a42324e | Jim Meyering | 19 February 2015, 21:11:10 UTC | build: do not relink every single binary just for a timestamp Summary: Prior to this change, "make check" would always waste a lot of time relinking 60+ binaries. With this change, it does that only when the generated file, util/build_version.cc, changes, and that happens only when the date changes or when the current git SHA changes. This change makes some other improvements: before, there was no rule to build a deleted util/build_version.cc. If it was somehow removed, any attempt to link a program would fail. There is no longer any need for the separate file, build_tools/build_detect_version. Its functionality is now in the Makefile. * Makefile (DEPFILES): Don't filter-out util/build_version.cc. No need, and besides, removing that dependency was wrong. (date, git_sha, gen_build_version): New helper variables. (util/build_version.cc): New rule, to create this file and update it only if it would contain new information. * build_tools/build_detect_platform: Remove file. * db/db_impl.cc: Now, print only date (not the time). * util/build_version.h (rocksdb_build_compile_time): Remove declaration. No longer used. Test Plan: - Run "make check" twice, and note that the second time no linking is performed. - Remove util/build_version.cc and ensure that any "make" command regenerates it before doing anything else. - Run this: strings librocksdb.a|grep _build_. That prints output including the following: rocksdb_build_git_date:2015-02-19 rocksdb_build_git_sha:2.8.fb-1792-g3cb6cc0 Reviewers: ljin, sdong, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D33591 | 19 February 2015, 21:11:10 UTC |
d45a6a4 | sdong | 12 February 2015, 01:10:43 UTC | Add rocksdb.num-live-versions: number of live versions Summary: Add a DB property about live versions. It can be helpful to figure out whether there are files not live but not yet deleted, in some use cases. Test Plan: make all check Reviewers: rven, yhchiang, igor Reviewed By: igor Subscribers: yoshinorim, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D33327 | 19 February 2015, 21:10:37 UTC |
11581b7 | Jim Meyering | 19 February 2015, 19:48:09 UTC | build: abbreviate AR command, too Summary: The "ar" command was excessively verbose. This abbreviates it to be like CC and LD. Also, factor "rs" options into ARFLAGS. Test Plan: $ rm librocksdb.a $ make librocksdb.a AR librocksdb.a ar: creating librocksdb.a Reviewers: ljin, sdong, igor.sugak, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D33699 | 19 February 2015, 19:48:09 UTC |
b8ac71b | Igor Canadi | 18 February 2015, 21:14:53 UTC | Revert "Fbson to Json" This reverts commit 7ce1b2c19c00f303214305ac4cc9a67296ede84a. | 18 February 2015, 21:14:53 UTC |
7ce1b2c | stash93 | 18 February 2015, 20:58:56 UTC | Fbson to Json Summary: Replaced rapidjson with fbson Test Plan: make all check make valgrind_check Reviewers: golovachalexander, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D32733 | 18 February 2015, 20:58:56 UTC |
7d81726 | Venkatesh Radhakrishnan | 18 February 2015, 19:49:31 UTC | Managed iterator Summary: This is a diff for managed iterator. A managed iterator is a wrapper around an iterator which saves the options for that iterator as well as the current key/value so that the underlying iterator and its associated memory can be released when it is aged out automatically or on the request of the user. Will provide the automatic release as a follow-up diff. Test Plan: Managed* tests in db_test and XF tests for managed iterator Reviewers: igor, yhchiang, anthony, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D31401 | 18 February 2015, 19:49:31 UTC |
b4b8c25 | Jim Meyering | 18 February 2015, 19:43:30 UTC | build: factor out AM_LINK command (trivial) Summary: Many link commands were identical. Factor that out into a variable, AM_LINK, and use it in place of all of those open-coded commands. Test Plan: run "make check" Reviewers: ljin, igor, sdong Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D33585 | 18 February 2015, 19:43:30 UTC |
