Commit Graph

290 Commits

Author SHA1 Message Date
Xiaoxi Wang 73c7240bfd code format 2022-04-26 17:34:34 -07:00
Xiaoxi Wang 9b211c48ee format code 2022-04-26 17:13:37 -07:00
Xiaoxi Wang 8cc6d9aaac determine timeThrottle and topK dynamically on the shard number 2022-04-25 16:59:20 -07:00
Xiaoxi Wang cc05f5e9db fix getMetrics keys bug 2022-04-24 21:21:18 -07:00
Xiaoxi Wang a0b45c2962 fix throttle bug 2022-04-24 15:51:18 -07:00
Xiaoxi Wang eefd0778c5 change canQueue to timeThrottle() 2022-04-22 15:26:44 -07:00
Xiaoxi Wang 4818f01de9 fix top10 shard index bug; add event detail; fix merge conflict 2022-04-22 14:14:58 -07:00
Xiaoxi Wang 0639810b66 merge upstream/main 2022-04-22 11:09:15 -07:00
Xiaoxi Wang eb949ee3dc change default shard size; enable valley filler best; top 10 random choice 2022-04-22 10:07:12 -07:00
Xiaoxi Wang 04311d001e topK shard random selection 2022-04-21 22:37:16 -07:00
Xiaoxi Wang 960a13f233 format 2022-04-21 21:40:49 -07:00
Xiaoxi Wang f9e57396e2 completeDest 2022-04-21 21:23:42 -07:00
Xiaoxi Wang a8bfd0f481 move canQueue, 60s each source server, random select portion of shards/destServer 2022-04-20 23:12:34 -07:00
Xiaoxi Wang af9e5ba885 move canQueue, 60s each source server, random select portion of shards 2022-04-20 22:19:56 -07:00
Xiaoxi Wang 131adec811 add canQueue 2022-04-20 15:28:03 -07:00
Xiaoxi Wang 25e1e75d9e enable destComplete 2022-04-20 13:32:04 -07:00
Xiaoxi Wang e0ae0942c4 fix inflight read division; temp destComplete fix; 0.1 constant poll time 2022-04-20 12:15:40 -07:00
Xiaoxi Wang a7a9de781e update unittests 2022-04-16 22:51:55 -07:00
Xiaoxi Wang 7b9432bdda revert to original BgDDValleyFiller and BgDDMountainChopper for disk rebalance 2022-04-12 18:01:28 -07:00
Xiaoxi Wang 8d3f851495 merge upstream/mainA 2022-04-12 17:03:09 -07:00
Xiaoxi Wang ed97a35dc0 Merge branch 'main' into readaware 2022-04-12 16:47:15 -07:00
Xiaoxi Wang 5e96bacb5b add new priority in RelocateData 2022-04-12 16:22:17 -07:00
Xiaoxi Wang 61a1f7683b fix dd command line read special key space error 2022-04-11 22:49:21 -07:00
Xiaoxi Wang 6c841cd32b merge readaware-better 2022-04-11 17:09:39 -07:00
Bharadwaj V.R 129a7b5daf Use boolean-param for GetTeamRequest params 2022-04-11 13:27:08 -07:00
Xiaoxi Wang 411550580e merge 2022-04-08 11:49:33 -07:00
Xiaoxi Wang 7c83f63e46 fix substraction bug; test1,2,3 generate good result 2022-04-08 10:44:56 -07:00
sfc-gh-tclinkenbeard e27b0d9ab5 Merge remote-tracking branch 'origin/main' into improve-snapshot-fault-tolerance 2022-04-07 23:30:16 -07:00
sfc-gh-tclinkenbeard 91930b8040 Remove getMinReplicasRemaining PromiseStream.
Instead, in order to enforce the maximum fault tolerance for snapshots,
update getStorageWorkers to return the number of unavailable storage
servers (instead of throwing an error when unavailable storage servers
exist).
2022-04-07 23:23:23 -07:00
Xiaoxi Wang c858b0eaa9 update penalty, reset sim skip to 3; add read_underutil to relocator priority 2022-04-07 11:59:40 -07:00
Xiaoxi Wang 6fa60a2cf9 fix substraction typo 2022-04-06 23:03:25 -07:00
Xiaoxi Wang 150b4318aa refactor datadistribution command; try dual-mode code 2022-04-06 22:10:23 -07:00
Xiaoxi Wang aba9d85560 merge main 2022-04-06 09:57:52 -07:00
Xiaoxi Wang b6594aebbf change inflight substraction priority (not non-negligible performance influence 2022-04-04 11:34:41 -07:00
sfc-gh-tclinkenbeard 70f378bacc Restrict write access to getUnhealthyRelocationCount 2022-04-03 23:47:54 -07:00
sfc-gh-tclinkenbeard 253db642be Add MAX_SNAPSHOT_FAULT_TOLERANCE knob 2022-04-03 22:31:45 -07:00
Josh Slocum 9e06881673 fix destination limiting and cancelling logic in move_to_removed_server case 2022-03-31 14:05:15 -05:00
