- 21 1月, 2016 2 次提交
-
-
由 sdong 提交于
Add test that verifies all options in BlockBasedTableOptions is settable through GetBlockBasedTableOptionsFromString() Summary: Add a test OptionsParserTest.BlockBasedTableOptionsAdded, which will fail if a new option is added to BlockBasedTableOptions but is not settable through GetBlockBasedTableOptionsFromString(). Test Plan: Run the test. Also manually remove and add options and make sure it fails. Reviewers: anthony, IslamAbdelRahman, kradhakrishnan, rven, yhchiang, andrewkr Reviewed By: andrewkr Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D52953
-
由 Andrew Kryczka 提交于
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
-
- 20 1月, 2016 8 次提交
-
-
由 sdong 提交于
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
-
由 sdong 提交于
Summary: In crash test, when coming to each kill point, we start a random class using seed as current second. With this approach, for every second, the random number used is the same. However, in each second, there are multiple kill points with different frequency. It makes it hard to reason about chance of kill point to trigger. With this commit, we use thread local random seed to generate the random number, so that it will take different values per second, hoping it makes chances of killing much easier to reason about. Also significantly reduce the kill odd to make sure time before kiling is similar as before. Test Plan: Run white box crash test and see the killing happens as expected and the run time time before killing reasonable. Reviewers: kradhakrishnan, IslamAbdelRahman, rven, yhchiang, andrewkr, anthony Reviewed By: anthony Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D52971
-
由 Siying Dong 提交于
Solaris Build
-
由 David Bernard 提交于
geodb_impl.cc
-
由 David Bernard 提交于
This reverts commit eaa56375.
-
由 Mike Kolupaev 提交于
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
-
由 Siying Dong 提交于
Add Rakuten Marketing to USERS.md
-
由 Igor Canadi 提交于
Simple changes to support builds for ppc64[le] consistent with X86
-
- 19 1月, 2016 5 次提交
-
-
由 bcbrock 提交于
These simple changes are required to allow builds on ppc64[le] systems consistent with X86. The Makefile now recognizes both ppc64 and ppc64le, and in the absence of PORTABLE=1, the code will be built analogously to the X86 -march=native. Note that although GCC supports -mcpu=native -mtune=native on POWER, it doesn't work correctly on all systems. This is why we need to get the actual machine model from the AUX vector.
-
由 David Bernard 提交于
-
由 David Bernard 提交于
-
由 David Bernard 提交于
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
-
由 Selva Sarangan 提交于
-
- 16 1月, 2016 1 次提交
-
-
由 agiardullo 提交于
Summary: update internal build scripts to use zstd 0.4.5. Test Plan: built and ran tests with and without ROCKSDB_FBCODE_BUILD_WITH_481 Reviewers: yhchiang, rven, kradhakrishnan, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D52833
-
- 15 1月, 2016 3 次提交
-
-
由 Gunnar Kudrjavets 提交于
Summary: Depending on the order of include paths and versions of various headers we may end up in a situation where we'll encounter a build break caused by redefinition of constants. gcc-4.9-glibc-2.20 header update to include/bits/fcntl-linux.h introduced the definitions of FALLOC_FL_* constants. However, linux/falloc.h from kernel-headers also has FALLOC_FL_* constants defined. Therefore during the compilation we'll get "previously defined" errors. Test Plan: Both in the environment where the build break manifests (to make sure that the change fixed the problem) and in the environment where everything builds fine (to make sure that there are no regressions): make clean make -j 32 Reviewers: sdong, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D52821
-
由 agiardullo 提交于
Summary: Prepare to cut release Test Plan: no code change. Reviewers: yhchiang Reviewed By: yhchiang Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D52827
-
由 Siying Dong 提交于
Align statistics
-
- 14 1月, 2016 2 次提交
-
-
由 Dmitri Smirnov 提交于
Use Yield macro to make it a little more portable between platforms.
