Commit Graph

2162 Commits

Author SHA1 Message Date
sdong
d20915d52a Disable stats about mutex duration by default
Summary: Measuring mutex duration will measure time inside DB mutex, which breaks our best practice. Add a stat level in Statistics class. By default, disable to measure the mutex operations.

Test Plan: Add a unit test to make sure it is off by default.

Reviewers: rven, anthony, IslamAbdelRahman, kradhakrishnan, andrewkr, yhchiang

Reviewed By: yhchiang

Subscribers: MarkCallaghan, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D53367
2016-01-26 14:56:55 -08:00
Islam AbdelRahman
0c433cd1eb Fix issue in Iterator::Seek when using Block based filter block with prefix_extractor
Summary: Similar to D53385 we need to check InDomain before checking the filter block.

Test Plan: unit tests

Reviewers: yhchiang, rven, sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D53421
2016-01-26 14:47:42 -08:00
Andrew Kryczka
035857a312 Fix RocksDB lite build
Summary:
NewMemEnv() is defined in rocksdb lite but just returns nullptr --
would it be better to just not define it so we can catch issues like this at
compile-time?

Test Plan:
  $ make clean && OPT="-DTRAVIS -DROCKSDB_LITE" V=1 make -j32 db_test
  $ ./db_test --gtest_filter='DBTest.MemEnvTest'
  ...
  [  PASSED  ] 0 tests.

Reviewers: yhchiang, sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D53427
2016-01-26 13:15:36 -08:00
Yueh-Hsuan Chiang
955ecf8b49 Fix an ASAN error in compact_files_test
Summary:
compact_files_test enables SyncPoint but never disable it before
the test terminates.  As a result, it might cause heap-use-after-free
error when some code path trying to access the static variable of
SyncPoint when it has already gone out of scope after the main thread
dies.

Test Plan:
COMPILE_WITH_ASAN=1 make compact_files_test -j32
./compact_files_test

Reviewers: sdong, anthony, kradhakrishnan, rven, andrewkr, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D53379
2016-01-26 11:30:30 -08:00
Islam AbdelRahman
b0afcdeeac Fix bug in block based tables with full filter block and prefix_extractor
Summary:
Right now when we are creating a BlockBasedTable with fill filter block
we add to the filter all the prefixes that are InDomain() based on the prefix_extractor

the problem is that when we read a key from the file, we check the filter block for the prefix whether or not it's InDomain()

Test Plan: unit tests

Reviewers: yhchiang, rven, anthony, kradhakrishnan, sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D53385
2016-01-26 11:07:08 -08:00
Andrew Kryczka
167bd8856d [directory includes cleanup] Finish removing util->db dependencies 2016-01-26 10:49:24 -08:00
Andrew Kryczka
acd7d58695 [directory includes cleanup] Remove util->db dependency for ThreadStatusUtil
Summary:
We can avoid the dependency by forward-declaring ColumnFamilyData and
then treating it as a black box. That means callers of ThreadStatusUtil need to
explicitly provide more options, even if they can be derived from the
ColumnFamilyData, since ThreadStatusUtil doesn't include the definition.

This is part of a series of diffs to eliminate circular dependencies between
directories (e.g., db/* files depending on util/* files and vice-versa).

Test Plan:
  $ ./db_test --gtest_filter=DBTest.GetThreadStatus
  $ make -j32 commit-prereq

Reviewers: sdong, yhchiang, IslamAbdelRahman

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D53361
2016-01-26 10:49:16 -08:00
Andrew Kryczka
46f9cd46af [directory includes cleanup] Move cross-function test points
Summary:
I split the db-specific test points out into a separate file under db/
directory. There were also a few bugs to fix in xfunc.{h,cc} that prevented it
from compiling previously; see https://reviews.facebook.net/D36825.

Test Plan:
compilation works now, below command works, will also run "make xfunc".

  $ make check ROCKSDB_XFUNC_TEST='managed_new' tests-regexp='DBTest' -j32

Reviewers: sdong, yhchiang

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D53343
2016-01-26 10:49:05 -08:00
Venkatesh Radhakrishnan
b7ecf3d214 Fix intermittent hang in ColumnFamilyTest.FlushAndDropRaceCondition
Summary:
ColumnFamilyTest.FlushAndDropRaceCondition sometimes
hangs because the sync point, "FlushJob::InstallResults", sleeps
holding the DB mutex. Fixing it by releasing the mutex before sleeping.

