Commit Graph

354 Commits

Author SHA1 Message Date
sdong
5aa81f04fa Fix extra compaction tasks scheduled after D16767 in some cases
Summary:
With D16767, there is a case compaction tasks are scheduled infinitely:
(1) no flush thread is configured and more than 1 compaction threads
(2) a flush is going on by one compaction hread
(3) the state of SST files is in the state that versions_->current()->NeedsCompaction() will generate a false positive (return true actually there is no work to be done)
In that case, a infinite loop will be formed.

This patch would fix it.

Test Plan: make all check

Reviewers: haobo, igor, ljin

Reviewed By: igor

CC: dhruba, yhchiang, leveldb

Differential Revision: https://reviews.facebook.net/D16863
2014-03-13 13:06:08 -07:00
Kai Liu
11da8bc5df A heuristic way to check if a memtable is full
Summary:
This is is based on https://reviews.facebook.net/D15027. It's not finished but I would like to give a prototype to avoid arena over-allocation while making better use of the already allocated memory blocks.

Instead of check approximate memtable size, we will take a deeper look at the arena, which incorporate essential idea that @sdong suggests: flush when arena has allocated its last and the last is "almost full"

Test Plan: N/A

Reviewers: haobo, sdong

Reviewed By: sdong

CC: leveldb, sdong

Differential Revision: https://reviews.facebook.net/D15051
2014-03-12 16:40:14 -07:00
Igor Canadi
45ad75db80 Correct version of D16821 2014-03-12 09:38:59 -07:00
sdong
bd45633b71 Fix data race against logging data structure because of LogBuffer
Summary:
@igor pointed out that there is a potential data race because of the way we use the newly introduced LogBuffer. After "bg_compaction_scheduled_--" or "bg_flush_scheduled_--", they can both become 0. As soon as the lock is released after that, DBImpl's deconstructor can go ahead and deconstruct all the states inside DB, including the info_log object hold in a shared pointer of the options object it keeps. At that point it is not safe anymore to continue using the info logger to write the delayed logs.

With the patch, lock is released temporarily for log buffer to be flushed before "bg_compaction_scheduled_--" or "bg_flush_scheduled_--". In order to make sure we don't miss any pending flush or compaction, a new flag bg_schedule_needed_ is added, which is set to be true if there is a pending flush or compaction but not scheduled because of the max thread limit. If the flag is set to be true, the scheduling function will be called before compaction or flush thread finishes.

Thanks @igor for this finding!

Test Plan: make all check

Reviewers: haobo, igor

Reviewed By: haobo

CC: dhruba, ljin, yhchiang, igor, leveldb

Differential Revision: https://reviews.facebook.net/D16767
2014-03-11 16:09:53 -07:00
sdong
6c66bc08d9 Temp Fix of LogBuffer flushing
Summary: To temp fix the log buffer flushing. Flush the buffer inside the lock. Clean the trunk before we find an eventual fix.

Test Plan: make all check

Reviewers: haobo, igor

Reviewed By: igor

CC: ljin, leveldb, yhchiang

Differential Revision: https://reviews.facebook.net/D16791
2014-03-11 11:37:40 -07:00
Igor Canadi
cb9802168f Add a comment after SignalAll()
Summary: Having code after SignalAll has already caused 2 bugs. Let's make sure this doesn't happen again.

Test Plan: no test

Reviewers: sdong, dhruba, haobo

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16785
2014-03-11 11:27:19 -07:00
Igor Canadi
d5de22dc09 Call PurgeObsoleteFiles() only when HaveSomethingToDelete()
Summary: as title

Test Plan: fixed the build failure http://ci-builds.fb.com/job/rocksdb_build/987/console

Reviewers: haobo

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16743
2014-03-10 15:42:14 -07:00
Haobo Xu
a91aed615a [RocksDB] Minor cleanup of PurgeObsoleteFiles
Summary: as title. also made info log output of file deletion a bit more descriptive.

Test Plan: make check; db_bench and look at LOG output

Reviewers: igor

Reviewed By: igor

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16731
2014-03-10 14:13:38 -07:00
Lei Jin
8d007b4aaf Consolidate SliceTransform object ownership
Summary:
(1) Fix SanitizeOptions() to also check HashLinkList. The current
dynamic case just happens to work because the 2 classes have the same
layout.
(2) Do not delete SliceTransform object in HashSkipListFactory and
HashLinkListFactory destructor. Reason: SanitizeOptions() enforces
prefix_extractor and SliceTransform to be the same object when
Hash**Factory is used. This makes the behavior strange: when
Hash**Factory is used, prefix_extractor will be released by RocksDB. If
other memtable factory is used, prefix_extractor should be released by
user.

