- 02 5月, 2015 2 次提交
-
-
由 Venkatesh Radhakrishnan 提交于
Summary: This diff fixes a hang reported by a Github user. https://www.facebook.com/l.php?u=https%3A%2F%2Fgithub.com%2Ffacebook%2Frocksdb%2Fissues%2F595%23issuecomment-96983273&h=9AQFYOWlo Multiple large write batches with column families cause a hang. The issue was caused by not doing flushes/compaction when the write controller was stopped. Test Plan: Create a DBTest from the user's test case Reviewers: igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37929
-
由 Mark Callaghan 提交于
Summary: The default, use one iter for the whole test, isn't good. This cost me a few hours of debugging and a few days of tessting. For readonly that isn't realistic and for read-write that keeps a lot of old sst files around. I remove the option because nothing uses it and not calling gettimeofday per loop iteration adds about 3% to QPS at 20 threads. Task ID: # Blame Rev: Test Plan: run db_bench Revert Plan: Database Impact: Memcache Impact: Other Notes: EImportant: - begin *PUBLIC* platform impact section - Bugzilla: # - end platform impact - Reviewers: igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D37965
-
- 01 5月, 2015 3 次提交
-
-
由 Igor Canadi 提交于
Summary: fix build Test Plan: works Reviewers: kradhakrishnan Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37911
-
由 krad 提交于
Summary: CPU profiling reveals GetApproximateSizes as a bottleneck for performance. The current implementation is sub-optimal, it scans every file in every level to compute the result. We can take advantage of the fact that all levels above 0 are sorted in the increasing order of key ranges and use binary search to locate the starting index. This can reduce the number of comparisons required to compute the result. Test Plan: We have good test coverage. Run the tests. Reviewers: sdong, igor, rven, dynamike Subscribers: dynamike, maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37755
-
由 Igor Canadi 提交于
-
- 30 4月, 2015 2 次提交
-
-
由 Igor Canadi 提交于
Summary: Before the fix we also marked the bottommost level for compaction. This is wrong because then RocksDB has N+1 levels instead of N as before the compaction. Test Plan: SuggestCompactRangeTest in db_test Reviewers: yhchiang, rven Reviewed By: rven Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37869
-
由 Igor Canadi 提交于
Summary: For very detailed explanation of what's happening read this: https://github.com/facebook/rocksdb/issues/596 Test Plan: make check + new unit test Reviewers: yhchiang, anthony, rven Reviewed By: rven Subscribers: adamretter, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37779
-
- 29 4月, 2015 1 次提交
-
-
由 Yueh-Hsuan Chiang 提交于
[RocksJava] Remove deprecated methods
-
- 28 4月, 2015 3 次提交
-
-
由 agiardullo 提交于
Summary: Remove duplicate code. If this diff looks good, I will cleanup other call sites as well. Test Plan: unit tests Reviewers: rven, yhchiang, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37761
-
由 Mark Callaghan 提交于
Summary: This runs a benchmark for LevelDB similar to what we have in tools/run_flash_bench.sh. It requires changes to db_bench that I published in a LevelDB fork on github. Some results are at: http://smalldatum.blogspot.com/2015/04/comparing-leveldb-and-rocksdb-take-2.html Sample output: ops/sec mb/sec usec/op avg p50 Test 525 16.4 1904.5 1904.5 111.0 fillseq.v32768 75187 15.5 13.3 13.3 4.4 fillseq.v200 28328 5.8 35.3 35.3 4.7 overwrite.t1.s0 175438 0.0 5.7 5.7 4.4 readrandom.t1 28490 5.9 35.1 35.1 4.7 overwrite.t1.s0 121951 0.0 8.2 8.2 5.7 readwhilewriting.t1 Task ID: # Blame Rev: Test Plan: Revert Plan: Database Impact: Memcache Impact: Other Notes: EImportant: - begin *PUBLIC* platform impact section - Bugzilla: # - end platform impact - Reviewers: igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D37749
-
由 Igor Canadi 提交于
