- 14 2月, 2017 2 次提交
-
-
由 Yi Wu 提交于
Summary: Seems to me `has_unpersisted_data_` is read from read thread and write from write thread concurrently without synchronization. Making it an atomic. I update the logic not because seeing any problem with it, but it just feel confusing. Closes https://github.com/facebook/rocksdb/pull/1869 Differential Revision: D4555837 Pulled By: yiwu-arbug fbshipit-source-id: eff2ab8
-
由 Sagar Vemuri 提交于
Summary: Remove disableDataSync, and another similarly named disable_data_sync options. This is being done to simplify options, and also because the performance gains of this feature can be achieved by other methods. Closes https://github.com/facebook/rocksdb/pull/1859 Differential Revision: D4541292 Pulled By: sagar0 fbshipit-source-id: 5b3a6ca
-
- 13 2月, 2017 1 次提交
-
-
由 Adam Retter 提交于
Summary: The previous version of zlib is no longer available. I have also updated the versions of the other static libraries and added checkum checks for the downloads; This is related to https://github.com/facebook/rocksdb/issues/1769 Closes https://github.com/facebook/rocksdb/pull/1863 Differential Revision: D4550742 Pulled By: yiwu-arbug fbshipit-source-id: 4414150
-
- 11 2月, 2017 4 次提交
-
-
由 Andrew Kryczka 提交于
Summary: needed so we can proactively find issues like #1858 Closes https://github.com/facebook/rocksdb/pull/1862 Differential Revision: D4545854 Pulled By: ajkr fbshipit-source-id: d77fcb7
-
由 Adam Retter 提交于
Summary: Closes https://github.com/facebook/rocksdb/issues/1317 Closes https://github.com/facebook/rocksdb/pull/1845 Differential Revision: D4546491 Pulled By: siying fbshipit-source-id: 86190b4
-
由 Siying Dong 提交于
Summary: Also clean up HISTORY.md a little bit. Closes https://github.com/facebook/rocksdb/pull/1854 Differential Revision: D4539556 Pulled By: siying fbshipit-source-id: 567391e
-
由 Dmitri Smirnov 提交于
Summary: Record the first parsed sequence number as the minimum so we can find the true minimum otherwise everything is larger than zero. Fix the comparator name comparision. Closes https://github.com/facebook/rocksdb/pull/1858 Differential Revision: D4544365 Pulled By: ajkr fbshipit-source-id: 439cbc2
-
- 09 2月, 2017 4 次提交
-
-
由 Andrew Kryczka 提交于
Summary: It was really annoying to have two places (top and bottom of compaction loop) where we cut output files. I had bugs in both DeleteRange and dictionary compression due to updating only one of the two. This diff consolidates the file-cutting logic to the bottom of the compaction loop. Keep in mind that my goal with input_status is to be consistent with the past behavior, even though I'm not sure it's ideal. Closes https://github.com/facebook/rocksdb/pull/1832 Differential Revision: D4503038 Pulled By: ajkr fbshipit-source-id: 7da5213
-
由 Maysam Yabandeh 提交于
Summary: Announce the experimetnal two-level index feature in HISTORY.md. Also updated the default for index_per_partition to 1024. Closes https://github.com/facebook/rocksdb/pull/1855 Differential Revision: D4530102 Pulled By: maysamyabandeh fbshipit-source-id: b0fc6ff
-
由 Maysam Yabandeh 提交于
Summary: Printing compaction stats used to operate on two variable: number_levels_: for printing the layer num_levels_to_check: for updating the compaction score After this commit: 361010d4 these two are mixed up and as a result the last layer might not be printed out: https://fb.facebook.com/groups/rocksdb.internal/permalink/1315716625143616/ number_levels_ was used to decide which layers to print: https://github.com/facebook/rocksdb/blob/672300f47f72b28c164fdf98a08171c09e311205/db/internal_stats.cc#L753 but after the patch it is based on the return value of DumpCFMapStats https://github.com/facebook/rocksdb/blob/361010d44738de48ffc4fd9add70caa0891a0719/db/internal_stats.cc#L929 which returns num_levels_to_check: https://github.com/facebook/rocksdb/blob/361010d44738de48ffc4fd9add70caa0891a0719/db/internal_stats.cc#L917 Closes https://github.com/facebook/rocksdb/pull/1853 Differential Revision: D4529280 Pulled By: maysamyabandeh fbshipit-source-id: 3fd9448
