Commit Graph

465 Commits

Author SHA1 Message Date
Xiaoxi Wang e94de126de merge with master 2020-08-14 01:59:09 +00:00
Xiaoxi Wang 8f1deaa47e Merge branch 'master' of https://github.com/apple/foundationdb 2020-08-12 23:32:23 +00:00
Xin Dong b17667323e Resolve review comments 2020-08-12 15:15:25 -07:00
Xin Dong 3ac6996844 Increased some knobs to throttle the spammy read hot logging. Also added more details inside the read hot log to make it useful 2020-08-12 14:27:34 -07:00
Xiaoxi Wang 7ee6ca342e merge with master 2020-08-11 01:01:15 +00:00
Xiaoxi Wang cae6f04070 sample on cost instead of bytes 2020-08-10 22:30:06 +00:00
Meng Xu 87bde08695 FR:fix:sending samples may have broken promise error
The error should not skip the ack reply from loader to controller, saying
the file has been loaded.
Otherwise, restore controller can get stuck at waiting for the ack reply.
2020-08-06 10:41:18 -07:00
Meng Xu fe5902994c
Merge pull request #3605 from apple/release-6.3
Merge Release 6.3 to master
2020-08-05 23:37:44 -07:00
Meng Xu 7992cef025 FR:Fix sample network pkg can be too big 2020-08-04 22:35:21 -07:00
Xiaoxi Wang d1cc87452c merge with master; solve conflicts; solve initialization; 2020-08-02 22:44:07 +00:00
Xiaoxi Wang 0352e8ee0b pick busiest commit tag periodically 2020-08-02 18:38:56 +00:00
Meng Xu 2f5293fcc7 Introduce knob FASTRESTORE_USE_LOG_FILE and FASTRESTORE_USE_RANGE_FILE 2020-07-31 10:40:29 -07:00
Meng Xu 8cace30bb2 FastRestore:change TXN_BATCH_MAX_BYTES default to 1KB from 1MB 2020-07-30 16:43:35 -07:00
Meng Xu ad915e462e Add knob FASTRESTORE_NOT_WRITE_DB to skip writting to DB 2020-07-30 10:17:17 -07:00
Evan Tschannen a49cb41de7 Merge branch 'release-6.3'
# Conflicts:
#	CMakeLists.txt
#	cmake/ConfigureCompiler.cmake
#	fdbserver/Knobs.cpp
#	fdbserver/StorageCache.actor.cpp
#	fdbserver/storageserver.actor.cpp
#	flow/ThreadHelper.actor.h
#	flow/serialize.h
#	tests/CMakeLists.txt
2020-07-29 00:31:55 -07:00
Evan Tschannen c3348be3a0 changed knobs to improve master recovery speeds 2020-07-27 10:59:06 -07:00
Evan Tschannen 937df4f839 Merge branch 'release-6.3' of github.com:apple/foundationdb into feature-lifetimetoken-fix
# Conflicts:
#	documentation/sphinx/source/release-notes/release-notes-630.rst
2020-07-27 10:03:02 -07:00
Xin Dong 2ac7df8a18
Merge pull request #3563 from xumengpanda/mengxu/fr-filesize-PR
FastRestore:Add trace for file size and bc progress
2020-07-25 20:08:57 -07:00
Meng Xu 99d8399f4e FastRestore:Add trace for file size and bc progress 2020-07-25 19:12:25 -07:00
Evan Tschannen be67e9cfc7 wait for the correct cluster controller interface before starting master recovery 2020-07-20 11:29:37 -07:00
Steve Atherton e646361501 Merge branch 'release-6.3' of github.com:apple/foundationdb into feature-redwood 2020-07-20 07:25:29 -07:00
Steve Atherton d05b7ee785 Pager remap remover now accumulates a configurable version interval of page updates behind the oldest retained version which are used to coalesce updates to the same original page ID to reduce write amplification for many workloads. 2020-07-20 04:08:33 -07:00
Meng Xu ef8c1060a2 Merge branch 'master' into mengxu/tmp-merge-6.3 2020-07-13 10:15:56 -07:00
A.J. Beamon b09dddc07e Merge branch 'release-6.2' into merge-release-6.2-into-release-6.3
# Conflicts:
#	cmake/ConfigureCompiler.cmake
#	documentation/sphinx/source/downloads.rst
#	fdbrpc/FlowTransport.actor.cpp
#	fdbrpc/fdbrpc.vcxproj
#	fdbserver/DataDistributionQueue.actor.cpp
#	fdbserver/Knobs.cpp
#	fdbserver/Knobs.h
#	fdbserver/LogSystemPeekCursor.actor.cpp
#	fdbserver/MasterProxyServer.actor.cpp
#	fdbserver/Status.actor.cpp
#	fdbserver/storageserver.actor.cpp
#	flow/flow.vcxproj
2020-07-10 15:06:34 -07:00
Evan Tschannen 4492a50e72 Merge branch 'release-6.2' of github.com:apple/foundationdb into feature-ha-fixes