Summary: Added these events: * Recovery start, finish and also when recovery creates a file * Trivial move * Compaction start, finish and when compaction creates a file * Flush start, finish Also includes small fix to EventLogger Also added option ROCKSDB_PRINT_EVENTS_TO_STDOUT which is useful when we debug things. I've spent far too much time chasing LOG files. Still didn't get sst table properties in JSON. They are written very deeply into the stack. I'll address in separate diff. TODO: * Write specification. Let's first use this for a while and figure out what's good data to put here, too. After that we'll write spec * Write tools that parse and analyze LOGs. This can be in python or go. Good intern task. Test Plan: Ran db_bench with ROCKSDB_PRINT_EVENTS_TO_STDOUT. Here's the output: https://phabricator.fb.com/P19811976 Reviewers: sdong, yhchiang, rven, MarkCallaghan, kradhakrishnan, anthony Reviewed By: anthony Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37521
-
- 27 4月, 2015 1 次提交
-
-
由 Aashish Pant 提交于
Test Plan: Verified that valgrind build passes for cache_test Reviewers: igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D37665
-
- 26 4月, 2015 2 次提交
-
-
由 Igor Canadi 提交于
Summary: Build broken by https://github.com/facebook/rocksdb/commit/6ede020dc419c1621254f26060076ee6d2c2d792 Test Plan: make all Reviewers: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37689
-
由 Igor Canadi 提交于
fix typos
-
- 25 4月, 2015 4 次提交
-
-
由 clark.kang 提交于
-
由 Igor Canadi 提交于
Summary: Since we enabled jemalloc for open source builds, Travis looks like it's dying. Don't install jemalloc when running in travis Test Plan: none Reviewers: yhchiang Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D37659
-
由 Aashish Pant 提交于
Summary: Added keyword override for SetCapacity() Test Plan: Fixes build Reviewers: igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D37647
-
由 Aashish Pant 提交于
Summary: When new capacity is larger than existing capacity, simply update the capacity to the new valie When new capacity is less than existing capacity, but more than the usage, simply update the capacity to new value When new capacity is less than the existing capacity and existing usage both, try to purge entries in LRU if feasible to make usage < capacity Test Plan: Created unit tests in cache_test.cc Reviewers: sdong, rven, yhchiang, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D37527
-
- 24 4月, 2015 9 次提交
-
-
由 sdong 提交于
Summary: Make it build for CYGWIN. Need to define "-std=gnu++11" instead of "-std=c++11" and use some replacement functions. Test Plan: Build it and run some unit tests in CYGWIN Reviewers: yhchiang, rven, anthony, kradhakrishnan, igor Reviewed By: igor Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D37605
-
由 sdong 提交于
Summary: CompactRange for universal compaction with num_levels > 1 seems to have a bug. The unit test also has a bug so it doesn't capture the problem. Fix it. Revert the compact range to the logic equivalent to num_levels=1. Always compact all files together. It should also fix DBTest.IncreaseUniversalCompactionNumLevels. The issue was that options.write_buffer_size = 100 << 10 and options.write_buffer_size = 100 << 10 are not used in later test scenarios. So write_buffer_size of 4MB was used. The compaction trigger condition is not anymore obvious as expected. Test Plan: Run the new test and all test suites Reviewers: yhchiang, rven, kradhakrishnan, anthony, igor Reviewed By: igor Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D37551
-
由 Igor Canadi 提交于
Summary: Based on feedback from D37083. Are all of these correct? In some spaces it seems like we're doing SetMaxPossibleForUserKey() although we want the smallest possible internal key for user key. Test Plan: make check Reviewers: sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37341
-
由 Igor Canadi 提交于
Summary: Currently open source rocksdb only builds with tcmalloc. This diff first checks if jemalloc is available. If it is, it compiles with jemalloc. If it isn't, it checks for tcmalloc. Test Plan: Tried this out on my Ubuntu virtual machine and confirms that jemalloc is correctly detected and compiled. Reviewers: MarkCallaghan, yhchiang, rven, sdong Reviewed By: sdong Subscribers: adamretter, meyering, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D36789
-
由 Igor Canadi 提交于
Summary: Reading CompactionPicker I noticed this dangerous substraction of two unsigned integers. We should assert to mark this as safe. Test Plan: make check Reviewers: anthony, rven, yhchiang, sdong Reviewed By: sdong Subscribers: kradhakrishnan, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37041
