failure, by
the means of ReversiblyMergeable concept. In a nut shell the idea is
to store old state in the source mutation as we apply it and swap back
in case of exception. At cell level this swapping is inexpensive, just
rewiring pointers. For this to work, the source mutation needs to be
brought into mutable form, so frozen mutations need to be unfrozen. In
practice this doesn't increase amount of cell allocations in the
memtable apply path because incoming data will usually be newer and we
will have to copy it into LSA anyway. There are extra allocations
though for the data structures which holds cells.

I didn't see significant change in performance of:

  build/release/tests/perf/perf_simple_query -c1 -m1G --write --duration 13

The score fluctuates around ~77k ops/s.

Fixes #283.

(cherry picked from commit dc290f0af7)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
80cb0a28e1 mutation_partition: Make intrusive sets ReversiblyMergeable
(cherry picked from commit e09d186c7c)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
95a9f66b75 mutation_partition: Make row_tombstones_entry ReversiblyMergeable
(cherry picked from commit f1a4feb1fc)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
58448d4b05 mutation_partition: Make rows_entry ReversiblyMergeable
(cherry picked from commit e4a576a90f)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
0a4d0e95f2 mutation_partition: Make row_marker ReversiblyMergeable
(cherry picked from commit aadcd75d89)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
2c73e1c2e8 mutation_partition: Make row ReversiblyMergeable
(cherry picked from commit ea7c2dd085)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
0ebd1ae62a atomic_cell_or_collection: Introduce as_atomic_cell_ref()
Needed for setting the REVERT flag on existing cell.

(cherry picked from commit c9d4f5a49c)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
14f616de3f atomic_cell_hash: Specialize appending_hash<> for atomic_cell and collection_mutation
(cherry picked from commit 1ffe06165d)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
827c0f68c3 atomic_cell: Add REVERT flag
Needed to make atomic cells ReversiblyMergeable.

(cherry picked from commit bfc6413414)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
e3607a4c16 tombstone: Make ReversiblyMergeable
(cherry picked from commit 7fcfa97916)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
59270c6d00 Introduce the concept of ReversiblyMergeable
(cherry picked from commit 1407173186)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
3be5d3a7c9 mutation_partition: row: Add empty()
(cherry picked from commit 9fc7f8a5ed)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
cd6697b506 mutation_partition: row: Allow storing empty cells internally
Currently only "set" storage could store empty cells, but not the
"vector" one because there empty cell has the meaning of being
missing. To implement rolback, we need to be able to distinguish empty
cells from missing ones. Solve by making vector storage use a bitmap
for presence checking instead of emptiness. This adds 4 bytes to
vector storage.

(cherry picked from commit d5e66a5b0d)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
acc9849e2b mutation_partition: Make row::merge() tolerate empty row
The row may be empty and still have a set storage, in which case
rbegin() dereference is undefined behavior.

(cherry picked from commit ed1e6515db)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
a445f6a7be managed_bytes: Mark move-assignment noexcept
(cherry picked from commit 184e2831e7)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
88ed9c53a6 managed_bytes: Make copy assignment exception-safe
(cherry picked from commit 92d4cfc3ab)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
50f98ff90a managed_bytes: Make linearization_context::forget() noexcept
It is needed for noexcept destruction, which we need for exception
safety in higher layers.

According to [1], erase() only throws if key comparison throws, and in
our case it doesn't.

[1] http://en.cppreference.com/w/cpp/container/unordered_map/erase

(cherry picked from commit 22d193ba9f)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
30ffb2917f mutation: Add copy assignment operator
We already have a copy constructor, so can have copy assignment as
well.

(cherry picked from commit 87d7279267)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
6ef8b45bf4 mutation_partition: Add cell_entry constructor which makes an empty cell
(cherry picked from commit 8134992024)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
144829606a mutation_partition: Make row::vector_to_set() exception-safe
Currently allocation failure can leave the old row in a
half-moved-from state and leak cell_entry objects.

(cherry picked from commit 518e956736)
2016-03-22 19:59:16 +02:00
Tomasz Grabiec
2eb54bb068 mutation_partition: Unmark cell_entry's copy constructor as noexcept
It was a mistake, it certainly may throw because it copies cells.

(cherry picked from commit c91eefa183)
2016-03-22 19:59:16 +02:00
Pekka Enberg
a133e48515 Merge seastar upstream
* seastar 6a207e1...9f2b868 (10):
  > memory: set free memory to non-zero value in debug mode
  > Merge "Increase IOTune's robustness by including a timeout" from Glauber
  > shared_future: add companion class, shared_promise
  > rpc: fix client connection stopping
  > semaphore: allow wait() and signal() after broken()
  > run reactor::stop() only once
  > sharded: fix start with reference parameter
  > core: add asserts to rwlock
  > util/defer: Fix cancel() not being respected
  > tcp: Do not return accept until the connection is connected
2016-03-22 15:49:51 +02:00
Asias He
5db0049d99 gossip: Sync gossip_digest.idl.hh and application_state.hh
We did the clean up in idl/gossip_digest.idl.hh, but the patch to clean
up gms/application_state.hh was never merged.

To maintain compatibility with previous version of scylla, we can not
change application_state.hh, instead change idl to be sync with
application_state.hh.

Message-Id: <3a78b159d5cb60bc65b354d323d163ce8528b36d.1458557948.git.asias@scylladb.com>
(cherry picked from commit 39992dd559)
2016-03-22 15:22:12 +02:00
Takuya ASADA
ac80445bd9 dist: enable collectd on scylla_setup by default, to make scyllatop usable
Fixes #1037

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1458324769-9152-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 6b2a8a2f70)
2016-03-22 15:16:54 +02:00
Asias He
0c3ffba5c8 messaging_service: Take reference of ms in send_message_timeout_and_retry
Take a reference of messaging_service object inside
send_message_timeout_and_retry to make sure it is not freed during the
life time of send_message_timeout_and_retry operation.

(cherry picked from commit b8abd88841)
2016-03-22 13:20:47 +02:00
Gleb Natapov
7ca3d22c7d messaging: do not admit new requests during messaging service shutdown.
Sending a message may open new client connection which will never be
closed in case messaging service is shutting down already.

Fixes #1059

Message-Id: <1458639452-29388-3-git-send-email-gleb@scylladb.com>
(cherry picked from commit 1e6352e398)
2016-03-22 13:18:12 +02:00
Gleb Natapov
9b1d2dad89 messaging: do not delete client during messaging service shutdown
Messaging service stop() method calls stop() on all clients. If
remove_rpc_client_one() is called while those stops are running
client::stop() will be called twice which not suppose to happen. Fix it
by ignoring client remove request during messaging service shutdown.

Fixes #1059

Message-Id: <1458639452-29388-2-git-send-email-gleb@scylladb.com>
(cherry picked from commit 357c91a076)
2016-03-22 13:18:05 +02:00
Pekka Enberg
7e6a7a6cb5 release: prepare for 1.0.rc1 2016-03-22 12:19:03 +02:00
Pekka Enberg
ec7f637384 dist/ubuntu: Use tilde for release candidate builds
The version number ordering rules are different for rpm and deb. Use
tilde ('~') for the latter to ensure a release candidate is ordered
_before_ a final version.

Message-Id: <1458627524-23030-1-git-send-email-penberg@scylladb.com>
(cherry picked from commit ae33e9fe76)
2016-03-22 12:18:52 +02:00
Nadav Har'El
eecfb2e4ef sstable: fix use-after-free of temporary ioclass copy
Commit 6a3872b355 fixed some use-after-free
bugs but introduced a new one because of a typo:

Instead of capturing a reference to the long-living io-class object, as
all the code does, one place in the code accidentally captured a *copy*
of this object. This copy had a very temporary life, and when a reference
to that *copy* was passed to sstable reading code which assumed that it
lives at least as long as the read call, a use-after-free resulted.

Fixes #1072

Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Message-Id: <1458595629-9314-1-git-send-email-nyh@scylladb.com>
(cherry picked from commit 2eb0627665)
2016-03-22 08:08:49 +02:00
Pekka Enberg
1f6476351a build: Invoke Seastar build only once
Make sure we invoke the Seastar ninja build only once from our own build
process so that we don't have multiple ninjas racing with each other.

Refs #1061.

Message-Id: <1458563076-29502-1-git-send-email-penberg@scylladb.com>
(cherry picked from commit 4892a6ded9)
2016-03-22 08:08:02 +02:00
Pekka Enberg
0d95dd310a Revert "build: prepare for 1.0 release series"
This reverts commit 80d2b72068. It breaks
the RPM build which does not allow the "-" character to appear in
version numbers.
2016-03-22 08:03:22 +02:00
Avi Kivity
80d2b72068 build: prepare for 1.0 release series 2016-03-21 18:44:05 +02:00
Asias He
ac95f04ff9 gossip: Handle unknown application_state when printing
In case an unknown application_state is received, we should be able to
handle it when printting.

Message-Id: <98d2307359292e90c8925f38f67a74b69e45bebe.1458553057.git.asias@scylladb.com>
(cherry picked from commit 7acc9816d2)
2016-03-21 11:59:35 +02:00
Pekka Enberg
08a8a4a1b4 main: Defer API server hooks until commitlog replay
Defer registering services to the API server until commitlog has been
replayed to ensure that nobody is able to trigger sstable operations via
'nodetool' before we are ready for them.
Message-Id: <1458116227-4671-1-git-send-email-penberg@scylladb.com>

(cherry picked from commit 972fc6e014)
2016-03-18 09:20:49 +02:00
Pekka Enberg
b7e9924299 main: Fix broadcast_address and listen_address validation errors
Fix the validation error message to look like this:

  Scylla version 666.development-20160316.49af399 starting ...
  WARN  2016-03-17 12:24:15,137 [shard 0] config - Option partitioner is not (yet) used.
  WARN  2016-03-17 12:24:15,138 [shard 0] init - NOFILE rlimit too low (recommended setting 200000, minimum setting 10000; you may run out of file descriptors.
  ERROR 2016-03-17 12:24:15,138 [shard 0] init - Bad configuration: invalid 'listen_address': eth0: boost::exception_detail::clone_impl<boost::exception_detail::error_info_injector<boost::system::system_error> > (Invalid argument)
  Exiting on unhandled exception of type 'bad_configuration_error': std::exception

Instead of:

  Exiting on unhandled exception of type 'boost::exception_detail::clone_impl<boost::exception_detail::error_info_injector<boost::system::system_error> >': Invalid argument

Fixes #1051.

Message-Id: <1458210329-4488-1-git-send-email-penberg@scylladb.com>
(cherry picked from commit 69dacf9063)
2016-03-18 09:00:23 +02:00
Takuya ASADA
19ed269cc7 dist: follow sysconfig setting when counting number of cpus on scylla_io_setup
When NR_CPU >= 8, we disabled cpu0 for AMI on scylla_sysconfig_setup.
But scylla_io_setup doesn't know that, try to assign NR_CPU queues, then scylla fails to start because queues > cpus.
So on this fix scylla_io_setup checks sysconfig settings, if '--smp <n>' specified on SCYLLA_ARGS, use n to limit queue size.
Also, when instance type is not supported pre-configured parameters, we need to passes --cpuset parameters to iotune. Otherwise iotune will run on a different set of CPUs, which may have different performance characteristics.

Fixes #996, #1043, #1046

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1458221762-10595-2-git-send-email-syuu@scylladb.com>
(cherry picked from commit 4cc589872d)
2016-03-18 08:58:00 +02:00
Takuya ASADA
a223450a56 dist: On scylla_sysconfig_setup, don't disable cpu0 on non-AMI environments
Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1458221762-10595-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 6f71173827)
2016-03-18 08:57:56 +02:00
Paweł Dziepak
8f4800b30e lsa: update _closed_occupancy after freeing all segments
_closed_occupancy will be used when a region is removed from its region
group, make sure that it is accurate.

Signed-off-by: Paweł Dziepak <pdziepak@scylladb.com>
(cherry picked from commit 338fd34770)
2016-03-18 08:11:31 +02:00
Pekka Enberg
7d13d115c6 dist: Fix '--developer-mode' parsing in scylla_io_setup
We need to support the following variations:

   --developer-mode true
   --developer-mode 1
   --developer-mode=true
   --developer-mode=1

Fixes #1026.
Message-Id: <1458203393-26658-1-git-send-email-penberg@scylladb.com>

(cherry picked from commit 0434bc3d33)
2016-03-17 11:00:14 +02:00
Glauber Costa
c9c52235a1 stream_session: print debug message for STREAM_MUTATION
For this verb(), we don't call get_session - and it doesn't look like we will.
We currently have no debug message for this one, which makes it harder to debug
the stream of messages. Print it.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
(cherry picked from commit a3ebf640c6)
2016-03-17 08:18:54 +02:00
Glauber Costa
52eeab089c stream_session: remove duplicated debug message
Whenever we call get_session, that will print a debug message about the arrival
of this new verb. Because we also print that explicitly in PREPARE_DONE, that
message gets duplicated.

That confuses poor developers who are, for a while, left wondering why is it that
the sender is sender the message twice.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
(cherry picked from commit 0ab4275893)
2016-03-17 08:18:49 +02:00
Glauber Costa
49af399a2e sstables: do not assume mutation_reader will be kept alive
Our sstables::mutation_reader has a specialization in which start and end
ranges are passed as futures. That is needed because we may have to read the
index file for those.

This works well under the assumption that every time a mutation_reader will be
created it will be used, since whoever is using it will surely keep the state
of the reader alive.

However, that assumption is no longer true - for a while. We use a reader
interface for reading everything from mutations and sstables to cache entries,
and when we create an sstable mutation_reader, that does not mean we'll use it.
In fact we won't, if the read can be serviced first by a higher level entity.

If that happens to be the case, the reader will be destructed. However, since
it may take more time than that for the start and end futures to resolve, by
the time they are resolved the state of the mutation reader will no longer be
valid.

The proposed fix for that is to only resolve the future inside
mutation_reader's read() function. If that function is called,  we can have a
reasonable expectation that the caller object is being kept alive.

A second way to fix this would be to force the mutation reader to be kept alive
by transforming it into a shared pointer and acquiring a reference to itself.
However, because the reader may turn out not to be used, the delayed read
actually has the advantage of not even reading anything from the disk if there
is no need for it.

Also, because sstables can be compacted, we can't guarantee that the sst object
itself , used in the resolution of start and end can be alive and that has the
same problem. If we delay the calling of those, we will also solve a similar
problem.  We assume here that the outter reader is keeping the SSTable object
alive.

I must note that I have not reproduced this problem. What goes above is the
result of the analysis we have made in #1036. That being the case, a thorough
review is appreciated.

Fixes #1036

Signed-off-by: Glauber Costa <glauber@scylladb.com>
Message-Id: <a7e4e722f76774d0b1f263d86c973061fb7fe2f2.1458135770.git.glauber@scylladb.com>
(cherry picked from commit 6a3872b355)
2016-03-16 19:41:06 +02:00
Nadav Har'El
d915370e3f Allow uncompression at end of file
Asking to read from byte 100 when a file has 50 bytes is an obvious error.
But what if we ask to read from byte 50? What if we ask to read 0 bytes at
byte 50? :-)

Before this patch, code which asked to read from the EOF position would
get an exception. After this patch, it would simply read nothing, without
error. This allows, for example, reading 0 bytes from position 0 on a file
with 0 bytes, which apparently happened in issue #1039...

A read which starts at a position higher than the EOF position still
generates an exception.

Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Message-Id: <1458137867-10998-1-git-send-email-nyh@scylladb.com>
(cherry picked from commit 02ba8ffbe8)
2016-03-16 19:40:59 +02:00
Nadav Har'El
a6d5e67923 Fix out-of-range exception when uncompressing 0 bytes
The uncompression code reads the compressed chunks containing the bytes
pos through pos + len - 1. This, however, is not correct when len==0,
and pos + len - 1 may even be -1, causing an out-of-range exception when
calling locate() to find the chunks containing this byte position.

So we need to treat len==0 specially, and in this case we don't read
anything, and don't need to locate() the chunks to read.

Refs #1039.

Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Message-Id: <1458135987-10200-1-git-send-email-nyh@scylladb.com>
(cherry picked from commit 73297c7872)
2016-03-16 15:55:12 +02:00
Takuya ASADA
f885750f90 dist: do not auto-start scylla-server job on Ubuntu package install time
Fixes #1017

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1458122424-22889-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit f1d18e9980)
2016-03-16 13:55:30 +02:00
Pekka Enberg
36f55e409d tests/gossip_test: Fix messaging service stop
This fixes gossip test shutdown similar to what commit 13ce48e ("tests:
Fix stop of storage_service in cql_test_env") did for CQL tests:

  gossip_test: /home/penberg/scylla/seastar/core/sharded.hh:439: Service& seastar::sharded<Service>::local() [with Service = net::messaging_service]: Assertion `local_is_initialized()' failed.
  Running 1 test case...

  [snip]

  unknown location(0): fatal error in "test_boot_shutdown": signal: SIGABRT (application abort requested)
  seastar/tests/test-utils.cc(32): last checkpoint
Message-Id: <1458126520-20025-1-git-send-email-penberg@scylladb.com>

(cherry picked from commit 2f519b9b34)
2016-03-16 13:15:39 +02:00
Asias He
c436fb5892 streaming: Handle cf is deleted after the deletion check
The cf can be deleted after the cf deletion check. Handle this case as
well.

Use "warn" level to log if cf is missing. Although we can handle the
case, but it is good to distingush where the receiver of streaming
applied all the stream mutations or not. We believe that the cf is
missing because it was dropped, but it could be missing because of a bug
or something we didn't anticipated here.

Related patch: "streaming: Handle cf is deleted when sending
STREAM_MUTATION_DONE"

Fixes simple_add_new_node_while_schema_changes_test failure.
Message-Id: <c4497e0500f50e0a3422efb37e73130765c88c57.1458090598.git.asias@scylladb.com>

(cherry picked from commit 2d50c71ca3)
2016-03-16 11:47:03 +02:00
Asias He
950bcd3e38 tests: Fix stop of storage_service in cql_test_env
In stop() of storage_service, it unregisters the verb handler. In the
test, we stop messaging_service before storage_service. Fix it by
deferring stop of messaging_service.
Message-Id: <c71f7b5b46e475efe2fac4c1588460406f890176.1458086329.git.asias@scylladb.com>

(cherry picked from commit 13ce48e775)
2016-03-16 11:36:36 +02:00
1172 changed files with 27667 additions and 119584 deletions

View File

@@ -1,9 +0,0 @@
*Installation details*
Scylla version (or git commit hash):
Cluster size:
OS (RHEL/CentOS/Ubuntu/AWS AMI):
*Hardware details (for performance issues)* Delete if unneeded
Platform (physical/VM/cloud instance type/docker):
Hardware: sockets= cores= hyperthreading= memory=
Disks: (SSD/HDD, count)

9
.gitignore vendored
View File

@@ -9,12 +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

View File

@@ -1,140 +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}
${SCYLLA_SOURCE_FILES})
# Note that since CLion does not undestand GCC6 concepts, we always disable them (even if users configure otherwise).
# CLion seems to have trouble with `-U` (macro undefinition), so we do it this way instead.
list(REMOVE_ITEM SEASTAR_CFLAGS "-DHAVE_GCC6_CONCEPTS")
# If the Seastar pkg-config information is available, append to the default flags.
#
# For ease of browsing the source code, we always pretend that DPDK is enabled.
target_compile_options(scylla PUBLIC
-std=gnu++14
-DHAVE_DPDK
-DHAVE_HWLOC
"${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}
build/release/gen)

View File

@@ -1,11 +0,0 @@
# Asking questions or requesting help
Use the [ScyllaDB user mailing list](https://groups.google.com/forum/#!forum/scylladb-users) for general questions and help.
# Reporting an issue
Please use the [Issue Tracker](https://github.com/scylladb/scylla/issues/) to report issues. Fill in as much information as you can in the issue template, especially for performance problems.
# Contributing Code to Scylla
To contribute code to Scylla, you need to sign the [Contributor License Agreement](http://www.scylladb.com/opensource/cla/) and send your changes as [patches](https://github.com/scylladb/scylla/wiki/Formatting-and-sending-patches) to the [mailing list](https://groups.google.com/forum/#!forum/scylladb-dev). We don't accept pull requests on GitHub.

View File

@@ -1,233 +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/).
### 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