Test Plan:
seq 1000 |parallel --gnu --eta 't=/dev/shm/rdb-{}; rm -rf $t;
mkdir $t && export TEST_TMPDIR=$t; ./column_family_test
-gtest_filter=*FlushAndDropRaceCondition* > $t/log-{}'

Reviewers: IslamAbdelRahman, anthony, kradhakrishnan, yhchiang, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D53349
2016-01-26 09:12:20 -08:00
sdong
da33dfe188 Parameterize DBTest.Randomized
Summary: Break down DBTest.Randomized to multiple gtest tests based on config type

Test Plan: Run the test and all tests. Make sure configurations are correctly set

Reviewers: yhchiang, IslamAbdelRahman, rven, kradhakrishnan, andrewkr, anthony

Reviewed By: anthony

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D53247
2016-01-25 14:49:08 -08:00
sdong
fb9811ee9b Add a perf context level that doesn't measure time for mutex operations
Summary: Timing mutex operations can impact scalability of the system. Add a new perf context level that can measure time counters except for mutex.

Test Plan: Add a new unit test case to make sure it is not set.

Reviewers: IslamAbdelRahman, rven, kradhakrishnan, yhchiang, anthony

Reviewed By: anthony

Subscribers: MarkCallaghan, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D53199
2016-01-25 14:45:03 -08:00
Andrew Kryczka
3e9209a078 Updated GetProperty documentation
Summary: As titled. Also added the kBaseLevel string, which was missing earlier.

Test Plan: built

Reviewers: yhchiang, anthony, rven, kradhakrishnan, IslamAbdelRahman, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D53271
2016-01-25 14:04:55 -08:00
Islam AbdelRahman
2fbc59a348 Disallow SstFileWriter from creating empty sst files
Summary:
SstFileWriter may create an sst file with no entries
Right now this will fail when being ingested using DB::AddFile() saying that the keys are corrupted

Test Plan: make check

Reviewers: yhchiang, rven, anthony, sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D52815
2016-01-25 13:47:07 -08:00
agiardullo
8019aa9b55 improve test for manifest write failure
Summary: Improve testing per discussion in D52989

Test Plan: ran test

Reviewers: sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D53211
2016-01-22 11:47:59 -08:00
agiardullo
bcd4ccbc33 Revert D7809
Summary: Revert the functionaility of D7809 (but I'm keeping the logging and test code).  We decided it was dangerous to ignore sync failures based on attempting to read the data written.  The read does not tell us whether the data was synced.

Test Plan: There was no test for the particular functionaility that was reverted.  Keeping the test code from D7809 that tests whether we set the DB to be readonly when paranoid checks are enabled.

Reviewers: rven, yhchiang, kradhakrishnan, IslamAbdelRahman, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D52989
2016-01-21 17:14:43 -08:00
Andrew Kryczka
bb2888738c Cleanup property-related variable names
Summary:
I noticed these names were quite confusing while updating GetProperty
documentation.

Test Plan: running "make commit-prereq -j32"

Reviewers: yhchiang, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D53073
2016-01-21 11:38:15 -08:00
Andrew Kryczka
29289333d0 Add named constants for remaining properties
Summary:
There were just these two properties that didn't have any named
constant.

Test Plan:
build and below test

  $ ./db_properties_test --gtest_filter=DBPropertiesTest.NumImmutableMemTable

Reviewers: yhchiang, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D53103
2016-01-21 10:59:36 -08:00
Andrew Kryczka
eceb5cb1b7 Split db_test.cc (part 1: properties)
Summary:
Moved all the tests that verify property correctness into a separate
file. The goal is to reduce compile time and complexity of db_test. I didn't
add parallelism for db_properties_test, even though these tests were
parallelized in db_test, since the file is small enough that it won't matter.

Some of these moves may be controversial since it's hard to say whether the
test is "verifying property correctness," or "using properties to verify
rocksdb's correctness." I'm interested in any opinions.

