- 26 11月, 2015 2 次提交
-
-
由 Igor Canadi 提交于
EnvWrapper: add ReuseWritableFile
-
由 Sage Weil 提交于
This was missed when ReuseWritableFile was added to Env in 1bcafb62. Signed-off-by: NSage Weil <sage@redhat.com>
-
- 25 11月, 2015 6 次提交
-
-
由 sdong 提交于
Summary: Now DBIter::Next() always compares with current key with itself first, which is unnecessary if the last key is not a merge key. I made the change and didn't see db_iter_test fails. Want to hear whether people have any idea what I miss. Test Plan: Run all unit tests Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D48279
-
由 Nathan Bronson 提交于
Summary: This diff completes the creation of InlineSkipList<Cmp>, which is like SkipList<const char*, Cmp> but it always allocates the key contiguously with the node. This allows us to remove the pointer from the node to the key. As a result the memory usage of the skip list is reduced (by 1 to sizeof(void*) bytes depending on the padding required to align the key storage), cache locality is improved, and we halve the number of calls to the allocator. For skip lists whose keys are freshly-allocated const char*, InlineSkipList is stricly preferrable to SkipList. This diff doesn't replace SkipList, however, because some of the use cases of SkipList in RocksDB are either character sequences that are not allocated at the same time as the skip list node allocation (for example hash_linklist_rep) or have different key types (for example write_batch_with_index). Taking advantage of inline allocation for those cases is left to future work. The perf win is biggest for small values. For single-threaded CPU-bound (32M fillrandom operations with no WAL log) with 16 byte keys and 0 byte values, the db_bench perf goes from ~310k ops/sec to ~410k ops/sec. For large values the improvement is less pronounced, but seems to be between 5% and 10% on the same configuration. Test Plan: make check Reviewers: igor, sdong Reviewed By: sdong Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D51123
-
由 Nathan Bronson 提交于
Summary: This diff is 2/3 in a sequence that introduces a skip list optimized for a key that is a freshly-allocated const char*. The change is broken into pieces to make it easier to review. This piece removes the Key template type, introduces the AllocateKey interface, and changes the unit test from using uint64_t as the Key type to using pointers to an 8 byte blob. Test Plan: unit test Reviewers: igor, sdong Reviewed By: sdong Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D51285
-
由 Nathan Bronson 提交于
Summary: This diff is 1/3 in a sequence that introduces a skip list optimized for a key that is a freshly-allocated const char*. The diff is broken into pieces to make it easier to review. This piece only introduces the new type by copying the existing SkipList, with mechanical naming changes and reformatting. Test Plan: new unit test Reviewers: igor, sdong Reviewed By: sdong Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D51279
-
由 Igor Canadi 提交于
Enable override to 3rd party linkage
-
由 Dmitri Smirnov 提交于
-
- 21 11月, 2015 4 次提交
-
-
由 agiardullo 提交于
Summary: DBTest.DynamicLevelCompressionPerLevel2 sometimes fails during valgrind runs. This causes our valgrind tests to fail. Not sure what the best fix is for this test, but hopefully this simple change is sufficient. Test Plan: run test Reviewers: sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D51111
-
由 Siying Dong 提交于
Build on Visual Studio 2015 Update 1
-
由 Venkatesh Radhakrishnan 提交于
Summary: Provide an API for compaction filter to specify that it needs to be applied even if there are snapshots. Test Plan: DBTestCompactionFilter.CompactionFilterIgnoreSnapshot Reviewers: yhchiang, IslamAbdelRahman, sdong, anthony Reviewed By: anthony Subscribers: yoshinorim, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D51087
-
由 yuslepukhin 提交于
-
- 20 11月, 2015 1 次提交
-
-
由 Islam AbdelRahman 提交于
Summary: Based on https://github.com/facebook/rocksdb/issues/843 It looks that when the data is hot we spend significant amount of time moving data out of RocksDB blocks. This patch reduce moving memory when possible Original performance ``` $ time ./ldb --db=/home/tec/local/ellina_test/testdb scan > /dev/null real 0m16.736s user 0m11.993s sys 0m4.725s ``` Performance after reducing memcpy ``` $ time ./ldb --db=/home/tec/local/ellina_test/testdb scan > /dev/null real 0m11.590s user 0m6.983s sys 0m4.595s ``` Test Plan: dump the output of the scan into 2 files and verifying the are exactly the same make check Reviewers: sdong, yhchiang, anthony, rven, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D51093
-
- 19 11月, 2015 5 次提交
-
-
由 Siying Dong 提交于
Enable MS Warning C4804 : unsafe use of type 'bool' in operation
-
由 sdong 提交于
Summary: In non-mmap mode, plain table reader can issue two pread() for index checking and reading the actual data, although it's for the same location. By reusing the key decoder, we reuse the buffer used for the two to avoid it. Test Plan: Run unit tests. Run table_reader_bench and see from strace the repeat read cases to disappear. Reviewers: anthony, yhchiang, rven, kradhakrishnan, IslamAbdelRahman Reviewed By: IslamAbdelRahman Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D50949
