Skip to content

R
rocksdb

kvdb / rocksdb
12 个月 前同步成功

通知 0
Star 0
Fork 0
R
rocksdb

体验新版 GitCode，发现更多精彩内容 >>

切换分支/标签
  1. 13 9月, 2016 1 次提交
  3. 10 9月, 2016 1 次提交
  5. 09 9月, 2016 3 次提交
  7. 08 9月, 2016 3 次提交
  9. 07 9月, 2016 6 次提交
  11. 06 9月, 2016 1 次提交
  13. 03 9月, 2016 6 次提交
  15. 02 9月, 2016 9 次提交
  17. 01 9月, 2016 4 次提交
    • I
      Fix Travis on Mac · 8ce1b844
      由 Islam AbdelRahman 提交于 
      Summary: not sure why travis complain about this line, works fine on my mac

Test Plan: run on my mac

Subscribers: andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D63045
      8ce1b844
    • K
      Fix Mac build failure (#1309) · 380e651a
      由 Kien-hung Li 提交于
      380e651a
    • A
      Thread-specific histogram statistics · 1613fa94
      由 Andrew Kryczka 提交于 
      Summary:
To reduce contention for atomics when HistogramStats are shared across
threads, this diff makes them thread-specific so updates are faster. This comes
at the expense of slower reads (much less frequent), which now require merging
all histograms. In this diff,

- Thread-specific HistogramImpl is created upon the thread's first measureTime()
- Thread-specific HistogramImpl are merged and deleted upon thread termination or ThreadLocalPtr destruction, whichever comes first
- getHistogramString() and histogramData() merge all histograms, both thread-specific and previously merged ones

Test Plan:
unit tests, ran db_bench and verified histograms look similar

before:

  $ TEST_TMPDIR=/dev/shm/ perf record -g ./db_bench --benchmarks=readwhilewriting --statistics --num=1000000 --use_existing_db --threads=64 --cache_size=250000000 --compression_type=lz4
  ...
  +    7.63%  db_bench     db_bench             [.] rocksdb::HistogramStat::Add

after:

  $ TEST_TMPDIR=/dev/shm/ perf record -g ./db_bench --benchmarks=readwhilewriting --statistics --num=1000000 --use_existing_db --threads=64 --cache_size=250000000 --compression_type=lz4
  ...
  +    0.98%  db_bench     db_bench             [.] rocksdb::HistogramStat::Add

Reviewers: sdong, MarkCallaghan, kradhakrishnan, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D62649
      1613fa94
    • A
      add prefix_seek_mode to db_iter_test · 6a14d55b
      由 Aaron Gao 提交于 
      Summary: add prefix_seek_mode to db_iter_test to enable data race test for iterator when prefix_extractor != nullptr

Test Plan: make all check -j64

Reviewers: andrewkr, IslamAbdelRahman, sdong

Reviewed By: sdong

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D63027
      6a14d55b
  19. 31 8月, 2016 4 次提交
    • Y
      Fix ClockCache memory leak · de47e2bd
      由 Yi Wu 提交于 
      Summary:
Fix ClockCache memory leak found by valgrind:
# Add destructor to cleanup cached values.
# Delete key with cache handle immediately after handle is recycled, and erase table entry immediately if duplicated cache entry is inserted.

Test Plan:
    make DISABLE_JEMALLOC=1 valgrind_check

Reviewers: IslamAbdelRahman, sdong

Reviewed By: sdong

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D62973
      de47e2bd
    • I
      Fix travis · f099af4c
      由 Islam AbdelRahman 提交于 
      Summary: Fix travis for mac by using gflags package instead of doing `brew install`

Test Plan: https://travis-ci.org/facebook/rocksdb/builds/156358515

Reviewers: sdong, andrewkr, lightmark, yiwu

Reviewed By: yiwu

Subscribers: andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D62997
      f099af4c
    • A
      fix bug in merge_iterator when data race happens · db74b1a2
      由 Aaron Gao 提交于 
      Summary:
core dump when run
`./db_stress --max_background_compactions=1 --max_write_buffer_number=3 --sync=0 --reopen=20 --write_buffer_size=33554432 --delpercent=5 --log2_keys_per_lock=10 --block_size=16384 --allow_concurrent_memtable_write=1 --test_batches_snapshots=0 --max_bytes_for_level_base=67108864 --progress_reports=0 --mmap_read=1 --kill_prefix_blacklist=WritableFileWriter::Append,WritableFileWriter::WriteBuffered --writepercent=35 --disable_data_sync=0 --readpercent=50 --subcompactions=3 --ops_per_thread=20000000 --memtablerep=skip_list --prefix_size=0 --target_file_size_multiplier=1 --column_families=1 --db=/dev/shm/rocksdb/rocksdb_crashtest_whitebox --threads=32 --disable_wal=0 --open_files=500000 --destroy_db_initially=0 --target_file_size_base=16777216 --nooverwritepercent=1 --iterpercent=10 --max_key=100000000 --prefixpercent=0 --use_clock_cache=false --kill_random_test=189 --cache_size=1048576 --verify_checksum=1`
Actually the relevant flag is `--threads`, data race when --thread > 1 cause problem.
It is possible that multiple
threads read/write memtable simultaneously. After one thread
calls Prev(), another thread may insert a new key just between
the current key and the key next, which may cause the
assert(current_ == CurrentForward()) failure when the first
thread calls Next() again if in prefix seek mode

Test Plan: rerun db_stress with >1 thread / make all check -j64

Reviewers: sdong, andrewkr, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D62979
      db74b1a2
    • A
      add nullptr check to internal_prefix_transform · b18f9c9e
      由 Aaron Gao 提交于 
      Summary: patch for D62361

Test Plan: make all check

Reviewers: sdong

Reviewed By: sdong

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D62883
      b18f9c9e
  21. 30 8月, 2016 2 次提交
    • J
      Update docs README.md · 4e395e87
      由 Joel Marcey 提交于 
      Summary: Update the docs `README.md` to be more specific to RocksDB as opposed to the more generic information that is there now.

Test Plan: visual

Reviewers: lgalanis, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D62733
      4e395e87
    • A
      support Prev() in prefix seek mode · 2482d5fb
      由 Aaron Gao 提交于 
      Summary: As title, make sure Prev() works as expected with Next() when the current iter->key() in the range of the same prefix in prefix seek mode

Test Plan: make all check -j64 (add prefix_test with PrefixSeekModePrev test case)

Reviewers: andrewkr, sdong, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: yoshinorim, andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D61419
      2482d5fb