Commit Graph

2604 Commits

Author SHA1 Message Date
Siying Dong
77b4806625 Fix 2PC with concurrent memtable insert
Summary:
If concurrent memtable insert is enabled, and one prepare command and a normal command are grouped into a commit group, the sequence ID will be calculated incorrectly.
Closes https://github.com/facebook/rocksdb/pull/1730

Differential Revision: D4371081

Pulled By: siying

fbshipit-source-id: cd40c6d
2017-01-17 11:24:28 -08:00
Mike Kolupaev
d18dd2c41f Abort compactions more reliably when closing DB
Summary:
DB shutdown aborts running compactions by setting an atomic shutting_down=true that CompactionJob periodically checks. Without this PR it checks it before processing every _output_ value. If compaction filter filters everything out, the compaction is uninterruptible. This PR adds checks for shutting_down on every _input_ value (in CompactionIterator and MergeHelper).

There's also some minor code cleanup along the way.
Closes https://github.com/facebook/rocksdb/pull/1639

Differential Revision: D4306571

Pulled By: yiwu-arbug

fbshipit-source-id: f050890
2017-01-11 15:09:21 -08:00
Changli Gao
9f246298e2 Performance: Iterate vector by reference
Summary: Closes https://github.com/facebook/rocksdb/pull/1763

Differential Revision: D4398796

Pulled By: yiwu-arbug

fbshipit-source-id: b82636d
2017-01-11 10:54:37 -08:00
Dmitri Smirnov
3c233ca4ea Fix Windows environment issues
Summary:
Enable directIO on WritableFileImpl::Append
     with offset being current length of the file.
     Enable UniqueID tests on Windows, disable others but
     leeting them to compile. Unique tests are valuable to
     detect failures on different filesystems and upcoming
     ReFS.
     Clear output in WinEnv Getchildren.This is different from
     previous strategy, do not touch output on failure.
     Make sure DBTest.OpenWhenOpen works with windows error message
Closes https://github.com/facebook/rocksdb/pull/1746

Differential Revision: D4385681

Pulled By: IslamAbdelRahman

fbshipit-source-id: c07b702
2017-01-09 15:54:12 -08:00
Maysam Yabandeh
d0ba8ec8f9 Revert "PinnableSlice"
Summary:
This reverts commit 54d94e9c2c.

The pull request was landed by mistake.
Closes https://github.com/facebook/rocksdb/pull/1755

Differential Revision: D4391678

Pulled By: maysamyabandeh

fbshipit-source-id: 36d5149
2017-01-08 14:24:12 -08:00
Maysam Yabandeh
54d94e9c2c PinnableSlice
Summary:
Currently the point lookup values are copied to a string provided by the user.
This incures an extra memcpy cost. This patch allows doing point lookup
via a PinnableSlice which pins the source memory location (instead of
copying their content) and releases them after the content is consumed
by the user. The old API of Get(string) is translated to the new API
underneath.

 Here is the summary for improvements:
 1. value 100 byte: 1.8%  regular, 1.2% merge values
 2. value 1k   byte: 11.5% regular, 7.5% merge values
 3. value 10k byte: 26% regular,    29.9% merge values

 The improvement for merge could be more if we extend this approach to
 pin the merge output and delay the full merge operation until the user
 actually needs it. We have put that for future work.

PS:
Sometimes we observe a small decrease in performance when switching from
t5452014 to this patch but with the old Get(string) API. The difference
is a little and could be noise. More importantly it is safely
cancelled
Closes https://github.com/facebook/rocksdb/pull/1732

Differential Revision: D4374613

Pulled By: maysamyabandeh

fbshipit-source-id: a077f1a
2017-01-08 13:54:13 -08:00
Andrew Kryczka
b104b87814 Maintain position in range deletions map
Summary:
When deletion-collapsing mode is enabled (i.e., for DBIter/CompactionIterator), we maintain position in the tombstone maps across calls to ShouldDelete(). Since iterators often access keys sequentially (or reverse-sequentially), scanning forward/backward from the last position can be faster than binary-searching the map for every key.