@@ -1,19 +1,29 @@
# Scylla
#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 --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 yum 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
```
* 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
```
@@ -73,6 +83,14 @@ Run the image with:
docker run -p $(hostname -i):9042:9042 -i -t <image name>
```
## Contributing to Scylla
[Guidelines for contributing](CONTRIBUTING.md)
Do not send pull requests.
Send patches to the mailing list address scylladb-dev@googlegroups.com.
Be sure to subscribe.
In order for your patches to be merged, you must sign the Contributor's
License Agreement, protecting your rights and ours. See
http://www.scylladb.com/opensource/cla/.

View File

@@ -1,6 +1,6 @@
#!/bin/sh
VERSION=2.1.4
VERSION=1.0.4
if test -f version
then
@@ -10,12 +10,7 @@ else
DATE=$(date +%Y%m%d)
GIT_COMMIT=$(git log --pretty=format:'%h' -n 1)
SCYLLA_VERSION=$VERSION
# For custom package builds, replace "0" with "counter.your_name",
# where counter starts at 1 and increments for successive versions.
# This ensures that the package manager will select your custom
# package over the standard release.
SCYLLA_BUILD=0
SCYLLA_RELEASE=$SCYLLA_BUILD.$DATE.$GIT_COMMIT
SCYLLA_RELEASE=$DATE.$GIT_COMMIT
fi
echo "$SCYLLA_VERSION-$SCYLLA_RELEASE"

View File

@@ -397,36 +397,6 @@
}
]
},
{
"path": "/cache_service/metrics/key/hits_moving_avrage",
"operations": [
{
"method": "GET",
"summary": "Get key hits moving avrage",
"type": "#/utils/rate_moving_average",
"nickname": "get_key_hits_moving_avrage",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/cache_service/metrics/key/requests_moving_avrage",
"operations": [
{
"method": "GET",
"summary": "Get key requests moving avrage",
"type": "#/utils/rate_moving_average",
"nickname": "get_key_requests_moving_avrage",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/cache_service/metrics/key/size",
"operations": [
@@ -517,36 +487,6 @@
}
]
},
{
"path": "/cache_service/metrics/row/hits_moving_avrage",
"operations": [
{
"method": "GET",
"summary": "Get row hits moving avrage",
"type": "#/utils/rate_moving_average",
"nickname": "get_row_hits_moving_avrage",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/cache_service/metrics/row/requests_moving_avrage",
"operations": [
{
"method": "GET",
"summary": "Get row requests moving avrage",
"type": "#/utils/rate_moving_average",
"nickname": "get_row_requests_moving_avrage",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/cache_service/metrics/row/size",
"operations": [
@@ -637,36 +577,6 @@
}
]
},
{
"path": "/cache_service/metrics/counter/hits_moving_avrage",
"operations": [
{
"method": "GET",
"summary": "Get counter hits moving avrage",
"type": "#/utils/rate_moving_average",
"nickname": "get_counter_hits_moving_avrage",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/cache_service/metrics/counter/requests_moving_avrage",
"operations": [
{
"method": "GET",
"summary": "Get counter requests moving avrage",
"type": "#/utils/rate_moving_average",
"nickname": "get_counter_requests_moving_avrage",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/cache_service/metrics/counter/size",
"operations": [

View File

@@ -55,57 +55,6 @@
"paramType":"query"
}
]
},
{
"method":"POST",
"summary":"Start reporting on one or more collectd metric",
"type":"void",
"nickname":"enable_collectd",
"produces":[
"application/json"
],
"parameters":[
{
"name":"pluginid",
"description":"The plugin ID, describe the component the metric belongs to. Examples are cache, thrift, etc'. Regex are supported.The plugin ID, describe the component the metric belong to. Examples are: cache, thrift etc'. regex are supported",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
},
{
"name":"instance",
"description":"The plugin instance typically #CPU indicating per CPU metric. Regex are supported. Omit for all",
"required":false,
"allowMultiple":false,
"type":"string",
"paramType":"query"
},
{
"name":"type",
"description":"The plugin type, the type of the information. Examples are total_operations, bytes, total_operations, etc'. Regex are supported. Omit for all",
"required":false,
"allowMultiple":false,
"type":"string",
"paramType":"query"
},
{
"name":"type_instance",
"description":"The plugin type instance, the specific metric. Exampls are total_writes, total_size, zones, etc'. Regex are supported, Omit for all",
"required":false,
"allowMultiple":false,
"type":"string",
"paramType":"query"
},
{
"name":"enable",
"description":"set to true to enable all, anything else or omit to disable",
"required":false,
"allowMultiple":false,
"type":"boolean",
"paramType":"query"
}
]
}
]
},
@@ -114,10 +63,10 @@
"operations":[
{
"method":"GET",
"summary":"Get a list of all collectd metrics and their status",
"summary":"Get a collectd value",
"type":"array",
"items":{
"type":"collectd_metric_status"
"type":"type_instance_id"
},
"nickname":"get_collectd_items",
"produces":[
@@ -125,25 +74,6 @@
],
"parameters":[
]
},
{
"method":"POST",
"summary":"Enable or disable all collectd metrics",
"type":"void",
"nickname":"enable_all_collectd",
"produces":[
"application/json"
],
"parameters":[
{
"name":"enable",
"description":"set to true to enable all, anything else or omit to disable",
"required":false,
"allowMultiple":false,
"type":"boolean",
"paramType":"query"
}
]
}
]
}
@@ -183,20 +113,6 @@
}
}
}
},
"collectd_metric_status":{
"id":"collectd_metric_status",
"description":"Holds a collectd id and an enable flag",
"properties":{
"id":{
"description":"The metric ID",
"type":"type_instance_id"
},
"enable":{
"description":"Is the metric enabled",
"type":"boolean"
}
}
}
}
}

View File

@@ -78,19 +78,11 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
},
{
"name":"split_output",
"description":"true if the output of the major compaction should be split in several sstables",
"required":false,
"allowMultiple":false,
"type":"bool",
"paramType":"query"
}
]
}
@@ -110,7 +102,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -137,7 +129,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -161,7 +153,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -188,7 +180,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -212,7 +204,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -252,7 +244,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -279,7 +271,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -306,7 +298,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -325,7 +317,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -357,7 +349,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -389,7 +381,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -413,7 +405,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -440,7 +432,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -467,7 +459,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -499,7 +491,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -526,7 +518,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -553,7 +545,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -577,7 +569,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -601,7 +593,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -641,7 +633,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -681,7 +673,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -721,7 +713,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -761,7 +753,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -801,7 +793,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -841,7 +833,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -881,7 +873,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -924,7 +916,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -951,7 +943,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -978,7 +970,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1002,7 +994,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1042,7 +1034,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1066,7 +1058,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1102,14 +1094,14 @@
"method":"GET",
"summary":"Get read latency histogram",
"$ref": "#/utils/histogram",
"nickname":"get_read_latency_histogram_depricated",
"nickname":"get_read_latency_histogram",
"produces":[
"application/json"
],
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1129,49 +1121,6 @@
"items":{
"$ref": "#/utils/histogram"
},
"nickname":"get_all_read_latency_histogram_depricated",
"produces":[
"application/json"
],
"parameters":[
]
}
]
},
{
"path":"/column_family/metrics/read_latency/moving_average_histogram/{name}",
"operations":[
{
"method":"GET",
"summary":"Get read latency moving avrage histogram",
"$ref": "#/utils/rate_moving_average_and_histogram",
"nickname":"get_read_latency_histogram",
"produces":[
"application/json"
],
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
}
]
}
]
},
{
"path":"/column_family/metrics/read_latency/moving_average_histogram/",
"operations":[
{
"method":"GET",
"summary":"Get read latency moving avrage histogram from all column family",
"type":"array",
"items":{
"$ref": "#/utils/rate_moving_average_and_histogram"
},
"nickname":"get_all_read_latency_histogram",
"produces":[
"application/json"
@@ -1211,7 +1160,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1251,7 +1200,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1275,7 +1224,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1311,14 +1260,14 @@
"method":"GET",
"summary":"Get write latency histogram",
"$ref": "#/utils/histogram",
"nickname":"get_write_latency_histogram_depricated",
"nickname":"get_write_latency_histogram",
"produces":[
"application/json"
],
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1338,49 +1287,6 @@
"items":{
"$ref": "#/utils/histogram"
},
"nickname":"get_all_write_latency_histogram_depricated",
"produces":[
"application/json"
],
"parameters":[
]
}
]
},
{
"path":"/column_family/metrics/write_latency/moving_average_histogram/{name}",
"operations":[
{
"method":"GET",
"summary":"Get write latency moving average histogram",
"$ref": "#/utils/rate_moving_average_and_histogram",
"nickname":"get_write_latency_histogram",
"produces":[
"application/json"
],
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
}
]
}
]
},
{
"path":"/column_family/metrics/write_latency/moving_average_histogram/",
"operations":[
{
"method":"GET",
"summary":"Get write latency moving average histogram of all column family",
"type":"array",
"items":{
"$ref": "#/utils/rate_moving_average_and_histogram"
},
"nickname":"get_all_write_latency_histogram",
"produces":[
"application/json"
@@ -1420,7 +1326,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1460,7 +1366,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1500,7 +1406,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1540,7 +1446,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1580,7 +1486,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1620,7 +1526,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1660,7 +1566,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1700,7 +1606,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1740,7 +1646,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1780,7 +1686,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1820,7 +1726,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1860,7 +1766,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1900,7 +1806,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1940,7 +1846,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -1980,7 +1886,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2020,7 +1926,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2060,7 +1966,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2100,7 +2006,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2124,7 +2030,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2164,7 +2070,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2204,7 +2110,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2244,7 +2150,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2284,7 +2190,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2308,7 +2214,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2332,7 +2238,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2359,7 +2265,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2386,7 +2292,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2413,7 +2319,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2440,7 +2346,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2509,7 +2415,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2533,7 +2439,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2557,7 +2463,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2581,7 +2487,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2605,7 +2511,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2629,7 +2535,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2653,7 +2559,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2677,7 +2583,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2701,7 +2607,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2725,7 +2631,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2749,7 +2655,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -2773,7 +2679,7 @@
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"description":"The column family name in keysspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",

View File

@@ -21,8 +21,8 @@
"parameters":[
{
"name":"host",
"description":"The host name. If absent, the local server broadcast/listen address is used",
"required":false,
"description":"The host name",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"query"
@@ -45,8 +45,8 @@
"parameters":[
{
"name":"host",
"description":"The host name. If absent, the local server broadcast/listen address is used",
"required":false,
"description":"The host name",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"query"

View File

@@ -42,25 +42,6 @@
}
]
},
{
"path":"/failure_detector/endpoint_phi_values",
"operations":[
{
"method":"GET",
"summary":"Get end point phi values",
"type":"array",
"items":{
"type":"endpoint_phi_values"
},
"nickname":"get_endpoint_phi_values",
"produces":[
"application/json"
],
"parameters":[
]
}
]
},
{
"path":"/failure_detector/endpoints/",
"operations":[
@@ -221,20 +202,6 @@
"description": "The application state version"
}
}
},
"endpoint_phi_value": {
"id" : "endpoint_phi_value",
"description": "Holds phi value for a single end point",
"properties": {
"phi": {
"type": "double",
"description": "Phi value"
},
"endpoint": {
"type": "string",
"description": "end point address"
}
}
}
}
}

View File

@@ -716,36 +716,6 @@
}
]
},
{
"path": "/storage_proxy/metrics/read/timeouts_rates",
"operations": [
{
"method": "GET",
"summary": "Get read metrics rates",
"type": "#/utils/rate_moving_average",
"nickname": "get_read_metrics_timeouts_rates",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/storage_proxy/metrics/read/unavailables_rates",
"operations": [
{
"method": "GET",
"summary": "Get read metrics rates",
"type": "#/utils/rate_moving_average",
"nickname": "get_read_metrics_unavailables_rates",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/storage_proxy/metrics/read/histogram",
"operations": [
@@ -753,7 +723,7 @@
"method": "GET",
"summary": "Get read metrics",
"$ref": "#/utils/histogram",
"nickname": "get_read_metrics_latency_histogram_depricated",
"nickname": "get_read_metrics_latency_histogram",
"produces": [
"application/json"
],
@@ -768,36 +738,6 @@
"method": "GET",
"summary": "Get range metrics",
"$ref": "#/utils/histogram",
"nickname": "get_range_metrics_latency_histogram_depricated",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/storage_proxy/metrics/read/moving_average_histogram",
"operations": [
{
"method": "GET",
"summary": "Get read metrics",
"$ref": "#/utils/rate_moving_average_and_histogram",
"nickname": "get_read_metrics_latency_histogram",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/storage_proxy/metrics/range/moving_average_histogram",
"operations": [
{
"method": "GET",
"summary": "Get range metrics rate and histogram",
"$ref": "#/utils/rate_moving_average_and_histogram",
"nickname": "get_range_metrics_latency_histogram",
"produces": [
"application/json"
@@ -836,36 +776,6 @@
}
]
},
{
"path": "/storage_proxy/metrics/range/timeouts_rates",
"operations": [
{
"method": "GET",
"summary": "Get range metrics rates",
"type": "#/utils/rate_moving_average",
"nickname": "get_range_metrics_timeouts_rates",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/storage_proxy/metrics/range/unavailables_rates",
"operations": [
{
"method": "GET",
"summary": "Get range metrics rates",
"type": "#/utils/rate_moving_average",
"nickname": "get_range_metrics_unavailables_rates",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/storage_proxy/metrics/write/timeouts",
"operations": [
@@ -896,36 +806,6 @@
}
]
},
{
"path": "/storage_proxy/metrics/write/timeouts_rates",
"operations": [
{
"method": "GET",
"summary": "Get write metrics rates",
"type": "#/utils/rate_moving_average",
"nickname": "get_write_metrics_timeouts_rates",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/storage_proxy/metrics/write/unavailables_rates",
"operations": [
{
"method": "GET",
"summary": "Get write metrics rates",
"type": "#/utils/rate_moving_average",
"nickname": "get_write_metrics_unavailables_rates",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/storage_proxy/metrics/write/histogram",
"operations": [
@@ -933,21 +813,6 @@
"method": "GET",
"summary": "Get write metrics",
"$ref": "#/utils/histogram",
"nickname": "get_write_metrics_latency_histogram_depricated",
"produces": [
"application/json"
],
"parameters": []
}
]
},
{
"path": "/storage_proxy/metrics/write/moving_average_histogram",
"operations": [
{
"method": "GET",
"summary": "Get write metrics",
"$ref": "#/utils/rate_moving_average_and_histogram",
"nickname": "get_write_metrics_latency_histogram",
"produces": [
"application/json"

View File

@@ -177,22 +177,6 @@
}
]
},
{
"path":"/storage_service/scylla_release_version",
"operations":[
{
"method":"GET",
"summary":"Fetch a string representation of the Scylla version.",
"type":"string",
"nickname":"get_scylla_release_version",
"produces":[
"application/json"
],
"parameters":[
]
}
]
},
{
"path":"/storage_service/schema_version",
"operations":[
@@ -952,22 +936,6 @@
}
]
},
{
"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":[
@@ -1217,12 +1185,11 @@
],
"parameters":[
{
"name":"type",
"description":"Which keyspaces to return",
"name":"non_system",
"description":"When set to true limit to non system",
"required":false,
"allowMultiple":false,
"type":"string",
"enum": [ "all", "user", "non_local_strategy" ],
"type":"boolean",
"paramType":"query"
}
]
@@ -1753,57 +1720,6 @@
}
]
},
{
"path":"/storage_service/slow_query",
"operations":[
{
"method":"POST",
"summary":"Set slow query parameter",
"type":"void",
"nickname":"set_slow_query",
"produces":[
"application/json"
],
"parameters":[
{
"name":"enable",
"description":"set it to true to enable, anything else to disable",
"required":false,
"allowMultiple":false,
"type":"boolean",
"paramType":"query"
},
{
"name":"ttl",
"description":"TTL in seconds",
"required":false,
"allowMultiple":false,
"type":"long",
"paramType":"query"
},
{
"name":"threshold",
"description":"Slow query record threshold in microseconds",
"required":false,
"allowMultiple":false,
"type":"long",
"paramType":"query"
}
]
},
{
"method":"GET",
"summary":"Returns the slow query record configuration.",
"type":"slow_query_info",
"nickname":"get_slow_query_info",
"produces":[
"application/json"
],
"parameters":[
]
}
]
},
{
"path":"/storage_service/auto_compaction/{keyspace}",
"operations":[
@@ -2201,24 +2117,6 @@
}
}
},
"slow_query_info": {
"id":"slow_query_info",
"description":"Slow query triggering information",
"properties":{
"enable":{
"type":"boolean",
"description":"Is slow query logging enable or disable"
},
"ttl":{
"type":"long",
"description":"The slow query TTL in seconds"
},
"threshold":{
"type":"long",
"description":"The slow query logging threshold in microseconds. Queries that takes longer, will be logged"
}
}
},
"endpoint_detail":{
"id":"endpoint_detail",
"description":"Endpoint detail",

View File

@@ -65,41 +65,6 @@
"description":"The series of values to which the counts in `buckets` correspond"
}
}
},
"rate_moving_average": {
"id":"rate_moving_average",
"description":"A meter metric which measures mean throughput and one, five, and fifteen-minute exponentially-weighted moving average throughputs",
"properties":{
"rates": {
"type":"array",
"items":{
"type":"double"
},
"description":"One, five and fifteen mintues rates"
},
"mean_rate": {
"type":"double",
"description":"The mean rate from startup"
},
"count": {
"type":"long",
"description":"Total number of events from startup"
}
}
},
"rate_moving_average_and_histogram": {
"id":"rate_moving_average_and_histogram",
"description":"A timer metric which aggregates timing durations and provides duration statistics, plus throughput statistics",
"properties":{
"meter": {
"type":"rate_moving_average",
"description":"The metric rate moving average"
},
"hist": {
"type":"histogram",
"description":"The metric histogram"
}
}
}
}
}
}
}

View File

@@ -49,7 +49,7 @@ 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) {
@@ -61,10 +61,10 @@ future<> set_server_init(http_context& ctx) {
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);
rb->register_function(r, "system",
"The system related API");
set_system(ctx, r);
rb->set_api_doc(r);
});
}
@@ -83,10 +83,6 @@ future<> set_server_storage_service(http_context& ctx) {
return register_api(ctx, "storage_service", "The storage service API", set_storage_service);
}
future<> set_server_snitch(http_context& ctx) {
return register_api(ctx, "endpoint_snitch_info", "The endpoint snitch info API", set_endpoint_snitch);
}
future<> set_server_gossip(http_context& ctx) {
return register_api(ctx, "gossiper",
"The gossiper API", set_gossiper);
@@ -122,6 +118,10 @@ future<> set_server_gossip_settle(http_context& ctx) {
rb->register_function(r, "cache_service",
"The cache service API");
set_cache_service(ctx,r);
rb->register_function(r, "endpoint_snitch_info",
"The endpoint snitch info API");
set_endpoint_snitch(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 {
@@ -111,49 +110,61 @@ future<json::json_return_type> sum_stats(distributed<T>& d, V F::*f) {
});
}
inline double pow2(double a) {
return a * a;
}
// FIXME: Move to utils::ihistogram::operator+=()
inline utils::ihistogram add_histogram(utils::ihistogram res,
const utils::ihistogram& val) {
if (res.count == 0) {
return val;
}
if (val.count == 0) {
return std::move(res);
}
if (res.min > val.min) {
res.min = val.min;
}
if (res.max < val.max) {
res.max = val.max;
}
double ncount = res.count + val.count;
// To get an estimated sum we take the estimated mean
// and multiply it by the true count
res.sum = res.sum + val.mean * val.count;
double a = res.count/ncount;
double b = val.count/ncount;
double mean = a * res.mean + b * val.mean;
res.variance = (res.variance + pow2(res.mean - mean) )* a +
(val.variance + pow2(val.mean -mean))* b;
res.mean = mean;
res.count = res.count + val.count;
for (auto i : val.sample) {
res.sample.push_back(i);
}
return res;
}
inline
httpd::utils_json::histogram to_json(const utils::ihistogram& val) {
httpd::utils_json::histogram h;
h = val;
h.sum = val.estimated_sum();
return h;
}
inline
httpd::utils_json::rate_moving_average meter_to_json(const utils::rate_moving_average& val) {
httpd::utils_json::rate_moving_average m;
m = val;
return m;
}
inline
httpd::utils_json::rate_moving_average_and_histogram timer_to_json(const utils::rate_moving_average_and_histogram& val) {
httpd::utils_json::rate_moving_average_and_histogram h;
h.hist = to_json(val.hist);
h.meter = meter_to_json(val.rate);
return h;
}
template<class T, class F>
future<json::json_return_type> sum_histogram_stats(distributed<T>& d, utils::timed_rate_moving_average_and_histogram F::*f) {
future<json::json_return_type> sum_histogram_stats(distributed<T>& d, utils::ihistogram F::*f) {
return d.map_reduce0([f](const T& p) {return (p.get_stats().*f).hist;}, utils::ihistogram(),
std::plus<utils::ihistogram>()).then([](const utils::ihistogram& val) {
return d.map_reduce0([f](const T& p) {return p.get_stats().*f;}, utils::ihistogram(),
add_histogram).then([](const utils::ihistogram& val) {
return make_ready_future<json::json_return_type>(to_json(val));
});
}
template<class T, class F>
future<json::json_return_type> sum_timer_stats(distributed<T>& d, utils::timed_rate_moving_average_and_histogram F::*f) {
return d.map_reduce0([f](const T& p) {return (p.get_stats().*f).rate();}, utils::rate_moving_average_and_histogram(),
std::plus<utils::rate_moving_average_and_histogram>()).then([](const utils::rate_moving_average_and_histogram& val) {
return make_ready_future<json::json_return_type>(timer_to_json(val));
});
}
inline int64_t min_int64(int64_t a, int64_t b) {
return std::min(a,b);
}
@@ -167,36 +178,33 @@ inline int64_t max_int64(int64_t a, int64_t b) {
* It combine total and the sub set for the ratio and its
* to_json method return the ration sub/total
*/
template<typename T>
struct basic_ratio_holder : public json::jsonable {
T total = 0;
T sub = 0;
struct ratio_holder : public json::jsonable {
double total = 0;
double sub = 0;
virtual std::string to_json() const {
if (total == 0) {
return "0";
}
return std::to_string(sub/total);
}
basic_ratio_holder() = default;
basic_ratio_holder& add(T _total, T _sub) {
ratio_holder() = default;
ratio_holder& add(double _total, double _sub) {
total += _total;
sub += _sub;
return *this;
}
basic_ratio_holder(T _total, T _sub) {
ratio_holder(double _total, double _sub) {
total = _total;
sub = _sub;
}
basic_ratio_holder<T>& operator+=(const basic_ratio_holder<T>& a) {
ratio_holder& operator+=(const ratio_holder& a) {
return add(a.total, a.sub);
}
friend basic_ratio_holder<T> operator+(basic_ratio_holder a, const basic_ratio_holder<T>& b) {
friend ratio_holder operator+(ratio_holder a, const ratio_holder& b) {
return a += b;
}
};
typedef basic_ratio_holder<double> ratio_holder;
typedef basic_ratio_holder<int64_t> integral_ratio_holder;
class unimplemented_exception : public base_exception {
public:

View File

@@ -38,7 +38,6 @@ struct http_context {
};
future<> set_server_init(http_context& ctx);
future<> set_server_snitch(http_context& ctx);
future<> set_server_storage_service(http_context& ctx);
future<> set_server_gossip(http_context& ctx);
future<> set_server_load_sstable(http_context& ctx);

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*
@@ -177,20 +177,6 @@ void set_cache_service(http_context& ctx, routes& r) {
return make_ready_future<json::json_return_type>(0);
});
cs::get_key_hits_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
// TBD
// FIXME