-
由 Dmitri Smirnov 提交于
-
由 sdong 提交于
Summary: Upgrade version of some dependencies in build_tools/fbcode_config4.8.1.sh. I didn't upgrade version for CLANG because some warnings are shown. Test Plan: build: ROCKSDB_FBCODE_BUILD_WITH_481=1 USE_CLANG=1 make all -j32 as well as ROCKSDB_FBCODE_BUILD_WITH_481=1 make all -j32 Reviewers: anthony, IslamAbdelRahman, kradhakrishnan, yhchiang, igor Reviewed By: igor Subscribers: igor, kradhakrishnan, leveldb, dhruba Differential Revision: https://reviews.facebook.net/D51003
-
由 sdong 提交于
Summary: forward_iterator_bench is not stable enough for build. Remove it for now. Test Plan: Build it with both of CLANG and non-CLANG and make sure it builds. Reviewers: rven, kradhakrishnan, anthony, yhchiang, igor, IslamAbdelRahman Reviewed By: igor, IslamAbdelRahman Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D50991
-
- 18 11月, 2015 15 次提交
-
-
由 Siying Dong 提交于
Fix log names when scheduling runs and reruns
-
由 Dmitri Smirnov 提交于
-
由 sdong 提交于
Summary: Now "ldb compact" skips the bottommost level compaction. This is an unintended behavior change. Reverting it now. Maybe we need to add another mode later for it. Test Plan: Run a manual test of 'ldb' to make sure bottom most level is compacted. Reviewers: IslamAbdelRahman, yhchiang, anthony, kradhakrishnan, rven Reviewed By: rven Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D50925
-
由 Siying Dong 提交于
Failed tests must be rerun with concurrency 1
-
由 Islam AbdelRahman 提交于
Support Memtable Factory Parse in option_helper.cc
-
由 sdong 提交于
Summary: The commit of option helper refactor broken the build: (1) a git merge problem (2) some uncaught compiler warning Fix it. Test Plan: Make sure "make all" passes Reviewers: anthony, IslamAbdelRahman, rven, kradhakrishnan, yhchiang Reviewed By: yhchiang Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D50943
-
由 Siying Dong 提交于
Option Helper Refactoring
-
由 sdong 提交于
Summary: SpecialEnv::time_elapse_only_sleep_ is not initialized, which might cause some test failures. Fix it. Test Plan: Run some unit tests. Since tests already broken. Might want to commit it sooner. Reviewers: IslamAbdelRahman, yhchiang, anthony Reviewed By: anthony Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D50937
-
由 sdong 提交于
Summary: DBTest.MergeTestTime is a test verifying timing counters. Depending on real time may cause non-determinstic results. Change to fake time to be determinsitic. Test Plan: Run the test and make sure it passes Reviewers: yhchiang, anthony, rven, kradhakrishnan, IslamAbdelRahman Reviewed By: IslamAbdelRahman Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D50883
-
由 SherlockNoMad 提交于
-
由 Dmitri Smirnov 提交于
Increase concurrency to 18 Fix exclusion but in the ps script
-
由 Yueh-Hsuan Chiang 提交于
Summary: In case rocksdb java package is built using make rocksdbjavastaticrelease, then only those rocksdb binary built under the virtual environments is release build. This patch fix this issue. Test Plan: PORTABLE=1 V=2 make rocksdbjavastaticrelease -j32 and make sure -O2 and -NDEBUG is included when compiling all source files. Reviewers: sdong, anthony, IslamAbdelRahman, rven, kradhakrishnan, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D50895
-
由 Islam AbdelRahman 提交于
Summary: Travis is now failing because we cannot compile forward_iterator_bench under MAC https://travis-ci.org/facebook/rocksdb/jobs/91524025 In forward_iterator_bench.cc we are using multiple functions that are not available in MAC like htobe64 be64toh Blocking forward_iterator_bench under MAC Test Plan: compile under mac Reviewers: rven, yhchiang, anthony, sdong Reviewed By: sdong Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D50889
-
由 Dmitri Smirnov 提交于
-
由 Venkatesh Radhakrishnan 提交于
Summary: db_tailing_iter_test was failing on some platforms because of an incorrect allocation and use. This diff fixes the issue. Test Plan: db_tailing_iter_test Run valgrind for db_tailing_iter_test Reviewers: igor, sdong Reviewed By: sdong Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D50835
-
- 17 11月, 2015 7 次提交
-
-
由 sdong 提交于
Summary: Timing counters' upper bounds depend on platform. It frequently fails in valgrind runs. Relax the upper bound. Test Plan: Run the same valgrind test and make sure it passes. Reviewers: rven, anthony, kradhakrishnan, IslamAbdelRahman Reviewed By: IslamAbdelRahman Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D50829
-
由 Islam AbdelRahman 提交于
Add necessary headers after cpplint rearranged includes
-
由 Dmitri Smirnov 提交于
-
由 Dmitri Smirnov 提交于
-
由 sdong 提交于
Summary: RocksDB 4.2 is already cut. Move to 4.3 Test Plan: Not needed Reviewers: IslamAbdelRahman Reviewed By: IslamAbdelRahman Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D50799
-
由 Reid Horuff 提交于
Summary: Handle multiple calls to DBImpl::PauseBackgroundWork() and DBImpl::ContinueBackgroundWork() Test Plan: rocksdb.information_schema handles this case. Reviewers: igor Reviewed By: igor Subscribers: hermanlee4, jkedgar, dhruba Differential Revision: https://reviews.facebook.net/D50781
-
由 Siying Dong 提交于
Remove forward_iter_bench from Win build.
-