- When Next() is invoked on an iterator, we use kForwardTraversal to scan forwards, if needed, until arriving at the range deletion containing the next key.
- Similarly for Prev(), we use kBackwardTraversal to scan backwards in the range deletion map.
- When the iterator seeks, we use kBinarySearch for repositioning
- After tombstones are added or before the first ShouldDelete() invocation, the current position is set to invalid, which forces kBinarySearch to be used.
- Non-iterator users (i.e., Get()) use kFullScan, which has the same behavior as before---scan the whole map for every key passed to ShouldDelete().
Closes https://github.com/facebook/rocksdb/pull/1701

Differential Revision: D4350318

Pulled By: ajkr

fbshipit-source-id: 5129b76
2017-01-05 10:39:12 -08:00
siddontang
653ac1f9c6 C API: support total_order_mode
Summary: Closes https://github.com/facebook/rocksdb/pull/1687

Differential Revision: D4349210

Pulled By: IslamAbdelRahman

fbshipit-source-id: 32d0fbd
2017-01-03 18:39:14 -08:00
Adam Retter
85ac1a320a Fix rocksdb::Status::getState
Summary:
This fixes the Java API for Status#getState use in Native code and also simplifies the implementation of rocksdb::Status::getState.
Closes https://github.com/facebook/rocksdb/issues/1688
Closes https://github.com/facebook/rocksdb/pull/1714

Differential Revision: D4364181

Pulled By: yiwu-arbug

fbshipit-source-id: 8e073b4
2017-01-03 18:39:14 -08:00
Islam AbdelRahman
76711b6e77 Make ExternalSSTFileTest::CompactionDeadlock more deterministic
Summary:
It's not always true that `ASSERT_EQ(running_threads.load(), 2);`
Closes https://github.com/facebook/rocksdb/pull/1736

Differential Revision: D4374091

Pulled By: IslamAbdelRahman

fbshipit-source-id: 4f70bbd
2017-01-03 18:09:20 -08:00
Islam AbdelRahman
c963460dbc Fix tests under GCC_481
Summary:
This fix the issue with tests failing under GCC 481, I am not sure what is the exact reason
Closes https://github.com/facebook/rocksdb/pull/1735

Differential Revision: D4374094

Pulled By: IslamAbdelRahman

fbshipit-source-id: b3625bc
2017-01-03 17:54:12 -08:00
Vincent Lee
e425ec1162 utilities/backupable: backup should limit the copy size of wal.
Summary:
Since the backup work as snapshot, we should only copy
 the bytes of the wal while we get the alive files.
Closes https://github.com/facebook/rocksdb/pull/1733

Differential Revision: D4373457

Pulled By: ajkr

fbshipit-source-id: 389318f
2016-12-31 10:54:20 -08:00
Maysam Yabandeh
0712d541d1 Delegate Cleanables
Summary:
Cleanable objects will perform the registered cleanups when
they are destructed. We however rather to delay this cleaning like when
we are gathering the merge operands. Current approach is to create the
Cleanable object on heap (instead of on stack) and delay deleting it.

By allowing Cleanables to delegate their cleanups to another cleanable
object we can delay the cleaning without however the need to craete the
cleanable object on heap and keeping it around. This patch applies this
technique for the cleanups of BlockIter and shows improved performance
for some in-memory benchmarks:
+1.8% for merge worklaod, +6.4% for non-merge workload when the merge
operator is specified.
https://our.intern.facebook.com/intern/tasks?t=15168163

Non-merge benchmark:
TEST_TMPDIR=/dev/shm/v100nocomp/ ./db_bench --benchmarks=fillrandom
--num=1000000 -value_size=100 -compression_type=none

Reading random with no merge operator specified:
TEST_TMPDIR=/dev/shm/v100nocomp/ ./db_bench
--benchmarks="read
Closes https://github.com/facebook/rocksdb/pull/1711

