Commit Graph

424 Commits

Author SHA1 Message Date
sfc-gh-ngoyal 693d9e8b89
Merge branch 'master' into fdb_cache_wo_allocator 2020-06-09 15:09:58 -07:00
negoyal cf13e00a8f Merge remote-tracking branch 'origin/release-6.3' into fdb_cache_wo_allocator 2020-06-01 17:38:31 -07:00
Meng Xu 1c35ad884f Merge branch 'master' into mengxu/release-6.3-conflict-PR
Has conflict with master;
Next commit will fix the conflicts.
2020-05-25 12:01:49 -07:00
Evan Tschannen ee6ff80064 another compile fix 2020-05-22 17:26:22 -07:00
Evan Tschannen ced65cd30b finished explicitly versioning everything stored in the database 2020-05-22 17:14:21 -07:00
A.J. Beamon 7a09d016a6 Merge branch 'release-6.3' into merge-release6.3-into-master 2020-05-19 12:52:44 -07:00
Markus Pilman c2bc75516f Merge branch 'release-6.3' of github.com:apple/foundationdb into features/trace-roles 2020-05-14 10:34:53 -07:00
Alvin Moore a160f9199f
Merge pull request #3171 from apple/release-6.3
Merge Release 6.3 into Master
2020-05-14 10:00:47 -07:00
Alex Miller bf6d056095 Changing the last suggestions from review. 2020-05-13 18:48:43 -07:00
Alex Miller ccaac162e2 Resolve performance concerns of nearly-no-op debugMutation being frequently called
This introduces unhygenic macro variants that inline a `ENABLED &&`
before the TraceEvent.  This way, they get entirely compiled out unless
enabled.

Then rewrite all debugMutation uses via sed.
2020-05-13 18:44:15 -07:00
Alex Miller 27da91ab9e Merge remote-tracking branch 'upstream/master' into mutation-debugging 2020-05-13 12:51:44 -07:00
Alex Miller f148412a32 Make UPDATE_STORAGE_BYTE_LIMIT the reference spill variety.
Which is unrelated, but a change I was supposed to do a while ago and
forgot.
2020-05-12 16:59:20 -07:00
Markus Pilman 5f9b127e56 Emit traces regularly about role assignment
We are currently emitting Role transition traces when a role starts and
when it ends. While this is useful for debugging, it doesn't work well
with tools that inject data and might potentially miss some trace lines.

We do decorate each trace lines with the roles assigned to that
particular process, however, this is not sufficient for tools that can
make use of the UID -> Role mapping
2020-05-08 16:27:57 -07:00
negoyal dd033736ed Merge branch 'master' into fdb_cache_subfeature2 2020-05-04 17:29:43 -07:00
Evan Tschannen 7cebe743f9 A number of bug fixes of rare correctness errors 2020-04-29 13:50:13 -07:00
Evan Tschannen c87aa33941 Merge branch 'release-6.2'
# Conflicts:
#	CMakeLists.txt
#	bindings/go/src/fdb/generated.go
#	documentation/sphinx/source/api-common.rst.inc
#	documentation/sphinx/source/api-ruby.rst
#	documentation/sphinx/source/release-notes.rst
#	fdbclient/FailureMonitorClient.actor.cpp
#	fdbclient/NativeAPI.actor.cpp
#	fdbclient/vexillographer/fdb.options
#	fdbrpc/FlowTransport.actor.cpp
#	fdbserver/OldTLogServer_6_0.actor.cpp
#	fdbserver/TLogServer.actor.cpp
#	fdbserver/fdbserver.actor.cpp
#	versions.target
2020-04-23 13:47:53 -07:00
Evan Tschannen 0a1b2a572f more compile fixes 2020-04-22 14:41:17 -07:00
Evan Tschannen 68906bf3c3 fix compile errors 2020-04-22 14:36:41 -07:00
Evan Tschannen d0cc2a1ee4 added logging for parallel peeks on TLogs 2020-04-22 14:24:45 -07:00
Alex Miller 122762cce1 Add debugMessagesAndTags, and track mutations in more places.
Like:
* Leaving the proxy
* Entering the TLog
* Leaving the TLog
* Being read on a cursor

All of this brought to you by TagsAndMessage!