dc885c6 | Jim Meyering | 18 February 2015, 19:42:54 UTC | build: make "make" output readable by default Summary: With this change, make now prints a summary line for each compiler and linker invocation, e.g.,: CC db/builder.o CC db/c.o CC db/column_family.o To see full commands, insert "V=1" into your make command. E.g., run "make V=1 all" if you want it to print each command in its full glory. $^ is GNU make's abbreviation for the prerequisites of the current target. These AM_V_... variables expand to some very short string like "CC" or "LD", by default, so that the output of "make" is readable. If/when you want more details, just build with "make V=1 ...", and make will print each full command as it is executed. If you prefer to see the noise all the time, and only want to optionally see the abbreviated output, set AM_DEFAULT_VERBOSITY=1 in your environment, and then build with V=0 to see the abbreviated command indicators. Test Plan: invoke make a few different ways and observe: make clean; make # abbreviated make clean; make V=0 # also abbreviated make clean; make V=1 # full detail Reviewers: sdong, ljin, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D33579 | 18 February 2015, 19:42:54 UTC |
a37b46a | Jim Meyering | 18 February 2015, 19:42:18 UTC | build: fix Makefile inconsistencies (trivial) Summary: This is in preparation for some factorization. * Makefile (deletefile_test): Add $(COVERAGEFLAGS) to link command. (options_test): Remove explicit (redundant) dependency on options_helper.o: that is already a dependent, via $(LIBOBJECTS) Test Plan: run make Reviewers: sdong, ljin, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D33573 | 18 February 2015, 19:42:18 UTC |
55277c3 | Jim Meyering | 18 February 2015, 19:40:56 UTC | build: remove unused rules: rocksdb_shell, DBClientProxy_test Summary: There were Makefile rules to build those two targets, but neither rule has worked for a long time, due to missing dependent source files. Remove those rules. Test Plan: run "make" Reviewers: sdong, ljin, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D33567 | 18 February 2015, 19:40:56 UTC |
3ad6b79 | Igor Sugak | 18 February 2015, 01:54:02 UTC | rocksdb: Fix 'Division by zero' scan-build warning Summary: scan-build complains with division by zero warning in a test. Added an assertion to prevent this. scan-build report: http://home.fburl.com/~sugak/latest6/report-c61be9.html#EndPath Test Plan: Make sure scan-build does not report 'Division by zero' and all tests are passing. ```lang=bash % make analyze % make check ``` Reviewers: igor, meyering Reviewed By: meyering Subscribers: sdong, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D33495 | 18 February 2015, 01:54:02 UTC |
1275313 | Yueh-Hsuan Chiang | 17 February 2015, 20:00:48 UTC | Remove ThreadStatusMultiCompaction test Summary: Remove ThreadStatusMultiCompaction test as it's currently written in a way that depends on some randomness, while the flush / compaction status of a single thread is also covered in ThreadStatusFlush and ThreadStatusSingleCompaction tests. Test Plan: ./db_test Reviewers: igor, sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D33537 | 17 February 2015, 20:04:56 UTC |
f0c36da | Yueh-Hsuan Chiang | 17 February 2015, 19:29:36 UTC | Add thread_status_util_debug.cc back Summary: Add thread_status_util_debug.cc back as InstrumentedMutex related tests are using it to produce wait that can be reflected in the counter. Test Plan: ./perf_context_test export ROCKSDB_TESTS=MutexWaitStats ./db_test Reviewers: sdong, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D33525 | 17 February 2015, 19:29:36 UTC |
daebb1f | Jim Meyering | 17 February 2015, 19:17:44 UTC | build: running "make" with no arguments must not "uninstall" Summary: Before this change, running "make" with no arguments would silently run the rules for the "uninstall" target(!). Don't do that. * Makefile (default): New, first target; depend on "all". (uninstall, install): Do not hide the commands we run. Test Plan: Run "make" and verify that the rules for "uninstall" are no longer run. Instead, note that many files are compiled and linked. Before, none were. Reviewers: sdong, ljin, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D33531 | 17 February 2015, 19:17:44 UTC |