// See above
return make_ready_future<json::json_return_type>(meter_to_json(utils::rate_moving_average()));
});
cs::get_key_requests_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
// TBD
// FIXME
// See above
return make_ready_future<json::json_return_type>(meter_to_json(utils::rate_moving_average()));
});
cs::get_key_size.set(r, [] (std::unique_ptr<request> req) {
// TBD
// FIXME
@@ -208,57 +194,41 @@ void set_cache_service(http_context& ctx, routes& r) {
});
cs::get_row_capacity.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, uint64_t(0), [](const column_family& cf) {
return map_reduce_cf(ctx, 0, [](const column_family& cf) {
return cf.get_row_cache().get_cache_tracker().region().occupancy().used_space();
}, std::plus<uint64_t>());
});
cs::get_row_hits.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, uint64_t(0), [](const column_family& cf) {
return cf.get_row_cache().stats().hits.count();
}, std::plus<uint64_t>());
return map_reduce_cf(ctx, 0, [](const column_family& cf) {
return cf.get_row_cache().stats().hits;
}, std::plus<int64_t>());
});
cs::get_row_requests.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, uint64_t(0), [](const column_family& cf) {
return cf.get_row_cache().stats().hits.count() + cf.get_row_cache().stats().misses.count();
}, std::plus<uint64_t>());
return map_reduce_cf(ctx, 0, [](const column_family& cf) {
return cf.get_row_cache().stats().hits + cf.get_row_cache().stats().misses;
}, std::plus<int64_t>());
});
cs::get_row_hit_rate.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, ratio_holder(), [](const column_family& cf) {
return ratio_holder(cf.get_row_cache().stats().hits.count() + cf.get_row_cache().stats().misses.count(),
cf.get_row_cache().stats().hits.count());
return ratio_holder(cf.get_row_cache().stats().hits + cf.get_row_cache().stats().misses,
cf.get_row_cache().stats().hits);
}, std::plus<ratio_holder>());
});
cs::get_row_hits_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const column_family& cf) {
return cf.get_row_cache().stats().hits.rate();
}, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
return make_ready_future<json::json_return_type>(meter_to_json(m));
});
});
cs::get_row_requests_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const column_family& cf) {
return cf.get_row_cache().stats().hits.rate() + cf.get_row_cache().stats().misses.rate();
}, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
return make_ready_future<json::json_return_type>(meter_to_json(m));
});
});
cs::get_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
// In origin row size is the weighted size.
// We currently do not support weights, so we use num entries instead
return 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>());
});
@@ -294,20 +264,6 @@ void set_cache_service(http_context& ctx, routes& r) {
return make_ready_future<json::json_return_type>(0);
});
cs::get_counter_hits_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
// TBD
// FIXME
// See above
return make_ready_future<json::json_return_type>(meter_to_json(utils::rate_moving_average()));
});
cs::get_counter_requests_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
// TBD
// FIXME
// See above
return make_ready_future<json::json_return_type>(meter_to_json(utils::rate_moving_average()));
});
cs::get_counter_size.set(r, [] (std::unique_ptr<request> req) {
// TBD
// FIXME

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*
@@ -25,14 +25,10 @@
#include "core/scollectd_api.hh"
#include "endian.h"
#include <boost/range/irange.hpp>
#include <regex>
namespace api {
using namespace scollectd;
using namespace httpd;
using namespace json;
namespace cd = httpd::collectd_json;
static auto transformer(const std::vector<collectd_value>& values) {
@@ -40,27 +36,19 @@ static auto transformer(const std::vector<collectd_value>& values) {
for (auto v: values) {
switch (v._type) {
case scollectd::data_type::GAUGE:
collected_value.values.push(v.d());
collected_value.values.push(v.u._d);
break;
case scollectd::data_type::DERIVE:
collected_value.values.push(v.i());
collected_value.values.push(v.u._i);
break;
default:
collected_value.values.push(v.ui());
collected_value.values.push(v.u._ui);
break;
}
}
return collected_value;
}
static const char* str_to_regex(const sstring& v) {
if (v != "") {
return v.c_str();
}
return ".*";
}
void set_collectd(http_context& ctx, routes& r) {
cd::get_collectd.set(r, [&ctx](std::unique_ptr<request> req) {
@@ -84,7 +72,7 @@ void set_collectd(http_context& ctx, routes& r) {
});
cd::get_collectd_items.set(r, [](const_req req) {
std::vector<cd::collectd_metric_status> res;
std::vector<cd::type_instance_id> res;
auto ids = scollectd::get_collectd_ids();
for (auto i: ids) {
cd::type_instance_id id;
@@ -92,44 +80,10 @@ void set_collectd(http_context& ctx, routes& r) {
id.plugin_instance = i.plugin_instance();
id.type = i.type();
id.type_instance = i.type_instance();
cd::collectd_metric_status it;
it.id = id;
it.enable = scollectd::is_enabled(i);
res.push_back(it);
res.push_back(id);
}
return res;
});
cd::enable_collectd.set(r, [](std::unique_ptr<request> req) -> future<json::json_return_type> {
std::regex plugin(req->param["pluginid"].c_str());
std::regex instance(str_to_regex(req->get_query_param("instance")));
std::regex type(str_to_regex(req->get_query_param("type")));
std::regex type_instance(str_to_regex(req->get_query_param("type_instance")));
bool enable = strcasecmp(req->get_query_param("enable").c_str(), "true") == 0;
return smp::invoke_on_all([enable, plugin, instance, type, type_instance]() {
for (auto id: scollectd::get_collectd_ids()) {
if (std::regex_match(std::string(id.plugin()), plugin) &&
std::regex_match(std::string(id.plugin_instance()), instance) &&
std::regex_match(std::string(id.type()), type) &&
std::regex_match(std::string(id.type_instance()), type_instance)) {
scollectd::enable(id, enable);
}
}
}).then([] {
return json::json_return_type(json_void());
});
});
cd::enable_all_collectd.set(r, [](std::unique_ptr<request> req) -> future<json::json_return_type> {
bool enable = strcasecmp(req->get_query_param("enable").c_str(), "true") == 0;
return smp::invoke_on_all([enable] {
for (auto id: scollectd::get_collectd_ids()) {
scollectd::enable(id, enable);
}
}).then([] {
return json::json_return_type(json_void());
});
});
}
}

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*
@@ -24,7 +24,7 @@
#include <vector>
#include "http/exception.hh"
#include "sstables/sstables.hh"
#include "utils/estimated_histogram.hh"
#include "sstables/estimated_histogram.hh"
#include <algorithm>
namespace api {
@@ -40,7 +40,7 @@ const utils::UUID& get_uuid(const sstring& name, const database& db) {
if (pos == sstring::npos) {
pos = name.find(":");
if (pos == sstring::npos) {
throw bad_param_exception("Column family name should be in keyspace:column_family format");
throw bad_param_exception("Column family name should be in keyspace::column_family format");
}
end = pos + 1;
} else {
@@ -77,14 +77,14 @@ future<json::json_return_type> get_cf_stats(http_context& ctx,
}
static future<json::json_return_type> get_cf_stats_count(http_context& ctx, const sstring& name,
utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
utils::ihistogram column_family::stats::*f) {
return map_reduce_cf(ctx, name, int64_t(0), [f](const column_family& cf) {
return (cf.get_stats().*f).hist.count;
return (cf.get_stats().*f).count;
}, std::plus<int64_t>());
}
static future<json::json_return_type> get_cf_stats_sum(http_context& ctx, const sstring& name,
utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
utils::ihistogram column_family::stats::*f) {
auto uuid = get_uuid(name, ctx.db.local());
return ctx.db.map_reduce0([uuid, f](database& db) {
// Histograms information is sample of the actual load
@@ -92,7 +92,7 @@ static future<json::json_return_type> get_cf_stats_sum(http_context& ctx, const
// with count. The information is gather in nano second,
// but reported in micro
column_family& cf = db.find_column_family(uuid);
return ((cf.get_stats().*f).hist.count/1000.0) * (cf.get_stats().*f).hist.mean;
return ((cf.get_stats().*f).count/1000.0) * (cf.get_stats().*f).mean;
}, 0.0, std::plus<double>()).then([](double res) {
return make_ready_future<json::json_return_type>((int64_t)res);
});
@@ -100,29 +100,28 @@ static future<json::json_return_type> get_cf_stats_sum(http_context& ctx, const
static future<json::json_return_type> get_cf_stats_count(http_context& ctx,
utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
utils::ihistogram column_family::stats::*f) {
return map_reduce_cf(ctx, int64_t(0), [f](const column_family& cf) {
return (cf.get_stats().*f).hist.count;
return (cf.get_stats().*f).count;
}, std::plus<int64_t>());
}
static future<json::json_return_type> get_cf_histogram(http_context& ctx, const sstring& name,
utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
utils::ihistogram column_family::stats::*f) {
utils::UUID uuid = get_uuid(name, ctx.db.local());
return ctx.db.map_reduce0([f, uuid](const database& p) {
return (p.find_column_family(uuid).get_stats().*f).hist;},
return ctx.db.map_reduce0([f, uuid](const database& p) {return p.find_column_family(uuid).get_stats().*f;},
utils::ihistogram(),
std::plus<utils::ihistogram>())
add_histogram)
.then([](const utils::ihistogram& val) {
return make_ready_future<json::json_return_type>(to_json(val));
});
}
static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils::ihistogram column_family::stats::*f) {
std::function<utils::ihistogram(const database&)> fun = [f] (const database& db) {
utils::ihistogram res;
for (auto i : db.get_column_families()) {
res += (i.second->get_stats().*f).hist;
res = add_histogram(res, i.second->get_stats().*f);
}
return res;
};
@@ -133,33 +132,6 @@ static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils:
});
}
static future<json::json_return_type> get_cf_rate_and_histogram(http_context& ctx, const sstring& name,
utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
utils::UUID uuid = get_uuid(name, ctx.db.local());
return ctx.db.map_reduce0([f, uuid](const database& p) {
return (p.find_column_family(uuid).get_stats().*f).rate();},
utils::rate_moving_average_and_histogram(),
std::plus<utils::rate_moving_average_and_histogram>())
.then([](const utils::rate_moving_average_and_histogram& val) {
return make_ready_future<json::json_return_type>(timer_to_json(val));
});
}
static future<json::json_return_type> get_cf_rate_and_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram column_family::stats::*f) {
std::function<utils::rate_moving_average_and_histogram(const database&)> fun = [f] (const database& db) {
utils::rate_moving_average_and_histogram res;
for (auto i : db.get_column_families()) {
res += (i.second->get_stats().*f).rate();
}
return res;
};
return ctx.db.map(fun).then([](const std::vector<utils::rate_moving_average_and_histogram> &res) {
std::vector<httpd::utils_json::rate_moving_average_and_histogram> r;
boost::copy(res | boost::adaptors::transformed(timer_to_json), std::back_inserter(r));
return make_ready_future<json::json_return_type>(r);
});
}
static future<json::json_return_type> get_cf_unleveled_sstables(http_context& ctx, const sstring& name) {
return map_reduce_cf(ctx, name, int64_t(0), [](const column_family& cf) {
return cf.get_unleveled_sstables();
@@ -169,7 +141,7 @@ static future<json::json_return_type> get_cf_unleveled_sstables(http_context& ct
static int64_t min_row_size(column_family& cf) {
int64_t res = INT64_MAX;
for (auto i: *cf.get_sstables() ) {
res = std::min(res, i->get_stats_metadata().estimated_row_size.min());
res = std::min(res, i.second->get_stats_metadata().estimated_row_size.min());
}
return (res == INT64_MAX) ? 0 : res;
}
@@ -177,113 +149,30 @@ static int64_t min_row_size(column_family& cf) {
static int64_t max_row_size(column_family& cf) {
int64_t res = 0;
for (auto i: *cf.get_sstables() ) {
res = std::max(i->get_stats_metadata().estimated_row_size.max(), res);
res = std::max(i.second->get_stats_metadata().estimated_row_size.max(), res);
}
return res;
}
static integral_ratio_holder mean_row_size(column_family& cf) {
integral_ratio_holder 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 ratio_holder mean_row_size(column_family& cf) {
ratio_holder res;
for (auto i: *cf.get_sstables() ) {
auto c = i->get_stats_metadata().estimated_row_size.count();
res.sub += i->get_stats_metadata().estimated_row_size.mean() * c;
auto c = i.second->get_stats_metadata().estimated_row_size.count();
res.sub += i.second->get_stats_metadata().estimated_row_size.mean() * c;
res.total += c;
}
return res;
}
static std::unordered_map<sstring, uint64_t> merge_maps(std::unordered_map<sstring, uint64_t> a,
const std::unordered_map<sstring, uint64_t>& b) {
a.insert(b.begin(), b.end());
return a;
}
static json::json_return_type sum_map(const std::unordered_map<sstring, uint64_t>& val) {
uint64_t res = 0;
for (auto i : val) {
res += i.second;
}
return res;
}
static future<json::json_return_type> sum_sstable(http_context& ctx, const sstring name, bool total) {
auto uuid = get_uuid(name, ctx.db.local());
return ctx.db.map_reduce0([uuid, total](database& db) {
std::unordered_map<sstring, uint64_t> m;
auto sstables = (total) ? db.find_column_family(uuid).get_sstables_including_compacted_undeleted() :
db.find_column_family(uuid).get_sstables();
for (auto t : *sstables) {
m[t->get_filename()] = t->bytes_on_disk();
}
return m;
}, std::unordered_map<sstring, uint64_t>(), merge_maps).
then([](const std::unordered_map<sstring, uint64_t>& val) {
return sum_map(val);
});
}
static future<json::json_return_type> sum_sstable(http_context& ctx, bool total) {
return map_reduce_cf_raw(ctx, std::unordered_map<sstring, uint64_t>(), [total](column_family& cf) {
std::unordered_map<sstring, uint64_t> m;
auto sstables = (total) ? cf.get_sstables_including_compacted_undeleted() :
cf.get_sstables();
for (auto t : *sstables) {
m[t->get_filename()] = t->bytes_on_disk();
}
return m;
},merge_maps).then([](const std::unordered_map<sstring, uint64_t>& val) {
return sum_map(val);
});
}
template <typename T>
class sum_ratio {
uint64_t _n = 0;
T _total = 0;
public:
future<> operator()(T value) {
if (value > 0) {
_total += value;
_n++;
}
return make_ready_future<>();
}
// Returns average value of all registered ratios.
T get() && {
return _n ? (_total / _n) : T(0);
}
};
static double get_compression_ratio(column_family& cf) {
sum_ratio<double> result;
for (auto i : *cf.get_sstables()) {
auto compression_ratio = i->get_compression_ratio();
if (compression_ratio != sstables::metadata_collector::NO_COMPRESSION_RATIO) {
result(compression_ratio);
}
}
return std::move(result).get();
}
static std::vector<uint64_t> concat_sstable_count_per_level(std::vector<uint64_t> a, std::vector<uint64_t>&& b) {
a.resize(std::max(a.size(), b.size()), 0UL);
for (auto i = 0U; i < b.size(); i++) {
a[i] += b[i];
}
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;
@@ -404,21 +293,21 @@ void set_column_family(http_context& ctx, routes& r) {
});
cf::get_estimated_row_size_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
utils::estimated_histogram res(0);
return map_reduce_cf(ctx, req->param["name"], sstables::estimated_histogram(0), [](column_family& cf) {
sstables::estimated_histogram res(0);
for (auto i: *cf.get_sstables() ) {
res.merge(i->get_stats_metadata().estimated_row_size);
res.merge(i.second->get_stats_metadata().estimated_row_size);
}
return res;
},
utils::estimated_histogram_merge, utils_json::estimated_histogram());
sstables::merge, utils_json::estimated_histogram());
});
cf::get_estimated_row_count.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
uint64_t res = 0;
for (auto i: *cf.get_sstables() ) {
res += i->get_stats_metadata().estimated_row_size.count();
res += i.second->get_stats_metadata().estimated_row_size.count();
}
return res;
},
@@ -426,14 +315,14 @@ void set_column_family(http_context& ctx, routes& r) {
});
cf::get_estimated_column_count_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
utils::estimated_histogram res(0);
return map_reduce_cf(ctx, req->param["name"], sstables::estimated_histogram(0), [](column_family& cf) {
sstables::estimated_histogram res(0);
for (auto i: *cf.get_sstables() ) {
res.merge(i->get_stats_metadata().estimated_column_count);
res.merge(i.second->get_stats_metadata().estimated_column_count);
}
return res;
},
utils::estimated_histogram_merge, utils_json::estimated_histogram());
sstables::merge, utils_json::estimated_histogram());
});
cf::get_all_compression_ratio.set(r, [] (std::unique_ptr<request> req) {
@@ -466,12 +355,8 @@ void set_column_family(http_context& ctx, routes& r) {
return get_cf_stats_count(ctx, &column_family::stats::writes);
});
cf::get_read_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_histogram(ctx, req->param["name"], &column_family::stats::reads);
});
cf::get_read_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_rate_and_histogram(ctx, req->param["name"], &column_family::stats::reads);
return get_cf_histogram(ctx, req->param["name"], &column_family::stats::reads);
});
cf::get_read_latency.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -482,40 +367,24 @@ void set_column_family(http_context& ctx, routes& r) {
return get_cf_stats_sum(ctx, req->param["name"] ,&column_family::stats::writes);
});
cf::get_all_read_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_histogram(ctx, &column_family::stats::writes);
});
cf::get_all_read_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_rate_and_histogram(ctx, &column_family::stats::writes);
});
cf::get_write_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_histogram(ctx, req->param["name"], &column_family::stats::writes);
return get_cf_histogram(ctx, &column_family::stats::writes);
});
cf::get_write_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_rate_and_histogram(ctx, req->param["name"], &column_family::stats::writes);
});
cf::get_all_write_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_histogram(ctx, &column_family::stats::writes);
return get_cf_histogram(ctx, req->param["name"], &column_family::stats::writes);
});
cf::get_all_write_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
return get_cf_rate_and_histogram(ctx, &column_family::stats::writes);
return get_cf_histogram(ctx, &column_family::stats::writes);
});
cf::get_pending_compactions.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
return cf.get_compaction_strategy().estimated_pending_compactions(cf);
}, std::plus<int64_t>());
return get_cf_stats(ctx, req->param["name"], &column_family::stats::pending_compactions);
});
cf::get_all_pending_compactions.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, int64_t(0), [](column_family& cf) {
return cf.get_compaction_strategy().estimated_pending_compactions(cf);
}, std::plus<int64_t>());
return get_cf_stats(ctx, &column_family::stats::pending_compactions);
});
cf::get_live_ss_table_count.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -531,19 +400,19 @@ void set_column_family(http_context& ctx, routes& r) {
});
cf::get_live_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return sum_sstable(ctx, req->param["name"], false);
return get_cf_stats(ctx, req->param["name"], &column_family::stats::live_disk_space_used);
});
cf::get_all_live_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return sum_sstable(ctx, false);
return get_cf_stats(ctx, &column_family::stats::live_disk_space_used);
});
cf::get_total_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return sum_sstable(ctx, req->param["name"], true);
return get_cf_stats(ctx, req->param["name"], &column_family::stats::total_disk_space_used);
});
cf::get_all_total_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return sum_sstable(ctx, true);
return get_cf_stats(ctx, &column_family::stats::total_disk_space_used);
});
cf::get_min_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -563,19 +432,17 @@ void set_column_family(http_context& ctx, routes& r) {
});
cf::get_mean_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
// Cassandra 3.x mean values are truncated as integrals.
return map_reduce_cf(ctx, req->param["name"], integral_ratio_holder(), mean_row_size, std::plus<integral_ratio_holder>());
return map_reduce_cf(ctx, req->param["name"], ratio_holder(), mean_row_size, std::plus<ratio_holder>());
});
cf::get_all_mean_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
// Cassandra 3.x mean values are truncated as integrals.
return map_reduce_cf(ctx, integral_ratio_holder(), mean_row_size, std::plus<integral_ratio_holder>());
return map_reduce_cf(ctx, ratio_holder(), mean_row_size, std::plus<ratio_holder>());
});
cf::get_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return s + sst->filter_get_false_positive();
return s + sst.second->filter_get_false_positive();
});
}, std::plus<uint64_t>());
});
@@ -583,7 +450,7 @@ void set_column_family(http_context& ctx, routes& r) {
cf::get_all_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return s + sst->filter_get_false_positive();
return s + sst.second->filter_get_false_positive();
});
}, std::plus<uint64_t>());
});
@@ -591,7 +458,7 @@ void set_column_family(http_context& ctx, routes& r) {
cf::get_recent_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return s + sst->filter_get_recent_false_positive();
return s + sst.second->filter_get_recent_false_positive();
});
}, std::plus<uint64_t>());
});
@@ -599,39 +466,51 @@ void set_column_family(http_context& ctx, routes& r) {
cf::get_all_recent_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return s + sst->filter_get_recent_false_positive();
return s + sst.second->filter_get_recent_false_positive();
});
}, std::plus<uint64_t>());
});
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.second->filter_get_false_positive();
return update_ratio(s, f, f + sst.second->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.second->filter_get_false_positive();
return update_ratio(s, f, f + sst.second->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.second->filter_get_recent_false_positive();
return update_ratio(s, f, f + sst.second->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.second->filter_get_recent_false_positive();
return update_ratio(s, f, f + sst.second->filter_get_recent_true_positive());
});
}, std::plus<double>());
});
cf::get_bloom_filter_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return sst->filter_size();
return sst.second->filter_size();
});
}, std::plus<uint64_t>());
});
@@ -639,7 +518,7 @@ void set_column_family(http_context& ctx, routes& r) {
cf::get_all_bloom_filter_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return sst->filter_size();
return sst.second->filter_size();
});
}, std::plus<uint64_t>());
});
@@ -647,7 +526,7 @@ void set_column_family(http_context& ctx, routes& r) {
cf::get_bloom_filter_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return sst->filter_memory_size();
return sst.second->filter_memory_size();
});
}, std::plus<uint64_t>());
});
@@ -655,7 +534,7 @@ void set_column_family(http_context& ctx, routes& r) {
cf::get_all_bloom_filter_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return sst->filter_memory_size();
return sst.second->filter_memory_size();
});
}, std::plus<uint64_t>());
});
@@ -663,7 +542,7 @@ void set_column_family(http_context& ctx, routes& r) {
cf::get_index_summary_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return sst->get_summary().memory_footprint();
return sst.second->get_summary().memory_footprint();
});
}, std::plus<uint64_t>());
});
@@ -671,7 +550,7 @@ void set_column_family(http_context& ctx, routes& r) {
cf::get_all_index_summary_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
return sst->get_summary().memory_footprint();
return sst.second->get_summary().memory_footprint();
});
}, std::plus<uint64_t>());
});
@@ -744,35 +623,27 @@ void set_column_family(http_context& ctx, routes& r) {
});
cf::get_row_cache_hit.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf_raw(ctx, req->param["name"], utils::rate_moving_average(), [](const column_family& cf) {
return cf.get_row_cache().stats().hits.rate();
}, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
return make_ready_future<json::json_return_type>(meter_to_json(m));
});
return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](const column_family& cf) {
return cf.get_row_cache().stats().hits;
}, std::plus<int64_t>());
});
cf::get_all_row_cache_hit.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const column_family& cf) {
return cf.get_row_cache().stats().hits.rate();
}, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
return make_ready_future<json::json_return_type>(meter_to_json(m));
});
return map_reduce_cf(ctx, int64_t(0), [](const column_family& cf) {
return cf.get_row_cache().stats().hits;
}, std::plus<int64_t>());
});
cf::get_row_cache_miss.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf_raw(ctx, req->param["name"], utils::rate_moving_average(), [](const column_family& cf) {
return cf.get_row_cache().stats().misses.rate();
}, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
return make_ready_future<json::json_return_type>(meter_to_json(m));
});
return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](const column_family& cf) {
return cf.get_row_cache().stats().misses;
}, std::plus<int64_t>());
});
cf::get_all_row_cache_miss.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const column_family& cf) {
return cf.get_row_cache().stats().misses.rate();
}, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
return make_ready_future<json::json_return_type>(meter_to_json(m));
});
return map_reduce_cf(ctx, int64_t(0), [](const column_family& cf) {
return cf.get_row_cache().stats().misses;
}, std::plus<int64_t>());
});
@@ -798,10 +669,10 @@ void set_column_family(http_context& ctx, routes& r) {
});
cf::get_sstables_per_read_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
return map_reduce_cf(ctx, req->param["name"], sstables::estimated_histogram(0), [](column_family& cf) {
return cf.get_stats().estimated_sstable_per_read;
},
utils::estimated_histogram_merge, utils_json::estimated_histogram());
sstables::merge, utils_json::estimated_histogram());
});
cf::get_tombstone_scanned_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -848,29 +719,25 @@ void set_column_family(http_context& ctx, routes& r) {
return std::vector<sstring>();
});
cf::get_compression_ratio.set(r, [&ctx](std::unique_ptr<request> req) {
auto uuid = get_uuid(req->param["name"], ctx.db.local());
return ctx.db.map_reduce(sum_ratio<double>(), [uuid](database& db) {
column_family& cf = db.find_column_family(uuid);
return make_ready_future<double>(get_compression_ratio(cf));
}).then([] (const double& result) {
return make_ready_future<json::json_return_type>(result);
});
cf::get_compression_ratio.set(r, [](const_req) {
// FIXME