Test Plan: ran db_properties_test, also waiting on "make commit-prereq -j32"

Reviewers: yhchiang, IslamAbdelRahman, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D52995
2016-01-20 15:17:52 -08:00
sdong
94918ae84b db_bench: explicitly clear buffer in compress benchmark
Summary: It is reported that in compress benchmark in db_bench, zlib will cause an OOM. The suggestd fix was to clear the buffer.

Test Plan: Build and run compress benchmark.

Reviewers: IslamAbdelRahman, yhchiang, rven, andrewkr, kradhakrishnan, anthony

Reviewed By: anthony

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D52857
2016-01-19 18:11:46 -08:00
Siying Dong
39c3e94ff4 Merge pull request #954 from davidbernard/solaris_build
Solaris Build
2016-01-19 18:05:02 -08:00
Mike Kolupaev
34704d5c7b [easy] Fixed a crash in LogAndApply() when CF creation failed
Summary: That line used to dereference `column_family_data`, which is nullptr if we're creating a column family.

Test Plan: `make -j check`

Reviewers: sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D52881
2016-01-19 11:46:52 -08:00
David Bernard
3f12e16f27 Make alloca.h optional 2016-01-19 06:17:31 +00:00
David Bernard
d78c6b28c4 Changes for build on solaris
Makefile adjust paths for solaris build
Makefile enable _GLIBCXX_USE_C99 so that std::to_string is available
db_compaction_test.cc Initialise a variable to avoid a compilation error
db_impl.cc Include <alloca.h>
db_test.cc Include <alloca.h>
Environment.java recognise solaris envrionment
options_bulder.cc Make log unambiguous
geodb_impl.cc Make log and floor unambiguous
2016-01-19 04:45:21 +00:00
Dmitri Smirnov
20d7902df9 Fix compile error.
Use constructor style initialization instead of a cast for
  simplicity.
2016-01-11 16:10:48 -08:00
sdong
235b162be1 Not scheduling more L1->L2 compaction if L0->L1 is pending with higher priority
Summary: When L0->L1 is pending, there may be one L1->L2 compaction going on which prevents the L0->L1 compaction from happening. If L1 needs more data to be moved to L2, then we may continue scheduling more L1->L2 compactions. The end result may be that L0->L1 compaction will not happen until L1 size drops to below target size. We can reduce the stalling because of number of L0 files by stopping schedling new L1->L2 compaction when L0's score is higher than L1.

Test Plan: Run all existing tests.

Reviewers: yhchiang, MarkCallaghan, rven, anthony, IslamAbdelRahman, igor

Reviewed By: igor

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D52401
2016-01-08 13:56:57 -08:00
sdong
9a8e3f73ed plain table reader: non-mmap mode to keep two recent buffers
Summary: In plain table reader's non-mmap mode, we only keep the most recent read buffer. However, for binary search, it is likely we come back to a location to read. To avoid one pread in such a case, we keep two read buffers. It should cover most of the cases.

Test Plan:
1. run tests
2. check the optimization works through strace when running
./table_reader_bench -mmap_read=false --num_keys2=1 -num_keys1=5000 -table_factory=plain_table --iterator --through_db

Reviewers: anthony, rven, kradhakrishnan, igor, yhchiang, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D51171
2016-01-08 10:53:57 -08:00
Venkatesh Radhakrishnan
7ece10ecb6 DeleteFilesInRange: Mark files to be deleted as being compacted before applying change
Summary:
While running the myrocks regression suite, I found that while
dropping a table soon after inserting rows into it resulted in an
assertion failure in CheckConsistencyForDeletes for not finding
a file which was recently added or moved. Marking the files to be
deleted as being compacted before calling LogAndApplyChange
fixed the assertion failures.