-
由 Maysam Yabandeh 提交于
Summary: Closes https://github.com/facebook/rocksdb/pull/1849 Differential Revision: D4528696 Pulled By: maysamyabandeh fbshipit-source-id: c12f3a2
-
- 08 2月, 2017 4 次提交
-
-
由 Andrew Kryczka 提交于
Summary: move the argument description to the right section, make it clearer that the '=' sign is required, and use it in one subcommand where it seemed forgotten before. Closes https://github.com/facebook/rocksdb/pull/1840 Differential Revision: D4515096 Pulled By: ajkr fbshipit-source-id: 7b5b1c1
-
由 Andrew Kryczka 提交于
Summary: I want to be able to, e.g., DECLARE_string(statistics_string); in my application such that I can override the default value of statistics_string. For this to work, we need to remove the unnamed namespace containing all the flags, and make sure all variables/functions covered by that namespace are static. Replaces #1828 due to internal tool issues. Closes https://github.com/facebook/rocksdb/pull/1844 Differential Revision: D4515124 Pulled By: ajkr fbshipit-source-id: 23b695e
-
由 Andrew Kryczka 提交于
Summary: statistics are always concurrently updated regardless of whether a single instance or multiple instances are used. remove the warning since it's unnecessarily preventing people from sharing stats objects across rocksdb instances. replace #1819 which was having some problem with our internal tools. Closes https://github.com/facebook/rocksdb/pull/1826 Differential Revision: D4495970 Pulled By: ajkr fbshipit-source-id: 6601f61
-
由 James Sun 提交于
Summary: …ring Replace the numerical output for compaction_style and compaction_pri with strings Closes https://github.com/facebook/rocksdb/pull/1817 Differential Revision: D4482796 Pulled By: highker fbshipit-source-id: 5785768
-
- 07 2月, 2017 3 次提交
-
-
由 Maysam Yabandeh 提交于
Summary: Partition Index blocks and use a Partition-index as a 2nd level index. The two-level index can be used by setting BlockBasedTableOptions::kTwoLevelIndexSearch as the index type and configuring BlockBasedTableOptions::index_per_partition t15539501 Closes https://github.com/facebook/rocksdb/pull/1814 Differential Revision: D4473535 Pulled By: maysamyabandeh fbshipit-source-id: bffb87e
-
由 Dmitri Smirnov 提交于
Summary: introduce new methods into a public threadpool interface, - allow submission of std::functions as they allow greater flexibility. - add Joining methods to the implementation to join scheduled and submitted jobs with an option to cancel jobs that did not start executing. - Remove ugly `#ifdefs` between pthread and std implementation, make it uniform. - introduce pimpl for a drop in replacement of the implementation - Introduce rocksdb::port::Thread typedef which is a replacement for std::thread. On Posix Thread defaults as before std::thread. - Implement WindowsThread that allocates memory in a more controllable manner than windows std::thread with a replaceable implementation. - should be no functionality changes. Closes https://github.com/facebook/rocksdb/pull/1823 Differential Revision: D4492902 Pulled By: siying fbshipit-source-id: c74cb11
-
由 Vitaliy Liptchinsky 提交于
Summary: Added method that returns approx num of entries as well as size for memtables. Closes https://github.com/facebook/rocksdb/pull/1841 Differential Revision: D4511990 Pulled By: VitaliyLi fbshipit-source-id: 9a4576e
-
- 04 2月, 2017 3 次提交
-
-
由 Rhys Parry 提交于
Summary: The gcc-4.8.1-glibc-2.17 platform is deprecated and will be removed soon. Closes https://github.com/facebook/rocksdb/pull/1839 Differential Revision: D4509684 Pulled By: siying fbshipit-source-id: 3efe296
-
由 Andrew Kryczka 提交于
Summary: make sst_dump print size/contents of the dictionary meta-block for easier debugging Closes https://github.com/facebook/rocksdb/pull/1837 Differential Revision: D4506399 Pulled By: ajkr fbshipit-source-id: b9bf668