Test Plan: db_bench && make asan_check

Reviewers: haobo, igor, sdong

Reviewed By: igor

CC: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D16587
2014-03-10 12:56:46 -07:00
Haobo Xu
9e0e6aa7f6 [RocksDB] make sure KSVObsolete does not get accessed as a valid pointer.
Summary: KSVObsolete is no longer nullptr and needs to be checked explicitly. Also did some minor code cleanup and added a stat counter to track superversion cleanups incurred in the foreground.

Test Plan: make check

Reviewers: ljin

Reviewed By: ljin

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16701
2014-03-10 12:55:25 -07:00
Haobo Xu
66da467983 [RocksDB] LogBuffer Cleanup
Summary: Moved LogBuffer class to an internal header. Removed some unneccesary indirection. Enabled log buffer for BackgroundCallFlush. Forced log buffer flush right after Unlock to improve time ordering of info log.

Test Plan: make check; db_bench compare LOG output

Reviewers: sdong

Reviewed By: sdong

CC: leveldb, igor

Differential Revision: https://reviews.facebook.net/D16707
2014-03-10 11:05:44 -07:00
Lei Jin
e5fa4944fc use CAS when returning SuperVersion to ThreadLocal
Summary:
Add a check at the end of GetImpl to release SuperVersion if it becomes
obsolete. Also do Scrape() inside InstallSuperVersion so it happens more
frequent.

Test Plan:
make all check
running asan_check now

Reviewers: igor, haobo, sdong, dhruba

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16641
2014-03-07 14:43:22 -08:00
Igor Canadi
eec8695206 Delete local sv when destroying DB from stress test
Summary: Not deleting local SV caused some an crash test issue: http://ci-builds.fb.com/job/rocksdb_asan_crash_test/83/console

Test Plan: ran unit tests

Reviewers: ljin

Reviewed By: ljin

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16635
2014-03-06 18:15:26 -08:00
sdong
ecb1ffa2a8 Buffer info logs when picking compactions and write them out after releasing the mutex
Summary: Now while the background thread is picking compactions, it writes out multiple info_logs, especially for universal compaction, which introduces a chance of waiting log writing in mutex, which is bad. To remove this risk, write all those info logs to a buffer and flush it after releasing the mutex.

Test Plan:
make all check
check the log lines while running some tests that trigger compactions.

Reviewers: haobo, igor, dhruba

Reviewed By: dhruba

CC: i.am.jin.lei, dhruba, yhchiang, leveldb, nkg-

Differential Revision: https://reviews.facebook.net/D16515
2014-03-05 15:36:32 -08:00
Igor Canadi
8ca30bd51b Merge pull request #47 from mlin/kCompactionStopStyleSimilarSize
An initial implementation of kCompactionStopStyleSimilarSize for universal compaction
2014-03-05 10:35:30 -08:00
sdong
e8ecca9e86 CleanupIteratorState() only to initialize DeletionState when super version cleanup needed
Summary:
Two changes:
1. DeletionState is only constructed when cleaning up is needed
2. Fix the bug of deletion state construction bug. A change was made in a previous patch: https://reviews.facebook.net/rROCKSDB774ed89c2405ee058086b099cbc8b29e243739cc#71a34e2e However, it somehow got lost when merging

Test Plan: make all check

Reviewers: kailiu, haobo, igor

Reviewed By: igor

CC: igor, dhruba, i.am.jin.lei, yhchiang, leveldb

Differential Revision: https://reviews.facebook.net/D16233
2014-03-04 20:58:20 -08:00
Igor Canadi
58ca641d53 Make Log::Reader more robust
Summary:
This diff does two things:
(1) Log::Reader does not report a corruption when the last record in a log or manifest file is truncated (meaning that log writer died in the middle of the write). Inherited the code from LevelDB: https://code.google.com/p/leveldb/source/detail?r=269fc6ca9416129248db5ca57050cd5d39d177c8#
(2) Turn off mmap writes for all writes to log and manifest files

(2) is necessary because if we use mmap writes, the last record is not truncated, but is actually filled with zeros, making checksum fail. It is hard to recover from checksum failing.

Test Plan:
Added unit tests from LevelDB
Actually recovered a "corrupted" MANIFEST file.