e60bc99 | Yueh-Hsuan Chiang | 17 February 2015, 18:13:52 UTC | Allow GetThreadList to reflect flush activity. Summary: Allow GetThreadList to reflect flush activity. Test Plan: Developed ThreadStatusFlush test and updated ThreadStatusMultiCompaction test. ./db_test ./thread_list_test Reviewers: sdong, rven, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D32871 | 17 February 2015, 18:13:52 UTC |
b9a0213 | Jim Meyering | 14 February 2015, 00:26:35 UTC | build: fix unportable Makefile syntax Summary: * Makefile (dummy): Prefix this statement with "dummy := ", so that it no longer triggers a syntax error from GNU make 3.80 and earlier. Reported by nielsl in https://github.com/facebook/rocksdb/issues/509 Test Plan: run make Reviewers: sdong, ljin, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D33429 | 14 February 2015, 00:26:35 UTC |
4e4b857 | Igor Sugak | 13 February 2015, 23:10:47 UTC | rocksdb: Fix scan-build 'Called C++ object pointer is null' and 'Dereference of null pointer' bugs Summary: In the existing implementation of `ASSERT*`, test termination happens in `~Tester`, which is called when instance of `Tester` goes out of scope. This is the cause of many scan-build bugs. This diff changes `ASSERT*` to terminate the test immediately. Also added one suppression in `util/signal_test.cc` scan-build bugs before: http://home.fburl.com/~sugak/latest/index.html after: http://home.fburl.com/~sugak/latest2/index.html Test Plan: Modify some test to fail an assertion and make sure that `ASSERT*` terminated the test. Run `make analyze` and make sure no 'Called C++ object pointer is null' and 'Dereference of null pointer' bugs reported. Run tests and make sure no failing tests: ```lang=bash % make check % USE_CLANG=1 make check ``` Reviewers: meyering, lgalanis, sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D33381 | 13 February 2015, 23:10:47 UTC |
b3fd162 | Jim Meyering | 13 February 2015, 19:40:23 UTC | build: remove unportable use of sed in favor of $(CXX)'s -MT Summary: The code being removed would invoke sed differently to work around a portability difference in how sed -i works (different on MacOS). Yet performing a host-type-based ifdef fails when the tools installed do not match. That sed use was solely to post-process the .d file. Instead, generate the desired output directly, by using the compiler's -MT<FILE> option. * Makefile (%.d: %.cc): With the prior use of Makefile-ifdef'd sed, when building on MacOS with gnu sed, every run of this rule would fail with a sed usage error. Also list each .d file as a dependent. Test Plan: Ensure that a selected .d file is the same as before both with g++ and with clang++. However, note that the new .d files each contain a new reference to the .d file itself. Reviewers: sdong, ljin, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D33369 | 13 February 2015, 19:40:23 UTC |
e7ea51a | Igor Canadi | 12 February 2015, 17:54:48 UTC | Introduce job_id for flush and compaction Summary: It would be good to assing background job their IDs. Two benefits: 1) makes LOGs more readable 2) I might use it in my EventLogger, which will try to make our LOG easier to read/query/visualize Test Plan: ran rocksdb, read the LOG Reviewers: sdong, rven, yhchiang Reviewed By: yhchiang Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D31617 | 12 February 2015, 17:54:48 UTC |
6a0e737 | fyrz | 12 February 2015, 17:20:02 UTC | [RocksJava] Raw use of parametrized class Resolved raw use of parametrized class issues. | 12 February 2015, 17:23:25 UTC |
4397012 | fyrz | 12 February 2015, 16:58:53 UTC | [RocksJava] Redundant access-modifier in interfaces Removed redundant access modifier in interfaces. | 12 February 2015, 16:58:53 UTC |
2d62e80 | Igor Canadi | 12 February 2015, 16:47:18 UTC | Merge pull request #504 from fyrz/RocksJava-Flush-Correction [RocksJava] FlushOptions Correction | 12 February 2015, 16:47:18 UTC |
eaf3956 | fyrz | 12 February 2015, 16:31:38 UTC | [RocksJava] FlushOptions Correction SetWaitForFlush did not set flush properly. | 12 February 2015, 16:31:38 UTC |
5d1151d | Ramki Balasubramanian | 12 February 2015, 02:40:11 UTC | Added simple monitoring script to monitor overusage of memory in db_bench Summary: rockuse more memory that asked to. Monitor and report. Test Plan: run the pro with conditions to simulate the overusage. It should report that the process is using more memory than needed. Reviewers: yhchiang, rven, sdong, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D33249 | 12 February 2015, 02:40:11 UTC |