-
由 Siying Dong 提交于
Summary: In theory, Get() can get a wrong result, if it races in a special with with flush. The bug can be reproduced in DBTest2.GetRaceFlush. Fix this bug by getting snapshot after referencing the super version. Closes https://github.com/facebook/rocksdb/pull/1816 Differential Revision: D4475958 Pulled By: siying fbshipit-source-id: bd9e67a
-
- 03 2月, 2017 4 次提交
-
-
由 Islam AbdelRahman 提交于
Summary: merger.h was always a confusing name for me, simply give the file a better name Closes https://github.com/facebook/rocksdb/pull/1836 Differential Revision: D4505357 Pulled By: IslamAbdelRahman fbshipit-source-id: 07b28d8
-
由 Dmitri Smirnov 提交于
Summary: Closes https://github.com/facebook/rocksdb/pull/1829 Differential Revision: D4502314 Pulled By: siying fbshipit-source-id: f46fac1
-
由 Siying Dong 提交于
Summary: Closes https://github.com/facebook/rocksdb/pull/1834 Differential Revision: D4503469 Pulled By: siying fbshipit-source-id: 761bfa6
-
由 Siying Dong 提交于
Summary: The recent update about fallocate failed OSX build. Fix it. Closes https://github.com/facebook/rocksdb/pull/1830 Differential Revision: D4500235 Pulled By: siying fbshipit-source-id: a5f2b40
-
- 02 2月, 2017 2 次提交
-
-
由 Siying Dong 提交于
Summary: Change the default of delayed slowdown value to 16MB/s and further increase the L0 stop condition to 36 files. Closes https://github.com/facebook/rocksdb/pull/1821 Differential Revision: D4489229 Pulled By: siying fbshipit-source-id: 1003981
-
由 Siying Dong 提交于
Summary: Closes https://github.com/facebook/rocksdb/pull/1824 Differential Revision: D4493862 Pulled By: siying fbshipit-source-id: c168446
-
- 01 2月, 2017 2 次提交
-
-
由 Islam AbdelRahman 提交于
Summary: C++11 in-class initialization is cleaner and makes it the default more explicit to our users and more visible. Use it for ColumnFamilyOptions and DBOptions Closes https://github.com/facebook/rocksdb/pull/1822 Differential Revision: D4490473 Pulled By: IslamAbdelRahman fbshipit-source-id: c493a87
-
由 Islam AbdelRahman 提交于
Summary: The code in DBOptions::Dump is simply a duplicate of the code in ImmutableDBOptions::Dump and MutableDBOptions.Dump consolidate duplicate code. tested visually Closes https://github.com/facebook/rocksdb/pull/1818 Differential Revision: D4486710 Pulled By: IslamAbdelRahman fbshipit-source-id: 7085189
-
- 28 1月, 2017 2 次提交
-
-
由 oranagra 提交于
Summary: - rocksdb_property_int (so that we don't have to parse strings) - and rocksdb_set_options (to allow controlling options via strings) - a few other missing options exposed - a documentation comment fix Closes https://github.com/facebook/rocksdb/pull/1793 Differential Revision: D4456569 Pulled By: yiwu-arbug fbshipit-source-id: 9f1fac1
-
由 Siying Dong 提交于
Summary: In the patch which LRU cache was made use dynamic shard bits, I changed to 2 shard bits to make the test happy. Look like it is occasionally still unhappy. Change it to 4 shard bits. Closes https://github.com/facebook/rocksdb/pull/1815 Differential Revision: D4475849 Pulled By: siying fbshipit-source-id: 575ff00
-
- 27 1月, 2017 5 次提交
-
-
由 Siying Dong 提交于
Summary: If the users use the NewLRUCache() without passing in the number of shard bits, instead of using hard-coded 6, we'll determine it based on capacity. Closes https://github.com/facebook/rocksdb/pull/1584 Differential Revision: D4242517 Pulled By: siying fbshipit-source-id: 86b0f18
-
由 Siying Dong 提交于
Summary: A current data race issue in Get() and Flush() can cause a Get() to return wrong results when a flush happened in the middle. Disable the test for now. Closes https://github.com/facebook/rocksdb/pull/1813 Differential Revision: D4472310 Pulled By: siying fbshipit-source-id: 5755ebd
-
由 Andrew Kryczka 提交于