Reviewers: dhruba, haobo

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16119
2014-02-28 13:19:47 -08:00
Yueh-Hsuan Chiang
a77527f2af Add ReadOptions to TransactionLogIterator.
Summary:
Add an optional input parameter ReadOptions to DB::GetUpdateSince(),
which allows the verification of checksums to be disabled by setting
ReadOptions::verify_checksums to false.

Test Plan: Tests are done off-line and will not be included in the regular unit test.

Reviewers: igor

Reviewed By: igor

CC: leveldb, xjin, dhruba

Differential Revision: https://reviews.facebook.net/D16305
2014-02-28 11:50:36 -08:00
Lei Jin
ad0c3747cb cache SuperVersion in thread local storage to avoid mutex lock
Summary: as title

Test Plan:
asan_check
will post results later

Reviewers: haobo, igor, dhruba, sdong

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16257
2014-02-27 11:38:55 -08:00
Igor Canadi
4209516359 Schedule flush when waiting on flush
Summary:
This will also help with avoiding the deadlock. If a flush failed and we're waiting for a memtable to be flushed, we should schedule a new flush and hope a new one succeedes.

If paranoid_checks = false, Wait() will still hang on ENOSPC, but at least it will automatically continue when the space frees up. Current behavior both hangs and deadlocks.

Also, I renamed some 'compaction' to 'flush'. 'compaction' was leveldb way of saying things.

Test Plan: make check

Reviewers: dhruba, haobo, ljin

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16281
2014-02-25 12:04:14 -08:00
Igor Canadi
6ed450a58c DeleteFile should schedule Flush or Compaction
Summary:
More info here: https://github.com/facebook/rocksdb/issues/89
If flush fails because of ENOSPC, we have a deadlock problem. This is a quick fix that will continue the normal operation when user deletes the file and frees up the space on the device.

We need to address the issue more broadly with bg_error_ cleanup.

Test Plan: make check

Reviewers: dhruba, haobo, ljin

Reviewed By: ljin

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16275
2014-02-24 16:00:13 -08:00
sdong
e90d3f7752 First Transaction Logs Should Not Skip Storage Options Given
Summary: Currently, the first transaction log file ignore bytes_per_sync and other storage-related options. It is not consistent. Fix it.

Test Plan: make all check. See the options set in GDB.

Reviewers: haobo, kailiu

Reviewed By: haobo

CC: igor, ljin, yhchiang, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D16215
2014-02-19 10:58:39 -08:00
kailiu
63690625cd Expose the table properties to application
Summary: Provide a public API for users to access the table properties for each SSTable.

Test Plan: Added a unit tests to test the function correctness under differnet conditions.

Reviewers: haobo, dhruba, sdong

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16083
2014-02-13 16:28:21 -08:00
Siying Dong
f3ae3d07cc Add more black-box tests for PlainTable and explicitly support total order mode
Summary:
1. Add some more implementation-aware tests for PlainTable
2. move from a hard-coded one index per 16 rows in one prefix to a configurable number. Also, make hash table ratio = 0  means binary search only. Also fixes some divide 0 risks.
3. Explicitly support total order (only use binary search)
4. some code cleaning up.

Test Plan: make all check

Reviewers: haobo, kailiu

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16023
2014-02-12 17:37:22 -08:00
Igor Canadi
ca5f1a225a CompactionContext to include is_manual_compaction
Summary: Added a bit more information to compaction context, requested by internal team at FB.

Test Plan: Modified CompactionFilter test to make sure is_manual_compaction is properly set.

Reviewers: haobo

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16095
2014-02-12 12:24:18 -08:00
Lei Jin
994c327b86 IOError cleanup
Summary: Clean up IOErrors so that it only indicates errors talking to device.

Test Plan: make all check

Reviewers: igor, haobo, dhruba, emayanke

Reviewed By: igor

CC: leveldb

Differential Revision: https://reviews.facebook.net/D15831
2014-02-12 11:42:54 -08:00
Lei Jin
5fbf2ef42d preload table handle on Recover() when max_open_files == -1
Summary: This covers existing table files before DB open happens and avoids contention on table cache

Test Plan: db_test

Reviewers: haobo, sdong, igor, dhruba

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16089
2014-02-12 10:43:27 -08:00
Kai Liu
d4b789fdee Add LIBRARY back to make dbg 2014-02-10 20:15:09 -08:00
kailiu
84f8185fc0 Merge branch 'master' into performance
Conflicts:
	HISTORY.md
	db/db_impl.cc
	db/memtable.cc
2014-02-05 21:21:00 -08:00
Lei Jin
5b3b6549d6 use super_version in NewIterator() and MultiGet() function
Summary:
Use super_version insider NewIterator to avoid Ref() each component
separately under mutex
The new added bench shows NewIterator QPS increases from 515K to 719K
No meaningful improvement for multiget I guess due to its relatively small
cost comparing to 90 keys fetch in the test.