// Currently there are no compression information
// so we return 0 as the ratio
return 0;
});
cf::get_read_latency_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
return map_reduce_cf(ctx, req->param["name"], sstables::estimated_histogram(0), [](column_family& cf) {
return cf.get_stats().estimated_read;
},
utils::estimated_histogram_merge, utils_json::estimated_histogram());
sstables::merge, utils_json::estimated_histogram());
});
cf::get_write_latency_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
return map_reduce_cf(ctx, req->param["name"], sstables::estimated_histogram(0), [](column_family& cf) {
return cf.get_stats().estimated_write;
},
utils::estimated_histogram_merge, utils_json::estimated_histogram());
sstables::merge, utils_json::estimated_histogram());
});
cf::set_compaction_strategy_class.set(r, [&ctx](std::unique_ptr<request> req) {
@@ -899,11 +766,12 @@ void set_column_family(http_context& ctx, routes& r) {
});
cf::get_sstable_count_per_level.set(r, [&ctx](std::unique_ptr<request> req) {
return map_reduce_cf_raw(ctx, req->param["name"], std::vector<uint64_t>(), [](const column_family& cf) {
return cf.sstable_count_per_level();
}, concat_sstable_count_per_level).then([](const std::vector<uint64_t>& res) {
return make_ready_future<json::json_return_type>(res);
});
// TBD
// FIXME
// This is a workaround, until there will be an API to return the count
// per level, we return an empty array
vector<uint64_t> res;
return make_ready_future<json::json_return_type>(res);
});
}
}

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*
@@ -34,44 +34,31 @@ future<> foreach_column_family(http_context& ctx, const sstring& name, std::func
template<class Mapper, class I, class Reducer>
future<I> map_reduce_cf_raw(http_context& ctx, const sstring& name, I init,
future<json::json_return_type> map_reduce_cf(http_context& ctx, const sstring& name, I init,
Mapper mapper, Reducer reducer) {
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>
future<json::json_return_type> map_reduce_cf(http_context& ctx, const sstring& name, I init,
Mapper mapper, Reducer reducer) {
return map_reduce_cf_raw(ctx, name, init, mapper, reducer).then([](const I& res) {
}, init, reducer).then([](const I& res) {
return make_ready_future<json::json_return_type>(res);
});
}
template<class Mapper, class I, class Reducer, class Result>
future<I> map_reduce_cf_raw(http_context& ctx, const sstring& name, I init,
future<json::json_return_type> map_reduce_cf(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, result).then([result](const I& res) mutable {
}, init, reducer).then([result](const I& res) mutable {
result = res;
return make_ready_future<json::json_return_type>(result);
});
}
template<class Mapper, class I, class Reducer>
future<I> map_reduce_cf_raw(http_context& ctx, I init,
future<json::json_return_type> map_reduce_cf(http_context& ctx, I init,
Mapper mapper, Reducer reducer) {
return ctx.db.map_reduce0([mapper, init, reducer](database& db) {
auto res = init;
@@ -79,18 +66,10 @@ future<I> map_reduce_cf_raw(http_context& ctx, I init,
res = reducer(res, mapper(*i.second.get()));
}
return res;
}, init, reducer);
}
template<class Mapper, class I, class Reducer>
future<json::json_return_type> map_reduce_cf(http_context& ctx, I init,
Mapper mapper, Reducer reducer) {
return map_reduce_cf_raw(ctx, init, mapper, reducer).then([](const I& res) {
}, init, reducer).then([](const I& res) {
return make_ready_future<json::json_return_type>(res);
});
}
future<json::json_return_type> get_cf_stats(http_context& ctx, const sstring& name,
int64_t column_family::stats::*f);

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*
@@ -20,13 +20,12 @@
*/
#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;
@@ -79,9 +78,7 @@ void set_compaction_manager(http_context& ctx, routes& r) {
});
cm::get_pending_tasks.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, int64_t(0), [](column_family& cf) {
return cf.get_compaction_strategy().estimated_pending_compactions(cf);
}, std::plus<int64_t>());
return get_cm_stats(ctx, &compaction_manager::stats::pending_tasks);
});
cm::get_completed_tasks.set(r, [&ctx] (std::unique_ptr<request> req) {

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*
@@ -22,22 +22,16 @@
#include "locator/snitch_base.hh"
#include "endpoint_snitch.hh"
#include "api/api-doc/endpoint_snitch_info.json.hh"
#include "utils/fb_utilities.hh"
namespace api {
void set_endpoint_snitch(http_context& ctx, routes& r) {
static auto host_or_broadcast = [](const_req req) {
auto host = req.get_query_param("host");
return host.empty() ? gms::inet_address(utils::fb_utilities::get_broadcast_address()) : gms::inet_address(host);
};
httpd::endpoint_snitch_info_json::get_datacenter.set(r, [](const_req req) {
return locator::i_endpoint_snitch::get_local_snitch_ptr()->get_datacenter(host_or_broadcast(req));
httpd::endpoint_snitch_info_json::get_datacenter.set(r, [] (const_req req) {
return locator::i_endpoint_snitch::get_local_snitch_ptr()->get_datacenter(req.get_query_param("host"));
});
httpd::endpoint_snitch_info_json::get_rack.set(r, [](const_req req) {
return locator::i_endpoint_snitch::get_local_snitch_ptr()->get_rack(host_or_broadcast(req));
httpd::endpoint_snitch_info_json::get_rack.set(r, [] (const_req req) {
return locator::i_endpoint_snitch::get_local_snitch_ptr()->get_rack(req.get_query_param("host"));
});
httpd::endpoint_snitch_info_json::get_snitch_name.set(r, [] (const_req req) {

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*
@@ -88,20 +88,6 @@ void set_failure_detector(http_context& ctx, routes& r) {
return make_ready_future<json::json_return_type>(state);
});
});
fd::get_endpoint_phi_values.set(r, [](std::unique_ptr<request> req) {
return gms::get_arrival_samples().then([](std::map<gms::inet_address, gms::arrival_window> map) {
std::vector<fd::endpoint_phi_value> res;
auto now = gms::arrival_window::clk::now();
for (auto& p : map) {
fd::endpoint_phi_value val;
val.endpoint = p.first.to_sstring();
val.phi = p.second.phi(now);
res.emplace_back(std::move(val));
}
return make_ready_future<json::json_return_type>(res);
});
});
}
}

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*
@@ -24,6 +24,7 @@
namespace api {
using namespace scollectd;
using namespace json;
namespace hh = httpd::hinted_handoff_json;

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*
@@ -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

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*
@@ -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

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*
@@ -33,36 +33,17 @@ namespace sp = httpd::storage_proxy_json;
using proxy = service::storage_proxy;
using namespace json;
static future<utils::rate_moving_average> sum_timed_rate(distributed<proxy>& d, utils::timed_rate_moving_average proxy::stats::*f) {
return d.map_reduce0([f](const proxy& p) {return (p.get_stats().*f).rate();}, utils::rate_moving_average(),
std::plus<utils::rate_moving_average>());
}
static future<json::json_return_type> sum_timed_rate_as_obj(distributed<proxy>& d, utils::timed_rate_moving_average proxy::stats::*f) {
return sum_timed_rate(d, f).then([](const utils::rate_moving_average& val) {
httpd::utils_json::rate_moving_average m;
m = val;
return make_ready_future<json::json_return_type>(m);
});
}
static future<json::json_return_type> sum_timed_rate_as_long(distributed<proxy>& d, utils::timed_rate_moving_average proxy::stats::*f) {
return sum_timed_rate(d, f).then([](const utils::rate_moving_average& val) {
return make_ready_future<json::json_return_type>(val.count);
});
}
static future<json::json_return_type> sum_estimated_histogram(http_context& ctx, utils::estimated_histogram proxy::stats::*f) {
return ctx.sp.map_reduce0([f](const proxy& p) {return p.get_stats().*f;}, utils::estimated_histogram(),
utils::estimated_histogram_merge).then([](const utils::estimated_histogram& val) {
static future<json::json_return_type> sum_estimated_histogram(http_context& ctx, sstables::estimated_histogram proxy::stats::*f) {
return ctx.sp.map_reduce0([f](const proxy& p) {return p.get_stats().*f;}, sstables::estimated_histogram(),
sstables::merge).then([](const sstables::estimated_histogram& val) {
utils_json::estimated_histogram res;
res = val;
return make_ready_future<json::json_return_type>(res);
});
}
static future<json::json_return_type> total_latency(http_context& ctx, utils::timed_rate_moving_average_and_histogram proxy::stats::*f) {
return ctx.sp.map_reduce0([f](const proxy& p) {return (p.get_stats().*f).hist.mean * (p.get_stats().*f).hist.count;}, 0.0,
static future<json::json_return_type> total_latency(http_context& ctx, utils::ihistogram proxy::stats::*f) {
return ctx.sp.map_reduce0([f](const proxy& p) {return (p.get_stats().*f).mean * (p.get_stats().*f).count;}, 0.0,
std::plus<double>()).then([](double val) {
int64_t res = val;
return make_ready_future<json::json_return_type>(res);
@@ -310,75 +291,39 @@ void set_storage_proxy(http_context& ctx, routes& r) {
});
sp::get_read_metrics_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::read_timeouts);
return sum_stats(ctx.sp, &proxy::stats::read_timeouts);
});
sp::get_read_metrics_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::read_unavailables);
return sum_stats(ctx.sp, &proxy::stats::read_unavailables);
});
sp::get_range_metrics_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::range_slice_timeouts);
return sum_stats(ctx.sp, &proxy::stats::range_slice_timeouts);
});
sp::get_range_metrics_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::range_slice_unavailables);
return sum_stats(ctx.sp, &proxy::stats::range_slice_unavailables);
});
sp::get_write_metrics_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::write_timeouts);
return sum_stats(ctx.sp, &proxy::stats::write_timeouts);
});
sp::get_write_metrics_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_long(ctx.sp, &proxy::stats::write_unavailables);
});
sp::get_read_metrics_timeouts_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::read_timeouts);
});
sp::get_read_metrics_unavailables_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::read_unavailables);
});
sp::get_range_metrics_timeouts_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::range_slice_timeouts);
});
sp::get_range_metrics_unavailables_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::range_slice_unavailables);
});
sp::get_write_metrics_timeouts_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::write_timeouts);
});
sp::get_write_metrics_unavailables_rates.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timed_rate_as_obj(ctx.sp, &proxy::stats::write_unavailables);
});
sp::get_range_metrics_latency_histogram_depricated.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_histogram_stats(ctx.sp, &proxy::stats::range);
});
sp::get_write_metrics_latency_histogram_depricated.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_histogram_stats(ctx.sp, &proxy::stats::write);
});
sp::get_read_metrics_latency_histogram_depricated.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_histogram_stats(ctx.sp, &proxy::stats::read);
return sum_stats(ctx.sp, &proxy::stats::write_unavailables);
});
sp::get_range_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timer_stats(ctx.sp, &proxy::stats::range);
return sum_histogram_stats(ctx.sp, &proxy::stats::range);
});
sp::get_write_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timer_stats(ctx.sp, &proxy::stats::write);
return sum_histogram_stats(ctx.sp, &proxy::stats::write);
});
sp::get_read_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
return sum_timer_stats(ctx.sp, &proxy::stats::read);
return sum_histogram_stats(ctx.sp, &proxy::stats::read);
});
sp::get_read_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
@@ -397,7 +342,7 @@ 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_histogram_stats(ctx.sp, &proxy::stats::read);
});
sp::get_range_latency.set(r, [&ctx](std::unique_ptr<request> req) {

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*
@@ -22,8 +22,6 @@
#include "storage_service.hh"
#include "api/api-doc/storage_service.json.hh"
#include "db/config.hh"
#include <boost/range/adaptor/map.hpp>
#include <boost/range/adaptor/filtered.hpp>
#include <service/storage_service.hh>
#include <db/commitlog/commitlog.hh>
#include <gms/gossiper.hh>
@@ -33,8 +31,6 @@
#include "locator/snitch_base.hh"
#include "column_family.hh"
#include "log.hh"
#include "release.hh"
#include "sstables/compaction_manager.hh"
namespace api {
@@ -125,9 +121,6 @@ void set_storage_service(http_context& ctx, routes& r) {
return service::get_local_storage_service().get_release_version();
});
ss::get_scylla_release_version.set(r, [](const_req req) {
return scylla_version();
});
ss::get_schema_version.set(r, [](const_req req) {
return service::get_local_storage_service().get_schema_version();
});
@@ -362,22 +355,16 @@ 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) {
@@ -395,21 +382,21 @@ void set_storage_service(http_context& ctx, routes& r) {
ss::remove_node.set(r, [](std::unique_ptr<request> req) {
auto host_id = req->get_query_param("host_id");
return service::get_local_storage_service().removenode(host_id).then([] {
return service::get_local_storage_service().remove_node(host_id).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
ss::get_removal_status.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().get_removal_status().then([] (auto status) {
return make_ready_future<json::json_return_type>(status);
});
//TBD
unimplemented();
return make_ready_future<json::json_return_type>("");
});
ss::force_remove_completion.set(r, [](std::unique_ptr<request> req) {
return service::get_local_storage_service().force_remove_completion().then([] {
return make_ready_future<json::json_return_type>(json_void());
});
//TBD
unimplemented();
return make_ready_future<json::json_return_type>(json_void());
});
ss::set_logging_level.set(r, [](std::unique_ptr<request> req) {
@@ -466,15 +453,8 @@ void set_storage_service(http_context& ctx, routes& r) {
});
ss::get_keyspaces.set(r, [&ctx](const_req req) {
auto type = req.get_query_param("type");
if (type == "user") {
return ctx.db.local().get_non_system_keyspaces();
} else if (type == "non_local_strategy") {
return map_keys(ctx.db.local().get_keyspaces() | boost::adaptors::filtered([](const auto& p) {
return p.second.get_replication_strategy().get_type() != locator::replication_strategy_type::local;
}));
}
return map_keys(ctx.db.local().get_keyspaces());
auto non_system = req.get_query_param("non_system");
return map_keys(ctx.db.local().keyspaces());
});
ss::update_snitch.set(r, [](std::unique_ptr<request> req) {
@@ -558,7 +538,9 @@ void set_storage_service(http_context& ctx, routes& r) {
});
ss::is_joined.set(r, [] (std::unique_ptr<request> req) {
return make_ready_future<json::json_return_type>(service::get_local_storage_service().is_joined());
return service::get_local_storage_service().is_joined().then([] (bool is_joined) {
return make_ready_future<json::json_return_type>(is_joined);
});
});
ss::set_stream_throughput_mb_per_sec.set(r, [](std::unique_ptr<request> req) {
@@ -677,59 +659,16 @@ void set_storage_service(http_context& ctx, routes& r) {
});
ss::set_trace_probability.set(r, [](std::unique_ptr<request> req) {
//TBD
unimplemented();
auto probability = req->get_query_param("probability");
return futurize<json::json_return_type>::apply([probability] {
double real_prob = std::stod(probability.c_str());
return tracing::tracing::tracing_instance().invoke_on_all([real_prob] (auto& local_tracing) {
local_tracing.set_trace_probability(real_prob);
}).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
}).then_wrapped([probability] (auto&& f) {
try {
f.get();
return make_ready_future<json::json_return_type>(json_void());
} catch (std::out_of_range& e) {
throw httpd::bad_param_exception(e.what());
} catch (std::invalid_argument&){
throw httpd::bad_param_exception(sprint("Bad format in a probability value: \"%s\"", probability.c_str()));
}
});
return make_ready_future<json::json_return_type>(json_void());
});
ss::get_trace_probability.set(r, [](std::unique_ptr<request> req) {
return make_ready_future<json::json_return_type>(tracing::tracing::get_local_tracing_instance().get_trace_probability());
});
ss::get_slow_query_info.set(r, [](const_req req) {
ss::slow_query_info res;
res.enable = tracing::tracing::get_local_tracing_instance().slow_query_tracing_enabled();
res.ttl = tracing::tracing::get_local_tracing_instance().slow_query_record_ttl().count() ;
res.threshold = tracing::tracing::get_local_tracing_instance().slow_query_threshold().count();
return res;
});
ss::set_slow_query.set(r, [](std::unique_ptr<request> req) {
auto enable = req->get_query_param("enable");
auto ttl = req->get_query_param("ttl");
auto threshold = req->get_query_param("threshold");
try {
return tracing::tracing::tracing_instance().invoke_on_all([enable, ttl, threshold] (auto& local_tracing) {
if (threshold != "") {
local_tracing.set_slow_query_threshold(std::chrono::microseconds(std::stol(threshold.c_str())));
}
if (ttl != "") {
local_tracing.set_slow_query_record_ttl(std::chrono::seconds(std::stol(ttl.c_str())));
}
if (enable != "") {
local_tracing.set_slow_query_enabled(strcasecmp(enable.c_str(), "true") == 0);
}
}).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
} catch (...) {
throw httpd::bad_param_exception(sprint("Bad format value: "));
}
//TBD
unimplemented();
return make_ready_future<json::json_return_type>(0);
});
ss::enable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
@@ -809,8 +748,10 @@ 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) {

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright (C) 2015 Cloudius Systems, Ltd.
*/
/*
@@ -28,12 +28,11 @@
#include "utils/managed_bytes.hh"
#include "net/byteorder.hh"
#include <cstdint>
#include <iosfwd>
#include <seastar/util/gcc6-concepts.hh>
#include <iostream>
template<typename T, typename Input>
template<typename T>
static inline
void set_field(Input& v, unsigned offset, T val) {
void set_field(managed_bytes& v, unsigned offset, T val) {
reinterpret_cast<net::packed<T>*>(v.begin() + offset)->raw = net::hton(val);
}
@@ -58,8 +57,6 @@ private:
static constexpr int8_t LIVE_FLAG = 0x01;
static constexpr int8_t EXPIRY_FLAG = 0x02; // When present, expiry field is present. Set only for live cells
static constexpr int8_t REVERT_FLAG = 0x04; // transient flag used to efficiently implement ReversiblyMergeable for atomic cells.
static constexpr int8_t COUNTER_UPDATE_FLAG = 0x08; // Cell is a counter update.
static constexpr int8_t COUNTER_IN_PLACE_REVERT = 0x10;
static constexpr unsigned flags_size = 1;
static constexpr unsigned timestamp_offset = flags_size;
static constexpr unsigned timestamp_size = 8;
@@ -69,25 +66,14 @@ private:
static constexpr unsigned deletion_time_size = 4;
static constexpr unsigned ttl_offset = expiry_offset + expiry_size;
static constexpr unsigned ttl_size = 4;
friend class counter_cell_builder;
private:
static bool is_counter_update(bytes_view cell) {
return cell[0] & COUNTER_UPDATE_FLAG;
}
static bool is_revert_set(bytes_view cell) {
return cell[0] & REVERT_FLAG;
}
static bool is_counter_in_place_revert_set(bytes_view cell) {
return cell[0] & COUNTER_IN_PLACE_REVERT;
}
template<typename BytesContainer>
static void set_revert(BytesContainer& cell, bool revert) {
cell[0] = (cell[0] & ~REVERT_FLAG) | (revert * REVERT_FLAG);
}
template<typename BytesContainer>
static void set_counter_in_place_revert(BytesContainer& cell, bool flag) {
cell[0] = (cell[0] & ~COUNTER_IN_PLACE_REVERT) | (flag * COUNTER_IN_PLACE_REVERT);
}
static bool is_live(const bytes_view& cell) {
return cell[0] & LIVE_FLAG;
}
@@ -101,30 +87,13 @@ private:
static api::timestamp_type timestamp(const bytes_view& cell) {
return get_field<api::timestamp_type>(cell, timestamp_offset);
}
template<typename BytesContainer>
static void set_timestamp(BytesContainer& cell, api::timestamp_type ts) {
set_field(cell, timestamp_offset, ts);
}
// Can be called on live cells only
private:
template<typename BytesView>
static BytesView do_get_value(BytesView cell) {
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;
}
public:
static bytes_view value(bytes_view cell) {
return do_get_value(cell);
}
static bytes_mutable_view value(bytes_mutable_view cell) {
return do_get_value(cell);
}
// Can be called on live counter update cells only
static int64_t counter_update_value(bytes_view cell) {
return get_field<int64_t>(cell, flags_size + timestamp_size);
}
// Can be called only when is_dead() is true.
static gc_clock::time_point deletion_time(const bytes_view& cell) {
assert(is_dead(cell));
@@ -157,14 +126,6 @@ public:
std::copy_n(value.begin(), value.size(), b.begin() + value_offset);
return b;
}
static managed_bytes make_live_counter_update(api::timestamp_type timestamp, int64_t value) {
auto value_offset = flags_size + timestamp_size;
managed_bytes b(managed_bytes::initialized_later(), value_offset + sizeof(value));
b[0] = LIVE_FLAG | COUNTER_UPDATE_FLAG;
set_field(b, timestamp_offset, timestamp);
set_field(b, value_offset, value);
return b;
}
static managed_bytes make_live(api::timestamp_type timestamp, bytes_view value, gc_clock::time_point expiry, gc_clock::duration ttl) {
auto value_offset = flags_size + timestamp_size + expiry_size + ttl_size;
managed_bytes b(managed_bytes::initialized_later(), value_offset + value.size());
@@ -175,31 +136,6 @@ public:
std::copy_n(value.begin(), value.size(), b.begin() + value_offset);
return b;
}
// make_live_from_serializer() is intended for users that need to serialise
// some object or objects to the format used in atomic_cell::value().
// With just make_live() the patter would look like follows:
// 1. allocate a buffer and write to it serialised objects
// 2. pass that buffer to make_live()
// 3. make_live() needs to prepend some metadata to the cell value so it
// allocates a new buffer and copies the content of the original one
//
// The allocation and copy of a buffer can be avoided.
// make_live_from_serializer() allows the user code to specify the timestamp
// and size of the cell value as well as provide the serialiser function
// object, which would write the serialised value of the cell to the buffer
// given to it by make_live_from_serializer().
template<typename Serializer>
GCC6_CONCEPT(requires requires(Serializer serializer, bytes::iterator it) {
serializer(it);
})
static managed_bytes make_live_from_serializer(api::timestamp_type timestamp, size_t size, Serializer&& serializer) {
auto value_offset = flags_size + timestamp_size;
managed_bytes b(managed_bytes::initialized_later(), value_offset + size);
b[0] = LIVE_FLAG;
set_field(b, timestamp_offset, timestamp);
serializer(b.begin() + value_offset);
return b;
}
template<typename ByteContainer>
friend class atomic_cell_base;
friend class atomic_cell;
@@ -213,23 +149,17 @@ protected:
atomic_cell_base(ByteContainer&& data) : _data(std::forward<ByteContainer>(data)) { }
friend class atomic_cell_or_collection;
public:
bool is_counter_update() const {
return atomic_cell_type::is_counter_update(_data);
}
bool is_revert_set() const {
return atomic_cell_type::is_revert_set(_data);
}
bool is_counter_in_place_revert_set() const {
return atomic_cell_type::is_counter_in_place_revert_set(_data);
}
bool is_live() const {
return atomic_cell_type::is_live(_data);
}
bool is_live(tombstone t, bool is_counter) const {
return is_live() && !is_covered_by(t, is_counter);
bool is_live(tombstone t) const {
return is_live() && !is_covered_by(t);
}
bool is_live(tombstone t, gc_clock::time_point now, bool is_counter) const {
return is_live() && !is_covered_by(t, is_counter) && !has_expired(now);
bool is_live(tombstone t, gc_clock::time_point now) const {
return is_live() && !is_covered_by(t) && !has_expired(now);
}
bool is_live_and_has_ttl() const {
return atomic_cell_type::is_live_and_has_ttl(_data);
@@ -237,24 +167,17 @@ public:
bool is_dead(gc_clock::time_point now) const {
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);
bool is_covered_by(tombstone t) const {
return timestamp() <= t.timestamp;
}
// Can be called on live and dead cells
api::timestamp_type timestamp() const {
return atomic_cell_type::timestamp(_data);
}
void set_timestamp(api::timestamp_type ts) {
atomic_cell_type::set_timestamp(_data, ts);
}
// Can be called on live cells only
auto value() const {
bytes_view value() const {
return atomic_cell_type::value(_data);
}
// Can be called on live counter update cells only
int64_t counter_update_value() const {
return atomic_cell_type::counter_update_value(_data);
}
// Can be called only when is_dead(gc_clock::time_point)
gc_clock::time_point deletion_time() const {
return !is_live() ? atomic_cell_type::deletion_time(_data) : expiry() - ttl();
@@ -269,7 +192,7 @@ public:
}
// 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 _data;
@@ -277,9 +200,6 @@ public:
void set_revert(bool revert) {
atomic_cell_type::set_revert(_data, revert);
}
void set_counter_in_place_revert(bool flag) {
atomic_cell_type::set_counter_in_place_revert(_data, flag);
}
};
class atomic_cell_view final : public atomic_cell_base<bytes_view> {
@@ -291,14 +211,6 @@ public:
friend std::ostream& operator<<(std::ostream& os, const atomic_cell_view& acv);
};
class atomic_cell_mutable_view final : public atomic_cell_base<bytes_mutable_view> {
atomic_cell_mutable_view(bytes_mutable_view data) : atomic_cell_base(std::move(data)) {}
public:
static atomic_cell_mutable_view from_bytes(bytes_mutable_view data) { return atomic_cell_mutable_view(data); }
friend class atomic_cell;
};
class atomic_cell_ref final : public atomic_cell_base<managed_bytes&> {
public:
atomic_cell_ref(managed_bytes& buf) : atomic_cell_base(buf) {}
@@ -324,22 +236,11 @@ public:
static atomic_cell make_live(api::timestamp_type timestamp, bytes_view value) {
return atomic_cell_type::make_live(timestamp, value);
}
static atomic_cell make_live(api::timestamp_type timestamp, const bytes& value) {
return make_live(timestamp, bytes_view(value));
}
static atomic_cell make_live_counter_update(api::timestamp_type timestamp, int64_t value) {
return atomic_cell_type::make_live_counter_update(timestamp, value);
}
static atomic_cell make_live(api::timestamp_type timestamp, bytes_view value,
gc_clock::time_point expiry, gc_clock::duration ttl)
{
return atomic_cell_type::make_live(timestamp, value, expiry, ttl);
}
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 atomic_cell_type::make_live(timestamp, value);
@@ -347,10 +248,6 @@ public:
return atomic_cell_type::make_live(timestamp, value, gc_clock::now() + *ttl, *ttl);
}
}
template<typename Serializer>
static atomic_cell make_live_from_serializer(api::timestamp_type timestamp, size_t size, Serializer&& serializer) {
return atomic_cell_type::make_live_from_serializer(timestamp, size, std::forward<Serializer>(serializer));