Xiaoxi Wang 20a0b8d761 enable sim skip; add readInFlight methods and inflight Penalty; add delayed inflight substraction: 2022-03-31 09:57:00 -07:00
Xiaoxi Wang b15f0eb2b0 add ReadInFlight 2022-03-28 14:20:07 -07:00
Xiaoxi Wang 25f757ba28 fix merge conflict bug caused by removal of cancellable(true) 2022-03-28 14:13:44 -07:00
Xiaoxi Wang 9799b3dc99 change teamSorter details 2022-03-24 22:20:58 -07:00
Xiaoxi Wang d93b57dd88 conflict solving 2022-03-24 20:45:51 -07:00
Xiaoxi Wang 1b631a9263 solve conflict with main 2022-03-24 16:29:11 -07:00
Trevor Clinkenbeard cc934ff1d7
Merge pull request #6632 from sfc-gh-jslocum/dd_better_cancelling
Better cancelling logic that reflects whether move has actually started
2022-03-24 16:28:01 -07:00
Xiaoxi Wang b811a62b65 fix teamSorter usage bug 2022-03-24 13:16:10 -07:00
Xiaoxi Wang 746778fa0a CPU reading 2022-03-23 11:18:58 -07:00
Xiaoxi Wang 0186e00256 set team too similar criteria for read rebalance 2022-03-22 12:01:42 -07:00
Trevor Clinkenbeard 6390d93efd
Merge pull request #6646 from sfc-gh-tclinkenbeard/fix-copyright-headers
Update copyright header dates
2022-03-21 16:49:20 -07:00
sfc-gh-tclinkenbeard a71099471b Update copyright header dates 2022-03-21 13:36:23 -07:00
sfc-gh-tclinkenbeard 305dead7f5 Merge remote-tracking branch 'origin/main' into change-rebalance-teams-signature 2022-03-18 21:12:47 -07:00
Xiaoxi Wang 4b92f8f546 add relocate reason and set teamSorter in relocator 2022-03-18 16:39:31 -07:00
sfc-gh-tclinkenbeard 4a0720e8ad Provide destTeam parameter to rebalanceTeams again.
There is a wait before the load bytes of the dest team is used, so the
last commit inadvertently caused a behaviour change. Instead, update the
comment for the function, and pass const IDataDistributionTeam
references.
2022-03-18 10:25:13 -07:00
Josh Slocum 5fbdbb5c4a Better cancelling logic that reflects whether move has actually started 2022-03-18 10:43:24 -05:00
sfc-gh-tclinkenbeard a04ca65ad5 Change signature of rebalanceTeams 2022-03-17 23:27:33 -07:00
Josh Slocum 67eba5ec7c Limiting DD Moves by destination SS. 2022-03-15 13:52:19 -05:00
Xiaoxi Wang 10eb082888 format code; fix DD ignore option bug" 2022-03-15 10:31:43 -07:00
Xiaoxi Wang d38b827906 fix DD ignore bug 2022-03-13 23:47:07 -07:00
Xiaoxi Wang 8d20ee8432 change storage metrics of read sample calculation 2022-03-07 17:36:43 -08:00
Xiaoxi Wang 970a84bf63 fix teamSorter setting 2022-03-03 12:58:45 -08:00
Xiaoxi Wang a28b0f4361 Merge branch 'main' of https://github.com/apple/foundationdb into readaware 2022-03-03 11:15:18 -08:00
Xiaoxi Wang a05f6f851a fix reference assign bug 2022-03-02 21:56:03 -08:00
Xiaoxi Wang f48ba989c3 add status 2022-03-01 15:27:27 -08:00
Xiaoxi Wang 5e74b5006e fix uninitialized member 2022-02-28 10:22:32 -08:00
Xiaoxi Wang 40a1f562a7 temporary change special key for data distributor 2022-02-25 11:01:23 -08:00
Xiaoxi Wang a07e413eae metrics comparator; rebalanceReadLoad() 2022-02-24 16:41:01 -08:00
A.J. Beamon 250a88e682 Enforce that trace event suppression calls happen first when using trace event call chaining. Fix various instances where we weren't following this requirement. 2022-02-24 12:25:52 -08:00
Evan Tschannen 1afef44f19 fix: self->shardsAffectedByTeamFailure->moveShard must be called without any waits after getting the destination team or we could miss failure notifications for the storage servers in the destination team 2021-11-23 15:26:38 -08:00
Xiaoxi Wang d1959122af consider wiggling when waitUntilHealthy 2021-10-27 09:08:37 -07:00
Chang Liu 8761960cdc fix roll trace event issue for data distribution(master)
Description