-
由 Giuseppe Ottaviano 提交于
Summary: This diff implements a new `DB` method `PromoteL0` which moves all files in L0 to a given level skipping compaction, provided that the files have disjoint ranges and all levels up to the target level are empty. This method provides finer-grain control for trivial compactions, and it is useful for bulk-loading pre-sorted keys. Compared to D34797, it does not change the semantics of an existing operation, which can impact existing code. PromoteL0 is designed to work well in combination with the proposed `GetSstFileWriter`/`AddFile` interface, enabling to "design" the level structure by populating one level at a time. Such fine-grained control can be very useful for static or mostly-static databases. Test Plan: `make check` Reviewers: IslamAbdelRahman, philipp, MarkCallaghan, yhchiang, igor, sdong Reviewed By: sdong Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D37107
-
由 sdong 提交于
Summary: Add more logging to help debugging issues. Test Plan: Run test suites Reviewers: yhchiang, rven, igor Reviewed By: igor Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D37401
-
由 sdong 提交于
Summary: To further distinguish the corruption cases were caused by storage media or in memory states when writing it, add a paranoid check after writing the file to iterate all the rows. Test Plan: Add a new unit test for it Reviewers: rven, igor Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D37335
-
由 Mark Callaghan 提交于
Summary: This is done to avoid having each thread use the same seed between runs of db_bench. Without this we can inflate the OS filesystem cache hit rate on reads for read heavy tests and generally see the same key sequences get generated between teste runs. Task ID: # Blame Rev: Test Plan: Revert Plan: Database Impact: Memcache Impact: Other Notes: EImportant: - begin *PUBLIC* platform impact section - Bugzilla: # - end platform impact - Reviewers: igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D37563
-
- 23 4月, 2015 5 次提交
-
-
由 Venkatesh Radhakrishnan 提交于
Summary: A couple of times on Travis, we have had the thread status say that there were no compactions done and since we assert for it, the test failed. We now fix this by waiting till compaction started. Test Plan: run DBTEST::*PreShutdown* d=/tmp/j; rm -rf $d; seq 200 | parallel --gnu --eta 'd=/tmp/j/d-{}; mkdir -p $d; TEST_TMPDIR=$d ./db_test --gtest_filter=DBTest.PreShutdown* >& '$d'/log-{}' Reviewers: sdong, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D37545
-
由 Jim Meyering 提交于
Summary: Without this change, someone on the machine on which I run "make check" could cause me to overwrite arbitrary files owned by me, via a symlink attack. Instead of using a predictable temporary directory and accepting to use a preexisting one, always create a new one using mkdtemp. If $TEST_IOCTL_FRIENDLY_TMPDIR is set and usable, attempt first to find a usable temporary directory therein. If not, or if unusable, then try /var/tmp and /tmp. If none of those is usable abort with a diagnostic. To do that, I added a new class. Its constructor finds a suitable directory or aborts, the sole member prints that directory's name, and the destructor unlinks what should be an empty directory. Note that while the code before this did not remove its temporary directory, there was only one per $UID. Now, there would be at least one per run or one per test, depending on implementation, so it is important to remove them. Test Plan: Run this on a fedora rawhide system, where /tmp is a tmpfs file system, and /var/tmp is ext4. # This gives a diagnostic that /dev/shm is not suitable # and ends up using /var/tmp. TEST_IOCTL_FRIENDLY_TMPDIR=/dev/shm ./env_test # Uses /var/tmp; same as when envvar not set. TEST_IOCTL_FRIENDLY_TMPDIR=/var/tmp ./env_test # Uses /tmp unless it's tmpfs, in which case it gives # a diagnostic and uses /var/tmp. TEST_IOCTL_FRIENDLY_TMPDIR=/tmp ./env_test Reviewers: ljin, rven, igor.sugak, yhchiang, sdong, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D37287
-
由 Mark Callaghan 提交于
