Summary:
Based on my recent findings (posted in our internal group), if we use fallocate without KEEP_SIZE flag, we get superior performance of fdatasync() in append-only workloads.
This diff provides an option for user to not use KEEP_SIZE flag, thus optimizing his sync performance by up to 2x-3x.
At one point we also just called posix_fallocate instead of fallocate, which isn't very fast: http://code.woboq.org/userspace/glibc/sysdeps/posix/posix_fallocate.c.html (tl;dr it manually writes out zero bytes to allocate storage). This diff also fixes that, by first calling fallocate and then posix_fallocate if fallocate is not supported.
Test Plan: make check
Reviewers: dhruba, sdong, haobo, ljin
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16761
Summary:
When the manifest is getting rolled the following happens:
1) manifest_file_number_ is assigned to a new manifest number (even though the old one is still current)
2) mutex is unlocked
3) SetCurrentFile() creates temporary file manifest_file_number_.dbtmp
4) SetCurrentFile() renames manifest_file_number_.dbtmp to CURRENT
5) mutex is locked
If FindObsoleteFiles happens between (3) and (4) it will:
1) Delete manifest_file_number_.dbtmp (because it's not in pending_outputs_)
2) Delete old manifest (because the manifest_file_number_ already points to a new one)
I introduce the concept of prev_manifest_file_number_ that will avoid the race condition.
However, we should discuss the future of MANIFEST file rolling. We found some race conditions with it last week and who knows how many more are there. Nobody is using it in production because we don't trust the implementation. Should we even support it?
Test Plan: make check
Reviewers: ljin, dhruba, haobo, sdong
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16929
Summary: Client doesn't need to know anything about ColumnFamily ID. By making WriteBatch take ColumnFamilyHandle as a parameter, we can eliminate method GetID() from ColumnFamilyHandle
Test Plan: column_family_test
Reviewers: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16887
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
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
Summary:
I'm cleaning up some code preparing for the big diff review tomorrow. This is the first part of the cleanup.
Changes are mostly cosmetic. The goal is to decrease amount of code difference between columnfamilies and master branch.
This diff also fixes race condition when dropping column family.
Test Plan: Ran db_stress with variety of parameters
Reviewers: dhruba, haobo
Differential Revision: https://reviews.facebook.net/D16833
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
Summary:
I had this diff for a while to test column families implementation. Last night, I ran it sucessfully for 10 hours with the command:
time ./db_stress --threads=30 --ops_per_thread=200000000 --max_key=5000 --column_families=20 --clear_column_family_one_in=3000000 --verify_before_write=1 --reopen=50 --max_background_compactions=10 --max_background_flushes=10 --db=/tmp/db_stress
It is ready to be committed :)
Test Plan: Ran it for 10 hours
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16797
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
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
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
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
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
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
Summary: Adding the last missing function -- NewIterators(). Pretty simple implementation
Test Plan: added a unit test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16689
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
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
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
Summary: When column family is dropped, we want to delete all WALs that refer to it. To do that, we need to make them obsolete by flushing all the memtables
Test Plan: column_family_test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16557
Summary: Added a function DeleteSuperVersion that can be called in DBImpl destructor before PurgingObsoleteFiles. That way, PurgeObsoleteFiles will be able to delete all files held by alive super versions.
Test Plan: column_family_test with valgrind
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16545
Summary:
This diff fixes two bugs:
* Increase sequence number even if WriteBatch fails. This is important because WriteBatches in WAL logs have implictly increasing sequence number, even if one update in a write batch fails. This caused some writes to get lost in my CF stress testing
* Tolerate 'invalid column family' errors on recovery. When a column family is dropped, processing WAL logs can have some WriteBatches that still refer to the dropped column family. In recovery environment, we want to ignore those errors. In client's Write() code path, however, we want to return the failure to the client if he's trying to add data to invalid column family.
Test Plan: db_stress's verification works now
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16533
Summary:
I though I might get away with as little changes to LogAndApply() as possible. It turns out this is not the case.
This diff introduces different behavior of LogAndApply() for three cases:
1. column family add
2. column family drop
3. no-column family manipulation
(1) and (2) don't support group commit yet.
There were a lot of problems with old version od LogAndApply, detected by db_stress. The biggest was non-atomicity of manifest writes and metadata changes (i.e. if column family add is in manifest, it also has to be in in-memory data structure).
Test Plan: db_stress
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16491
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
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
Summary:
This fixes few bugs with CreateColumnFamily
* We first have to LogAndApply and then call VersionSet::CreateColumnFamily. Otherwise, WriteSnapshot might be invoked, writing out column family add inside of LogAndApply, even though it's not really committed
* Fix LogAndApplyHelper() to not apply log number to column_family_data, which is in case of column family add, just a dummy (default) column family
* Create SuperVerion when creating column family
Test Plan: column_family_test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16443
Summary:
Previously, we first wrote to the manifest and then created internal data structure.
Now, we first create internal data structure. That way, we can write out internal comparator to the manifest
Test Plan: column_family_test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16425
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
Summary:
Two new column family tests:
* DifferentMergeOperators -- three column families, one without merge operator, one with add operator and one with append operator. verify that operations work as expected.
* DifferentCompactionStyles -- three column families, two with level compactions and one with universal compaction. trigger the compactions and verify they work as expected.
Test Plan: nope
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16377
Summary: New unit tests for column families
Test Plan: this is a test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16359
Summary: Big CF diff uncovered some lint errors. This diff fixes some of them. Not much to see here
Test Plan: make check
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16347
Summary:
* Add ColumnFamilyHandle::GetID() function. Client needs to know column family's ID to be able to construct WriteBatch
* Handle WriteBatch::Handler failure gracefully. Since WriteBatch is not a very smart function (it takes raw CF id), client can add data to WriteBatch for column family that doesn't exist. In that case, we need to gracefully return failure status from DB::Write(). To do that, I added a return Status to WriteBatch functions PutCF, DeleteCF and MergeCF.
Test Plan: Added test to column_family_test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16323
Summary:
* Added unit test that verifies that obsolete files are deleted.
* Advance log number for empty column family when cutting log file.
* MinLogNumber() bug fix! (caught by the new unit test)
Test Plan: unit test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16311
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
Summary: DBImpl now keeps a list of alive_log_files_. On every FindObsoleteFiles, it deletes all alive log files that are smaller than versions_->MinLogNumber()
Test Plan:
make check passes
no specific unit tests yet, will add
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16293
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
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
Summary: Adapt table properties to column family world
Test Plan: make check
Reviewers: kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16161
Summary:
This is a huge diff and it was hectic, but the idea is actually quite simple. Every operation (Put, Get, etc.) done on default column family in DBTest is now forwarded to non-default ("pikachu"). The good news is that we had zero test failures! Column families look stable so far.
One interesting test that I adapted for column families is MultiThreadedTest. I replaced every Put() with a WriteBatch writing to all column families concurrently. Every Put in the write batch contains unique_id. Instead of Get() I do a multiget across all column families with the same key. If atomicity holds, I expect to see the same unique_id in all column families.
Test Plan: This is a test!
Reviewers: dhruba, haobo, kailiu, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16149
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
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
Igor Canadi