Differential Revision: D4361163

Pulled By: maysamyabandeh

fbshipit-source-id: 9801e07
2016-12-29 15:54:19 -08:00
Islam AbdelRahman
d58ef52ba6 Allow SstFileWriter to Fadvise the file away from page cache
Summary:
Add `fadvise_trigger` option to `SstFileWriter`

If fadvise_trigger is passed with a non-zero value, SstFileWriter will invalidate the os page cache every `fadvise_trigger` bytes for the sst file
Closes https://github.com/facebook/rocksdb/pull/1731

Differential Revision: D4371246

Pulled By: IslamAbdelRahman

fbshipit-source-id: 91caff1
2016-12-29 15:09:19 -08:00
Siying Dong
17a4b75cc3 Always fsync the file after file copying
Summary:
File copying happens when creating checkpoints and bulkloading files from different FS partition. We should fsync the files when copying them to guarantee durability. A side effect will be that the dirty pages in file system buffers won't grow too large.
Closes https://github.com/facebook/rocksdb/pull/1728

Differential Revision: D4371083

Pulled By: siying

fbshipit-source-id: 579e14c
2016-12-28 19:09:16 -08:00
leipeng
a738af8f84 db/pinned_iterators_manager.h: bugfix
Summary:
std::unique(beg, end) returns an iterator of unique_end, data behind unique_end should not be accessed.
Closes https://github.com/facebook/rocksdb/pull/1726

Differential Revision: D4371076

Pulled By: IslamAbdelRahman

fbshipit-source-id: 5564450
2016-12-28 18:54:57 -08:00
Siying Dong
438f22bc56 Fix bug of Checkpoint loses recent transactions with 2PC
Summary:
If 2PC is enabled, checkpoint may not copy previous log files that contain uncommitted prepare records. In this diff we keep those files.
Closes https://github.com/facebook/rocksdb/pull/1724