This also slides in a minor optimization as to how mutations are serialized per target log.
2020-03-27 03:31:04 -07:00
negoyal acaf91ac47 Merge branch 'master' into fdb_cache_subfeature2 2020-03-26 13:33:08 -07:00
negoyal 8abac91033 Fixed a bug in cache server while peeking at a version lower than popped version and added some logging. 2020-03-26 12:39:07 -07:00
Evan Tschannen e08f0201f1 merge release 6.2 into master 2020-03-17 12:51:47 -07:00
Evan Tschannen ea98c7a40a added additional timeout on initPersistentState 2020-03-16 11:38:14 -07:00
Evan Tschannen d6d347f665 treat a tlog which takes a long time to create its disk queue as failed 2020-03-13 10:31:59 -07:00
Evan Tschannen 96258b9809 Merge branch 'release-6.2'
# Conflicts:
#	documentation/sphinx/source/release-notes.rst
#	fdbcli/fdbcli.actor.cpp
#	fdbclient/ManagementAPI.actor.cpp
#	fdbrpc/FlowTransport.actor.cpp
#	fdbserver/ClusterController.actor.cpp
#	fdbserver/DataDistribution.actor.cpp
#	fdbserver/DataDistribution.actor.h
#	fdbserver/DataDistributionQueue.actor.cpp
#	fdbserver/KeyValueStoreMemory.actor.cpp
#	fdbserver/MasterProxyServer.actor.cpp
#	fdbserver/QuietDatabase.actor.cpp
#	fdbserver/SkipList.cpp
#	fdbserver/StorageMetrics.actor.h
#	fdbserver/TLogServer.actor.cpp
#	fdbserver/fdbserver.actor.cpp
#	fdbserver/storageserver.actor.cpp
#	fdbserver/workloads/KVStoreTest.actor.cpp
#	flow/CMakeLists.txt
#	flow/Knobs.cpp
#	flow/Knobs.h
#	flow/genericactors.actor.cpp
#	flow/serialize.h
2020-02-21 19:09:16 -08:00
Evan Tschannen 8129f74a10
Merge pull request #2698 from etschannen/feature-recruit-delay
The CC waits until no new workers register before starting a bad recruitment
2020-02-20 14:42:37 -08:00
A.J. Beamon fcbdcda490
Merge pull request #2650 from ajbeamon/fix-reverse-range-read-byte-limit-bug
Fix reverse range read performance bug
2020-02-20 12:47:17 -08:00
Evan Tschannen fbd45963d8 The cluster controller waits until no new workers register for 1.0 before starting a bad recruitment 2020-02-19 16:48:30 -08:00
A.J. Beamon 1d9140d874 Removed TLogVersion logging.
Added logging of SharedTLog ID for each TLog.
Switched ID logged for TLogRejoining event to the TLog instead of the SharedTLog.
Made some parameters to startRole passed by reference.
2020-02-14 12:33:43 -08:00
A.J. Beamon 56053c565b Improve TLog "Role" event by adding the worker ID, the TLog version, and under what circumstances the TLog is being started (Restored, Recruited, or Recovered).
The SharedTLog role was being started and stopped twice, so remove one instance of it.
2020-02-12 15:11:38 -08:00
Markus Pilman e71fe44ee3
Merge branch 'master' into features/icc 2020-02-08 21:33:02 -08:00
A.J. Beamon df2b0452b4 Step 3 of fixing storage server range reads: change return type of readRange from VectorRef<KeyValueRef> to RangeResultRef. 2020-02-06 13:19:24 -08:00
mpilman d09e07f1f5 Merge remote-tracking branch 'upstream/master' into features/icc 2020-02-04 10:26:18 -08:00
Jingyu Zhou 7544ff88d9 Comment out frequent TLogPop trace event 2020-01-31 19:29:09 -08:00
Evan Tschannen 6c0b934dda
Merge pull request #2242 from alexmiller-apple/fix-10min-stall-again
Fix the 10min multi-region recovery stall again
2020-01-23 17:53:02 -08:00
Jingyu Zhou 8b67a89eed More review comments fixed. 2020-01-22 19:42:13 -08:00
Jingyu Zhou 9d7a1a77d0 Small fixes. 2020-01-22 19:38:45 -08:00
Jingyu Zhou 85c4a4e422 Address review comments for PR #1625 2020-01-22 19:38:45 -08:00
Jingyu Zhou 73824faf65 Track pseudo tags popping for individual IDs
For each log router ID, we track the popped version of each pseudo tag so that
the popping only applied to the minimum of these versions.

Also add more tracing for popping and epochs.
2020-01-22 19:38:45 -08:00
Jingyu Zhou 11964733b7 WIP: should be divided into smaller commits. 2020-01-22 19:38:45 -08:00
Jingyu Zhou 03a17a30ef Refactor: check displacement in LogSystemConfig 2020-01-22 19:38:45 -08:00
Jingyu Zhou 442738b6db Small code refactoring 2020-01-22 19:35:30 -08:00
Jingyu Zhou 8221d33eb1 Use emplace_back instead of push_back for TLogServer 2020-01-22 19:35:30 -08:00
Alex Miller f0fe62a298 TLogs should not respond with data earlier than the begin version
Parallel peek more code would prefer the begin version it was sent by
the previous parallel peek over the request's begin version.  This means
that a merge cursor trying to advance past message versions would still
get old data that it would have to filter out.

A simple application of std::max fixes this.
2020-01-21 19:09:07 -08:00
Alex Miller 7798456201 Make TLogs have consistent parallel peek behavior.
TLogServer and LogRouter had some leftover code from me trying to be
more "correct" about parallel peek semantics, but those changes weren't
reflected in the OldTLog* files.  I've reverted the changes, as
realistically, they are more likely to waste CPU than improve TLog behavior.
2020-01-21 18:23:16 -08:00
Alex Miller ffc3506fff Continuing a parallel peek after a timeout would hang. 2020-01-21 17:12:18 -08:00
Alex Miller 9c47bbe460 Remove trackerData time bump
As we're in an error handling case, so this shouldn't be considered
making forward progress.
2020-01-21 17:08:42 -08:00
Alex Miller 1cb311fcb8 Add an ASSERT_WE_THINK that peek cursors don't get timed_out()
This should prevent us from regressing and having multi-region
recoveries hang for 10min again.
2020-01-21 17:07:37 -08:00
Evan Tschannen 3f9d9d8b84 Merge branch 'release-6.2'
# Conflicts:
#	CMakeLists.txt
#	cmake/FlowCommands.cmake
#	documentation/sphinx/source/release-notes.rst
#	fdbclient/StorageServerInterface.h
#	fdbserver/DataDistributionTracker.actor.cpp
#	fdbserver/MasterProxyServer.actor.cpp
#	fdbserver/fdbserver.actor.cpp
#	flow/Knobs.h
#	flow/Platform.cpp
#	versions.target
2020-01-16 18:37:47 -08:00