-
由 sdong 提交于
Summary: util/testutil.h doesn't seem to be used in tools/sst_dump_tool_imp.h. Remove it. Also move some other include to tools/sst_dump_tool.cc instead. Test Plan: Build with GCC, CLANG and with GCC 4.81 and 4.9. Reviewers: yuslepukhin, yhchiang, rven, anthony, IslamAbdelRahman Reviewed By: IslamAbdelRahman Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D52791
-
- 13 1月, 2016 1 次提交
-
-
由 Igor Canadi 提交于
fix a compile error on 32-bit (fixes #634)
-
- 12 1月, 2016 3 次提交
-
-
由 Islam AbdelRahman 提交于
Summary: After introducing Iterator::PinData(), we have extra overhead of deleting the pinned iterators that we track in a std::set This patch avoid inserting to the std::set if we have only one iterator (normal use case when no iterators are pinned) Before this change ``` DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="newiterator" --db="/tmp/rocksdbtest-8616/dbbench" --use_existing_db --disable_auto_compactions newiterator : 1.006 micros/op 994013 ops/sec; newiterator : 0.994 micros/op 1006295 ops/sec; newiterator : 0.990 micros/op 1010422 ops/sec; ``` After change ``` DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="newiterator" --db="/tmp/rocksdbtest-8616/dbbench" --use_existing_db --disable_auto_compactions newiterator : 0.754 micros/op 1326588 ops/sec; newiterator : 0.759 micros/op 1317394 ops/sec; newiterator : 0.691 micros/op 1446704 ops/sec; ``` Test Plan: make check -j64 Reviewers: yhchiang, rven, anthony, sdong Reviewed By: sdong Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D52761
-
由 Igor Canadi 提交于
Fix compile error.
-
由 Dmitri Smirnov 提交于
Use constructor style initialization instead of a cast for simplicity.
-
- 10 1月, 2016 2 次提交
-
-
由 dhruba borthakur 提交于
Add Smyte to USERS.md
-
由 Pete Hunt 提交于
-
- 09 1月, 2016 3 次提交
-
-
由 sdong 提交于
Summary: <array> is not included in table/plain_table_key_coding.h. It may be the cause of one CLANG build failure. Test Plan: Build it Reviewers: yhchiang, rven, IslamAbdelRahman Reviewed By: IslamAbdelRahman Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D52725
-
由 sdong 提交于
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
-
由 sdong 提交于
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
-
- 08 1月, 2016 6 次提交
-
-
由 Venkatesh Radhakrishnan 提交于
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
-
由 Warren Falk 提交于
-
由 Warren Falk 提交于
-
由 Warren Falk 提交于
-
由 Islam AbdelRahman 提交于
Summary: table_test is failing because we are creating a temp InternalComparator 14:27:28 [ RUN ] BlockBasedTableTest.NoopTransformSeek 14:27:28 pure virtual method called 14:27:28 terminate called without an active exception 14:27:28 /bin/sh: line 7: 2346261 Aborted (core dumped) ./$t Test Plan: make table_test -j64 && ./table_test --gtest_filter="BlockBasedTableTest.NoopTransformSeek" Reviewers: igor, sdong, anthony, rven Reviewed By: rven Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D52671
-
由 Warren Falk 提交于
-
- 07 1月, 2016 4 次提交
-
-
由 Islam AbdelRahman 提交于
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
-
由 Yueh-Hsuan Chiang 提交于
Summary: This patch reverts commit 57605d7e as it will cause BlockBasedTableTest.NoopTransformSeek test crashes in some environment. Test Plan: revert the patch Reviewers: anthony, IslamAbdelRahman, rven, kradhakrishnan, sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D52623
-
由 Yueh-Hsuan Chiang 提交于
Summary: When both whole_key_filtering and prefix_extractor are set, RocksDB will mistakenly encode prefix + whole key into the database instead of simply whole key when BlockBasedTable is used. This patch fixes this bug. Test Plan: Add a test in table_test Reviewers: anthony, IslamAbdelRahman, rven, kradhakrishnan, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D52233
-
由 Yueh-Hsuan Chiang 提交于
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
-