}
friend class atomic_cell_or_collection;
friend std::ostream& operator<<(std::ostream& os, const atomic_cell& ac);
};
@@ -388,6 +285,11 @@ 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);

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright (C) 2015 Cloudius Systems, Ltd.
*/
/*
@@ -26,17 +26,16 @@
#include "types.hh"
#include "atomic_cell.hh"
#include "hashing.hh"
#include "counters.hh"
template<>
struct appending_hash<collection_mutation_view> {
template<typename Hasher>
void operator()(Hasher& h, collection_mutation_view cell, const column_definition& cdef) const {
void operator()(Hasher& h, collection_mutation_view cell) const {
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);
::feed_hash(h, key_and_value.second);
}
}
};
@@ -44,14 +43,10 @@ struct appending_hash<collection_mutation_view> {
template<>
struct appending_hash<atomic_cell_view> {
template<typename Hasher>
void operator()(Hasher& h, atomic_cell_view cell, const column_definition& cdef) const {
void operator()(Hasher& h, atomic_cell_view cell) const {
feed_hash(h, cell.is_live());
feed_hash(h, cell.timestamp());
if (cell.is_live()) {
if (cdef.is_counter()) {
::feed_hash(h, counter_cell_view(cell));
return;
}
if (cell.is_live_and_has_ttl()) {
feed_hash(h, cell.expiry());
feed_hash(h, cell.ttl());
@@ -66,15 +61,15 @@ struct appending_hash<atomic_cell_view> {
template<>
struct appending_hash<atomic_cell> {
template<typename Hasher>
void operator()(Hasher& h, const atomic_cell& cell, const column_definition& cdef) const {
feed_hash(h, static_cast<atomic_cell_view>(cell), cdef);
void operator()(Hasher& h, const atomic_cell& cell) const {
feed_hash(h, static_cast<atomic_cell_view>(cell));
}
};
template<>
struct appending_hash<collection_mutation> {
template<typename Hasher>
void operator()(Hasher& h, const collection_mutation& cm, const column_definition& cdef) const {
feed_hash(h, static_cast<collection_mutation_view>(cm), cdef);
void operator()(Hasher& h, const collection_mutation& cm) const {
feed_hash(h, static_cast<collection_mutation_view>(cm));
}
};

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright (C) 2015 Cloudius Systems, Ltd.
*/
/*
@@ -39,14 +39,10 @@ public:
static atomic_cell_or_collection from_atomic_cell(atomic_cell data) { return { std::move(data._data) }; }
atomic_cell_view as_atomic_cell() const { return atomic_cell_view::from_bytes(_data); }
atomic_cell_ref as_atomic_cell_ref() { return { _data }; }
atomic_cell_mutable_view as_mutable_atomic_cell() { return atomic_cell_mutable_view::from_bytes(_data); }
atomic_cell_or_collection(collection_mutation cm) : _data(std::move(cm.data)) {}
explicit operator bool() const {
return !_data.empty();
}
bool can_use_mutable_view() const {
return !_data.is_fragmented();
}
static atomic_cell_or_collection from_collection_mutation(collection_mutation data) {
return std::move(data.data);
}
@@ -62,13 +58,10 @@ public:
template<typename Hasher>
void feed_hash(Hasher& h, const column_definition& def) const {
if (def.is_atomic()) {
::feed_hash(h, as_atomic_cell(), def);
::feed_hash(h, as_atomic_cell());
} else {
::feed_hash(h, as_collection_mutation(), def);
::feed_hash(as_collection_mutation(), h, def.type);
}
}
size_t external_memory_usage() const {
return _data.external_memory_usage();
}
friend std::ostream& operator<<(std::ostream&, const atomic_cell_or_collection&);
};

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

@@ -1,97 +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/>.
*/
#pragma once
#include <stdexcept>
#include "auth/authenticator.hh"
#include "auth/authenticated_user.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&) {
}
future<> start() override {
return make_ready_future<>();
}
future<> stop() override {
return make_ready_future<>();
}
const sstring& qualified_java_name() const override {
return allow_all_authenticator_name();
}
bool require_authentication() const override {
return false;
}
option_set supported_options() const override {
return option_set();
}
option_set alterable_options() const override {
return option_set();
}
future<::shared_ptr<authenticated_user>> authenticate(const credentials_map& credentials) const override {
return make_ready_future<::shared_ptr<authenticated_user>>(::make_shared<authenticated_user>());
}
future<> create(sstring username, const option_map& options) override {
return make_ready_future();
}
future<> alter(sstring username, const option_map& options) override {
return make_ready_future();
}
future<> drop(sstring username) override {
return make_ready_future();
}
const resource_ids& protected_resources() const override {
static const resource_ids ids;
return ids;
}
::shared_ptr<sasl_challenge> new_sasl_challenge() const override {
throw std::runtime_error("Should not reach");
}
};
}

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

@@ -1,98 +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 "authorizer.hh"
#include "exceptions/exceptions.hh"
#include "stdx.hh"
namespace cql3 {
class query_processor;
}
namespace service {
class migration_manager;
}
namespace auth {
class service;
const sstring& allow_all_authorizer_name();
class allow_all_authorizer final : public authorizer {
public:
allow_all_authorizer(cql3::query_processor&, ::service::migration_manager&) {
}
future<> start() override {
return make_ready_future<>();
}
future<> stop() override {
return make_ready_future<>();
}
const sstring& qualified_java_name() const override {
return allow_all_authorizer_name();
}
future<permission_set> authorize(service&, ::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(
service&,
::shared_ptr<authenticated_user> performer,
permission_set,
stdx::optional<data_resource>,
stdx::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();
}
};
}

306
auth/auth.cc Normal file
View File

@@ -0,0 +1,306 @@
/*
* 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 2016 Cloudius Systems
*
* Modified by Cloudius Systems
*/
/*
* 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 "auth.hh"
#include "authenticator.hh"
#include "database.hh"
#include "cql3/query_processor.hh"
#include "cql3/statements/cf_statement.hh"
#include "cql3/statements/create_table_statement.hh"
#include "db/config.hh"
#include "service/migration_manager.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_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_drop_keyspace(const sstring& ks_name) override {
// TODO:
//DatabaseDescriptor.getAuthorizer().revokeAll(DataResource.keyspace(ksName));
}
void on_drop_column_family(const sstring& ks_name, const sstring& cf_name) override {
// TODO:
//DatabaseDescriptor.getAuthorizer().revokeAll(DataResource.columnFamily(ksName, cfName));
}
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 {}
};
static auth_migration_listener auth_migration;
/**
* 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();
auto type = cfg.authenticator();
if (is_class_type(type, authenticator::ALLOW_ALL_AUTHENTICATOR_NAME)) {
return authenticator::setup(type).discard_result(); // just create the object
}
future<> f = make_ready_future();
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);
f = service::get_local_migration_manager().announce_new_keyspace(ksm, 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([type] {
return authenticator::setup(type).discard_result();
}).then([] {
// TODO 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();
});
}
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::cf_statement> parsed = static_pointer_cast<
cql3::statements::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)->statement);
// Origin sets "Legacy Cf Id" for the new table. We have no need to be
// pre-2.1 compatible (afaik), so lets skip a whole lotta hoolaballo
return statement->announce_migration(qp.proxy(), false).then([statement](bool) {});
}
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());
});
});
});
}

121
auth/auth.hh Normal file
View File

@@ -0,0 +1,121 @@
/*
* 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 2016 Cloudius Systems
*
* Modified by Cloudius Systems
*/
/*
* 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 "exceptions/exceptions.hh"
namespace auth {
class auth {
public:
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);
#if 0
public static Set<Permission> getPermissions(AuthenticatedUser user, IResource resource)
{
return permissionsCache.getPermissions(user, resource);
}
#endif
/**
* 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

@@ -17,9 +17,9 @@
*/
/*
* Copyright (C) 2016 ScyllaDB
* Copyright 2016 Cloudius Systems
*
* Modified by ScyllaDB
* Modified by Cloudius Systems
*/
/*
@@ -52,9 +52,6 @@ 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;
}

View File

@@ -17,9 +17,9 @@
*/
/*
* Copyright (C) 2016 ScyllaDB
* Copyright 2016 Cloudius Systems
*
* Modified by ScyllaDB
* Modified by Cloudius Systems
*/
/*
@@ -42,8 +42,6 @@
#pragma once
#include <seastar/core/sstring.hh>
#include <seastar/core/future.hh>
#include "seastarx.hh"
namespace auth {
@@ -53,11 +51,17 @@ public:
authenticated_user();
authenticated_user(sstring name);
authenticated_user(authenticated_user&&);
authenticated_user(const authenticated_user&);
const sstring& name() const;
/**
* 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).
*/
bool is_super() const;
/**
* If IAuthenticator doesn't require authentication, this method may return true.
*/

View File

@@ -17,9 +17,9 @@
*/
/*
* Copyright (C) 2016 ScyllaDB
* Copyright 2016 Cloudius Systems
*
* Modified by ScyllaDB
* Modified by Cloudius Systems
*/
/*
@@ -41,27 +41,70 @@
#include "authenticator.hh"
#include "authenticated_user.hh"
#include "common.hh"
#include "password_authenticator.hh"
#include "cql3/query_processor.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;
/**
* 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();
}
resource_ids protected_resources() const override {
return resource_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);
}
throw std::invalid_argument(name);
return make_ready_future();
}
sstring auth::authenticator::option_to_string(option opt) {
switch (opt) {
case option::PASSWORD:
return "PASSWORD";
default:
throw std::invalid_argument(sprint("Unknown option {}", opt));
}
auth::authenticator& auth::authenticator::get() {
assert(global_authenticator);
return *global_authenticator;
}

View File

@@ -17,9 +17,9 @@
*/
/*
* Copyright (C) 2016 ScyllaDB
* Copyright 2016 Cloudius Systems
*
* Modified by ScyllaDB
* Modified by Cloudius Systems
*/
/*
@@ -69,6 +69,7 @@ class authenticator {
public:
static const sstring USERNAME_KEY;
static const sstring PASSWORD_KEY;
static const sstring ALLOW_ALL_AUTHENTICATOR_NAME;
/**
* Supported CREATE USER/ALTER USER options.
@@ -78,21 +79,32 @@ public:
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>;
/**
* Resource id mappings, i.e. keyspace and/or column families.
*/
using resource_ids = std::set<data_resource>;
/**
* 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 future<> start() = 0;
virtual future<> stop() = 0;
virtual const sstring& qualified_java_name() const = 0;
virtual const sstring& class_name() const = 0;
/**
* Whether or not the authenticator requires explicit login.
@@ -119,7 +131,7 @@ public:
*
* @throws authentication_exception if credentials don't match any known user.
*/
virtual future<::shared_ptr<authenticated_user>> authenticate(const credentials_map& credentials) const = 0;
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).
@@ -131,7 +143,7 @@ public:
* @throws exceptions::request_validation_exception
* @throws exceptions::request_execution_exception
*/
virtual future<> create(sstring username, const option_map& options) = 0;
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.
@@ -144,7 +156,7 @@ public:
* @throws exceptions::request_validation_exception
* @throws exceptions::request_execution_exception
*/
virtual future<> alter(sstring username, const option_map& options) = 0;
virtual future<> alter(sstring username, const option_map& options) throw(exceptions::request_validation_exception, exceptions::request_execution_exception) = 0;
/**
@@ -154,7 +166,7 @@ public:
* @throws exceptions::request_validation_exception
* @throws exceptions::request_execution_exception
*/
virtual future<> drop(sstring username) = 0;
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.
@@ -162,14 +174,14 @@ public:
* @return Keyspaces, column families that will be unmodifiable by users; other resources.
* @see resource_ids
*/
virtual const resource_ids& protected_resources() const = 0;
virtual resource_ids protected_resources() const = 0;
class sasl_challenge {
public:
virtual ~sasl_challenge() {}
virtual bytes evaluate_response(bytes_view client_response) = 0;
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 = 0;
virtual future<::shared_ptr<authenticated_user>> get_authenticated_user() const throw(exceptions::authentication_exception) = 0;
};
/**
@@ -182,9 +194,5 @@ public:
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);
}
}

View File

@@ -1,118 +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 "authorizer.hh"
#include "authenticated_user.hh"
#include "common.hh"
#include "default_authorizer.hh"
#include "auth.hh"
#include "cql3/query_processor.hh"
#include "db/config.hh"
#include "utils/class_registrator.hh"
const sstring& auth::allow_all_authorizer_name() {
static const sstring name = meta::AUTH_PACKAGE_NAME + "AllowAllAuthorizer";
return name;
}
/**
* 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;
using authorizer_registry = class_registry<auth::authorizer, cql3::query_processor&>;
future<>
auth::authorizer::setup(const sstring& type) {
if (type == allow_all_authorizer_name()) {
class allow_all_authorizer : public authorizer {
public:
future<> start() override {
return make_ready_future<>();
}
future<> stop() override {
return make_ready_future<>();
}
const sstring& qualified_java_name() const override {
return allow_all_authorizer_name();
}
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>();
return make_ready_future();
} else {
auto a = authorizer_registry::create(type, cql3::get_local_query_processor());
auto f = a->start();
return f.then([a = std::move(a)]() mutable {
global_authorizer = std::move(a);
});
}
}
auth::authorizer& auth::authorizer::get() {
assert(global_authorizer);
return *global_authorizer;
}

View File

@@ -1,167 +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 <vector>
#include <tuple>
#include <experimental/optional>
#include <seastar/core/future.hh>
#include <seastar/core/shared_ptr.hh>
#include "permission.hh"
#include "data_resource.hh"
#include "seastarx.hh"
namespace auth {
class service;
class authenticated_user;
struct permission_details {
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);
}
};
using std::experimental::optional;
class authorizer {
public:
virtual ~authorizer() {}
virtual future<> start() = 0;
virtual future<> stop() = 0;
virtual const sstring& qualified_java_name() const = 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(service&, ::shared_ptr<authenticated_user>, data_resource) 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;
/**
* 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;
/**
* 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(service&, ::shared_ptr<authenticated_user> performer, permission_set, optional<data_resource>, optional<sstring>) 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;
/**
* 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;
/**
* 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;
/**
* Validates configuration of IAuthorizer implementation (if configurable).
*
* @throws ConfigurationException when there is a configuration error.
*/
virtual future<> validate_configuration() const = 0;
};
}

View File

@@ -1,70 +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 "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.");
}
future<> create_metadata_table_if_missing(
const sstring& table_name,
cql3::query_processor& qp,
const sstring& cql,
::service::migration_manager& mm) {
auto& db = qp.db().local();
if (db.has_schema(meta::AUTH_KS, 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();
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);
}
}

View File

@@ -1,74 +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 <seastar/core/future.hh>
#include <seastar/core/reactor.hh>
#include <seastar/core/resource.hh>
#include <seastar/core/sstring.hh>
#include "delayed_tasks.hh"
#include "seastarx.hh"
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<>();
}
template <class Task, class Clock>
void delay_until_system_ready(delayed_tasks<Clock>& ts, Task&& f) {
static const typename std::chrono::milliseconds delay_duration(10000);
ts.schedule_after(delay_duration, std::forward<Task>(f));
}
future<> create_metadata_table_if_missing(
const sstring& table_name,
cql3::query_processor&,
const sstring& cql,
::service::migration_manager&);
}

View File

@@ -17,9 +17,9 @@
*/
/*
* Copyright (C) 2016 ScyllaDB
* Copyright 2016 Cloudius Systems
*
* Modified by ScyllaDB
* Modified by Cloudius Systems
*/
/*
@@ -47,8 +47,11 @@
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)
: _ks(ks), _cf(cf)
{
if (l != get_level()) {
throw std::invalid_argument("level/keyspace/column mismatch");
}
}
auth::data_resource::data_resource()
@@ -64,7 +67,14 @@ auth::data_resource::data_resource(const sstring& ks, const sstring& cf)
{}
auth::data_resource::level auth::data_resource::get_level() const {
return _level;
if (!_cf.empty()) {
assert(!_ks.empty());
return level::COLUMN_FAMILY;
}
if (!_ks.empty()) {
return level::KEYSPACE;
}
return level::ROOT;
}
auth::data_resource auth::data_resource::from_name(
@@ -115,14 +125,16 @@ auth::data_resource auth::data_resource::get_parent() const {
}
}
const sstring& auth::data_resource::keyspace() const {
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 {
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()));
}
@@ -146,15 +158,7 @@ bool auth::data_resource::exists() const {
}
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);
}
return name();
}
bool auth::data_resource::operator==(const data_resource& v) const {
@@ -166,6 +170,6 @@ bool auth::data_resource::operator<(const data_resource& v) const {
}
std::ostream& auth::operator<<(std::ostream& os, const data_resource& r) {
return os << r.to_string();
return os << r.name();
}

View File

@@ -17,9 +17,9 @@
*/
/*
* Copyright (C) 2016 ScyllaDB
* Copyright 2016 Cloudius Systems
*
* Modified by ScyllaDB
* Modified by Cloudius Systems
*/
/*
@@ -41,11 +41,8 @@
#pragma once
#include "utils/hash.hh"
#include <iosfwd>
#include <set>
#include <seastar/core/sstring.hh>
#include "seastarx.hh"
namespace auth {
@@ -57,7 +54,6 @@ private:
static const sstring ROOT_NAME;
level _level;
sstring _ks;
sstring _cf;
@@ -118,13 +114,13 @@ public:
* @return keyspace of the resource.
* @throws std::invalid_argument if it's the root-level resource.
*/
const sstring& keyspace() const;
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;
const sstring& column_family() const throw(std::invalid_argument);
/**
* @return Whether or not the resource has a parent in the hierarchy.
@@ -140,17 +136,8 @@ public:
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

@@ -1,257 +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 <unistd.h>
#include <crypt.h>
#include <random>
#include <chrono>
#include <seastar/core/reactor.hh>
#include "common.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"
const sstring& auth::default_authorizer_name() {
static const sstring name = meta::AUTH_PACKAGE_NAME + "CassandraAuthorizer";
return name;
}
static const sstring USER_NAME = "username";
static const sstring RESOURCE_NAME = "resource";
static const sstring PERMISSIONS_NAME = "permissions";
static const sstring PERMISSIONS_CF = "permissions";
static logging::logger alogger("default_authorizer");
// To ensure correct initialization order, we unfortunately need to use a string literal.
static const class_registrator<
auth::authorizer,
auth::default_authorizer,
cql3::query_processor&,
::service::migration_manager&> password_auth_reg("org.apache.cassandra.auth.CassandraAuthorizer");
auth::default_authorizer::default_authorizer(cql3::query_processor& qp, ::service::migration_manager& mm)
: _qp(qp)
, _migration_manager(mm) {
}
auth::default_authorizer::~default_authorizer() {
}
future<> auth::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, USER_NAME, RESOURCE_NAME, PERMISSIONS_NAME,
USER_NAME, RESOURCE_NAME, 90 * 24 * 60 * 60); // 3 months.
return auth::once_among_shards([this] {
return auth::create_metadata_table_if_missing(
PERMISSIONS_CF,
_qp,
create_table,
_migration_manager);
});
}
future<> auth::default_authorizer::stop() {
return make_ready_future<>();
}
future<auth::permission_set> auth::default_authorizer::authorize(
service& ser, ::shared_ptr<authenticated_user> user, data_resource resource) const {
return auth::is_super_user(ser, *user).then([this, user, resource = std::move(resource)](bool is_super) {
if (is_super) {
return make_ready_future<permission_set>(permissions::ALL);
}
/**
* TOOD: could create actual data type for permission (translating string<->perm),
* but this seems overkill right now. We still must store strings so...
*/
auto query = sprint("SELECT %s FROM %s.%s WHERE %s = ? AND %s = ?"
, PERMISSIONS_NAME, meta::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();
if (res->empty() || !res->one().has(PERMISSIONS_NAME)) {
return make_ready_future<permission_set>(permissions::NONE);
}
return make_ready_future<permission_set>(permissions::from_strings(res->one().get_set<sstring>(PERMISSIONS_NAME)));
} catch (exceptions::request_execution_exception& e) {
alogger.warn("CassandraAuthorizer failed to authorize {} for {}", user->name(), resource);
return make_ready_future<permission_set>(permissions::NONE);
}
});
});
}
#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 query = sprint("UPDATE %s.%s SET %s = %s %s ? WHERE %s = ? AND %s = ?",
meta::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<> 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), "+");
}
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(
service& ser, ::shared_ptr<authenticated_user> performer, permission_set set,
optional<data_resource> resource, optional<sstring> user) const {
return auth::is_super_user(ser, *performer).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"));
}
auto query = sprint("SELECT %s, %s, %s FROM %s.%s", USER_NAME, RESOURCE_NAME, PERMISSIONS_NAME, meta::AUTH_KS, PERMISSIONS_CF);
// 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, {});
}
return f.then([set](::shared_ptr<cql3::untyped_result_set> res) {
std::vector<permission_details> result;
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());
result.emplace_back(permission_details {username, resource, ps});
}
}
return make_ready_future<std::vector<permission_details>>(std::move(result));
});
});
}
future<> auth::default_authorizer::revoke_all(sstring dropped_user) {
auto query = sprint("DELETE FROM %s.%s WHERE %s = ?", meta::AUTH_KS,
PERMISSIONS_CF, USER_NAME);
return _qp.process(query, db::consistency_level::ONE, { dropped_user }).discard_result().handle_exception(
[dropped_user](auto ep) {
try {
std::rethrow_exception(ep);
} catch (exceptions::request_execution_exception& e) {
alogger.warn("CassandraAuthorizer failed to revoke all permissions of {}: {}", dropped_user, e);
}
});
}
future<> auth::default_authorizer::revoke_all(data_resource resource) {
auto query = sprint("SELECT %s FROM %s.%s WHERE %s = ? ALLOW FILTERING",
USER_NAME, meta::AUTH_KS, PERMISSIONS_CF, RESOURCE_NAME);
return _qp.process(query, db::consistency_level::LOCAL_ONE, { resource.name() })
.then_wrapped([this, resource](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) {
auto query = sprint("DELETE FROM %s.%s WHERE %s = ? AND %s = ?"
, meta::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);
}
});
});
} catch (exceptions::request_execution_exception& e) {
alogger.warn("CassandraAuthorizer failed to revoke all permissions on {}: {}", resource, e);
return make_ready_future();
}
});
}
const auth::resource_ids& auth::default_authorizer::protected_resources() {
static const resource_ids ids({ data_resource(meta::AUTH_KS, PERMISSIONS_CF) });
return ids;
}
future<> auth::default_authorizer::validate_configuration() const {
return make_ready_future();
}

View File

@@ -1,92 +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 <functional>
#include "authorizer.hh"
#include "cql3/query_processor.hh"
#include "service/migration_manager.hh"
namespace auth {
const sstring& default_authorizer_name();
class default_authorizer : public authorizer {
cql3::query_processor& _qp;
::service::migration_manager& _migration_manager;
public:
default_authorizer(cql3::query_processor&, ::service::migration_manager&);
~default_authorizer();
future<> start() override;
future<> stop() override;
const sstring& qualified_java_name() const override {
return default_authorizer_name();
}
future<permission_set> authorize(service&, ::shared_ptr<authenticated_user>, data_resource) const override;
future<> grant(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring) override;
future<> revoke(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring) override;
future<std::vector<permission_details>> list(service&, ::shared_ptr<authenticated_user>, permission_set, optional<data_resource>, optional<sstring>) const override;
future<> revoke_all(sstring) override;
future<> revoke_all(data_resource) override;
const resource_ids& protected_resources() override;
future<> validate_configuration() const override;
private:
future<> modify(::shared_ptr<authenticated_user>, permission_set, data_resource, sstring, sstring);
};
} /* namespace auth */

View File

@@ -17,9 +17,9 @@
*/
/*
* Copyright (C) 2016 ScyllaDB
* Copyright 2016 Cloudius Systems
*
* Modified by ScyllaDB
* Modified by Cloudius Systems
*/
/*
@@ -46,42 +46,28 @@
#include <seastar/core/reactor.hh>
#include "common.hh"
#include "auth.hh"
#include "password_authenticator.hh"
#include "authenticated_user.hh"
#include "cql3/untyped_result_set.hh"
#include "cql3/query_processor.hh"
#include "log.hh"
#include "service/migration_manager.hh"
#include "utils/class_registrator.hh"
const sstring& auth::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 USER_NAME = "username";
static const sstring DEFAULT_USER_NAME = auth::meta::DEFAULT_SUPERUSER_NAME;
static const sstring DEFAULT_USER_PASSWORD = auth::meta::DEFAULT_SUPERUSER_NAME;
static const sstring DEFAULT_USER_NAME = auth::auth::DEFAULT_SUPERUSER_NAME;
static const sstring DEFAULT_USER_PASSWORD = auth::auth::DEFAULT_SUPERUSER_NAME;
static const sstring CREDENTIALS_CF = "credentials";
static logging::logger plogger("password_authenticator");
// To ensure correct initialization order, we unfortunately need to use a string literal.
