- 02 2月, 2016 1 次提交
-
-
由 Dmitri Smirnov 提交于
This change impacts only non-buffered I/O on Windows. Currently, there is a buffer per RandomAccessFile instance that is protected by a lock. The reason we maintain the buffer is non-buffered I/O requires an aligned buffer to work. XPerf traces demonstrate that we accumulate a considerable wait time while waiting for that lock. This change enables to set random access buffer size to zero which would indicate a per request allocation. We are expecting that allocation expense would be much less than I/O costs plus wait time due to the fact that the memory heap would tend to re-use page aligned allocations especially with the use of Jemalloc. This change does not affect buffer use as a read_ahead_buffer for compaction purposes.
-
- 30 1月, 2016 1 次提交
-
-
由 Venkatesh Radhakrishnan 提交于
Summary: If options.base_background_compactions is given, we try to schedule number of compactions not existing this number, only when L0 files increase to certain number, or pending compaction bytes more than certain threshold, we schedule compactions based on options.max_background_compactions. The watermarks are calculated based on slowdown thresholds. Test Plan: Add new test cases in column_family_test. Adding more unit tests. Reviewers: IslamAbdelRahman, yhchiang, kradhakrishnan, rven, anthony Reviewed By: anthony Subscribers: leveldb, dhruba, yoshinorim Differential Revision: https://reviews.facebook.net/D53409
-
- 29 1月, 2016 4 次提交
-
-
由 sdong 提交于
Summary: Now slowing down for the last mem table takes priority against some stopping conditions. This is logically confusing. Fix it. Test Plan: Run all existing tests. Reviewers: yhchiang, IslamAbdelRahman, kradhakrishnan, andrewkr, anthony Reviewed By: anthony Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D53529
-
由 Islam AbdelRahman 提交于
Summary: Add a new class SstFileTracker that will be notified whenever a DB add/delete/move and sst file, it will also replace DeleteScheduler SstFileTracker can be used later to abort writes when we exceed a specific size Test Plan: unit tests Reviewers: rven, anthony, yhchiang, sdong Reviewed By: sdong Subscribers: igor, lovro, march, dhruba Differential Revision: https://reviews.facebook.net/D50469
-
由 agiardullo 提交于
Summary: Removed a couple of memory allocations Test Plan: changes covered by existing tests Reviewers: rven, yhchiang, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D53523
-
由 Igor Canadi 提交于
fix build for raspberry 2
-
- 28 1月, 2016 5 次提交
-
-
由 benoitc 提交于
fix #810
-
由 sdong 提交于
Summary: It's a regression bug caused by e089db40. With the change, if options.optimize_filters_for_hits=true and there are only L0 files (like single level universal compaction), we skip all the files in L0, which is more than necessary. Fix it by always trying to query bloom filter for files in level 0. Test Plan: Add a unit test for it. Reviewers: anthony, rven, yhchiang, IslamAbdelRahman, kradhakrishnan, andrewkr Reviewed By: andrewkr Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D53493
-
由 Siying Dong 提交于
Fixing generated GenerateBuildVersion.vcxproj on non English locale
-
由 Igor Canadi 提交于
Add Wingify to USERS.md
-
由 Ankit Jain 提交于
VWO, the flagship product of Wingify, uses RocksDB to populate the list of URLs where clients can run A/B test campaigns. It is also used to provide a way for the clients to see if VWO's Smart Code is installed on a specific URL of their account.
-
- 27 1月, 2016 13 次提交
-
-
由 Tomas Kolda 提交于
-
由 Tomas Kolda 提交于
locale than english. The problem is that date and time CLI utilities generates different format so that REGEX in CMake does not work.