5f00af4 | sdong | 12 February 2015, 00:11:40 UTC | DBTest.DestroyDBMetaDatabase: create DB directories if not exists Summary: DBTest.DestroyDBMetaDatabase occasionally fails on my dev host, for file not existing. Always create directories to avoid that. Test Plan: Run the test Reviewers: rven, yhchiang, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D33321 | 12 February 2015, 00:16:50 UTC |
68af781 | sdong | 05 February 2015, 01:03:57 UTC | Remember whole key/prefix filtering on/off in SST file Summary: Remember whole key or prefix filtering on/off in SST files. If user opens the DB with a different setting that cannot be satisfied while reading the SST file, ignore the bloom filter. Test Plan: Add a unit test for it Reviewers: yhchiang, igor, rven Reviewed By: rven Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D32889 | 11 February 2015, 19:20:04 UTC |
fd5970b | Igor Canadi | 11 February 2015, 03:56:33 UTC | Merge pull request #503 from weiweisd/master modify double type equal check in json_document.cc | 11 February 2015, 03:56:33 UTC |
513ad86 | Wei Wei | 11 February 2015, 02:19:52 UTC | modify double type euqal compare in json_document.cc | 11 February 2015, 02:19:52 UTC |
933973d | Yueh-Hsuan Chiang | 11 February 2015, 01:16:24 UTC | Merge pull request #495 from fyrz/RocksJava-CF-Name-Byte-Handling [RocksJava] CF Name shall handle bytes correctly | 11 February 2015, 01:16:24 UTC |
5e8e453 | fyrz | 10 February 2015, 19:57:08 UTC | [RocksJava] Integrated changes from D33165 | 10 February 2015, 20:12:27 UTC |
677d024 | fyrz | 03 February 2015, 19:28:33 UTC | [RocksJava] CF Name shall handle bytes correctly Summary: Bytes are currently misinterpreted by the Java if the byte array contains zero bytes within its content. For Strings thats usually not useful. As the Java API allows every kind of byte array values it might be the case that zero padding might happen. Test Plan: make rocksdbjava make jtest Reviewers: adamretter, yhchiang, ankgup87 Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D33165 | 10 February 2015, 20:00:00 UTC |
d1cafc0 | Wei Wei | 10 February 2015, 14:57:28 UTC | Merge pull request #1 from facebook/master merge from facebook | 10 February 2015, 14:57:28 UTC |
6d6305d | sdong | 10 February 2015, 00:12:31 UTC | Perf Context to report DB mutex waiting time Summary: Add counters in perf context to allow users to figure out how time spent on waiting for DB mutex Test Plan: Add a test and run it. Reviewers: yhchiang, rven, igor Reviewed By: igor Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D33177 | 10 February 2015, 01:55:12 UTC |
863009b | Igor Canadi | 10 February 2015, 01:38:32 UTC | Fix deleting obsolete files #2 Summary: For description of the bug, see comment in db_test. The fix is pretty straight forward. Test Plan: added unit test. eventually we need better testing of FOF/POF process. Reviewers: yhchiang, rven, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D33081 | 10 February 2015, 01:38:32 UTC |
1851f97 | Grace Law | 09 February 2015, 22:53:58 UTC | Added RocksDB stats GET_HIT_L0 and GET_HIT_L1 Summary: - In statistics.h , added tickers. - In version_set.cc, -- Added a getter method for hit_file_level_ in the class FilePicker -- Added a line in the Get() method in case of a found, increment the corresponding counters based on the level of the file respectively. Corresponding task: https://our.intern.facebook.com/intern/tasks/?s=506100481&t=5952818 Personal fork: https://github.com/sycamlaw43/rocksdb/commit/0c3f2e3600a1e0faad63249c45f3951fd0430b30 Test Plan: In terminal, ``` make -j32 db_test ROCKSDB_TESTS=L0L1L2AndUpHitCounter ./db_test ``` Or to use debugger, ``` make -j32 db_test export ROCKSDB_TESTS=L0L1L2AndUpHitCounter gdb db_test ``` Reviewers: rven, sdong Reviewed By: sdong Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D32205 | 09 February 2015, 22:53:58 UTC |