static const class_registrator<
auth::authenticator,
auth::password_authenticator,
cql3::query_processor&,
::service::migration_manager&> password_auth_reg("org.apache.cassandra.auth.PasswordAuthenticator");
static logging::logger logger("password_authenticator");
auth::password_authenticator::~password_authenticator()
{}
auth::password_authenticator::password_authenticator(cql3::query_processor& qp, ::service::migration_manager& mm)
: _qp(qp)
, _migration_manager(mm) {
}
auth::password_authenticator::password_authenticator()
{}
// TODO: blowfish
// Origin uses Java bcrypt library, i.e. blowfish salt
@@ -102,10 +88,12 @@ auth::password_authenticator::password_authenticator(cql3::query_processor& qp,
// 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());
}
@@ -134,14 +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;
}
@@ -153,52 +144,39 @@ static sstring hashpw(const sstring& pass) {
return hashpw(pass, gensalt());
}
future<> auth::password_authenticator::start() {
return auth::once_among_shards([this] {
gensalt(); // do this once to determine usable hashing
future<> auth::password_authenticator::init() {
gensalt(); // do this once to determine usable hashing
static const 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",
meta::AUTH_KS,
CREDENTIALS_CF, USER_NAME, SALTED_HASH, USER_NAME,
90 * 24 * 60 * 60); // 3 months.
sstring create_table = sprint(
"CREATE TABLE %s.%s ("
"%s text,"
"%s text," // salt + hash + number of rounds
"options map<text,text>,"// for future extensions
"PRIMARY KEY(%s)"
") WITH gc_grace_seconds=%d",
auth::auth::AUTH_KS,
CREDENTIALS_CF, USER_NAME, SALTED_HASH, USER_NAME,
90 * 24 * 60 * 60); // 3 months.
return auth::create_metadata_table_if_missing(
CREDENTIALS_CF,
_qp,
create_table,
_migration_manager).then([this] {
auth::delay_until_system_ready(_delayed, [this] {
return has_existing_users().then([this](bool existing) {
if (!existing) {
return _qp.process(
sprint(
"INSERT INTO %s.%s (%s, %s) VALUES (?, ?) USING TIMESTAMP 0",
meta::AUTH_KS,
CREDENTIALS_CF,
USER_NAME, SALTED_HASH),
db::consistency_level::ONE,
{ DEFAULT_USER_NAME, hashpw(DEFAULT_USER_PASSWORD) }).then([](auto) {
plogger.info("Created default user '{}'", DEFAULT_USER_NAME);
});
}
return make_ready_future<>();
});
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);
});
}
});
});
});
}
future<> auth::password_authenticator::stop() {
return make_ready_future<>();
}
db::consistency_level auth::password_authenticator::consistency_for_user(const sstring& username) {
if (username == DEFAULT_USER_NAME) {
return db::consistency_level::QUORUM;
@@ -206,8 +184,8 @@ db::consistency_level auth::password_authenticator::consistency_for_user(const s
return db::consistency_level::LOCAL_ONE;
}
const sstring& auth::password_authenticator::qualified_java_name() const {
return password_authenticator_name();
const sstring& auth::password_authenticator::class_name() const {
return PASSWORD_AUTHENTICATOR_NAME;
}
bool auth::password_authenticator::require_authentication() const {
@@ -223,7 +201,8 @@ auth::authenticator::option_set auth::password_authenticator::alterable_options(
}
future<::shared_ptr<auth::authenticated_user> > auth::password_authenticator::authenticate(
const credentials_map& credentials) const {
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));
}
@@ -239,11 +218,12 @@ future<::shared_ptr<auth::authenticated_user> > auth::password_authenticator::au
// obsolete prepared statements pretty quickly.
// Rely on query processing caching statements instead, and lets assume
// that a map lookup string->statement is not gonna kill us much.
return futurize_apply([this, username, password] {
return _qp.process(sprint("SELECT %s FROM %s.%s WHERE %s = ?", SALTED_HASH,
meta::AUTH_KS, CREDENTIALS_CF, USER_NAME),
consistency_for_user(username), {username}, true);
}).then_wrapped([=](future<::shared_ptr<cql3::untyped_result_set>> f) {
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))) {
@@ -254,57 +234,62 @@ future<::shared_ptr<auth::authenticated_user> > auth::password_authenticator::au
std::throw_with_nested(exceptions::authentication_exception("Could not verify password"));
} catch (exceptions::request_execution_exception& e) {
std::throw_with_nested(exceptions::authentication_exception(e.what()));
} catch (...) {
std::throw_with_nested(exceptions::authentication_exception("authentication failed"));
}
});
}
future<> auth::password_authenticator::create(sstring username,
const option_map& options) {
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 (?, ?)",
meta::AUTH_KS, CREDENTIALS_CF, USER_NAME, SALTED_HASH);
return _qp.process(query, consistency_for_user(username), { username, hashpw(password) }).discard_result();
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");
}
}
future<> auth::password_authenticator::alter(sstring username,
const option_map& options) {
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 = ?",
meta::AUTH_KS, CREDENTIALS_CF, SALTED_HASH, USER_NAME);
return _qp.process(query, consistency_for_user(username), { hashpw(password), username }).discard_result();
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");
}
}
future<> auth::password_authenticator::drop(sstring username) {
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 = ?",
meta::AUTH_KS, CREDENTIALS_CF, USER_NAME);
return _qp.process(query, consistency_for_user(username), { username }).discard_result();
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");
}
}
const auth::resource_ids& auth::password_authenticator::protected_resources() const {
static const resource_ids ids({ data_resource(meta::AUTH_KS, CREDENTIALS_CF) });
return ids;
auth::authenticator::resource_ids auth::password_authenticator::protected_resources() const {
return { data_resource(auth::AUTH_KS, CREDENTIALS_CF) };
}
::shared_ptr<auth::authenticator::sasl_challenge> auth::password_authenticator::new_sasl_challenge() const {
class plain_text_password_challenge: public sasl_challenge {
const password_authenticator& _self;
public:
plain_text_password_challenge(const password_authenticator& self) : _self(self)
plain_text_password_challenge(const password_authenticator& a)
: _authenticator(a)
{}
/**
@@ -320,8 +305,9 @@ const auth::resource_ids& auth::password_authenticator::protected_resources() co
* 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;
@@ -358,59 +344,14 @@ const auth::resource_ids& auth::password_authenticator::protected_resources() co
bool is_complete() const override {
return _complete;
}
future<::shared_ptr<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);
}
//
// Similar in structure to `auth::service::has_existing_users()`, but trying to generalize the pattern breaks all kinds
// of module boundaries and leaks implementation details.
//
future<bool> auth::password_authenticator::has_existing_users() const {
static const sstring default_user_query = sprint(
"SELECT * FROM %s.%s WHERE %s = ?",
meta::AUTH_KS,
CREDENTIALS_CF,
USER_NAME);
static const sstring all_users_query = sprint(
"SELECT * FROM %s.%s LIMIT 1",
meta::AUTH_KS,
CREDENTIALS_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,
{ 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,
{ 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).then([](auto results) {
return make_ready_future<bool>(!results->empty());
});
});
});
}

View File

@@ -17,9 +17,9 @@
*/
/*
* Copyright (C) 2016 ScyllaDB
* Copyright 2016 Cloudius Systems
*
* Modified by ScyllaDB
* Modified by Cloudius Systems
*/
/*
@@ -42,48 +42,31 @@
#pragma once
#include "authenticator.hh"
#include "cql3/query_processor.hh"
#include "delayed_tasks.hh"
namespace service {
class migration_manager;
}
namespace auth {
const sstring& password_authenticator_name();
class password_authenticator : public authenticator {
cql3::query_processor& _qp;
::service::migration_manager& _migration_manager;
delayed_tasks<> _delayed{};
public:
password_authenticator(cql3::query_processor&, ::service::migration_manager&);
static const sstring PASSWORD_AUTHENTICATOR_NAME;
password_authenticator();
~password_authenticator();
future<> start() override;
future<> init();
future<> stop() override;
const sstring& qualified_java_name() const override;
const sstring& class_name() const override;
bool require_authentication() const override;
option_set supported_options() const override;
option_set alterable_options() const override;
future<::shared_ptr<authenticated_user>> authenticate(const credentials_map& credentials) const override;
future<> create(sstring username, const option_map& options) override;
future<> alter(sstring username, const option_map& options) override;
future<> drop(sstring username) override;
const resource_ids& protected_resources() const override;
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;
resource_ids protected_resources() const override;
::shared_ptr<sasl_challenge> new_sasl_challenge() const override;
static db::consistency_level consistency_for_user(const sstring& username);
private:
future<bool> has_existing_users() const;
};
}

View File

@@ -17,9 +17,9 @@
*/
/*
* Copyright (C) 2016 ScyllaDB
* Copyright 2016 Cloudius Systems
*
* Modified by ScyllaDB
* Modified by Cloudius Systems
*/
/*
@@ -39,66 +39,11 @@
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include <unordered_map>
#include <boost/algorithm/string.hpp>
#include "permission.hh"
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 },
});
const sstring& auth::permissions::to_string(permission p) {
for (auto& v : permission_names) {
if (v.second == p) {
return v.first;
}
}
throw std::out_of_range("unknown permission");
}
auth::permission auth::permissions::from_string(const sstring& s) {
sstring upper(s);
boost::to_upper(upper);
return permission_names.at(upper);
}
std::unordered_set<sstring> auth::permissions::to_strings(const permission_set& set) {
std::unordered_set<sstring> res;
for (auto& v : permission_names) {
if (set.contains(v.second)) {
res.emplace(v.first);
}
}
return res;
}
auth::permission_set auth::permissions::from_strings(const std::unordered_set<sstring>& set) {
permission_set res = auth::permissions::NONE;
for (auto& s : set) {
res.set(from_string(s));
}
return res;
}
bool auth::operator<(const permission_set& p1, const permission_set& p2) {
return p1.mask() < p2.mask();
}
const auth::permission_set auth::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::ALL = auth::ALL_DATA;
const auth::permission_set auth::NONE;

View File

@@ -17,9 +17,9 @@
*/
/*
* Copyright (C) 2016 ScyllaDB
* Copyright 2016 Cloudius Systems
*
* Modified by ScyllaDB
* Modified by Cloudius Systems
*/
/*
@@ -41,10 +41,6 @@
#pragma once
#include <unordered_set>
#include <seastar/core/sstring.hh>
#include "seastarx.hh"
#include "enum_set.hh"
namespace auth {
@@ -78,22 +74,8 @@ typedef enum_set<super_enum<permission,
permission::MODIFY,
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&);
std::unordered_set<sstring> to_strings(const permission_set&);
permission_set from_strings(const std::unordered_set<sstring>&);
}
}

View File

@@ -1,51 +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.name());
return ser.underlying_authorizer().authorize(ser, ::make_shared<authenticated_user>(k.first), k.second);
}) {
}
future<permission_set> permissions_cache::get(::shared_ptr<authenticated_user> user, data_resource r) {
return _cache.get(key_type(*user, r));
}
}

View File

@@ -1,99 +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 <functional>
#include <iostream>
#include <utility>
#include <seastar/core/future.hh>
#include <seastar/core/shared_ptr.hh>
#include "auth/authenticated_user.hh"
#include "auth/data_resource.hh"
#include "auth/permission.hh"
#include "log.hh"
#include "utils/loading_cache.hh"
namespace std {
template <>
struct hash<auth::data_resource> final {
size_t operator()(const auth::data_resource & v) const {
return v.hash_value();
}
};
template <>
struct hash<auth::authenticated_user> final {
size_t operator()(const auth::authenticated_user & v) const {
return utils::tuple_hash()(v.name(), v.is_anonymous());
}
};
inline std::ostream& operator<<(std::ostream& os, const std::pair<auth::authenticated_user, auth::data_resource>& p) {
os << "{user: " << p.first.name() << ", data_resource: " << p.second << "}";
return os;
}
}
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<authenticated_user, data_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(::shared_ptr<authenticated_user>, data_resource);
};
}

View File

@@ -1,355 +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 <map>
#include <seastar/core/future-util.hh>
#include <seastar/core/shared_ptr.hh>
#include "auth/allow_all_authenticator.hh"
#include "auth/allow_all_authorizer.hh"
#include "auth/common.hh"
#include "cql3/query_processor.hh"
#include "cql3/untyped_result_set.hh"
#include "db/config.hh"
#include "db/consistency_level.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::data_resource(ks_name));
}
void on_drop_column_family(const sstring& ks_name, const sstring& cf_name) override {
_authorizer.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 db::consistency_level consistency_for_user(const sstring& name) {
if (name == meta::DEFAULT_SUPERUSER_NAME) {
return db::consistency_level::QUORUM;
} else {
return db::consistency_level::LOCAL_ONE;
}
}
static future<::shared_ptr<cql3::untyped_result_set>> select_user(cql3::query_processor& qp, const sstring& name) {
// 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 qp.process(
sprint(
"SELECT * FROM %s.%s WHERE %s = ?",
meta::AUTH_KS,
meta::USERS_CF,
meta::user_name_col_name),
consistency_for_user(name),
{ name },
true);
}
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());
service_config c;
c.authorizer_java_name = qualified_authorizer_name;
c.authenticator_java_name = qualified_authenticator_name;
return c;
}
service::service(
permissions_cache_config c,
cql3::query_processor& qp,
::service::migration_manager& mm,
std::unique_ptr<authorizer> a,
std::unique_ptr<authenticator> b)
: _permissions_cache_config(std::move(c))
, _permissions_cache(nullptr)
, _qp(qp)
, _migration_manager(mm)
, _authorizer(std::move(a))
, _authenticator(std::move(b))
, _migration_listener(std::make_unique<auth_migration_listener>(*_authorizer)) {
}
service::service(
permissions_cache_config cache_config,
cql3::query_processor& qp,
::service::migration_manager& mm,
const service_config& sc)
: service(
std::move(cache_config),
qp,
mm,
create_object<authorizer>(sc.authorizer_java_name, qp, mm),
create_object<authenticator>(sc.authenticator_java_name, qp, mm)) {
}
bool service::should_create_metadata() const {
const bool null_authorizer = _authorizer->qualified_java_name() == allow_all_authorizer_name();
const bool null_authenticator = _authenticator->qualified_java_name() == allow_all_authenticator_name();
return !null_authorizer || !null_authenticator;
}
future<> service::create_metadata_if_missing() {
auto& db = _qp.db().local();
auto f = make_ready_future<>();
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.
f = _migration_manager.announce_new_keyspace(ksm, api::min_timestamp, false);
}
return f.then([this] {
// 3 months.
static const auto gc_grace_seconds = 90 * 24 * 60 * 60;
static const sstring users_table_query = sprint(
"CREATE TABLE %s.%s (%s text, %s boolean, PRIMARY KEY (%s)) WITH gc_grace_seconds=%s",
meta::AUTH_KS,
meta::USERS_CF,
meta::user_name_col_name,
meta::superuser_col_name,
meta::user_name_col_name,
gc_grace_seconds);
return create_metadata_table_if_missing(
meta::USERS_CF,
_qp,
users_table_query,
_migration_manager);
}).then([this] {
delay_until_system_ready(_delayed, [this] {
return has_existing_users().then([this](bool existing) {
if (!existing) {
//
// Create default superuser.
//
static const sstring query = sprint(
"INSERT INTO %s.%s (%s, %s) VALUES (?, ?) USING TIMESTAMP 0",
meta::AUTH_KS,
meta::USERS_CF,
meta::user_name_col_name,
meta::superuser_col_name);
return _qp.process(
query,
db::consistency_level::ONE,
{ meta::DEFAULT_SUPERUSER_NAME, true }).then([](auto&&) {
log.info("Created default superuser '{}'", meta::DEFAULT_SUPERUSER_NAME);
}).handle_exception([](auto exn) {
try {
std::rethrow_exception(exn);
} catch (const exceptions::request_execution_exception&) {
log.warn("Skipped default superuser setup: some nodes were not ready");
}
}).discard_result();
}
return make_ready_future<>();
});
});
return make_ready_future<>();
});
}
future<> service::start() {
return once_among_shards([this] {
if (should_create_metadata()) {
return create_metadata_if_missing();
}
return make_ready_future<>();
}).then([this] {
return when_all_succeed(_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 once_among_shards([this] {
_delayed.cancel_all();
return make_ready_future<>();
}).then([this] {
return _permissions_cache->stop();
}).then([this] {
return when_all_succeed(_authorizer->stop(), _authenticator->stop());
});
}
future<bool> service::has_existing_users() const {
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,
{ 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,
{ 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).then([](auto results) {
return make_ready_future<bool>(!results->empty());
});
});
});
}
future<bool> service::is_existing_user(const sstring& name) const {
return select_user(_qp, name).then([](auto results) {
return !results->empty();
});
}
future<bool> service::is_super_user(const sstring& name) const {
return select_user(_qp, name).then([](auto results) {
return !results->empty() && results->one().template get_as<bool>(meta::superuser_col_name);
});
}
future<> service::insert_user(const sstring& name, bool is_superuser) {
return _qp.process(
sprint(
"INSERT INTO %s.%s (%s, %s) VALUES (?, ?)",
meta::AUTH_KS,
meta::USERS_CF,
meta::user_name_col_name,
meta::superuser_col_name),
consistency_for_user(name),
{ name, is_superuser }).discard_result();
}
future<> service::delete_user(const sstring& name) {
return _qp.process(
sprint(
"DELETE FROM %s.%s WHERE %s = ?",
meta::AUTH_KS,
meta::USERS_CF,
meta::user_name_col_name),
consistency_for_user(name),
{ name }).discard_result();
}
future<permission_set> service::get_permissions(::shared_ptr<authenticated_user> u, data_resource r) const {
return _permissions_cache->get(std::move(u), std::move(r));
}
//
// Free functions.
//
future<bool> is_super_user(const service& ser, const authenticated_user& u) {
if (u.is_anonymous()) {
return make_ready_future<bool>(false);
}
return ser.is_super_user(u.name());
}
}

View File

@@ -1,133 +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 <memory>
#include <seastar/core/future.hh>
#include <seastar/core/sstring.hh>
#include "auth/authenticator.hh"
#include "auth/authorizer.hh"
#include "auth/authenticated_user.hh"
#include "auth/permission.hh"
#include "auth/permissions_cache.hh"
#include "delayed_tasks.hh"
#include "seastarx.hh"
namespace cql3 {
class query_processor;
}
namespace db {
class config;
}
namespace service {
class migration_manager;
class migration_listener;
}
namespace auth {
class authenticator;
class authorizer;
struct service_config final {
static service_config from_db_config(const db::config&);
sstring authorizer_java_name;
sstring authenticator_java_name;
};
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;
// 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;
delayed_tasks<> _delayed{};
public:
service(
permissions_cache_config,
cql3::query_processor&,
::service::migration_manager&,
std::unique_ptr<authorizer>,
std::unique_ptr<authenticator>);
service(
permissions_cache_config,
cql3::query_processor&,
::service::migration_manager&,
const service_config&);
future<> start();
future<> stop();
future<bool> is_existing_user(const sstring& name) const;
future<bool> is_super_user(const sstring& name) const;
future<> insert_user(const sstring& name, bool is_superuser);
future<> delete_user(const sstring& name);
future<permission_set> get_permissions(::shared_ptr<authenticated_user>, data_resource) const;
authenticator& underlying_authenticator() {
return *_authenticator;
}
const authenticator& underlying_authenticator() const {
return *_authenticator;
}
authorizer& underlying_authorizer() {
return *_authorizer;
}
const authorizer& underlying_authorizer() const {
return *_authorizer;
}
private:
future<bool> has_existing_users() const;
bool should_create_metadata() const;
future<> create_metadata_if_missing();
};
future<bool> is_super_user(const service&, const authenticated_user&);
}

View File

@@ -1,232 +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 "authenticator.hh"
#include "authenticated_user.hh"
#include "authenticator.hh"
#include "authorizer.hh"
#include "password_authenticator.hh"
#include "default_authorizer.hh"
#include "permission.hh"
#include "db/config.hh"
#include "utils/class_registrator.hh"
namespace auth {
class service;
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))
{}
future<> start() override {
return _authenticator->start();
}
future<> stop() override {
return _authenticator->stop();
}
const sstring& qualified_java_name() const override {
return transitional_authenticator_name();
}
bool require_authentication() const override {
return true;
}
option_set supported_options() const override {
return _authenticator->supported_options();
}
option_set alterable_options() const override {
return _authenticator->alterable_options();
}
future<::shared_ptr<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<::shared_ptr<authenticated_user>>(::make_shared<authenticated_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<::shared_ptr<authenticated_user>>(::make_shared<authenticated_user>());
}
});
}
future<> create(sstring username, const option_map& options) override {
return _authenticator->create(username, options);
}
future<> alter(sstring username, const option_map& options) override {
return _authenticator->alter(username, options);
}
future<> drop(sstring username) override {
return _authenticator->drop(username);
}
const resource_ids& protected_resources() const override {
return _authenticator->protected_resources();
}
::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))
{}
bytes evaluate_response(bytes_view client_response) override {
try {
return _sasl->evaluate_response(client_response);
} catch (exceptions::authentication_exception&) {
_complete = true;
return {};
}
}
bool is_complete() const {
return _complete || _sasl->is_complete();
}
future<::shared_ptr<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<::shared_ptr<authenticated_user>>(::make_shared<authenticated_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()
{}
future<> start() override {
return _authorizer->start();
}
future<> stop() override {
return _authorizer->stop();
}
const sstring& qualified_java_name() const override {
return transitional_authorizer_name();
}
future<permission_set> authorize(service& ser, ::shared_ptr<authenticated_user> user, data_resource resource) const override {
return is_super_user(ser, *user).then([](bool s) {
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>(s ? permissions::ALL : transitional_permissions);
});
}
future<> grant(::shared_ptr<authenticated_user> user, permission_set ps, data_resource r, sstring s) override {
return _authorizer->grant(std::move(user), std::move(ps), std::move(r), std::move(s));
}
future<> revoke(::shared_ptr<authenticated_user> user, permission_set ps, data_resource r, sstring s) override {
return _authorizer->revoke(std::move(user), std::move(ps), std::move(r), std::move(s));
}
future<std::vector<permission_details>> list(service& ser, ::shared_ptr<authenticated_user> user, permission_set ps, optional<data_resource> r, optional<sstring> s) const override {
return _authorizer->list(ser, std::move(user), std::move(ps), std::move(r), std::move(s));
}
future<> revoke_all(sstring s) override {
return _authorizer->revoke_all(std::move(s));
}
future<> revoke_all(data_resource r) override {
return _authorizer->revoke_all(std::move(r));
}
const resource_ids& protected_resources() override {
return _authorizer->protected_resources();
}
future<> validate_configuration() const override {
return _authorizer->validate_configuration();
}
};
}
//
// 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("com.scylladb.auth.TransitionalAuthenticator");
static const class_registrator<
auth::authorizer,
auth::transitional_authorizer,
cql3::query_processor&,
::service::migration_manager&> transitional_authorizer_reg("com.scylladb.auth.TransitionalAuthorizer");

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2014 ScyllaDB
* Copyright (C) 2014 Cloudius Systems, Ltd.
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright (C) 2015 Cloudius Systems, Ltd.
*/
/*
@@ -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>;
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;

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*
@@ -38,7 +38,6 @@ class bytes_ostream {
public:
using size_type = bytes::size_type;
using value_type = bytes::value_type;
static constexpr size_type max_chunk_size() { return 16 * 1024; }
private:
static_assert(sizeof(value_type) == 1, "value_type is assumed to be one byte long");
struct chunk {
@@ -59,6 +58,7 @@ private:
};
// FIXME: consider increasing chunk size as the buffer grows
static constexpr size_type chunk_size{512};
static constexpr size_type usable_chunk_size{chunk_size - sizeof(chunk)};
private:
std::unique_ptr<chunk> _begin;
chunk* _current;
@@ -99,19 +99,6 @@ private:
}
return _current->size - _current->offset;
}
// Figure out next chunk size.
// - must be enough for data_size
// - must be at least chunk_size
// - try to double each time to prevent too many allocations
// - do not exceed max_chunk_size
size_type next_alloc_size(size_t data_size) const {
auto next_size = _current
? _current->size * 2
: chunk_size;
next_size = std::min(next_size, max_chunk_size());
// FIXME: check for overflow?
return std::max<size_type>(next_size, data_size + sizeof(chunk));
}
// Makes room for a contiguous region of given size.
// The region is accounted for as already written.
// size must not be zero.
@@ -122,7 +109,7 @@ private:
_size += size;
return ret;
} else {
auto alloc_size = next_alloc_size(size);
auto alloc_size = size <= usable_chunk_size ? chunk_size : (size + sizeof(chunk));
auto space = malloc(alloc_size);
if (!space) {
throw std::bad_alloc();
@@ -166,18 +153,19 @@ public:
}
bytes_ostream& operator=(const bytes_ostream& o) {
if (this != &o) {
auto x = bytes_ostream(o);
*this = std::move(x);
}
_size = 0;
_current = nullptr;
_begin = {};
append(o);
return *this;
}
bytes_ostream& operator=(bytes_ostream&& o) noexcept {
if (this != &o) {
this->~bytes_ostream();
new (this) bytes_ostream(std::move(o));
}
_size = o._size;
_begin = std::move(o._begin);
_current = o._current;
o._current = nullptr;
o._size = 0;
return *this;
}
@@ -186,7 +174,7 @@ public:
value_type* ptr;
// makes the place_holder looks like a stream