-
由 sdong 提交于
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
-
由 Islam AbdelRahman 提交于
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
-
由 Andrew Kryczka 提交于
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
-
由 Islam AbdelRahman 提交于
Summary: This patch update fbcode_config4.8.1.sh to get it's dependencies the same way we updated fbcode_config.sh in D53037 as a result zstd is upgraded to 0.4.7 instead of 0.4.5 Test Plan: make clean && ROCKSDB_FBCODE_BUILD_WITH_481=1 make check -j64 make clean && ROCKSDB_FBCODE_BUILD_WITH_481=1 USE_CLANG=1 make check -j64 Reviewers: yhchiang, andrewkr, rven, kradhakrishnan, sdong Reviewed By: sdong Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D53355
-
由 Yueh-Hsuan Chiang 提交于
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
-
由 Islam AbdelRahman 提交于
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
-
由 Andrew Kryczka 提交于
-
由 Andrew Kryczka 提交于
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
-
由 Andrew Kryczka 提交于
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
-
由 krad 提交于
Summary: Initially I removed "valgrind" from the list since it take too much time (3+hr) compared to tsan (40 min) when the tests are run in parallel. It is not effective to run the tests in parallel in sandcastle and tsan takes about 3hrs as well. Adding valgrind to the list. Test Plan: Submit this diff and watch the run Reviewers: sdong, rven Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D53337
-
由 Venkatesh Radhakrishnan 提交于
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
-
- 26 1月, 2016 8 次提交
-
-
由 sdong 提交于
Summary: Add an option --column_family option, so that users can query or update specific column family. Also add an create column family parameter to make unit test easier. Still need to add unit tests. Test Plan: Will add a test case in ldb python test. Reviewers: yhchiang, rven, andrewkr, IslamAbdelRahman, kradhakrishnan, anthony Reviewed By: anthony Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D53265
-
由 sdong 提交于
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
-
由 sdong 提交于
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
-
由 Islam AbdelRahman 提交于
Summary: This diff - Include the rest of the dependencies (kernel-headers, binutils, valgrind) in dependencies.sh - updtade zst to 0.4.7 - It also fix a problem in clang scan build Test Plan: make check USE_CLANG=1 make check USE_CLANG=1 make analyze coverage_test.sh Reviewers: sdong, yhchiang, rven, andrewkr, kradhakrishnan Reviewed By: kradhakrishnan Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D53301
-
由 Andrew Kryczka 提交于
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
-
由 Venkatesh Radhakrishnan 提交于
Summary: Added make targets parallel_test and parallel_dbtest to run tests in parallel. Each test is run 32 times in parallel. There is a timeout to catch hangs. The test continues after a failure and reports non-zero status on failure Test Plan: Run the two make targets Reviewers: anthony, yhchiang, IslamAbdelRahman, kradhakrishnan, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D53079
-
由 Islam AbdelRahman 提交于
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
-
由 krad 提交于
Summary: Cosmetic fixes and some comments for the script. It is one big hack and hopefully the comments will make it easy to maintain. Test Plan: Run manual tests Reviewers: sdong, rven Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D53277
-
- 23 1月, 2016 4 次提交
-
-
由 sdong 提交于
Summary: Add a test to fail if someone adds a DB options. Test Plan: Run the test, run the test with valgrind. Add an option to DB option in the middle or in the end and make sure it fails. Reviewers: yhchiang, anthony, IslamAbdelRahman, kradhakrishnan, rven, andrewkr Reviewed By: andrewkr Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D53097
-
由 krad 提交于
Summary: - UI is enhanced to lists the tests, status and the results - We are using the same pre-commit tool as the make equivalent - No more emails to user on failure - Dropped valgrind from the list since it can be a time hogger (and can hurt scheduling for others) - Patching bug fix - Made the jobs run in parallel in sandcastle Test Plan: Manual test Reviewers: sdong, rven, igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D53217 Making parallel requests to sandcastle Test Plan: Run manual tests Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D53259
-
由 Islam AbdelRahman 提交于
Summary: Update fbcode_config.sh so that It try to use the latest version for dependencies that we are using, after updating the code these libraries where updated ``` Snappy: 1.0.3 => 1.1.3 GFLAGS: 1.6 => 2.1.1 JEMALLOC: 3.6.0 => 4.0.3 ``` I have also updated clang from 3.7 to 3.7.1 ``` Clang 3.7 => 3.7.1 ``` Another change is that we use the same tp2 directory as fbcode, so we dont need to keep changing commit hash every time we need to change a version of a compiler or a library Test Plan: make check -j64 USE_CLANG=1 make check -j64 DISABLE_JEMALLOC=1 OPT=-g make all valgrind_check -j32 (make sure it's running) Reviewers: yhchiang, anthony, rven, kradhakrishnan, andrewkr, sdong Reviewed By: sdong Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D53037
-
由 agiardullo 提交于
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
-
- 22 1月, 2016 4 次提交
-
-
由 agiardullo 提交于
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
-
由 krad 提交于
Summary: This patch provides a mechanism to run pre commit tests on the local branch before committing. This can help prevent frequent build breaks. The tests can be run in parallel by specifying the J=<..> environment variable. Test Plan: Run manually Reviewers: sdong rven tec CC: leveldb@ Task ID: #9689218 Blame Rev:
-
由 Andrew Kryczka 提交于
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
-
由 Andrew Kryczka 提交于
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
-