91ac3b2 | sdong | 09 February 2015, 20:03:45 UTC | Print DB pointer when opening a DB Summary: Having a pointer for DB will be helpful to debug when GDB or working on a dump. If the client process doesn't have any thread actively working on RocksDB, it can be hard to find out. Test Plan: make all check Reviewers: rven, yhchiang, igor Reviewed By: igor Subscribers: yoshinorim, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D33159 | 09 February 2015, 20:52:58 UTC |
bee4e51 | Igor Canadi | 09 February 2015, 20:21:32 UTC | Merge pull request #492 from fyrz/logger-logv-virtual Switch logv with loglevel to virtual | 09 February 2015, 20:21:32 UTC |
cfe8837 | fyrz | 01 February 2015, 19:08:19 UTC | Switch logv with loglevel to virtual | 09 February 2015, 19:59:29 UTC |
aaceef3 | Igor Canadi | 09 February 2015, 17:53:30 UTC | Fix formatting | 09 February 2015, 17:53:30 UTC |
ee4aa9a | Igor Canadi | 09 February 2015, 17:51:19 UTC | Merge pull request #481 from mkevac/backupable Allow creating and restoring backups from C | 09 February 2015, 17:51:19 UTC |
82faa37 | Marko Kevac | 09 February 2015, 16:34:50 UTC | added simple example for db restore from backup | 09 February 2015, 16:34:50 UTC |
d090330 | Marko Kevac | 09 February 2015, 09:16:04 UTC | fixed c_simple_example and added some comments | 09 February 2015, 09:16:04 UTC |
9651308 | Marko Kevac | 09 February 2015, 09:11:42 UTC | renamed backup to backup_and_restore in c_test for clarity | 09 February 2015, 09:11:42 UTC |
bbb52b2 | Yueh-Hsuan Chiang | 09 February 2015, 06:53:11 UTC | Merge pull request #483 from adamretter/restructure-java-build Restructure java build | 09 February 2015, 06:53:11 UTC |
7e50ed8 | Marko Kevac | 07 February 2015, 11:25:10 UTC | Added some more wrappers and wrote a test for backup in C | 07 February 2015, 11:25:10 UTC |
218c3ec | Igor Canadi | 06 February 2015, 21:01:59 UTC | Fix std::cout data race Summary: std::cout is not thread safe. tsan complains. Eliminate it. Test Plan: env_test with TSAN Reviewers: yhchiang, rven, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D33087 | 06 February 2015, 21:01:59 UTC |
8f679c2 | Karthikeyan Radhakrishnan | 06 February 2015, 19:02:25 UTC | Merge branch 'master' of github.com:facebook/rocksdb | 06 February 2015, 19:02:25 UTC |
da9cbce | Karthikeyan Radhakrishnan | 02 February 2015, 17:47:24 UTC | Add Header to logging to capture application level information Summary: This change adds LogHeader provision to the logger. For the rolling logger implementation, the headers are copied over to the new log file every time there is a log roll over. Test Plan: Added a unit test to test the rolling log case. Reviewers: sdong Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D32817 | 06 February 2015, 18:37:45 UTC |
2a97982 | Igor Canadi | 06 February 2015, 16:44:30 UTC | Fix deleting obsolete files Summary: This diff basically reverts D30249 and also adds a unit test that was failing before this patch. I have no idea how I didn't catch this terrible bug when writing a diff, sorry about that :( I think we should redesign our system of keeping track of and deleting files. This is already a second bug in this critical piece of code. I'll think of few ideas. BTW this diff is also a regression when running lots of column families. I plan to revisit this separately. Test Plan: added a unit test Reviewers: yhchiang, rven, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D33045 | 06 February 2015, 16:44:30 UTC |
8e83a9d | Yueh-Hsuan Chiang | 06 February 2015, 10:38:14 UTC | Add a missing field for STATE_MUTEX_WAIT to global_state_table Summary: Add a missing field for STATE_MUTEX_WAIT to global_state_table. This will fix the failure of thread_list_test. Test Plan: thread_list_test | 06 February 2015, 10:38:14 UTC |
6f10130 | Igor Canadi | 06 February 2015, 04:09:42 UTC | Fix DestroyDB Summary: When DestroyDB() finds a wal file in the DB directory, it assumes it is actually in WAL directory. This can lead to confusion, since it reports IO error when it tries to delete wal file from DB directory. For example: https://ci-builds.fb.com/job/rocksdb_clang_build/296/console This change will fix our unit tests. Test Plan: unit tests work Reviewers: yhchiang, rven, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D32907 | 06 February 2015, 04:09:42 UTC |