Test Plan: DBCompactionTest.DeleteFileRange

Reviewers: IslamAbdelRahman, anthony, yhchiang, kradhakrishnan, sdong

Reviewed By: sdong

Subscribers: dhruba, yoshinorim, leveldb

Differential Revision: https://reviews.facebook.net/D52599
2016-01-07 14:48:45 -08:00
Islam AbdelRahman
8c71eb5afc Optimize DBIter::Prev() by reducing stack overhead
Summary:
It looks like we are spending significant amount of time creating std::deque<std::string> every time we do Iterator::Prev()

{F921567}

By using merge_operands_ as a DBIter data member w create it once and reduce this overhead and see ~30% performance improvement when using Iterator::Prev() on hot data

Orignal performance

```
DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readreverse" --db="/dev/shm/bench_prev_opt/" --use_existing_db --disable_auto_compactions
readreverse  :       0.713 micros/op 1402219 ops/sec;  155.1 MB/s
readreverse  :       0.609 micros/op 1641386 ops/sec;  181.6 MB/s
readreverse  :       0.684 micros/op 1461150 ops/sec;  161.6 MB/s
readreverse  :       0.629 micros/op 1589842 ops/sec;  175.9 MB/s
readreverse  :       0.647 micros/op 1544530 ops/sec;  170.9 MB/s
```

After optimization

```
DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readreverse" --db="/dev/shm/bench_prev_opt/" --use_existing_db --disable_auto_compactions
readreverse  :       0.488 micros/op 2051189 ops/sec;  226.9 MB/s
readreverse  :       0.505 micros/op 1980892 ops/sec;  219.1 MB/s
readreverse  :       0.541 micros/op 1846971 ops/sec;  204.3 MB/s
readreverse  :       0.497 micros/op 2013612 ops/sec;  222.8 MB/s
readreverse  :       0.480 micros/op 2082665 ops/sec;  230.4 MB/s
```

Test Plan: make check -j64

Reviewers: sdong, anthony, rven, igor, yhchiang

Reviewed By: yhchiang

Subscribers: jkedgar, dhruba

Differential Revision: https://reviews.facebook.net/D52563
2016-01-07 07:59:14 -08:00
Yueh-Hsuan Chiang
6935eb24e0 Add ColumnFamilyHandle::GetDescriptor()
Summary:
This patch addes ColumnFamilyHandle::GetDescriptor(), which allows
developers to obtain the CF options and names of the associated column
family given its handle.

  // Returns the up-to-date descriptor used by the current handle.  Since it
  // returns the up-to-date information, this call might internally locks
  // and releases DB mutex to access the up-to-date CF options.
  virtual ColumnFamilyDescriptor GetDescriptor() = 0;

Test Plan: augment column_family_test

Reviewers: sdong, yoshinorim, IslamAbdelRahman, rven, kradhakrishnan, anthony

Reviewed By: anthony

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D51543
2016-01-06 18:14:01 -08:00
Reid Horuff
da032495d3 Optimize GetLatestSequenceForKey
Summary: DBImpl::GetLatestSequenceForKey() can do memcpy's to load a value that will never be used.  This can be optimized by changing all the Get() functions called to optionally not fetch the value (and only fetch the sequencenumber).

Test Plan: optimistic_transaction_test and transaction_test

Reviewers: anthony

Reviewed By: anthony

Subscribers: leveldb, dhruba, hermanlee4

Differential Revision: https://reviews.facebook.net/D52227
2016-01-06 13:43:22 -08:00
agiardullo
51adc5457a fix sporadic failure in fault_injection_test
Summary: Need to make sure the background task gets scheduled before it goes out of scope.

Test Plan: ran test.  Will see if sporadic valgrind failures go away.

Reviewers: kradhakrishnan

Reviewed By: kradhakrishnan

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D52575
2016-01-06 11:51:53 -08:00
agiardullo
a2422f0533 fix potential test SleepingTask race condition
Summary: Make sure SleepingTask has bene run before it goes out of scope.

Test Plan: run test

Reviewers: kradhakrishnan

Reviewed By: kradhakrishnan

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D52581
2016-01-06 11:51:09 -08:00
Mark Callaghan
4041903ecd Enhance db_bench write rate limit
Summary:
1) changes tools/{benchmark,run_flash_bench}.sh to optionally use the write rate limit
2) removes code for --writes_per_second and switches the 'background' write rate limit
to use --benchmark_write_rate_limit

Replaces https://reviews.facebook.net/D49113

Task ID: #9555881

Blame Rev:

Test Plan:
tools/run_flash_bench.sh

Revert Plan:

Database Impact:

Memcache Impact:

Other Notes:

EImportant:

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

Reviewers: igor

Reviewed By: igor

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D52485
2016-01-04 12:01:27 -08:00
Venkatesh Radhakrishnan
d74c9f0a57 DeleteFilesInRange: Clean job context if no files deleted
Summary:
We need to clean the job context if we end up not deleting any
files because no files are in the range specified.