Testing
2021-09-24 15:40:17 -07:00
Chang Liu 814e3c729f fix roll trace event issue for data distribution(master)
Description

Testing
2021-09-24 15:40:17 -07:00
Chang Liu c10dd0df4b fix roll trace event issue for data distribution
Description

Testing
2021-09-24 15:40:17 -07:00
Xiaoge Su abf73047ca Enforce std:: specifier rather than using namespace 2021-09-16 19:40:28 -07:00
sfc-gh-tclinkenbeard 3442ebd3b7 Fix more -Wreorder-ctor warnings across many files 2021-07-24 11:20:51 -07:00
Daniel Smith 8efe3b296a Delete remaining extern declarations for noUnseed 2021-07-08 19:19:22 -04:00
Xiaoxi Wang 0493d149e6 wait remove 2021-06-21 05:18:42 +00:00
Xiaoxi Wang d46fccc30f Revert "Revert "Properly set simulation test for perpetual storage wiggle and bug fixing""
This reverts commit ad576e8c20.
2021-06-11 22:58:05 +00:00
Xiaoxi Wang ad576e8c20
Revert "Properly set simulation test for perpetual storage wiggle and bug fixing" 2021-06-11 09:07:45 -07:00
Xiaoxi Wang 17ac91bac4
Merge pull request #4929 from sfc-gh-xwang/ppwtest
Properly set simulation test for perpetual storage wiggle and bug fixing
2021-06-10 14:09:50 -07:00
Xiaoxi Wang 4220a548ce use the same health check as exclude to avoid 'best team get stuck' 2021-06-09 22:51:46 +00:00
sfc-gh-tclinkenbeard 371a38e6e5 Merge remote-tracking branch 'origin/master' into remove-extra-copies 2021-06-07 10:26:06 -07:00
Xiaoxi Wang 85cd2b9945 add perpetualStorageWiggler 2021-05-20 23:31:08 +00:00
sfc-gh-tclinkenbeard f28ac955c3 Remove unnecessary temporary objects while growing objects of type std::vector<std::pair<A, B>> 2021-05-10 16:32:50 -07:00
sfc-gh-tclinkenbeard 5c2d7b6080 Create RangeResult type alias 2021-05-03 13:14:16 -07:00
FDB Formatster df90cc89de apply clang-format to *.c, *.cpp, *.h, *.hpp files 2021-03-10 10:18:07 -08:00
Andrew Noyes 4ee97c0784 Use clang-tidy to automatically fix missing overrides
Use `clang-tidy -p . $file -checks='-*,modernize-use-override' -header-filter='.*' -fix`
to fix missing overrides, and then use git clang-format to reformat just
those changes. This went pretty well for most files.

Formatting the following files went off the rails, so I'm going to
follow up with a commit that's just clang-tidy and no clang-format.

- fdbclient/DatabaseBackupAgent.actor.cpp
- fdbclient/FileBackupAgent.actor.cpp
- fdbserver/OldTLogServer_4_6.actor.cpp
- fdbmonitor/SimpleIni.h
- fdbserver/workloads/ClientTransactionProfileCorrectness.actor.cpp
2021-01-26 02:04:12 +00:00
Andrew Noyes 7fbc4d7391 Resolve conflicts 2020-12-04 23:58:42 +00:00
Andrew Noyes 877997632d Merge branch 'release-6.3' into anoyes/merge-release-6.3-master
Include conflict markers for review purposes
2020-12-04 01:38:07 +00:00
Andrew Noyes dc2bac5670 Resolve conflicts 2020-11-24 19:09:42 +00:00
Andrew Noyes 1f541f02be Merge branch 'anoyes/merge-6.2-to-6.3' into anoyes/release-6.3-merge
Merge, leaving conflict markers for now
2020-11-24 16:55:34 +00:00
David Youngworth d64cf8b9e3 Merge branch 6.3 into master 2020-11-17 11:22:45 -08:00
David Youngworth 489ba20641 Fix several merge issues 2020-11-16 14:46:36 -08:00
David Youngworth d0391db862 Merge branch 'release-6.2' into release-6.3 2020-11-16 10:15:23 -08:00
Xiaoge Su 15d10d68cd Cleanup DataDistributionQueue.actor.cpp and storageserver.actor.cpp 2020-11-09 15:23:51 -08:00
Xin Dong 2909e35415 When moving dispaching shard relocations, log the source and destination storage servers. 2020-11-05 16:13:18 -08:00
Xin Dong cedcfc7d87 Removed unused uid field inside ParallelTCInfo 2020-10-26 16:48:09 -07:00
Xin Dong 9ef29d0cea Changed getTeamID() to return a string instead of UID as suggested by reviews. 2020-10-26 16:44:52 -07:00
Xin Dong 7ebb2e5c09 Piggy back this PR to polish more TraceEvent by:
- Making it clear that it's tracking machine team info or server team info
- Added ID to both machine team and server team for better trackability
- Attach distributor id to some trace events.
2020-10-26 16:44:09 -07:00
sfc-gh-tclinkenbeard e0b1f95740 Merge remote-tracking branch 'origin/master' into remove-global-ddenabled-flag 2020-10-21 18:22:08 -07:00
Young Liu 8cc3e4d3c6 Merge release-6.3 into master 2020-10-19 22:51:56 -07:00
sfc-gh-tclinkenbeard 652d753daf Remove global ddEnabled flag 2020-10-17 11:23:52 -07:00