7de4e99 | Igor Canadi | 05 February 2015, 19:44:17 UTC | Revert "Fix wal_dir not getting cleaned" This reverts commit f36d394aeddf420661e54a1a0a54fcc790c9cffb. | 05 February 2015, 19:44:17 UTC |
9a52e06 | Jonah Cohen | 05 February 2015, 16:26:33 UTC | Add GetID to ColumnFamilyHandle Summary: Expose GetID to ColumnFamilyHandle interface so that we can save column family data by id instead of name. Test Plan: Testing in MySQL on Rocks. Reviewers: sdong, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D32943 | 05 February 2015, 16:26:33 UTC |
181191a | Yueh-Hsuan Chiang | 05 February 2015, 05:39:45 UTC | Add a counter for collecting the wait time on db mutex. Summary: Add a counter for collecting the wait time on db mutex. Also add MutexWrapper and CondVarWrapper for measuring wait time. Test Plan: ./db_test export ROCKSDB_TESTS=MutexWaitStats ./db_test verify stats output using db_bench make clean make release ./db_bench --statistics=1 --benchmarks=fillseq,readwhilewriting --num=10000 --threads=10 Sample output: rocksdb.db.mutex.wait.micros COUNT : 7546866 Reviewers: MarkCallaghan, rven, sdong, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D32787 | 05 February 2015, 05:39:45 UTC |
f36d394 | Igor Canadi | 05 February 2015, 02:57:22 UTC | Fix wal_dir not getting cleaned | 05 February 2015, 02:57:22 UTC |
53ae09c | sdong | 05 February 2015, 02:03:36 UTC | db_test: fix a data race in SpecialEnv Summary: db_test's test class SpecialEnv has a thread unsafe variable rnd_ but it can be accessed by multiple threads. It is complained by TSAN. Protect it by a mutex. Test Plan: Run the test Reviewers: yhchiang, rven, igor Reviewed By: igor Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D32895 | 05 February 2015, 02:32:53 UTC |
fe9f691 | sdong | 04 February 2015, 23:32:06 UTC | Fix fault_injestion_test Summary: A bug in MockEnv causes fault_injestion_test to fail. I don't know why it doesn't fail every time but it doesn't seem to be right. Test Plan: Run fault_injestion_test Also run db_test with MEM_ENV=1 until the first failure. Reviewers: yhchiang, rven, igor Reviewed By: igor Subscribers: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D32877 | 05 February 2015, 01:49:07 UTC |
b37f5ff | Igor Canadi | 05 February 2015, 00:24:52 UTC | Put db_test back to TESTS in Makefile | 05 February 2015, 00:24:52 UTC |
108470e | Igor Canadi | 05 February 2015, 00:24:02 UTC | Fix stack trace on mac | 05 February 2015, 00:24:02 UTC |
3e53760 | Igor Canadi | 05 February 2015, 00:20:25 UTC | Fix compaction_picker_test | 05 February 2015, 00:20:25 UTC |
e39f4f6 | Igor Canadi | 05 February 2015, 00:04:51 UTC | Fix data race #3 Summary: Added requirement that ComputeCompactionScore() be executed in mutex, since it's accessing being_compacted bool, which can be mutated by other threads. Also added more comments about thread safety of FileMetaData, since it was a bit confusing. However, it seems that FileMetaData doesn't have data races (except being_compacted) Test Plan: Ran 100 ConvertCompactionStyle tests with thread sanitizer. On master -- some failures. With this patch -- none. Reviewers: yhchiang, rven, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D32283 | 05 February 2015, 00:04:51 UTC |
e63140d | sdong | 03 February 2015, 01:42:57 UTC | Get() to use prefix bloom filter when filter is not block based Summary: Get() now doesn't make use of bloom filter if it is prefix based. Add the check. Didn't touch block based bloom filter. I can't fully reason whether it is correct to do that. But it's straight-forward to for full bloom filter. Test Plan: make all check Add a test case in DBTest Reviewers: rven, yhchiang, igor Reviewed By: igor Subscribers: MarkCallaghan, leveldb, dhruba, yoshinorim Differential Revision: https://reviews.facebook.net/D31941 | 04 February 2015, 23:15:41 UTC |
678503e | Yueh-Hsuan Chiang | 04 February 2015, 09:47:32 UTC | Add utility functions for interpreting ThreadStatus Summary: Add ThreadStatus::GetOperationName() and ThreadStatus::GetStateName(), two utility functions that help interpreting ThreadStatus. Test Plan: ./thread_list_test Reviewers: sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D32793 | 04 February 2015, 09:47:32 UTC |