Differential Revision: D4368319

Pulled By: siying

fbshipit-source-id: cc2c746
2016-12-28 12:24:16 -08:00
Aaron Gao
972f96b3fb direct io write support
Summary:
rocksdb direct io support

```
[gzh@dev11575.prn2 ~/rocksdb] ./db_bench -benchmarks=fillseq --num=1000000
Initializing RocksDB Options from the specified file
Initializing RocksDB Options from command-line flags
RocksDB:    version 5.0
Date:       Wed Nov 23 13:17:43 2016
CPU:        40 * Intel(R) Xeon(R) CPU E5-2660 v2 @ 2.20GHz
CPUCache:   25600 KB
Keys:       16 bytes each
Values:     100 bytes each (50 bytes after compression)
Entries:    1000000
Prefix:    0 bytes
Keys per prefix:    0
RawSize:    110.6 MB (estimated)
FileSize:   62.9 MB (estimated)
Write rate: 0 bytes/second
Compression: Snappy
Memtablerep: skip_list
Perf Level: 1
WARNING: Assertions are enabled; benchmarks unnecessarily slow
------------------------------------------------
Initializing RocksDB Options from the specified file
Initializing RocksDB Options from command-line flags
DB path: [/tmp/rocksdbtest-112628/dbbench]
fillseq      :       4.393 micros/op 227639 ops/sec;   25.2 MB/s

[gzh@dev11575.prn2 ~/roc
Closes https://github.com/facebook/rocksdb/pull/1564

Differential Revision: D4241093

Pulled By: lightmark

fbshipit-source-id: 98c29e3
2016-12-22 13:09:19 -08:00
Islam AbdelRahman
989e644ed8 Remove sst_file_manager option from LITE
Summary:
Remove sst_file_manager option from LITE
Closes https://github.com/facebook/rocksdb/pull/1690

Differential Revision: D4341331

Pulled By: IslamAbdelRahman

fbshipit-source-id: 9f9328d
2016-12-21 17:54:21 -08:00
Islam AbdelRahman
1beef6569a Fix c_test
Summary:
addfile phase in c_test could fail because in previous steps we did a DeleteRange.
Fix the test by simply moving the addfile phase before DeleteRange
Closes https://github.com/facebook/rocksdb/pull/1672

Differential Revision: D4328896

Pulled By: IslamAbdelRahman

fbshipit-source-id: 1d946df
2016-12-21 17:39:14 -08:00
Andrew Kryczka
50e305de98 Collapse range deletions
Summary:
Added a tombstone-collapsing mode to RangeDelAggregator, which eliminates overlap in the TombstoneMap. In this mode, we can check whether a tombstone covers a user key using upper_bound() (i.e., binary search). However, the tradeoff is the overhead to add tombstones is now higher, so at first I've only enabled it for range scans (compaction/flush/user iterators), where we expect a high number of calls to ShouldDelete() for the same tombstones. Point queries like Get() will still use the linear scan approach.

Also in this diff I changed RangeDelAggregator's TombstoneMap to use multimap with user keys instead of map with internal keys. Callers sometimes provided ParsedInternalKey directly, from which it would've required string copying to derive an internal key Slice with which we could search the map.
Closes https://github.com/facebook/rocksdb/pull/1614

Differential Revision: D4270397

Pulled By: ajkr

fbshipit-source-id: 93092c7
2016-12-19 16:54:12 -08:00
Yi Wu
5d1457dbbf Dump persistent cache options
Summary:
Dump persistent cache options
Closes https://github.com/facebook/rocksdb/pull/1679

Differential Revision: D4337019

Pulled By: yiwu-arbug

fbshipit-source-id: 3812f8a
2016-12-19 14:09:12 -08:00
Daniel Black
342370f1d3 Simplify MemTable::Update
Summary:
As suggested by testn in #1650

The Add is at the end of the function. Having a fallthough
will result in it being added twice.
Closes https://github.com/facebook/rocksdb/pull/1676

Differential Revision: D4331906

Pulled By: yiwu-arbug

fbshipit-source-id: 895c4a0
2016-12-17 00:09:13 -08:00
Ding Ma
1a136c1f13 Expose file size
Summary:
add a new function to SstFileWriter that will tell the user how big is there file right now.
Closes https://github.com/facebook/rocksdb/pull/1686

Differential Revision: D4338868

Pulled By: mdyuki1016

fbshipit-source-id: c1ee16a
2016-12-16 18:39:12 -08:00
Andrew Kryczka
fbff4628a9 Reduce compaction iterator status checks