Test Plan: DBCompactionTest.DeleteFileRange

Reviewers: sdong, anthony, yhchiang, kradhakrishnan, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D52467
2016-01-04 10:55:31 -08:00
Igor Canadi
1dec5b8f5d Merge pull request #916 from warrenfalk/capi_huge_page_option
Expose the option, memtable_prefix_bloom_huge_page_tlb_size, via C API
2016-01-04 09:24:30 -08:00
Warren Falk
0fde291abe expose memtable_prefix_bloom_huge_page_tlb_size option to C API 2015-12-31 09:27:03 -05:00
Warren Falk
7e81dba5cf Support creation of "full" format bloom filter from C API 2015-12-31 09:26:49 -05:00
Nathan Bronson
ac16663bd6 use -Werror=missing-field-initializers, to closer match MyRocks build
Summary:
myrocks seems to build rocksdb using
-Wmissing-field-initializers (and treats warnings as errors).  This diff
adds that flag to the rocksdb build, and fixes the compilation failures
that result.  I have not checked for any other differences in the build
flags for rocksdb build as part of myrocks.

Test Plan: make check

Reviewers: sdong, rven

Reviewed By: rven

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D52443
2015-12-30 14:56:18 -08:00
Venkatesh Radhakrishnan
7238be090e Fix clang build in db_compaction_test
Summary:
Fix CLANG build error caused by type mismatch. Changed type to
size_t.

Test Plan: Clang build and make check

Reviewers: sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D52413
2015-12-29 16:44:12 -08:00
Venkatesh Radhakrishnan
63ddb783db Delete files in given key range
Summary:
This is an initial diff for providing the ability to delete
files which are completely within a given range of keys.

Test Plan: DBCompactionTest.DeleteRange

Reviewers: IslamAbdelRahman, sdong

Reviewed By: sdong

Subscribers: yoshinorim, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D52293
2015-12-29 13:22:13 -08:00
sdong
d8677a8d2c Upgrade internal CLANG version for FB-internal gcc 4.8.1
Summary: After removing two move operations, we can make CLANG 3.7 build pass under GCC 4.8.1.

Test Plan: USE_CLANG=1 ROCKSDB_FBCODE_BUILD_WITH_481=1 make all -j32

Reviewers: yhchiang, IslamAbdelRahman, rven, anthony

Reviewed By: anthony

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D52365
2015-12-29 10:33:23 -08:00
Siying Dong
22c0ed8a5f Disable Visual Studio Warning C4351
Currently Windows build is broken because of Warning C4351. Disable the warning before figuring out the right way to fix it.
2015-12-28 15:06:34 -08:00
sdong
fcafac053f Fix memory leak in ColumnFamilyTest.WriteStall*
Summary: ColumnFamilyTest.WriteStallSingleColumnFamily and ColumnFamilyTest.WriteStallTwoColumnFamilies didn't clean up test state cleanly, causing memory leak. Fix it.

Test Plan: Run the two tests in valgrind and make sure they now pass.

Reviewers: yhchiang, anthony, rven, kradhakrishnan, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D52347
2015-12-28 12:30:21 -08:00
sdong
11672df19a Fix CLANG errors introduced by 7d87f02799
Summary: Fix some CLANG errors introduced in 7d87f02799

Test Plan: Build with both of CLANG and gcc

Reviewers: rven, yhchiang, kradhakrishnan, anthony, IslamAbdelRahman, ngbronson

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D52329
2015-12-28 10:00:58 -08:00
Nathan Bronson
7d87f02799 support for concurrent adds to memtable
Summary:
This diff adds support for concurrent adds to the skiplist memtable
implementations.  Memory allocation is made thread-safe by the addition of
a spinlock, with small per-core buffers to avoid contention.  Concurrent
memtable writes are made via an additional method and don't impose a
performance overhead on the non-concurrent case, so parallelism can be
selected on a per-batch basis.