Test Plan: unit test and db_bench

Reviewers: igor, sdong

Reviewed By: igor

CC: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D15609
2014-02-03 13:13:36 -08:00
Siying Dong
d169b67680 [Performance Branch] PlainTable to encode rows with seqID 0, value type using 1 internal byte.
Summary: In PlainTable, use one single byte to represent 8 bytes of internal bytes, if seqID = 0 and it is value type (which should be common for bottom most files). It is to save 7 bytes for uncompressed cases.

Test Plan: make all check

Reviewers: haobo, dhruba, kailiu

Reviewed By: haobo

CC: igor, leveldb

Differential Revision: https://reviews.facebook.net/D15489
2014-02-03 12:19:30 -08:00
kailiu
4f6cb17bdb First phase API clean up
Summary:
Addressed all the issues in https://reviews.facebook.net/D15447.
Now most table-related modules are hidden from user land.

Test Plan: make check

Reviewers: sdong, haobo, dhruba

CC: leveldb

Differential Revision: https://reviews.facebook.net/D15525
2014-02-03 00:30:43 -08:00
Igor Canadi
dbbffbd772 Mark the log_number file number used
Summary:
VersionSet::next_file_number_ is always assumed to be strictly greater than VersionSet::log_number_. In our new recovery code, we artificially set log_number_  to be (log_number + 1), so that once we flush, we don't recover from the same log file again (this is important because of merge operator non-idempotence)

When we set VersionSet::log_number_ to (log_number + 1), we also have to mark that file number used, such that next_file_number_ is increased to a legal level. Otherwise, VersionSet might assert.

This has not be a problem so far because here's what happens:
1. assume next_file_number is 5, we're recovering log_number 10
2. in DBImpl::Recover() we call MarkFileNumberUsed with 10. This will set VersionSet::next_file_number_ to 11.
3. If there are some updates, we will call WriteTable0ForRecovery(), which will use file number 11 as a new table file and advance VersionSet::next_file_number_ to 12.
4. When we LogAndApply() with log_number 11, assertion is true: assert(11 <= 12);

However, this was a lucky occurrence. Even though this diff doesn't cause a bug, I think the issue is important to fix.

Test Plan: In column families I have different recovery logic and this code path asserted. When adding MarkFileNumberUsed(log_number + 1) assert is gone.

Reviewers: dhruba, kailiu

Reviewed By: kailiu

CC: leveldb

Differential Revision: https://reviews.facebook.net/D15783
2014-01-31 14:43:16 -08:00
Siying Dong
56bea9f80d When using Universal Compaction, Zero out seqID in the last file too
Summary: I didn't figure out the reason why the feature of zeroing out earlier sequence ID is disabled in universal compaction. I do see bottommost_level is set correctly. It should simply work if we remove the constraint of universal compaction.

Test Plan: make all check

Reviewers: haobo, dhruba, kailiu, igor

Reviewed By: dhruba

CC: leveldb

Differential Revision: https://reviews.facebook.net/D15423
2014-01-31 09:59:52 -08:00
Igor Canadi
ac92420fc5 Merge branch 'master' into performance
Conflicts:
	db/db_impl.h
2014-01-30 10:09:23 -08:00
Igor Canadi
3c0dcf0e25 InternalStatistics
Summary:
In DBImpl we keep track of some statistics internally and expose them via GetProperty(). This diff encapsulates all the internal statistics into a class InternalStatisics. Most of it is copy/paste.

Apart from cleaning up db_impl.cc, this diff is also necessary for Column families, since every column family should have its own CompactionStats, MakeRoomForWrite-stall stats, etc. It's much easier to keep track of it in every column family if it's nicely encapsulated in its own class.