# Conflicts:
#	documentation/sphinx/source/mr-status-json-schemas.rst.inc
#	documentation/sphinx/source/mr-status.rst
#	fdbclient/Schemas.cpp
2020-07-10 10:37:43 -07:00
A.J. Beamon 28b6281848 Increase latency sample size by a factor of 10. 2020-07-10 08:52:59 -07:00
Evan Tschannen dd10dbe7c7 Merge branch 'release-6.2' of github.com:apple/foundationdb into feature-ha-fixes 2020-07-09 23:09:14 -07:00
Evan Tschannen 717242a0ee reset WAN network connections every 5 minutes is responses take more than 500ms 2020-07-09 22:50:47 -07:00
A.J. Beamon 04d1217941 Track statistics about server-side request latency on each process, to include min, max, mean, and various percentiles. 2020-07-09 16:39:15 -07:00
Evan Tschannen 0e2f5e8bb5 Added a flow lock to prevent too many source server fetches from happening at the same time and running the data distributor out of memory 2020-07-09 10:38:19 -07:00
Young Liu 7546ed3edf Remove trace events 2020-07-02 15:17:11 -07:00
Young Liu ed89d69916 Change order between reporting commit version and setting committedVersion 2020-07-02 15:13:28 -07:00
Young Liu ab95de6e1e Add a warning message 2020-06-30 17:43:07 -07:00
Young Liu e613d85895 Fix errors in joshua related to PR_3307 2020-06-30 17:22:59 -07:00
Meng Xu f3302833ce
Merge pull request #3435 from apple/release-6.3
Merge Release 6.3 to master
2020-06-30 10:08:28 -07:00
Meng Xu efb61bcac0 Rename knob to FASTRESTORE_TXN_EXTRA_DELAY 2020-06-29 21:16:30 -07:00
Meng Xu 4b35685e99 FastRestore:Adjust knob based on circus test 2020-06-29 10:13:18 -07:00
Meng Xu 78c45c1200 Knob for txn delay and add back FlowLock to control txn concurrency 2020-06-27 10:13:34 -07:00
Young Liu f211a54593 Merged from upstream master 2020-06-13 16:47:12 -07:00
A.J. Beamon 739767b838 Delay cluster controller candidacy for all worst fit processes, not just storage servers. 2020-06-10 09:59:56 -07:00
Steve Atherton c3c7db6a9d Added flowlock around reads done on the write path so that those reads cannot starve reads to support reads done by the storage server. 2020-06-09 17:00:21 -07:00
Young Liu a038a02cdd Serve GetReadVersion through master 2020-06-09 11:16:23 -07:00
A.J. Beamon d128252e90 Merge release-6.3 into master 2020-05-22 09:25:32 -07:00
Meng Xu c0c15130b8
Merge pull request #3172 from jzhou77/backup-fix
Limit memory usage of backup workers
2020-05-20 15:46:11 -07:00
Steve Atherton 4a827c9304 Merge branch 'release-6.3' of github.com:apple/foundationdb into feature-redwood 2020-05-19 03:08:26 -07:00
Steve Atherton e8626724f9 More refactor of Redwood metrics. Added per-level BTree stats. Added Pager total physical disk reads/writes, and uncacheable read hit/miss counts. Added logging to TraceEvents. 2020-05-16 02:51:57 -07:00
Jingyu Zhou 89ae1200dd Increase backup worker memory buffer size in simulation
Lower limit causes backup worker to become stuck.
2020-05-15 09:45:52 -07:00
Steve Atherton 32f4639168 Refactored page remap removal. The process is now called remap cleanup, does batches of remap entries in parallel, coalesces remaps of the same page ID to skip unnecessary writes, and has some knobs for controlling it. FIFOQueue now has peek() to support remap cleanup version lag limits. Added counters for remap cleanup and lazy subtree deletion. Refactored Redwood counters, normalized and grouped their names. 2020-05-15 02:10:51 -07:00
Jingyu Zhou 17915e13b0 Limit memory usage of backup workers 2020-05-14 13:24:56 -07:00
Steve Atherton 421a6581c1 Lazy delete cycles now run more often and not just when the btree is having mutations actively merged into it. Specifically, it is launched upon recovery, then stopped and relaunched after every commit. This will make better use of I/O in between calls to commit(). Also added knobs to control lazy delete cycle parallelism and work limits. 2020-05-13 02:27:03 -07:00