Summary:
seems it's expensive to check status since the underlying merge iterator checks status of all its children. so only do it when it's really necessary to get the status before invoking Next(), i.e., when we're advancing to get the first key in the next file.
Closes https://github.com/facebook/rocksdb/pull/1691

Differential Revision: D4343446

Pulled By: siying

fbshipit-source-id: 70ab315
2016-12-16 17:39:09 -08:00
Daniel Black
816c1e30ca gcc-7 requires include <functional> for std::function
Summary:
Fixes compile error:

In file included from ./util/statistics.h:17:0,
                 from ./util/stop_watch.h:8,
                 from ./util/perf_step_timer.h:9,
                 from ./util/iostats_context_imp.h:8,
                 from ./util/posix_logger.h:27,
                 from ./port/util_logger.h:18,
                 from ./db/auto_roll_logger.h:15,
                 from db/auto_roll_logger.cc:6:
./util/thread_local.h:65:16: error: 'function' in namespace 'std' does not name a template type
   typedef std::function<void(void*, void*)> FoldFunc;
Closes https://github.com/facebook/rocksdb/pull/1656

Differential Revision: D4318702

Pulled By: yiwu-arbug

fbshipit-source-id: 8c5d17a
2016-12-16 11:24:18 -08:00
Yi Wu
c270735861 Iterator should be in corrupted status if merge operator return false
Summary:
Iterator should be in corrupted status if merge operator return false.
Also add test to make sure if max_successive_merges is hit during write,
data will not be lost.
Closes https://github.com/facebook/rocksdb/pull/1665

Differential Revision: D4322695

Pulled By: yiwu-arbug

fbshipit-source-id: b327b05
2016-12-16 11:09:16 -08:00
siddontang
8f5d24ae68 C API: support get usage and pinned_usage for cache
Summary: Closes https://github.com/facebook/rocksdb/pull/1671

Differential Revision: D4327453

Pulled By: yiwu-arbug

fbshipit-source-id: bcdbc65
2016-12-15 17:24:17 -08:00
Daniel Black
cfc34d7c4e Missing break in case in DBTestBase::CurrentOptions
Summary:
Found by gcc-7 compile error.

This appeared to be a fault as these options seems too different.
Closes https://github.com/facebook/rocksdb/pull/1667

Differential Revision: D4324174

Pulled By: yiwu-arbug

fbshipit-source-id: 0f65383
2016-12-13 18:39:14 -08:00
Daniel Black
bfbcec2339 Gcc 7 error expansion to defined
Summary:
sorry if these gcc-7/clang-4 cleanups are getting tedious.
Closes https://github.com/facebook/rocksdb/pull/1658

Differential Revision: D4318792

Pulled By: yiwu-arbug

fbshipit-source-id: 8e85891
2016-12-13 18:39:14 -08:00
Daniel Black
67adc937b6 intentional fallthough (prevents gcc-7/clang-4 error)
Summary:
db/memtable.cc: In member function 'void rocksdb::MemTable::Update(rocksdb::SequenceNumber, const rocksdb::Slice&, const rocksdb::Slice&)':
db/memtable.cc:736:11: error: this statement may fall through [-Werror=implicit-fallthrough=]
           }
           ^
db/memtable.cc:738:9: note: here
         default:
         ^~~~~~~
cc1plus: all warnings being treated as errors

closes #1650
Closes https://github.com/facebook/rocksdb/pull/1655

Differential Revision: D4318696

Pulled By: yiwu-arbug

fbshipit-source-id: 1a8981c
2016-12-13 14:39:17 -08:00
Islam AbdelRahman
1a146f89c7 break Flush wait for dropped CF
Summary:
In FlushJob we dont do the Flush if the CF is dropped
https://github.com/facebook/rocksdb/blob/master/db/flush_job.cc#L184-L188

but inside WaitForFlushMemTable we keep waiting forever even if the CF is dropped.
Closes https://github.com/facebook/rocksdb/pull/1664

Differential Revision: D4321032

Pulled By: IslamAbdelRahman

fbshipit-source-id: 6e2b25d
2016-12-13 14:09:12 -08:00
Yi Wu
36d42e65d0 Disable test to unblock travis build
Summary:
The two tests keep failing in travis. Disable them and will fix later.
Closes https://github.com/facebook/rocksdb/pull/1648

Differential Revision: D4316389

Pulled By: yiwu-arbug

fbshipit-source-id: 0a370e7
2016-12-13 11:54:14 -08:00
