1. 13 8月, 2014 2 次提交
  2. 12 8月, 2014 6 次提交
    • S
      Flush only one column family · 06a52bda
      Stanislau Hlebik 提交于
      Summary:
      Currently DBImpl::Flush() triggers flushes in all column families.
      Instead we need to trigger just the column family specified.
      
      Test Plan: make all check
      
      Reviewers: igor, ljin, yhchiang, sdong
      
      Reviewed By: sdong
      
      Subscribers: leveldb
      
      Differential Revision: https://reviews.facebook.net/D20841
      06a52bda
    • R
      Integrating Cuckoo Hash SST Table format into RocksDB · 9674c11d
      Radheshyam Balasundaram 提交于
      Summary:
      Contains the following changes:
      - Implementation of cuckoo_table_factory
      - Adding cuckoo table into AdaptiveTableFactory
      - Adding cuckoo_table_db_test, similar to lines of plain_table_db_test
      - Minor fixes to Reader: When a key is found in the table, return the key found instead of the search key.
      - Minor fixes to Builder: Add table properties that are required by Version::UpdateTemporaryStats() during Get operation. Don't define curr_node as a reference variable as the memory locations may get reassigned during tree.push_back operation, leading to invalid memory access.
      
      Test Plan:
      cuckoo_table_reader_test --enable_perf
      cuckoo_table_builder_test
      cuckoo_table_db_test
      make check all
      make valgrind_check
      make asan_check
      
      Reviewers: sdong, igor, yhchiang, ljin
      
      Reviewed By: ljin
      
      Subscribers: leveldb
      
      Differential Revision: https://reviews.facebook.net/D21219
      9674c11d
    • L
      make statistics ToString function empty instead of pure virtual · 37c6740c
      Lei Jin 提交于
      Summary: as title
      
      Test Plan: make release
      
      Reviewers: yhchiang, sdong
      
      Reviewed By: sdong
      
      Subscribers: leveldb
      
      Differential Revision: https://reviews.facebook.net/D21549
      37c6740c
    • S
      Merge pull request #228 from miguelportilla/develop · 18efdba8
      Siying Dong 提交于
      Changes to support unity build:
      
      Script for building the unity.cc file via Makefile
      Unity executable Makefile target for testing builds
      Source code changes to fix compilation of unity build
      18efdba8
    • F
      check prefix_size when using hash search in db_bench · d3f2ec69
      Feng Zhu 提交于
      Summary:
      1. Check prefix_size when enable use_hash_search in db_bench
      2. Remove include/statistics.h in db_bench
      
      Test Plan: ./db_bench --use_hash_search=1
      
      Reviewers: ljin, yhchiang, igor, sdong
      
      Reviewed By: sdong
      
      Subscribers: leveldb
      
      Differential Revision: https://reviews.facebook.net/D21375
      d3f2ec69
    • M
      Changes to support unity build: · 93e6b5e9
      miguelportilla 提交于
      * Script for building the unity.cc file via Makefile
      * Unity executable Makefile target for testing builds
      * Source code changes to fix compilation of unity build
      93e6b5e9
  3. 09 8月, 2014 4 次提交
  4. 08 8月, 2014 3 次提交
  5. 07 8月, 2014 7 次提交
  6. 06 8月, 2014 3 次提交
  7. 05 8月, 2014 1 次提交
  8. 02 8月, 2014 1 次提交
    • I
      Simplify SpatialIndexCursor · 5e3d5c5f
      Igor Canadi 提交于
      Summary:
      Since we have enough memory to hold all primary keys loaded from spatial index, it is better if we first load all of them (store them in unordered_set for deduplication) and then query on primary key column family one by one.
      
      We need to dedup all IDs, so we'll end up storing all of them in memory even with the current approach.
      