Summary: This lets the production toolchain libraries get used on devservers and in production. Task ID: #6849362 Blame Rev: Test Plan: Revert Plan: Database Impact: Memcache Impact: Other Notes: EImportant: - begin *PUBLIC* platform impact section - Bugzilla: # - end platform impact - Reviewers: igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D37533
-
由 Mark Callaghan 提交于
Summary: This adds: 1) use of --level_compaction_dynamic_level_bytes=true 2) use of --bytes_per_sync=2M The second is a big win for disks. The first helps in general. This also adds a new test, fillseq with 32kb values to increase the peak ingest and make it more likely that storage limits throughput. Sample outpout from the first 3 tests - https://gist.github.com/mdcallag/e793bd3038e367b05d6f Task ID: # Blame Rev: Test Plan: Revert Plan: Database Impact: Memcache Impact: Other Notes: EImportant: - begin *PUBLIC* platform impact section - Bugzilla: # - end platform impact - Reviewers: igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D37509
-
由 Igor Canadi 提交于
Summary: `echo` correctly interpretes \n on mac, but not on linux. On linux you have to give it `-e` to interpret \n. Unfortunately, `-e` options is not available on Mac. Go back to old way of checking gflags Test Plan: build_tools/build_detect_platform on mac and linux Reviewers: sdong Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D37515
-
- 22 4月, 2015 2 次提交
-
-
由 Siying Dong 提交于
Add "Tango Me" section in USERS.md
-
由 Min Zhou 提交于
-
- 21 4月, 2015 5 次提交
-
-
由 Igor Canadi 提交于
Summary: Based on comment from D37455 Test Plan: make install after make static_lib Reviewers: meyering Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D37461
-
由 Igor Canadi 提交于
Summary: make install fails when there is no shared lib. We need to revert the conditions, which will have the same effect, but without the failure Test Plan: make install after only compiling static library Reviewers: meyering Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37455
-
由 Igor Canadi 提交于
Summary: We should send error output to /dev/null Test Plan: none Reviewers: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37449
-
由 Igor Canadi 提交于
Summary: The current version tries to install librocksdb.so even though it doesn't exist. This version will install librocksdb.so.3.10.0 and then create soft links in place Test Plan: `make static_lib; sudo make install` does not try to install librocksdb.so `make shared_lib; sudo make install` installs one library and 3 symlinks. Before, four libraries were installed Reviewers: sdong, meyering Reviewed By: meyering Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37425
-
由 Igor Canadi 提交于
Summary: If the system has gflags with both `google` and `gflags` namespaces installed, we try to define GFLAGS as two things. This breaks the compile. Fix: Use `else if` -- try compiling with `google` namespace only if compile with `gflags` failed Test Plan: build_tools/build_detect_platform correctly identifies gflags Reviewers: lgalanis Reviewed By: lgalanis Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37389
-
- 18 4月, 2015 1 次提交
-
-
由 Jim Meyering 提交于
Summary: [NB: this is a prerequisite for the /tmp-abuse-fixing patch] This avoids spurious test failure on Linux systems like Fedora for which /tmp is a tmpfs file system. On a devtmpfs file system, ioctl(fd, FS_IOC_GETVERSION, &version) returns -1 with errno == ENOTTTY, indicating that that ioctl is not supported on such a file system. Do not let this cause test failures, e.g., where env_test would assert that file->GetUniqueId(...) > 0. Before this change, ./env_test would fail these three tests on a fedora rawhide system: [ FAILED ] 3 tests, listed below: [ FAILED ] EnvPosixTest.RandomAccessUniqueID [ FAILED ] EnvPosixTest.RandomAccessUniqueIDConcurrent [ FAILED ] EnvPosixTest.RandomAccessUniqueIDDeletes 3 FAILED TESTS The fix: When support for that ioctl is lacking, skip each affected test. Could be improved by noting which sub-tests are being skipped. Test Plan: run these on F21 and note that they now pass. TEST_TMPDIR=/dev/shm/rdb ./env_test ./env_test Reviewers: ljin, rven, igor.sugak, yhchiang, sdong, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D37323
-