seastar::simple_output_stream get_stream() {
return seastar::simple_output_stream(reinterpret_cast<char*>(ptr), sizeof(T));
return seastar::simple_output_stream{reinterpret_cast<char*>(ptr)};
}
};
@@ -207,19 +195,19 @@ public:
if (v.empty()) {
return;
}
auto this_size = std::min(v.size(), size_t(current_space_left()));
if (this_size) {
memcpy(_current->data + _current->offset, v.begin(), this_size);
_current->offset += this_size;
_size += this_size;
v.remove_prefix(this_size);
}
while (!v.empty()) {
auto this_size = std::min(v.size(), size_t(max_chunk_size()));
std::copy_n(v.begin(), this_size, alloc(this_size));
v.remove_prefix(this_size);
auto space_left = current_space_left();
if (v.size() <= space_left) {
memcpy(_current->data + _current->offset, v.begin(), v.size());
_current->offset += v.size();
_size += v.size();
} else {
if (space_left) {
memcpy(_current->data + _current->offset, v.begin(), space_left);
_current->offset += space_left;
_size += space_left;
v.remove_prefix(space_left);
}
memcpy(alloc(v.size()), v.begin(), v.size());
}
}
@@ -284,8 +272,13 @@ public:
}
void append(const bytes_ostream& o) {
for (auto&& bv : o.fragments()) {
write(bv);
if (o.size() > 0) {
auto dst = alloc(o.size());
auto r = o._begin.get();
while (r) {
dst = std::copy_n(r->data, r->offset, dst);
r = r->next.get();
}
}
}
@@ -335,45 +328,6 @@ public:
_current->next = nullptr;
_current->offset = pos._offset;
}
void reduce_chunk_count() {
// FIXME: This is a simplified version. It linearizes the whole buffer
// if its size is below max_chunk_size. We probably could also gain
// some read performance by doing "real" reduction, i.e. merging
// all chunks until all but the last one is max_chunk_size.
if (size() < max_chunk_size()) {
linearize();
}
}
bool operator==(const bytes_ostream& other) const {
auto as = fragments().begin();
auto as_end = fragments().end();
auto bs = other.fragments().begin();
auto bs_end = other.fragments().end();
auto a = *as++;
auto b = *bs++;
while (!a.empty() || !b.empty()) {
auto now = std::min(a.size(), b.size());
if (!std::equal(a.begin(), a.begin() + now, b.begin(), b.begin() + now)) {
return false;
}
a.remove_prefix(now);
if (a.empty() && as != as_end) {
a = *as++;
}
b.remove_prefix(now);
if (b.empty() && bs != bs_end) {
b = *bs++;
}
}
return true;
}
bool operator!=(const bytes_ostream& other) const {
return !(*this == other);
}
};
template<>

View File

@@ -1,650 +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 "streamed_mutation.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
};
lw_shared_ptr<partition_snapshot> _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;
// We need to be prepared that we may get overlapping and out of order
// range tombstones. We must emit fragments with strictly monotonic positions,
// so we can't just trim such tombstones to the position of the last fragment.
// To solve that, range tombstones are accumulated first in a range_tombstone_stream
// and emitted once we have a fragment with a larger position.
range_tombstone_stream _tombstones;
// Holds the lower bound of a position range which hasn't been processed yet.
// Only fragments with positions < _lower_bound have been emitted.
//
// It is assumed that !_lower_bound.is_clustering_row(). We depend on this when
// calling range_tombstone::trim_front() and when inserting dummy entries. Dummy
// entries are assumed to be only at !is_clustering_row() positions.
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;
future<> do_fill_buffer();
void copy_from_cache_to_buffer();
future<> process_static_row();
void move_to_end();
void move_to_next_range();
void move_to_range(query::clustering_row_ranges::const_iterator);
void move_to_next_entry();
// Emits all delayed range tombstones with positions smaller than upper_bound.
void drain_tombstones(position_in_partition_view upper_bound);
// Emits all delayed range tombstones.
void drain_tombstones();
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();
void start_reading_from_underlying();
bool after_current_range(position_in_partition_view position);
bool can_populate() const;
void maybe_update_continuity();
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;
}
public:
cache_flat_mutation_reader(schema_ptr s,
dht::decorated_key dk,
query::clustering_key_filter_ranges&& crr,
lw_shared_ptr<read_context> ctx,
lw_shared_ptr<partition_snapshot> 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)
, _tombstones(*_schema)
, _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() override;
virtual ~cache_flat_mutation_reader() {
maybe_merge_versions(_snp, _lsa_manager.region(), _lsa_manager.read_section());
}
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&) override {
clear_buffer();
_end_of_stream = true;
return make_ready_future<>();
}
virtual future<> fast_forward_to(position_range pr) override {
throw std::bad_function_call();
}
};
inline
future<> cache_flat_mutation_reader::process_static_row() {
if (_snp->version()->partition().static_row_continuous()) {
_read_context->cache().on_row_hit();
row sr = _lsa_manager.run_in_read_section([this] {
return _snp->static_row();
});
if (!sr.empty()) {
push_mutation_fragment(mutation_fragment(static_row(std::move(sr))));
}
return make_ready_future<>();
} else {
_read_context->cache().on_row_miss();
return _read_context->get_next_fragment().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
future<> cache_flat_mutation_reader::fill_buffer() {
if (_state == state::before_static_row) {
auto after_static_row = [this] {
if (_ck_ranges_curr == _ck_ranges_end) {
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();
};
if (_schema->has_static_columns()) {
return process_static_row().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] {
return do_fill_buffer();
});
}
inline
future<> cache_flat_mutation_reader::do_fill_buffer() {
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)}).then([this] {
return read_from_underlying();
});
}
if (_state == state::reading_from_underlying) {
return read_from_underlying();
}
// 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());
while (!is_buffer_full() && _state == state::reading_from_cache) {
copy_from_cache_to_buffer();
if (need_preempt()) {
break;
}
}
return make_ready_future<>();
});
}
inline
future<> cache_flat_mutation_reader::read_from_underlying() {
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) {
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 (!_ck_ranges_curr->start() || _last_row.refresh(*_snp)) {
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);
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
void cache_flat_mutation_reader::maybe_update_continuity() {
if (can_populate() && (!_ck_ranges_curr->start() || _last_row.refresh(*_snp))) {
if (_next_row.is_in_latest_version()) {
clogger.trace("csm {}: mark {} continuous", this, _next_row.get_iterator_in_latest_version()->position());
_next_row.get_iterator_in_latest_version()->set_continuous(true);
} else {
// Cover entry from older version
with_allocator(_snp->region().allocator(), [&] {
auto& rows = _snp->version()->partition().clustered_rows();
rows_entry::compare less(*_schema);
auto e = alloc_strategy_unique_ptr<rows_entry>(
current_allocator().construct<rows_entry>(*_schema, _next_row.position(), is_dummy(_next_row.dummy()), is_continuous::yes));
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, e->position());
e.release();
}
});
}
} 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);
auto new_entry = alloc_strategy_unique_ptr<rows_entry>(
current_allocator().construct<rows_entry>(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) {
_read_context->cache().on_row_insert();
new_entry.release();
}
it = insert_result.first;
rows_entry& e = *it;
if (!_ck_ranges_curr->start() || _last_row.refresh(*_snp)) {
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);
});
});
}
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;
}
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);
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(*_schema, _lower_bound, _next_row_in_range ? next_lower_bound : _upper_bound)) {
add_to_buffer(std::move(rts));
if (is_buffer_full()) {
return;
}
}
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() {
drain_tombstones();
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);
_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);
});
_last_row = partition_snapshot_row_weakref(*_snp, it);
} 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::drain_tombstones(position_in_partition_view pos) {
while (true) {
reserve_one();
auto mfo = _tombstones.get_next(pos);
if (!mfo) {
break;
}
push_mutation_fragment(std::move(*mfo));
}
}
inline
void cache_flat_mutation_reader::drain_tombstones() {
while (true) {
reserve_one();
auto mfo = _tombstones.get_next();
if (!mfo) {
break;
}
push_mutation_fragment(std::move(*mfo));
}
}
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());
}
}
// 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 key = row.key();
try {
drain_tombstones(row.position());
push_mutation_fragment(std::move(mf));
_lower_bound = position_in_partition::after_key(std::move(key));
} catch (...) {
// We may have emitted some of the range tombstones which start after the old _lower_bound
_lower_bound = position_in_partition::for_key(std::move(key));
throw;
}
}
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
if (!rt.trim_front(*_schema, _lower_bound)) {
return;
}
_lower_bound = position_in_partition(rt.position());
_tombstones.apply(std::move(rt));
drain_tombstones(_lower_bound);
}
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_row_insert();
_lsa_manager.run_in_update_section_with_allocator([&] {
_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,
lw_shared_ptr<partition_snapshot> 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

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright (C) 2015 Cloudius Systems, Ltd.
*/
/*
@@ -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

@@ -22,7 +22,6 @@
#include "canonical_mutation.hh"
#include "mutation.hh"
#include "mutation_partition_serializer.hh"
#include "counters.hh"
#include "converting_mutation_partition_applier.hh"
#include "hashing_partition_visitor.hh"
#include "utils/UUID.hh"
@@ -45,7 +44,7 @@ canonical_mutation::canonical_mutation(const mutation& m)
mutation_partition_serializer part_ser(*m.schema(), m.partition());
bytes_ostream out;
ser::writer_of_canonical_mutation<bytes_ostream> wr(out);
ser::writer_of_canonical_mutation wr(out);
std::move(wr).write_table_id(m.schema()->id())
.write_schema_version(m.schema()->version())
.write_key(m.key())

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*
*/

View File

@@ -1,566 +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 <boost/intrusive/unordered_set.hpp>
#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 "streamed_mutation.hh"
#include "mutation_partition.hh"
class cells_range {
using ids_vector_type = small_vector<column_id, 5>;
position_in_partition_view _position;
ids_vector_type _ids;
public:
using iterator = ids_vector_type::iterator;
using const_iterator = ids_vector_type::const_iterator;
cells_range()
: _position(position_in_partition_view(position_in_partition_view::static_row_tag_t())) { }
explicit cells_range(position_in_partition_view pos, const row& cells)
: _position(pos)
{
_ids.reserve(cells.size());
cells.for_each_cell([this] (auto id, auto&&) {
_ids.emplace_back(id);
});
}
position_in_partition_view position() const { return _position; }
bool empty() const { return _ids.empty(); }
auto begin() const { return _ids.begin(); }
auto end() const { return _ids.end(); }
};
class partition_cells_range {
const mutation_partition& _mp;
public:
class iterator {
const mutation_partition& _mp;
stdx::optional<mutation_partition::rows_type::const_iterator> _position;
cells_range _current;
public:
explicit iterator(const mutation_partition& mp)
: _mp(mp)
, _current(position_in_partition_view(position_in_partition_view::static_row_tag_t()), mp.static_row())
{ }
iterator(const mutation_partition& mp, mutation_partition::rows_type::const_iterator it)
: _mp(mp)
, _position(it)
{ }
iterator& operator++() {
if (!_position) {
_position = _mp.clustered_rows().begin();
} else {
++(*_position);
}
if (_position != _mp.clustered_rows().end()) {
auto it = *_position;
_current = cells_range(position_in_partition_view(position_in_partition_view::clustering_row_tag_t(), it->key()),
it->row().cells());
}
return *this;
}
iterator operator++(int) {
iterator it(*this);
operator++();
return it;
}
cells_range& operator*() {
return _current;
}
cells_range* operator->() {
return &_current;
}
bool operator==(const iterator& other) const {
return _position == other._position;
}
bool operator!=(const iterator& other) const {
return !(*this == other);
}
};
public:
explicit partition_cells_range(const mutation_partition& mp) : _mp(mp) { }
iterator begin() const {
return iterator(_mp);
}
iterator end() const {
return iterator(_mp, _mp.clustered_rows().end());
}
};
class locked_cell;
struct cell_locker_stats {
uint64_t lock_acquisitions = 0;
uint64_t operations_waiting_for_lock = 0;
};
class cell_locker {
public:
using timeout_clock = lowres_clock;
private:
using semaphore_type = basic_semaphore<default_timeout_exception_factory, timeout_clock>;
class partition_entry;
struct cell_address {
position_in_partition position;
column_id id;
};
class cell_entry : public bi::unordered_set_base_hook<bi::link_mode<bi::auto_unlink>>,
public enable_lw_shared_from_this<cell_entry> {
partition_entry& _parent;
cell_address _address;
semaphore_type _semaphore { 0 };
friend class cell_locker;
public:
cell_entry(partition_entry& parent, position_in_partition position, column_id id)
: _parent(parent)
, _address { std::move(position), id }
{ }
// Upgrades cell_entry to another schema.
// Changes the value of cell_address, so cell_entry has to be
// temporarily removed from its parent partition_entry.
// Returns true if the cell_entry still exist in the new schema and
// should be reinserted.
bool upgrade(const schema& from, const schema& to, column_kind kind) noexcept {
auto& old_column_mapping = from.get_column_mapping();
auto& column = old_column_mapping.column_at(kind, _address.id);
auto cdef = to.get_column_definition(column.name());
if (!cdef) {
return false;
}
_address.id = cdef->id;
return true;
}
const position_in_partition& position() const {
return _address.position;
}
future<> lock(timeout_clock::time_point _timeout) {
return _semaphore.wait(_timeout);
}
void unlock() {
_semaphore.signal();
}
~cell_entry() {
if (!is_linked()) {
return;
}
unlink();
if (!--_parent._cell_count) {
delete &_parent;
}
}
class hasher {
const schema* _schema; // pointer instead of reference for default assignment
public:
explicit hasher(const schema& s) : _schema(&s) { }
size_t operator()(const cell_address& ca) const {
fnv1a_hasher hasher;
ca.position.feed_hash(hasher, *_schema);
::feed_hash(hasher, ca.id);
return hasher.finalize();
}
size_t operator()(const cell_entry& ce) const {
return operator()(ce._address);
}
};
class equal_compare {
position_in_partition::equal_compare _cmp;
private:
bool do_compare(const cell_address& a, const cell_address& b) const {
return a.id == b.id && _cmp(a.position, b.position);
}
public:
explicit equal_compare(const schema& s) : _cmp(s) { }
bool operator()(const cell_address& ca, const cell_entry& ce) const {
return do_compare(ca, ce._address);
}
bool operator()(const cell_entry& ce, const cell_address& ca) const {
return do_compare(ca, ce._address);
}
bool operator()(const cell_entry& a, const cell_entry& b) const {
return do_compare(a._address, b._address);
}
};
};
class partition_entry : public bi::unordered_set_base_hook<bi::link_mode<bi::auto_unlink>> {
using cells_type = bi::unordered_set<cell_entry,
bi::equal<cell_entry::equal_compare>,
bi::hash<cell_entry::hasher>,
bi::constant_time_size<false>>;
static constexpr size_t initial_bucket_count = 16;
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;
friend class cell_entry;
private:
static constexpr size_t compute_rehash_at_size(size_t bucket_count) {
return bucket_count * max_load_factor::num / max_load_factor::den;
}
void maybe_rehash() {
if (_cell_count >= _rehash_at_size) {
auto new_bucket_count = std::min(_cells.bucket_count() * 2, _cells.bucket_count() + 1024);
auto buckets = std::make_unique<cells_type::bucket_type[]>(new_bucket_count);
_cells.rehash(cells_type::bucket_traits(buckets.get(), new_bucket_count));
_buckets = std::move(buckets);
_rehash_at_size = compute_rehash_at_size(new_bucket_count);
}
}
public:
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),
cell_entry::hasher(*s), cell_entry::equal_compare(*s))
, _schema(s)
{ }
~partition_entry() {
if (is_linked()) {
_parent._partition_count--;
}
}
// Upgrades partition entry to new schema. Returns false if all
// cell_entries has been removed during the upgrade.
bool upgrade(schema_ptr new_schema);
void insert(lw_shared_ptr<cell_entry> cell) {
_cells.insert(*cell);
_cell_count++;
maybe_rehash();
}
cells_type& cells() {
return _cells;
}
struct hasher {
size_t operator()(const dht::decorated_key& dk) const {
return std::hash<dht::decorated_key>()(dk);
}
size_t operator()(const partition_entry& pe) const {
return operator()(pe._key);
}
};
class equal_compare {
dht::decorated_key_equals_comparator _cmp;
public:
explicit equal_compare(const schema& s) : _cmp(s) { }
bool operator()(const dht::decorated_key& dk, const partition_entry& pe) {
return _cmp(dk, pe._key);
}
bool operator()(const partition_entry& pe, const dht::decorated_key& dk) {
return _cmp(dk, pe._key);
}
bool operator()(const partition_entry& a, const partition_entry& b) {
return _cmp(a._key, b._key);
}
};
};
using partitions_type = bi::unordered_set<partition_entry,
bi::equal<partition_entry::equal_compare>,
bi::hash<partition_entry::hasher>,
bi::constant_time_size<false>>;
static constexpr size_t initial_bucket_count = 4 * 1024;
using max_load_factor = std::ratio<3, 4>;
std::unique_ptr<partitions_type::bucket_type[]> _buckets;
partitions_type _partitions;
size_t _partition_count = 0;
size_t _rehash_at_size = compute_rehash_at_size(initial_bucket_count);
schema_ptr _schema;
// 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:
struct locker;
static constexpr size_t compute_rehash_at_size(size_t bucket_count) {
return bucket_count * max_load_factor::num / max_load_factor::den;
}
void maybe_rehash() {
if (_partition_count >= _rehash_at_size) {
auto new_bucket_count = std::min(_partitions.bucket_count() * 2, _partitions.bucket_count() + 64 * 1024);
auto buckets = std::make_unique<partitions_type::bucket_type[]>(new_bucket_count);
_partitions.rehash(partitions_type::bucket_traits(buckets.get(), new_bucket_count));
_buckets = std::move(buckets);
_rehash_at_size = compute_rehash_at_size(new_bucket_count);
}
}
public:
explicit cell_locker(schema_ptr s, cell_locker_stats& stats)
: _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() {
assert(_partitions.empty());
}
void set_schema(schema_ptr s) {
_schema = s;
}
schema_ptr schema() const {
return _schema;
}
// 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,
timeout_clock::time_point timeout);
};
class locked_cell {
lw_shared_ptr<cell_locker::cell_entry> _entry;
public:
explicit locked_cell(lw_shared_ptr<cell_locker::cell_entry> entry)
: _entry(std::move(entry)) { }
locked_cell(const locked_cell&) = delete;
locked_cell(locked_cell&&) = default;
~locked_cell() {
if (_entry) {
_entry->unlock();
}
}
};
struct cell_locker::locker {
cell_entry::hasher _hasher;
cell_entry::equal_compare _eq_cmp;
partition_entry& _partition_entry;
partition_cells_range _range;
partition_cells_range::iterator _current_ck;
cells_range::const_iterator _current_cell;
timeout_clock::time_point _timeout;
std::vector<locked_cell> _locks;
cell_locker_stats& _stats;
private:
void update_ck() {
if (!is_done()) {
_current_cell = _current_ck->begin();
}
}
future<> lock_next();
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, timeout_clock::time_point timeout)
: _hasher(s)
, _eq_cmp(s)
, _partition_entry(pe)
, _range(std::move(range))
, _current_ck(_range.begin())
, _timeout(timeout)
, _stats(st)
{
update_ck();
}
locker(const locker&) = delete;
locker(locker&&) = delete;
future<> lock_all() {
// Cannot defer before first call to lock_next().
return lock_next().then([this] {
return do_until([this] { return is_done(); }, [this] {
return lock_next();
});
});
}
std::vector<locked_cell> get() && { return std::move(_locks); }
};
inline
future<std::vector<locked_cell>> cell_locker::lock_cells(const dht::decorated_key& dk, partition_cells_range&& range, timeout_clock::time_point timeout) {
partition_entry::hasher pe_hash;
partition_entry::equal_compare pe_eq(*_schema);
auto it = _partitions.find(dk, pe_hash, pe_eq);
std::unique_ptr<partition_entry> partition;
if (it == _partitions.end()) {
partition = std::make_unique<partition_entry>(_schema, *this, dk);
} else if (!it->upgrade(_schema)) {
partition = std::unique_ptr<partition_entry>(&*it);
_partition_count--;
_partitions.erase(it);
}
if (partition) {
std::vector<locked_cell> locks;
for (auto&& r : range) {
if (r.empty()) {
continue;
}
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));
}
}
if (!locks.empty()) {
_partitions.insert(*partition.release());
_partition_count++;
maybe_rehash();
}
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 f = l->lock_all();
return f.then([l = std::move(l)] {
return std::move(*l).get();
});
}
inline
future<> cell_locker::locker::lock_next() {
while (!is_done()) {
if (_current_cell == _current_ck->end()) {
++_current_ck;
update_ck();
continue;
}
auto cid = *_current_cell++;
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++;
_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));
}
return make_ready_future<>();
}
inline
bool cell_locker::partition_entry::upgrade(schema_ptr new_schema) {
if (_schema == new_schema) {
return true;
}
auto buckets = std::make_unique<cells_type::bucket_type[]>(_cells.bucket_count());
auto cells = cells_type(cells_type::bucket_traits(buckets.get(), _cells.bucket_count()),
cell_entry::hasher(*new_schema), cell_entry::equal_compare(*new_schema));
_cells.clear_and_dispose([&] (cell_entry* cell_ptr) noexcept {
auto& cell = *cell_ptr;
auto kind = cell.position().is_static_row() ? column_kind::static_column
: column_kind::regular_column;
auto reinsert = cell.upgrade(*_schema, *new_schema, kind);
if (reinsert) {
cells.insert(cell);
} else {
_cell_count--;
}
});
// bi::unordered_set move assignment is actually a swap.
// Original _buckets cannot be destroyed before the container using them is
// so we need to explicitly make sure that the original _cells is no more.
_cells = std::move(cells);
auto destroy = [] (auto) { };
destroy(std::move(cells));
_buckets = std::move(buckets);
_schema = new_schema;
return _cell_count;
}

View File

@@ -1,151 +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 "seastar/core/file.hh"
#include "disk-error-handler.hh"
class checked_file_impl : public file_impl {
public:
checked_file_impl(const io_error_handler& error_handler, file f)
: _error_handler(error_handler), _file(f) {
_memory_dma_alignment = f.memory_dma_alignment();
_disk_read_dma_alignment = f.disk_read_dma_alignment();
_disk_write_dma_alignment = f.disk_write_dma_alignment();
}
virtual future<size_t> write_dma(uint64_t pos, const void* buffer, size_t len, const io_priority_class& pc) override {
return do_io_check(_error_handler, [&] {
return get_file_impl(_file)->write_dma(pos, buffer, len, pc);
});
}
virtual future<size_t> write_dma(uint64_t pos, std::vector<iovec> iov, const io_priority_class& pc) override {
return do_io_check(_error_handler, [&] {
return get_file_impl(_file)->write_dma(pos, iov, pc);
});
}
virtual future<size_t> read_dma(uint64_t pos, void* buffer, size_t len, const io_priority_class& pc) override {
return do_io_check(_error_handler, [&] {
return get_file_impl(_file)->read_dma(pos, buffer, len, pc);
});
}
virtual future<size_t> read_dma(uint64_t pos, std::vector<iovec> iov, const io_priority_class& pc) override {
return do_io_check(_error_handler, [&] {
return get_file_impl(_file)->read_dma(pos, iov, pc);
});
}
virtual future<> flush(void) override {
return do_io_check(_error_handler, [&] {
return get_file_impl(_file)->flush();
});
}
virtual future<struct stat> stat(void) override {
return do_io_check(_error_handler, [&] {
return get_file_impl(_file)->stat();
});
}
virtual future<> truncate(uint64_t length) override {
return do_io_check(_error_handler, [&] {
return get_file_impl(_file)->truncate(length);
});
}
virtual future<> discard(uint64_t offset, uint64_t length) override {
return do_io_check(_error_handler, [&] {
return get_file_impl(_file)->discard(offset, length);
});
}
virtual future<> allocate(uint64_t position, uint64_t length) override {
return do_io_check(_error_handler, [&] {
return get_file_impl(_file)->allocate(position, length);
});
}
virtual future<uint64_t> size(void) override {
return do_io_check(_error_handler, [&] {
return get_file_impl(_file)->size();
});
}
virtual future<> close() override {
return do_io_check(_error_handler, [&] {
return get_file_impl(_file)->close();
});
}
// returns a handle for plain file, so make_checked_file() should be called
// on file returned by handle.
virtual std::unique_ptr<seastar::file_handle_impl> dup() override {
return get_file_impl(_file)->dup();
}
virtual subscription<directory_entry> list_directory(std::function<future<> (directory_entry de)> next) override {
return do_io_check(_error_handler, [&] {
return get_file_impl(_file)->list_directory(next);
});
}
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;
};
inline file make_checked_file(const io_error_handler& error_handler, file f)
{
return file(::make_shared<checked_file_impl>(error_handler, f));
}
future<file>
inline open_checked_file_dma(const io_error_handler& error_handler,
sstring name, open_flags flags,
file_open_options options = {})
{
return do_io_check(error_handler, [&] {
return open_file_dma(name, flags, options).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)
{
return do_io_check(error_handler, [&] {
return engine().open_directory(name).then([&] (file f) {
return make_ready_future<file>(make_checked_file(error_handler, f));
});
});
}

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

@@ -1,156 +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 "keys.hh"
#include "schema.hh"
#include "range.hh"
/**
* Represents the kind of bound in a range tombstone.
*/
enum class bound_kind : uint8_t {
excl_end = 0,
incl_start = 1,
// values 2 to 5 are reserved for forward Origin compatibility
incl_end = 6,
excl_start = 7,
};
std::ostream& operator<<(std::ostream& out, const bound_kind k);
bound_kind invert_kind(bound_kind k);
int32_t weight(bound_kind k);
class bound_view {
public:
const static thread_local clustering_key empty_prefix;
const clustering_key_prefix& prefix;
bound_kind kind;
bound_view(const clustering_key_prefix& prefix, bound_kind kind)
: prefix(prefix)
, kind(kind)
{ }
bound_view(const bound_view& other) noexcept = default;
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.
std::reference_wrapper<const schema> _s;
tri_compare(const schema& s) : _s(s)
{ }
int operator()(const clustering_key_prefix& p1, int32_t w1, const clustering_key_prefix& p2, int32_t w2) const {
auto type = _s.get().clustering_key_prefix_type();
auto res = prefix_equality_tri_compare(type->types().begin(),
type->begin(p1), type->end(p1),
type->begin(p2), type->end(p2),
::tri_compare);
if (res) {
return res;
}
auto d1 = p1.size(_s);
auto d2 = p2.size(_s);
if (d1 == d2) {
return w1 - w2;
}
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);
}
int operator()(const clustering_key_prefix& p, const bound_view b) const {
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));
}
};
struct compare {
// To make it assignable and to avoid taking a schema_ptr, we
// wrap the schema reference.
tri_compare _cmp;
compare(const schema& s) : _cmp(s)
{ }
bool operator()(const clustering_key_prefix& p1, int32_t w1, const clustering_key_prefix& p2, int32_t w2) const {
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);
}
bool operator()(const clustering_key_prefix& p, const bound_view b) const {
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));
}
};
bool equal(const schema& s, const bound_view other) const {
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.equal(s, other.prefix);
}
static bound_view bottom() {
return {empty_prefix, bound_kind::incl_start};
}
static bound_view top() {
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 == &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.view(), inclusive)};
}
friend std::ostream& operator<<(std::ostream& out, const bound_view& b) {
return out << "{bound: prefix=" << b.prefix << ", kind=" << b.kind << "}";
}
};

View File

@@ -1,68 +0,0 @@
/*
* 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 "schema.hh"
#include "query-request.hh"
namespace query {
class clustering_key_filter_ranges {
clustering_row_ranges _storage;
const clustering_row_ranges& _ref;
public:
clustering_key_filter_ranges(const clustering_row_ranges& ranges) : _ref(ranges) { }
struct reversed { };
clustering_key_filter_ranges(reversed, const clustering_row_ranges& ranges)
: _storage(ranges.rbegin(), ranges.rend()), _ref(_storage) { }
clustering_key_filter_ranges(clustering_key_filter_ranges&& other) noexcept
: _storage(std::move(other._storage))
, _ref(&other._ref == &other._storage ? _storage : other._ref)
{ }
clustering_key_filter_ranges& operator=(clustering_key_filter_ranges&& other) noexcept {
if (this != &other) {
this->~clustering_key_filter_ranges();
new (this) clustering_key_filter_ranges(std::move(other));
}
return *this;
}
auto begin() const { return _ref.begin(); }
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);
if (slice.options.contains(query::partition_slice::option::reversed)) {
return clustering_key_filter_ranges(clustering_key_filter_ranges::reversed{}, ranges);
}
return clustering_key_filter_ranges(ranges);
}
};
}

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 "streamed_mutation.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

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright (C) 2015 Cloudius Systems, Ltd.
*/
/*

View File

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*
@@ -21,12 +21,7 @@
#pragma once
#include "sstables/shared_sstable.hh"
#include "exceptions/exceptions.hh"
class column_family;
class schema;
using schema_ptr = lw_shared_ptr<const schema>;
namespace sstables {
@@ -35,15 +30,12 @@ enum class compaction_strategy_type {
major,
size_tiered,
leveled,
date_tiered,
time_window,
// FIXME: Add support to DateTiered.
};
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;
@@ -57,22 +49,7 @@ 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);
// 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);
// Return if parallel compaction is allowed by strategy.
bool parallel_compaction() const;
// Return if optimization to rule out sstables based on clustering key filter should be applied.
bool use_clustering_key_filter() const;
// An estimation of number of compaction for strategy to be satisfied.
int64_t estimated_pending_compactions(column_family& cf) const;
compaction_descriptor get_sstables_for_compaction(column_family& cfs, std::vector<lw_shared_ptr<sstable>> candidates);
static sstring name(compaction_strategy_type type) {
switch (type) {
@@ -84,10 +61,6 @@ public:
return "SizeTieredCompactionStrategy";
case compaction_strategy_type::leveled:
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");
}
@@ -104,10 +77,6 @@ public:
return compaction_strategy_type::size_tiered;
} else if (short_name == "LeveledCompactionStrategy") {
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));
}
@@ -118,8 +87,6 @@ public:
sstring name() const {
return name(type());
}
sstable_set make_sstable_set(schema_ptr schema) const;
};
// Creates a compaction_strategy object from one of the strategies available.

View File

@@ -1,67 +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 <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

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright (C) 2015 Cloudius Systems, Ltd.
*/
/*
@@ -22,7 +22,7 @@
#pragma once
#include "types.hh"
#include <iosfwd>
#include <iostream>
#include <algorithm>
#include <vector>
#include <boost/range/iterator_range.hpp>
@@ -130,10 +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;
@@ -220,9 +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

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright 2015 Cloudius Systems
*/
/*
@@ -21,10 +21,7 @@
#pragma once
#include <boost/range/algorithm/copy.hpp>
#include <boost/range/adaptor/transformed.hpp>
#include "compound.hh"
#include "schema.hh"
//
// This header provides adaptors between the representation used by our compound_type<>
@@ -183,422 +180,3 @@ bytes to_legacy(CompoundType& type, bytes_view packed) {
std::copy(lv.begin(), lv.end(), legacy_form.begin());
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:
//
// <representation> ::= ( <component> )+
// <component> ::= <length> <value> <EOC>
// <length> ::= <uint16_t>
// <EOC> ::= <uint8_t>
//
// If false, then it encodes a single value, without a prefix length or a suffix EOC.
class composite final {
bytes _bytes;
bool _is_compound;
public:
composite(bytes&& b, bool is_compound)
: _bytes(std::move(b))
, _is_compound(is_compound)
{ }
explicit composite(bytes&& b)
: _bytes(std::move(b))
, _is_compound(true)
{ }
composite()
: _bytes()
, _is_compound(true)
{ }
using size_type = uint16_t;
using eoc_type = int8_t;
/*
* The 'end-of-component' byte should always be 0 for actual column name.
* However, it can set to 1 for query bounds. This allows to query for the
* equivalent of 'give me the full range'. That is, if a slice query is:
* start = <3><"foo".getBytes()><0>
* end = <3><"foo".getBytes()><1>
* then we'll return *all* the columns whose first component is "foo".
* If for a component, the 'end-of-component' is != 0, there should not be any
* following component. The end-of-component can also be -1 to allow
* non-inclusive query. For instance:
* end = <3><"foo".getBytes()><-1>
* allows to query everything that is smaller than <3><"foo".getBytes()>, but
* not <3><"foo".getBytes()> itself.
*/
enum class eoc : eoc_type {
start = -1,
none = 0,
end = 1
};
using component = std::pair<bytes, eoc>;
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) {
return val.size();
}
static size_t size(const data_value& val) {
return val.serialized_size();
}
template<typename Value, typename = std::enable_if_t<!std::is_same<data_value, std::decay_t<Value>>::value>>
static void write_value(Value&& val, bytes::iterator& out) {
out = std::copy(val.begin(), val.end(), out);
}
static void write_value(const data_value& val, bytes::iterator& out) {
val.serialize(out);
}
template<typename RangeOfSerializedComponents>
static void serialize_value(RangeOfSerializedComponents&& values, bytes::iterator& out, bool is_compound) {
if (!is_compound) {
auto it = values.begin();
write_value(std::forward<decltype(*it)>(*it), out);
return;
}
for (auto&& val : values) {
write<size_type>(out, static_cast<size_type>(size(val)));
write_value(std::forward<decltype(val)>(val), out);
// Range tombstones are not keys. For collections, only frozen
// values can be keys. Therefore, for as long as it is safe to
// assume that this code will be used to create keys, it is safe
// to assume the trailing byte is always zero.
write<eoc_type>(out, eoc_type(eoc::none));
}
}
template <typename RangeOfSerializedComponents>
static size_t serialized_size(RangeOfSerializedComponents&& values, bool is_compound) {
size_t len = 0;
auto it = values.begin();
if (it != values.end()) {
// CQL3 uses a specific prefix (0xFFFF) to encode "static columns"
// (CASSANDRA-6561). This does mean the maximum size of the first component of a
// composite is 65534, not 65535 (or we wouldn't be able to detect if the first 2
// bytes is the static prefix or not).
auto value_size = size(*it);
if (value_size > static_cast<size_type>(std::numeric_limits<size_type>::max() - uint8_t(is_compound))) {
throw std::runtime_error(sprint("First component size too large: %d > %d", value_size, std::numeric_limits<size_type>::max() - is_compound));
}
if (!is_compound) {
return value_size;
}
len += sizeof(size_type) + value_size + sizeof(eoc_type);
++it;
}
for ( ; it != values.end(); ++it) {
auto value_size = size(*it);
if (value_size > std::numeric_limits<size_type>::max()) {
throw std::runtime_error(sprint("Component size too large: %d > %d", value_size, std::numeric_limits<size_type>::max()));
}
len += sizeof(size_type) + value_size + sizeof(eoc_type);
}
return len;
}
public:
template <typename Describer>
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) {
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);
}
class iterator : public std::iterator<std::input_iterator_tag, const component_view> {
bytes_view _v;
component_view _current;
private:
void read_current() {
size_type len;
{
if (_v.empty()) {
_v = bytes_view(nullptr, 0);
return;
}
len = read_simple<size_type>(_v);
if (_v.size() < len) {
throw marshal_exception();
}
}
auto value = bytes_view(_v.begin(), len);
_v.remove_prefix(len);
_current = component_view(std::move(value), to_eoc(read_simple<eoc_type>(_v)));
}
public:
struct end_iterator_tag {};
iterator(const bytes_view& v, bool is_compound, bool is_static)
: _v(v) {
if (is_static) {
_v.remove_prefix(2);
}
if (is_compound) {
read_current();
} else {
_current = component_view(_v, eoc::none);
_v.remove_prefix(_v.size());
}
}
iterator(end_iterator_tag) : _v(nullptr, 0) {}
iterator& operator++() {
read_current();
return *this;
}
iterator operator++(int) {
iterator i(*this);
++(*this);
return i;
}
const value_type& operator*() const { return _current; }
const value_type* operator->() const { return &_current; }
bool operator!=(const iterator& i) const { return _v.begin() != i._v.begin(); }
bool operator==(const iterator& i) const { return _v.begin() == i._v.begin(); }
};
iterator begin() const {
return iterator(_bytes, _is_compound, is_static());
}
iterator end() const {
return iterator(iterator::end_iterator_tag());
}
boost::iterator_range<iterator> components() const & {
return { begin(), end() };
}
auto values() const & {
return components() | boost::adaptors::transformed([](auto&& c) { return c.first; });
}
std::vector<component> components() const && {
std::vector<component> result;
std::transform(begin(), end(), std::back_inserter(result), [](auto&& p) {
return component(bytes(p.first.begin(), p.first.end()), p.second);
});
return result;
}
std::vector<bytes> values() const && {
std::vector<bytes> result;
boost::copy(components() | boost::adaptors::transformed([](auto&& c) { return to_bytes(c.first); }), std::back_inserter(result));
return result;
}
const bytes& get_bytes() const {
return _bytes;
}
bytes release_bytes() && {
return std::move(_bytes);
}
size_t size() const {
return _bytes.size();
}
bool empty() const {
return _bytes.empty();
}
static bool is_static(bytes_view bytes, bool is_compound) {
return is_compound && bytes.size() > 2 && (bytes[0] & bytes[1] & 0xff) == 0xff;
}
bool is_static() const {
return is_static(_bytes, _is_compound);
}
bool is_compound() const {
return _is_compound;
}
template <typename ClusteringElement>
static composite from_clustering_element(const schema& s, const ClusteringElement& ce) {
return serialize_value(ce.components(s), s.is_compound());
}
static composite from_exploded(const std::vector<bytes_view>& v, bool is_compound, eoc marker = eoc::none) {
if (v.size() == 0) {
return composite(bytes(size_t(1), bytes::value_type(marker)), is_compound);
}
return serialize_value(v, is_compound, marker);
}
static composite static_prefix(const schema& s) {
return serialize_static(s, std::vector<bytes_view>());
}
explicit operator bytes_view() const {
return _bytes;
}
template <typename Component>
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 {
bytes_view _bytes;
bool _is_compound;
public:
composite_view(bytes_view b, bool is_compound = true)
: _bytes(b)
, _is_compound(is_compound)
{ }
composite_view(const composite& c)
: composite_view(static_cast<bytes_view>(c), c.is_compound())
{ }
composite_view()
: _bytes(nullptr, 0)
, _is_compound(true)
{ }
std::vector<bytes_view> explode() const {
if (!_is_compound) {
return { _bytes };
}
std::vector<bytes_view> ret;
ret.reserve(8);
for (auto it = begin(), e = end(); it != e; ) {
ret.push_back(it->first);
auto marker = it->second;
++it;
if (it != e && marker != composite::eoc::none) {
throw runtime_exception(sprint("non-zero component divider found (%d) mid", sprint("0x%02x", composite::eoc_type(marker) & 0xff)));
}
}
return ret;
}
composite::iterator begin() const {
return composite::iterator(_bytes, _is_compound, is_static());
}
composite::iterator end() const {
return composite::iterator(composite::iterator::end_iterator_tag());
}
boost::iterator_range<composite::iterator> components() const {
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; });
}
size_t size() const {
return _bytes.size();
}
bool empty() const {
return _bytes.empty();
}
bool is_static() const {
return composite::is_static(_bytes, _is_compound);
}
explicit operator bytes_view() const {
return _bytes;
}
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

@@ -1,5 +1,5 @@
/*
* Copyright (C) 2015 ScyllaDB
* Copyright (C) 2015 Cloudius Systems, Ltd.
*/
/*
@@ -32,24 +32,24 @@ enum class compressor {
class compression_parameters {
public:
static constexpr int32_t DEFAULT_CHUNK_LENGTH = 4 * 1024;
static constexpr int32_t DEFAULT_CHUNK_LENGTH = 64 * 1024;
static constexpr double DEFAULT_CRC_CHECK_CHANCE = 1.0;
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 _compressor;
compressor _compressor = compressor::none;
std::experimental::optional<int> _chunk_length;
std::experimental::optional<double> _crc_check_chance;
public:
compression_parameters(compressor c = compressor::lz4) : _compressor(c) { }
compression_parameters() = default;
compression_parameters(compressor c) : _compressor(c) { }
compression_parameters(const std::map<sstring, sstring>& options) {
validate_options(options);
auto it = options.find(SSTABLE_COMPRESSION);
if (it == options.end() || it->second.empty()) {
_compressor = compressor::none;
return;
}
const auto& compressor_class = it->second;

View File

@@ -1,2 +0,0 @@
[housekeeping]
check-version: True

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
@@ -87,26 +85,10 @@ 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
@@ -124,19 +106,6 @@ write_request_timeout_in_ms: 2000
# most users should never need to adjust this.
# phi_convict_threshold: 8
# IEndpointSnitch. The snitch has two functions:
# - it teaches Scylla enough about your network topology to route
# requests efficiently
# - it allows Scylla to spread replicas around your cluster to avoid
# correlated failures. It does this by grouping machines into
# "datacenters" and "racks." Scylla will do its best not to have
# more than one replica on the same "rack" (which may not actually
# be a physical location)
#
# IF YOU CHANGE THE SNITCH AFTER DATA IS INSERTED INTO THE CLUSTER,
# YOU MUST RUN A FULL REPAIR, SINCE THE SNITCH AFFECTS WHERE REPLICAS
# ARE PLACED.
#
# Out of the box, Scylla provides
# - SimpleSnitch:
# Treats Strategy order as proximity. This can improve cache
@@ -210,27 +179,10 @@ 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}.
#
# - AllowAllAuthenticator performs no checks - set it to disable authentication.
# - PasswordAuthenticator relies on username/password pairs to authenticate
# users. It keeps usernames and hashed passwords in system_auth.credentials table.
# Please increase system_auth keyspace replication factor if you use this authenticator.
# authenticator: AllowAllAuthenticator
# Authorization backend, implementing IAuthorizer; used to limit access/provide permissions
# Out of the box, Scylla provides org.apache.cassandra.auth.{AllowAllAuthorizer,
# CassandraAuthorizer}.
#
# - AllowAllAuthorizer allows any action to any user - set it to disable authorization.
# - CassandraAuthorizer stores permissions in system_auth.permissions table. Please
# increase system_auth keyspace replication factor if you use this authorizer.
# authorizer: AllowAllAuthorizer
###################################################
## Not currently supported, reserved for future use
###################################################
# initial_token allows you to specify tokens manually. While you can use # it with
# vnodes (num_tokens > 1, above) -- in which case you should provide a
@@ -238,19 +190,6 @@ batch_size_fail_threshold_in_kb: 50
# that do not have vnodes enabled.
# initial_token:
# RPC address to broadcast to drivers and other Scylla nodes. This cannot
# be set to 0.0.0.0. If left blank, this will be set to the value of
# rpc_address. If rpc_address is set to 0.0.0.0, broadcast_rpc_address must
# be set.
# broadcast_rpc_address: 1.2.3.4
# Uncomment to enable experimental features
# experimental: true
###################################################
## 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
# of data centers to enable per-datacenter.
@@ -277,19 +216,38 @@ batch_size_fail_threshold_in_kb: 50
# reduced proportionally to the number of nodes in the cluster.
# batchlog_replay_throttle_in_kb: 1024
# Authentication backend, identifying users
# Out of the box, Scylla provides org.apache.cassandra.auth.{AllowAllAuthenticator,
# PasswordAuthenticator}.
#
# - AllowAllAuthenticator performs no checks - set it to disable authentication.
# - PasswordAuthenticator relies on username/password pairs to authenticate
# users. It keeps usernames and hashed passwords in system_auth.credentials table.
# Please increase system_auth keyspace replication factor if you use this authenticator.
# authenticator: AllowAllAuthenticator
# Authorization backend, implementing IAuthorizer; used to limit access/provide permissions
# Out of the box, Scylla provides org.apache.cassandra.auth.{AllowAllAuthorizer,
# CassandraAuthorizer}.
#
# - AllowAllAuthorizer allows any action to any user - set it to disable authorization.
# - CassandraAuthorizer stores permissions in system_auth.permissions table. Please
# increase system_auth keyspace replication factor if you use this authorizer.
# authorizer: AllowAllAuthorizer
# 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
@@ -303,6 +261,28 @@ 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
@@ -417,6 +397,29 @@ partitioner: org.apache.cassandra.dht.Murmur3Partitioner
# the smaller of 1/4 of heap or 512MB.
# file_cache_size_in_mb: 512
# Total permitted memory to use for memtables. Scylla will stop
# accepting writes when the limit is exceeded until a flush completes,
# and will trigger a flush based on memtable_cleanup_threshold
# If omitted, Scylla will set both to 1/4 the size of the heap.
# memtable_heap_space_in_mb: 2048
# memtable_offheap_space_in_mb: 2048
# Ratio of occupied non-flushing memtable size to total permitted size
# that will trigger a flush of the largest memtable. Lager mct will
# mean larger flushes and hence less compaction, but also less concurrent
# flush activity which can make it difficult to keep your disks fed
# under heavy write load.
#
# memtable_cleanup_threshold defaults to 1 / (memtable_flush_writers + 1)
# memtable_cleanup_threshold: 0.11
# Specify the way Scylla allocates and manages memtable memory.
# Options are:
# heap_buffers: on heap nio buffers
# offheap_buffers: off heap (direct) nio buffers
# offheap_objects: native memory, eliminating nio buffer heap overhead
# memtable_allocation_type: heap_buffers
# Total space to use for commitlogs.
#
# If space gets above this value (it will round up to the next nearest
@@ -428,6 +431,17 @@ partitioner: org.apache.cassandra.dht.Murmur3Partitioner
# available for Scylla.
commitlog_total_space_in_mb: -1
# This sets the amount of memtable flush writer threads. These will
# be blocked by disk io, and each one will hold a memtable in memory
# while blocked.
#
# memtable_flush_writers defaults to the smaller of (number of disks,
# number of cores), with a minimum of 2 and a maximum of 8.
#
# If your data directories are backed by SSD, you should increase this
# to the number of cores.
#memtable_flush_writers: 8
# A fixed memory pool size in MB for for SSTable index summaries. If left
# empty, this will default to 5% of the heap size. If the memory usage of
# all index summaries exceeds this limit, SSTables with low read rates will
@@ -492,6 +506,13 @@ commitlog_total_space_in_mb: -1
# Whether to start the thrift rpc server.
# start_rpc: true
# RPC address to broadcast to drivers and other Scylla nodes. This cannot
# be set to 0.0.0.0. If left blank, this will be set to the value of
# rpc_address. If rpc_address is set to 0.0.0.0, broadcast_rpc_address must
# be set.
# broadcast_rpc_address: 1.2.3.4
# enable or disable keepalive on rpc/native connections
# rpc_keepalive: true
@@ -659,6 +680,58 @@ commitlog_total_space_in_mb: -1
# Default value is 0, which never timeout streams.
# streaming_socket_timeout_in_ms: 0
# endpoint_snitch -- Set this to a class that implements
# IEndpointSnitch. The snitch has two functions:
# - it teaches Scylla enough about your network topology to route
# requests efficiently
# - it allows Scylla to spread replicas around your cluster to avoid
# correlated failures. It does this by grouping machines into
# "datacenters" and "racks." Scylla will do its best not to have
# more than one replica on the same "rack" (which may not actually
# be a physical location)
#
# IF YOU CHANGE THE SNITCH AFTER DATA IS INSERTED INTO THE CLUSTER,
# YOU MUST RUN A FULL REPAIR, SINCE THE SNITCH AFFECTS WHERE REPLICAS
# ARE PLACED.
#
# Out of the box, Scylla provides
# - SimpleSnitch:
# Treats Strategy order as proximity. This can improve cache
# locality when disabling read repair. Only appropriate for
# single-datacenter deployments.
# - GossipingPropertyFileSnitch
# This should be your go-to snitch for production use. The rack
# and datacenter for the local node are defined in
# cassandra-rackdc.properties and propagated to other nodes via
# gossip. If cassandra-topology.properties exists, it is used as a
# fallback, allowing migration from the PropertyFileSnitch.
# - PropertyFileSnitch:
# Proximity is determined by rack and data center, which are
# explicitly configured in cassandra-topology.properties.
# - Ec2Snitch:
# Appropriate for EC2 deployments in a single Region. Loads Region
# and Availability Zone information from the EC2 API. The Region is
# treated as the datacenter, and the Availability Zone as the rack.
# Only private IPs are used, so this will not work across multiple
# Regions.
# - Ec2MultiRegionSnitch:
# Uses public IPs as broadcast_address to allow cross-region
# connectivity. (Thus, you should set seed addresses to the public
# IP as well.) You will need to open the storage_port or
# ssl_storage_port on the public IP firewall. (For intra-Region
# traffic, Scylla will switch to the private IP after
# establishing a connection.)
# - RackInferringSnitch:
# Proximity is determined by rack and data center, which are
# assumed to correspond to the 3rd and 2nd octet of each node's IP
# address, respectively. Unless this happens to match your
# deployment conventions, this is best used as an example of
# writing a custom Snitch class and is provided in that spirit.
#
# You can use a custom Snitch by setting this to the full class name
# of the snitch, which will be assumed to be on your classpath.
# controls how often to perform the more expensive part of host score
# calculation
# dynamic_snitch_update_interval_in_ms: 100
@@ -729,24 +802,29 @@ 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.
# can be: all - all traffic is compressed
# dc - traffic between different datacenters is compressed
# none - nothing is compressed.
# internode_compression: none
# internode_compression: all
# Enable or disable tcp_nodelay for inter-dc communication.
# Disabling it will result in larger (but fewer) network packets being sent,
@@ -767,41 +845,3 @@ commitlog_total_space_in_mb: -1
# true: relaxed environment checks; performance and reliability may degraade.
#
# developer_mode: false
# Idle-time background processing
#
# Scylla can perform certain jobs in the background while the system is otherwise idle,
# freeing processor resources when there is other work to be done.
#
# defragment_memory_on_idle: true
#
# prometheus port
# By default, Scylla opens prometheus API port on port 9180
# setting the port to 0 will disable the prometheus API.
# prometheus_port: 9180
#
# prometheus address
# By default, Scylla binds all interfaces to the prometheus API
# It is possible to restrict the listening address to a specific one
# prometheus_address: 0.0.0.0
# Distribution of data among cores (shards) within a node
#
# Scylla distributes data within a node among shards, using a round-robin
# strategy:
# [shard0] [shard1] ... [shardN-1] [shard0] [shard1] ... [shardN-1] ...
#
# Scylla versions 1.6 and below used just one repetition of the pattern;
# this intefered with data placement among nodes (vnodes).
#
# Scylla versions 1.7 and above use 4096 repetitions of the pattern; this
# provides for better data distribution.
#
# the value below is log (base 2) of the number of repetitions.
#
# Set to 0 to avoid rewriting all data when upgrading from Scylla 1.6 and
# below.
#
# Keep at 12 for new clusters.
murmur3_partitioner_ignore_msb_bits: 12

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