      Test Plan: ./spatial_db_test is happy
      
      Reviewers: yinwang
      
      Reviewed By: yinwang
      
      Subscribers: leveldb
      
      Differential Revision: https://reviews.facebook.net/D20949
      5e3d5c5f
  9. 01 8月, 2014 6 次提交
  10. 31 7月, 2014 7 次提交
    • F
      use stack instead of heap memory in ReadBlockContents in some case · b0999011
      Feng Zhu 提交于
      Summary:
        When compression is enabled, and blocksize is not too big, use the
        space in stack to hold bytes read from block.
      
      Bencmark:
      base version: commit 8f09d53f
        malloc: 1.30% -> 0.98%
        free: 1.49% -> 1.07%
      
      Test Plan:
        make all check
      
      Reviewers: ljin, yhchiang, dhruba, igor, sdong
      
      Reviewed By: sdong
      
      Subscribers: leveldb
      
      Differential Revision: https://reviews.facebook.net/D20679
      b0999011
    • Y
      Merge pull request #217 from zxcvdavid/patch-1 · 2ea5e78a
      Yueh-Hsuan Chiang 提交于
      fix project name in the comments
      2ea5e78a
    • D
      fix project name in the comments · 7ef7df00
      Demon 提交于
      fix project name in the comments
      7ef7df00
    • S
      Fix readonly db · 32159672
      Stanislau Hlebik 提交于
      Summary:
      DBImplReadOnly::CompactRange wasn't override DBImpl::CompactRange;
      this can cause problem when using StackableDB inheritors like
      DbWithTtl.
      P. S. Thanks C++11 for override :)
      
      Test Plan: make all check
      
      Reviewers: igor, sdong
      
      Reviewed By: sdong
      
      Subscribers: yhchiang, leveldb
      
      Differential Revision: https://reviews.facebook.net/D20829
      32159672
    • Y
      Fixed a typo in the comment for merge operator. · e9269e6e
      Yueh-Hsuan Chiang 提交于
      Summary:
      Fixed a typo in the comment for merge operator.
      
      Test Plan:
      n/a
      e9269e6e
    • Y
      Fixed the crash when merge_operator is not properly set after reopen. · 49ee5a4a
      Yueh-Hsuan Chiang 提交于
      Summary:
      Fixed the crash when merge_operator is not properly set after reopen
      and added two test cases for this.
      
      Test Plan:
      make merge_test
      ./merge_test
      
      Reviewers: igor, ljin, sdong
      
      Reviewed By: sdong
      
      Subscribers: benj, mvikjord, leveldb
      
      Differential Revision: https://reviews.facebook.net/D20793
      49ee5a4a
    • F
      remove malloc when create data and index iterator in Get · 8f09d53f
      Feng Zhu 提交于
      Summary:
        Define Block::Iter to be an independent class to be used by block_based_table_reader
        When creating data and index iterator, update an existing iterator rather than new one
        Thus malloc and free could be reduced
      
      Benchmark,
      Base:
      commit 76286ee6
      commands:
      --db=/dev/shm/rocksdb --num_levels=6 --key_size=20 --prefix_size=20 --keys_per_prefix=0 --value_size=100 --write_buffer_size=134217728 --max_write_buffer_number=2 --target_file_size_base=33554432 --max_bytes_for_level_base=1073741824 --verify_checksum=false --max_background_compactions=4 --use_plain_table=0 --memtablerep=prefix_hash --open_files=-1 --mmap_read=1 --mmap_write=0 --bloom_bits=10 --bloom_locality=1 --memtable_bloom_bits=500000 --compression_type=lz4 --num=2621440 --use_hash_search=1 --block_size=1024 --block_restart_interval=1 --use_existing_db=1 --threads=1 --benchmarks=readrandom —disable_auto_compactions=1
      
      malloc: 3.30% -> 1.42%
      free: 3.59%->1.61%
      
      Test Plan:
        make all check
        run db_stress
        valgrind ./db_test ./table_test
      
      Reviewers: ljin, yhchiang, dhruba, igor, sdong
      
      Reviewed By: sdong
      
      Subscribers: leveldb
      
      Differential Revision: https://reviews.facebook.net/D20655
      8f09d53f