siddontang
b57dd9262a C API: support writebatch delete range
Summary:
Seem that writebatch delete range can work now, so I add C API for later use.

Btw, can we use this feature in production now?
Closes https://github.com/facebook/rocksdb/pull/1647

Differential Revision: D4314534

Pulled By: ajkr

fbshipit-source-id: e835165
2016-12-13 11:24:18 -08:00
Islam AbdelRahman
2ba59b5a1e Disallow ingesting files into dropped CFs
Summary:
This PR update IngestExternalFile to return an error if we try to ingest a file into a dropped CF.

Right now if IngestExternalFile want to flush a memtable, and it's ingesting a file into a dropped CF, it will wait forever since flushing is not possible for the dropped CF
Closes https://github.com/facebook/rocksdb/pull/1657

Differential Revision: D4318657

Pulled By: IslamAbdelRahman

fbshipit-source-id: ed6ea2b
2016-12-13 00:54:14 -08:00
Jonathan Lee
2cabdb8f44 Increase buffer size
Summary:
When compiling with GCC>=7.0.0, "db/internal_stats.cc" fails to compile as the data being written to the buffer potentially exceeds its size.

This fix simply doubles the size of the buffer, thus accommodating the max possible data size.
Closes https://github.com/facebook/rocksdb/pull/1635

Differential Revision: D4302162

Pulled By: yiwu-arbug

fbshipit-source-id: c76ad59
2016-12-09 11:54:22 -08:00
Jonathan Lee
4a17b47bb5 Remove unnecessary header include
Summary:
Remove "util/testharness.h" from list of includes for "db/db_filesnapshot.cc", as it wasn't being used and thus caused an extraneous dependency on gtest.
Closes https://github.com/facebook/rocksdb/pull/1634

Differential Revision: D4302146

Pulled By: yiwu-arbug

fbshipit-source-id: e900c0b
2016-12-09 11:54:21 -08:00
Mike Kolupaev
8c2b921fdf Fixed a crash in debug build in flush_job.cc
Summary:
It was doing `&range_del_iters[0]` on an empty vector. Even though the resulting pointer is never dereferenced, it's still bad for two reasons:
* the practical reason: it crashes with `std::out_of_range` exception in our debug build,
* the "C++ standard lawyer" reason: it's undefined behavior because, in `std::vector` implementation, it probably "dereferences" a null pointer, which is invalid even though it doesn't actually read the pointed memory, just converts a pointer into a reference (and then flush_job.cc converts it back to pointer); nullptr references are undefined behavior.
Closes https://github.com/facebook/rocksdb/pull/1612

Differential Revision: D4265625

Pulled By: al13n321

fbshipit-source-id: db26fb9
2016-12-09 10:39:12 -08:00
Islam AbdelRahman
20ce081fae Fix issue where IngestExternalFile insert blocks in block cache with g_seqno=0
Summary:
When we Ingest an external file we open it to read some metadata and first/last key
during doing that we insert blocks into the block cache with global_seqno = 0

If we move the file (did not copy it) into the DB, we will use these blocks with the wrong seqno in the read path
Closes https://github.com/facebook/rocksdb/pull/1627

Differential Revision: D4293332

Pulled By: yiwu-arbug

fbshipit-source-id: 3ce5523
2016-12-08 13:39:18 -08:00
zhangjinpeng1987
45c7ce1377 CompactRangeOptions C API
Summary:
Add C API for CompactRangeOptions.
Closes https://github.com/facebook/rocksdb/pull/1596

Differential Revision: D4252339

Pulled By: yiwu-arbug

fbshipit-source-id: f768f93
2016-12-07 17:54:14 -08:00
Andrew Kryczka
b821984d31 DeleteRange read path end-to-end tests
Summary: Closes https://github.com/facebook/rocksdb/pull/1592

Differential Revision: D4246260

Pulled By: ajkr

fbshipit-source-id: ce03fa2
2016-12-07 12:54:17 -08:00
Artemiy Kolesnikov
2f4fc539c6 Compaction::IsTrivialMove relaxing
Summary:
IsTrivialMove returns true if no input file overlaps with output_level+1 with more than max_compaction_bytes_ bytes.
Closes https://github.com/facebook/rocksdb/pull/1619

Differential Revision: D4278338

Pulled By: yiwu-arbug

fbshipit-source-id: 994c001