Test Plan: make check

Reviewers: dhruba, kailiu, haobo, sdong, emayanke

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D15273
2014-01-29 20:40:41 -08:00
Lei Jin
d118707f8d set bg_error_ when background flush goes wrong
Summary: as title

Test Plan: unit test

Reviewers: haobo, igor, sdong, kailiu, dhruba

Reviewed By: dhruba

CC: leveldb

Differential Revision: https://reviews.facebook.net/D15435
2014-01-29 15:55:58 -08:00
kailiu
a5e220f5ef Merge branch 'master' into performance
Conflicts:
	Makefile
	db/db_impl.cc
	db/db_test.cc
	db/memtable_list.cc
	db/memtable_list.h
	table/block_based_table_reader.cc
	table/table_test.cc
	util/cache.cc
	util/coding.cc
2014-01-28 10:35:55 -08:00
Mark Callaghan
90f29ccbef Update monitoring to include average time per compaction and stall
Summary:
The new columns are msComp and msStall that provide average time per compaction and stall for that level in milliseconds.
Level  Files Size(MB) Score Time(sec)  Read(MB) Write(MB)    Rn(MB)  Rnp1(MB)  Wnew(MB) RW-Amplify Read(MB/s) Write(MB/s)      Rn     Rnp1     Wnp1     NewW    Count   msComp   msStall  Ln-stall Stall-cnt
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
  0        8       15   1.5         2         0        30         0         0        30        0.0       0.0        15.5        0        0        0        0       16      112       0.2       1.3      7568
  1        8       16   1.6         1        26        26        15        11        16        3.5      17.6        18.1        8        6       13        7        3      362       0.0       0.0         0
  2        1        2   0.0         0         0         2         0         0         2        0.0       0.0        18.4        0        0        0        0        1       50       0.0       0.0         0

Task ID: #

Blame Rev:

Test Plan:
run db_bench

Revert Plan:

Database Impact:

Memcache Impact:

Other Notes:

EImportant:

- begin *PUBLIC* platform impact section -
Bugzilla: #
- end platform impact -

Reviewers: haobo

Reviewed By: haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D15345
2014-01-27 15:06:04 -08:00
Igor Canadi
832158e7f7 Fsync directory after we create a new file
Summary:
@dhruba, I'm not sure where we need to sync the directory. I implemented the function in Env() and added the dir sync just after we close the newly created file in the builder.

Should I also add FsyncDir() to new files that get created by a compaction?

Test Plan: Confirmed that FsyncDir is returning Status::OK()

Reviewers: dhruba, haobo

Reviewed By: dhruba

CC: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D14751
2014-01-27 11:02:21 -08:00
Igor Canadi
6c2ca1d3e6 Move NeedsCompaction() from VersionSet to Version
Summary: There is no reason to have functions NeedCompaction(), MaxCompactionScore() and MaxCompactionScoreLevel() in VersionSet, since they don't access any data in VersionSet.

Test Plan: make check

Reviewers: kailiu, haobo, sdong

Reviewed By: kailiu

CC: leveldb

Differential Revision: https://reviews.facebook.net/D15333
2014-01-27 09:59:00 -08:00
Igor Canadi
f653fdcf5a Fixing iterator cleanup for Tailing iterator
Immutable tailing iterator doesn't set CleanupState::mem, so we don't
have to unref it.
2014-01-24 15:51:06 -08:00
Igor Canadi
c583157d49 MemTableListVersion
Summary:
MemTableListVersion is to MemTableList what Version is to VersionSet. I took almost the same ideas to develop MemTableListVersion. The reason is to have copying std::list done in background, while flushing, rather than in foreground (MultiGet() and NewIterator()) under a mutex! Also, whenever we copied MemTableList, we copied also some MemTableList metadata (flush_requested_, commit_in_progress_, etc.), which was wasteful.

This diff avoids std::list copy under a mutex in both MultiGet() and NewIterator(). I created a small database with some number of immutable memtables, and creating 100.000 iterators in a single-thread (!) decreased from {188739, 215703, 198028} to {154352, 164035, 159817}. A lot of the savings come from code under a mutex, so we should see much higher savings with multiple threads. Creating new iterator is very important to LogDevice team.

I also think this diff will make SuperVersion obsolete for performance reasons. I will try it in the next diff. SuperVersion gave us huge savings on Get() code path, but I think that most of the savings came from copying MemTableList under a mutex. If we had MemTableListVersion, we would never need to copy the entire object (like we still do in NewIterator() and MultiGet())

Test Plan: `make check` works. I will also do `make valgrind_check` before commit

Reviewers: dhruba, haobo, kailiu, sdong, emayanke, tnovak

Reviewed By: kailiu

CC: leveldb

Differential Revision: https://reviews.facebook.net/D15255
2014-01-24 14:52:08 -08:00
Lei Jin
aba2acb5ec CompactRange() to return status
Summary: as title

Test Plan:
make all check
What else tests shall I cover?