Write thread synchronization is an increasing bottleneck for higher levels
of concurrency, so this diff adds --enable_write_thread_adaptive_yield
(default off).  This feature causes threads joining a write batch
group to spin for a short time (default 100 usec) using sched_yield,
rather than going to sleep on a mutex.  If the timing of the yield calls
indicates that another thread has actually run during the yield then
spinning is avoided.  This option improves performance for concurrent
situations even without parallel adds, although it has the potential to
increase CPU usage (and the heuristic adaptation is not yet mature).

Parallel writes are not currently compatible with
inplace updates, update callbacks, or delete filtering.
Enable it with --allow_concurrent_memtable_write (and
--enable_write_thread_adaptive_yield).  Parallel memtable writes
are performance neutral when there is no actual parallelism, and in
my experiments (SSD server-class Linux and varying contention and key
sizes for fillrandom) they are always a performance win when there is
more than one thread.

Statistics are updated earlier in the write path, dropping the number
of DB mutex acquisitions from 2 to 1 for almost all cases.

This diff was motivated and inspired by Yahoo's cLSM work.  It is more
conservative than cLSM: RocksDB's write batch group leader role is
preserved (along with all of the existing flush and write throttling
logic) and concurrent writers are blocked until all memtable insertions
have completed and the sequence number has been advanced, to preserve
linearizability.

My test config is "db_bench -benchmarks=fillrandom -threads=$T
-batch_size=1 -memtablerep=skip_list -value_size=100 --num=1000000/$T
-level0_slowdown_writes_trigger=9999 -level0_stop_writes_trigger=9999
-disable_auto_compactions --max_write_buffer_number=8
-max_background_flushes=8 --disable_wal --write_buffer_size=160000000
--block_size=16384 --allow_concurrent_memtable_write" on a two-socket
Xeon E5-2660 @ 2.2Ghz with lots of memory and an SSD hard drive.  With 1
thread I get ~440Kops/sec.  Peak performance for 1 socket (numactl
-N1) is slightly more than 1Mops/sec, at 16 threads.  Peak performance
across both sockets happens at 30 threads, and is ~900Kops/sec, although
with fewer threads there is less performance loss when the system has
background work.

Test Plan:
1. concurrent stress tests for InlineSkipList and DynamicBloom
2. make clean; make check
3. make clean; DISABLE_JEMALLOC=1 make valgrind_check; valgrind db_bench
4. make clean; COMPILE_WITH_TSAN=1 make all check; db_bench
5. make clean; COMPILE_WITH_ASAN=1 make all check; db_bench
6. make clean; OPT=-DROCKSDB_LITE make check
7. verify no perf regressions when disabled

Reviewers: igor, sdong

Reviewed By: sdong

Subscribers: MarkCallaghan, IslamAbdelRahman, anthony, yhchiang, rven, sdong, guyg8, kradhakrishnan, dhruba

Differential Revision: https://reviews.facebook.net/D50589
2015-12-25 11:03:40 -08:00
sdong
5b2587b5cb DBTest.HardLimit use special memtable
Summary: DBTest.HardLimit fails in appveyor build. Use special mem table to make the test behavior depends less on platform

Test Plan: Run the test with JEMALLOC both on and off.

Reviewers: yhchiang, kradhakrishnan, rven, anthony, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D52317
2015-12-25 10:25:34 -08:00
Siying Dong
298ba27ae2 Merge pull request #846 from yuslepukhin/enble_c4244_lossofdata
Enable MS compiler warning c4244.
2015-12-23 22:59:42 -08:00
Siying Dong
7810aa802a Merge pull request #899 from zhipeng-jia/fix_clang_warning
Fix clang warnings
2015-12-23 22:58:52 -08:00
Siying Dong
4c5560d70a Merge pull request #895 from zhipeng-jia/develop
Fix computation of size of last sub-compaction
2015-12-23 22:45:03 -08:00
sdong
d43da8ae0d DBTest.DelayedWriteRate: fix assert of sign and unsign comparison
Summary: DBTest.DelayedWriteRate has sign and unsign comparisons that break Windows build. Fix it.

Test Plan: Build and run the test modified.

Reviewers: IslamAbdelRahman, rven, anthony, yhchiang, kradhakrishnan

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D52311
2015-12-23 22:38:12 -08:00