4d98e29 | Igor Sugak | 04 February 2015, 05:43:06 UTC | rocksdb: Enable scan-build static analysis Summary: Added new target ##make analyze## into Makefile. This command runs clang static analyzer and builds the sources as ##make all##. The result report is put into ##$(RocksDbSourceRoot)/can_build_report/## If the development environment is a Facebook devserver and ##ROCKSDB_NO_FBCODE## is not set, then scan-build is used from fbcode. If it is run not on a Facebook devserver, scan-build should be available in ##$PATH##. I'll add details to wiki how to install scan-build on a non Facebook devserver environment. Test Plan: Run the fallowing commands on a Facebook devserver and Mac OS, and ensure no build or test errors. ``` % make all check -j32 % make clean % USE_CLANG=1 make all -j32 % make analyze % USE_CLANG=1 make analyze ``` Reviewers: sdong, lgalanis, leveldb, igor Reviewed By: igor Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D32799 | 04 February 2015, 05:43:06 UTC |
756e1f1 | Yueh-Hsuan Chiang | 04 February 2015, 01:53:05 UTC | Remove unused util/thread_event_info.h Summary: Remove unused util/thread_event_info.h, which is replaced by util/thread_operation.h Test Plan: make dbg -j32 make release -j32 | 04 February 2015, 01:53:05 UTC |
dad98dd | Venkatesh Radhakrishnan | 03 February 2015, 20:19:56 UTC | Changes for supporting cross functional tests for inplace_update Summary: This diff containes the changes to the code and db_test for supporting cross functional tests for inplace_update Test Plan: Run XF with inplace_test and also without Reviewers: igor, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D32367 | 03 February 2015, 20:19:56 UTC |
9898f63 | sdong | 03 February 2015, 17:47:29 UTC | Divide test DBIteratorTest.DBIterator to smaller tests Summary: When building on my host, I saw warning: In file included from db/db_iter_test.cc:17:0: db/db_iter_test.cc: In member function ‘void rocksdb::_Test_DBIterator::_Run()’: ./util/testharness.h:147:14: note: variable tracking size limit exceeded with -fvar-tracking-assignments, retrying without void TCONCAT(_Test_,name)::_Run() ^ ./util/testharness.h:134:23: note: in definition of macro ‘TCONCAT1’ #define TCONCAT1(a,b) a##b ^ ./util/testharness.h:147:6: note: in expansion of macro ‘TCONCAT’ void TCONCAT(_Test_,name)::_Run() ^ db/db_iter_test.cc:589:1: note: in expansion of macro ‘TEST’ TEST(DBIteratorTest, DBIterator) { ^ By dividing the test into small tests, it should fix the problem Test Plan: Run the test Reviewers: rven, yhchiang, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D32679 | 03 February 2015, 17:48:03 UTC |
829363b | sdong | 02 February 2015, 19:09:21 UTC | Options::PrepareForBulkLoad() to increase parallelism of flushes Summary: Increasing parallelism of flushes will help bulk load throughput. Test Plan: Compile it. Reviewers: MarkCallaghan, yhchiang, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D32685 | 03 February 2015, 17:46:04 UTC |
b04408c | Igor Canadi | 03 February 2015, 06:32:11 UTC | Fix unity build Summary: I broke it with https://github.com/facebook/rocksdb/commit/2fd8f750ab05bd100b627f1e043603d1069246ed Test Plan: make unity Reviewers: yhchiang, rven, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D32577 | 03 February 2015, 06:32:11 UTC |
8d38193 | Igor Canadi | 03 February 2015, 06:29:43 UTC | NewIteratorWithBase() for default column family Summary: I'm moving mongo to a single column family, so I need DeltaBase iterator with default column family. Test Plan: Added unit test Reviewers: sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D32589 | 03 February 2015, 06:29:43 UTC |
2c2d5ab | Yueh-Hsuan Chiang | 02 February 2015, 23:20:19 UTC | Fix compile warning in util/xfunc.h Summary: ./util/xfunc.h:31:1: error: class 'Options' was previously declared as a struct [-Werror,-Wmismatched-tags] class Options; ^ Test Plan: make dbg -j32 | 02 February 2015, 23:20:19 UTC |