Reviewers: igor, haobo

CC:

Differential Revision: https://reviews.facebook.net/D15339
2014-01-23 16:41:46 -08:00
Kai Liu
054c5dda8c Merge branch 'master' into performance
Conflicts:
	db/db_impl.cc
	db/db_test.cc
	db/memtable.cc
	db/version_set.cc
	include/rocksdb/statistics.h
	util/statistics_imp.h
2014-01-23 16:32:49 -08:00
Tomislav Novak
81c9cc9b3b Tailing iterator
Summary:
This diff implements a special type of iterator that doesn't create a snapshot
(can be used to read newly inserted data) and is optimized for doing sequential
reads.

TailingIterator uses current superversion number to determine whether to
invalidate its internal iterators. If the version hasn't changed, it can often
avoid doing expensive seeks over immutable structures (sst files and immutable
memtables).

Test Plan:
* new unit tests
* running LD with this patch

Reviewers: igor, dhruba, haobo, sdong, kailiu

Reviewed By: sdong

CC: leveldb, lovro, march

Differential Revision: https://reviews.facebook.net/D15285
2014-01-23 16:26:08 -08:00
Igor Canadi
6fe9b57748 Refactor Recover() code
Summary:
This diff does two things:
* Rethinks how we call Recover() with read_only option. Before, we call it with pointer to memtable where we'd like to apply those changes to. This memtable is set in db_impl_readonly.cc and it's actually DBImpl::mem_. Why don't we just apply updates to mem_ right away? It seems more intuitive.
* Changes when we apply updates to manifest. Before, the process is to recover all the logs, flush it to sst files and then do one giant commit that atomically adds all recovered sst files and sets the next log number. This works good enough, but causes some small troubles for my column family approach, since I can't have one VersionEdit apply to more than single column family[1]. The change here is to commit the files recovered from logs right away. Here is the state of the world before the change:
1. Recover log 5, add new sst files to edit
2. Recover log 7, add new sst files to edit
3. Recover log 8, add new sst files to edit
4. Commit all added sst files to manifest and mark log files 5, 7 and 8 as recoverd (via SetLogNumber(9) function)
After the change, we'll do:
1. Recover log 5, commit the new sst files and set log 5 as recovered
2. Recover log 7, commit the new sst files and set log 7 as recovered
3. Recover log 8, commit the new sst files and set log 8 as recovered

The added (small) benefit is that if we fail after (2), the new recovery will only have to recover log 8. In previous case, we'll have to restart the recovery from the beginning. The bigger benefit will be to enable easier integration of multiple column families in Recovery code path.

[1] I'm happy to dicuss this decison, but I believe this is the cleanest way to go. It also makes backward compatibility much easier. We don't have a requirement of adding multiple column families atomically.

Test Plan: make check

Reviewers: dhruba, haobo, kailiu, sdong

Reviewed By: kailiu

CC: leveldb

Differential Revision: https://reviews.facebook.net/D15237
2014-01-22 10:45:26 -08:00
Mark Callaghan
4e8321bfea Boost access before mutex is unlocked
Summary:
This moves the use of versions_ to before the mutex is unlocked
to avoid a possible race.

Task ID: #

Blame Rev:

Test Plan:
make check

Revert Plan:

Database Impact:

Memcache Impact:

Other Notes:

EImportant:

- begin *PUBLIC* platform impact section -
Bugzilla: #
- end platform impact -

Reviewers: haobo, dhruba

Reviewed By: dhruba

CC: leveldb

Differential Revision: https://reviews.facebook.net/D15279
2014-01-17 21:32:23 -08:00
Igor Canadi
83681bf9ef Statistics code cleanup
Summary: I'm separating code-cleanup part of https://reviews.facebook.net/D14517. This will make D14517 easier to understand and this diff easier to review.

Test Plan: make check

Reviewers: haobo, kailiu, sdong, dhruba, tnovak

Reviewed By: tnovak

CC: leveldb

Differential Revision: https://reviews.facebook.net/D15099
2014-01-17 12:46:06 -08:00
Igor Canadi
8079dd5d24 Merge branch 'master' into performance 2014-01-17 12:20:07 -08:00