Summary: Added -statistics_string to deserialize a Statistics object using the factory functions registered by applications. Closes https://github.com/facebook/rocksdb/pull/1812 Differential Revision: D4469811 Pulled By: ajkr fbshipit-source-id: 2d80862
-
由 Andrew Kryczka 提交于
Summary: I added the Cache::Ref() function a couple weeks ago (#1761) to make this feature possible. Like other meta-blocks, rep_->range_del_entry holds a cache handle to pin the range deletion block in uncompressed block cache for the duration of the table reader's lifetime. We can reuse this cache handle to create an iterator over this meta-block without any cache lookup. Ref() is used to increment the cache handle's refcount in case the returned iterator outlives the table reader. Closes https://github.com/facebook/rocksdb/pull/1801 Differential Revision: D4458782 Pulled By: ajkr fbshipit-source-id: 2883f10
-
由 Andrew Kryczka 提交于
Summary: For case !handle->InCache() && handle->refs >= 1 (the third case mentioned in lru_cache.h), the key was overwritten by Insert(). In this case, the refcount can still be incremented, and the cache handle will never enter LRU list. Fix Ref() logic for this case. Closes https://github.com/facebook/rocksdb/pull/1808 Differential Revision: D4467656 Pulled By: ajkr fbshipit-source-id: c0784d8
-
- 26 1月, 2017 4 次提交
-
-
由 Andrew Kryczka 提交于
Summary: The Env registration framework supports registering client Envs and selecting which one to instantiate according to a text field. This enabled things like adding the -env_uri argument to db_bench, so the same binary could be reused with different Envs just by changing CLI config. Now this problem has come up again in a non-Env context, as I want to instantiate a client Statistics implementation from db_bench, which is configured entirely via text parameters. Also, in the future we may wish to use it for deserializing client objects when loading OPTIONS file. This diff generalizes the Env registration logic to work with arbitrary types. - Generalized registration and instantiation code by templating them - The entire implementation is in a header file as that's Google style guide's recommendation for template definitions - Pattern match with std::regex_match rather than checking prefix, which was the previous behavior - Rename functions/files to be non-Env-specific Closes https://github.com/facebook/rocksdb/pull/1776 Differential Revision: D4421933 Pulled By: ajkr fbshipit-source-id: 34647d1
-
由 sdong 提交于
Summary: If we don't wait for the threads to finish after each run, the thread queue may not be empty while the next test starts to run, which can cause unexpected behaviors. Also make some of the relaxed read/write more restrict. Closes https://github.com/facebook/rocksdb/pull/1590 Reviewed By: AsyncDBConnMarkedDownDBException Differential Revision: D4245922 Pulled By: AsyncDBConnMarkedDownDBException fbshipit-source-id: f83b74b
-
由 sdong 提交于
Summary: logs_.back() is called out of DB mutex, which can cause data race. We move the access into the DB mutex protection area. Closes https://github.com/facebook/rocksdb/pull/1774 Reviewed By: AsyncDBConnMarkedDownDBException Differential Revision: D4417472 Pulled By: AsyncDBConnMarkedDownDBException fbshipit-source-id: 2da1f1e
-
由 Islam AbdelRahman 提交于
Summary: GetAndRefSuperVersion() should not be called again in the same thread before ReturnAndCleanupSuperVersion() is called. If we have a compaction filter that is using DB::Get, This will happen ``` CompactFiles() { GetAndRefSuperVersion() // -- first call .. CompactionFilter() { GetAndRefSuperVersion() // -- second call ReturnAndCleanupSuperVersion() } .. ReturnAndCleanupSuperVersion() } ``` We solve this issue in the same way Iterator is solving it, but using GetReferencedSuperVersion() This was discovered in https://github.com/facebook/mysql-5.6/issues/427 by alxyang Closes https://github.com/facebook/rocksdb/pull/1803 Differential Revision: D4460155 Pulled By: IslamAbdelRahman fbshipit-source-id: 5e54322
-