2016-12-07 11:54:11 -08:00
Islam AbdelRahman
ed8fbdb560 Add EventListener::OnExternalFileIngested() event
Summary:
Add EventListener::OnExternalFileIngested() to allow user to subscribe to external file ingestion events
Closes https://github.com/facebook/rocksdb/pull/1623

Differential Revision: D4285844

Pulled By: IslamAbdelRahman

fbshipit-source-id: 0b95a88
2016-12-06 14:09:17 -08:00
Mike Kolupaev
beb36d9c1e Fixed CompactionFilter::Decision::kRemoveAndSkipUntil
Summary:
Embarassingly enough, the first time I tried to use my new feature in logdevice it crashed with this assertion failure:

  db/pinned_iterators_manager.h:30: void rocksdb::PinnedIteratorsManager::StartPinning(): Assertion `pinning_enabled == false' failed

The issue was that `pinned_iters_mgr_.StartPinning()` was called but `pinned_iters_mgr_.ReleasePinnedData()` wasn't.
Closes https://github.com/facebook/rocksdb/pull/1611

Differential Revision: D4265622

Pulled By: al13n321

fbshipit-source-id: 747b10f
2016-12-05 15:24:11 -08:00
Islam AbdelRahman
67f37cf198 Allow user to specify a CF for SST files generated by SstFileWriter
Summary:
Allow user to explicitly specify that the generated file by SstFileWriter will be ingested in a specific CF.
This allow us to persist the CF id in the generated file
Closes https://github.com/facebook/rocksdb/pull/1615

Differential Revision: D4270422

Pulled By: IslamAbdelRahman

fbshipit-source-id: 7fb954e
2016-12-05 14:24:16 -08:00
Anton Safonov
9053fe2a5c Made delete_obsolete_files_period_micros option dynamic
Summary:
Made delete_obsolete_files_period_micros option dynamic. It can be updating using DB::SetDBOptions().
Closes https://github.com/facebook/rocksdb/pull/1595

Differential Revision: D4246569

Pulled By: tonek

fbshipit-source-id: d23f560
2016-12-05 14:24:16 -08:00
Islam AbdelRahman
edde954e7b fix clang build
Summary:
override is missing for FilterV2
Closes https://github.com/facebook/rocksdb/pull/1606

Differential Revision: D4263832

Pulled By: IslamAbdelRahman

fbshipit-source-id: d8b337a
2016-12-01 18:39:10 -08:00
Islam AbdelRahman
e39d080871 Fix travis (compile for clang < 3.9)
Summary:
Travis fail because it uses clang 3.6 which don't recognize
`__attribute__((__no_sanitize__("undefined")))`
Closes https://github.com/facebook/rocksdb/pull/1601

Differential Revision: D4257175

Pulled By: IslamAbdelRahman

fbshipit-source-id: fb4d1ab
2016-12-01 10:09:22 -08:00
fangchenliaohui
b77007df8b Bug: paralle_group status updated in WriteThread::CompleteParallelWorker
Summary:
Multi-write thread may update the status of the parallel_group in
WriteThread::CompleteParallelWorker if the status of Writer is not ok!
When copy write status to the paralle_group, the write thread just hold the
mutex of the the writer processed by itself. it is useless. The thread
should held the the leader of the parallel_group instead.
Closes https://github.com/facebook/rocksdb/pull/1598

Differential Revision: D4252335

Pulled By: siying

fbshipit-source-id: 3864cf7
2016-12-01 09:54:11 -08:00
Mike Kolupaev
247d0979aa Support for range skips in compaction filter
Summary:
This adds the ability for compaction filter to say "drop this key-value, and also drop everything up to key x". This will cause the compaction to seek input iterator to x, without reading the data. This can make compaction much faster when large consecutive chunks of data are filtered out. See the changes in include/rocksdb/compaction_filter.h for the new API.

Along the way this diff also adds ability for compaction filter changing merge operands, similar to how it can change values; we're not going to use this feature, it just seemed easier and cleaner to implement it than to document that it's not implemented :)

The diff is not as big as it may seem, about half of the lines are a test.
Closes https://github.com/facebook/rocksdb/pull/1599

Differential Revision: D4252092

Pulled By: al13n321

fbshipit-source-id: 41e1e48
2016-12-01 07:09:15 -08:00