0b8dec7 | Venkatesh Radhakrishnan | 02 February 2015, 22:49:22 UTC | Cross functional test infrastructure for RocksDB. Summary: This Diff provides the implementation of the cross functional test infrastructure. This provides the ability to test a single feature with every existing regression test in order to identify issues with interoperability between features. Test Plan: Reference implementation of inplace update support cross functional test. Able to find interoperability issues with inplace support and ran all of db_test. Will add separate diff for those changes. Reviewers: igor, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D32247 | 02 February 2015, 22:49:22 UTC |
868bfa4 | Igor Canadi | 02 February 2015, 06:13:25 UTC | Merge pull request #488 from ekg/master remove old debugging message (#487) | 02 February 2015, 06:13:25 UTC |
9900f38 | Adam Retter | 01 February 2015, 21:03:10 UTC | Merge pull request #484 from fyrz/RocksJava-Release-MD-change Release.md - Remove version change instruction | 01 February 2015, 21:03:10 UTC |
e6eaf93 | Erik Garrison | 01 February 2015, 20:34:24 UTC | remove old debugging message (#487) It doesn't seem this is needed. | 01 February 2015, 20:34:24 UTC |
f33f395 | Adam Retter | 31 January 2015, 23:43:01 UTC | Moved Java Samples main classes into samples/src/main/java | 01 February 2015, 20:05:13 UTC |
ad32551 | Adam Retter | 31 January 2015, 23:21:19 UTC | Update test lib versions and maven plugin versions | 01 February 2015, 20:05:10 UTC |
d6187d0 | Adam Retter | 31 January 2015, 22:57:35 UTC | Maven can now build a standard project layout | 01 February 2015, 20:05:10 UTC |
1577688 | Adam Retter | 31 January 2015, 22:42:13 UTC | Moved Java Benchmark main classes into benchmark/src/main/java | 01 February 2015, 20:05:10 UTC |
dd8d547 | Adam Retter | 31 January 2015, 22:24:35 UTC | Adjustment to NativeLibraryLoader to allow native library to be loaded from either java.library.path or from extracting from the Jar. Means that the test in the build do not need to rely on the Jar, useful when creating similar builds (and executing tests) from Maven | 01 February 2015, 20:05:10 UTC |
353db6d | Adam Retter | 31 January 2015, 22:23:59 UTC | Moved Java main classes into src/main/java | 01 February 2015, 20:04:51 UTC |
98cb501 | Adam Retter | 31 January 2015, 19:43:09 UTC | Moved Java test classes into src/test/java | 01 February 2015, 19:30:31 UTC |
7479a62 | fyrz | 01 February 2015, 13:30:41 UTC | Release.md - Remove version change instrcution The version change instruction is obsolete with the change that maven pulls versioning information from version.h. | 01 February 2015, 13:32:51 UTC |
4a4e427 | Jörg Maier | 31 January 2015, 15:13:06 UTC | Update HISTORY-JAVA.md | 31 January 2015, 15:13:06 UTC |
384cb66 | Adam Retter | 31 January 2015, 15:06:12 UTC | Merge pull request #480 from fyrz/RocksJava-Deprecate-SkipLogError [RocksJava] Deprecate setSkipLogErrorOnRecovery | 31 January 2015, 15:06:12 UTC |
ca52a67 | fyrz | 30 January 2015, 23:21:45 UTC | [RocksJava] Deprecate setSkipLogErrorOnRecovery - see: 62ad0a9b19f0be4cefa70b6b32876e764b7f3c11 | 31 January 2015, 14:59:57 UTC |
114d218 | Adam Retter | 31 January 2015, 14:57:37 UTC | Merge pull request #479 from fyrz/RocksJava-Snapshot-Sequence-Number [RocksJava] Snapshot - GetSequenceNumber | 31 January 2015, 14:57:37 UTC |
cb5c315 | fyrz | 30 January 2015, 20:05:45 UTC | [RocksJava] Snapshot - GetSequenceNumber Summary: As the C++ part exposes now SequenceNumber retrieval for Snapshots we want this obviously also in the Java API. Test Plan: make rocksdbjava make jtest mvn -f rocksjni.pom test Reviewers: yhchiang, adamretter, ankgup87 Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D32571 | 31 January 2015, 14:50:34 UTC |
ea189b3 | Adam Retter | 31 January 2015, 14:41:06 UTC | Merge pull request #474 from fyrz/RocksJava-GetUpdatesSince [RocksJava] GetUpdatesSince | 31 January 2015, 14:41:06 UTC |
391f85f | fyrz | 30 January 2015, 20:57:40 UTC | [RocksJava] Incorporated changes for D32151 | 31 January 2015, 14:15:49 UTC |
68cd93b | fyrz | 25 January 2015, 21:59:48 UTC | [RocksJava] GetUpdatesSince support Summary: This differential describes further changes to the Java-API New methods: * GetUpdatesSince * GetLatestSequenceNumber * EnableFileDeletions * DisableFileDeletions This pull requests depends on: https://github.com/facebook/rocksdb/pull/472 Test Plan: make rocksdbjava make jtest mvn -f rocksjni.pom package Reviewers: yhchiang, adamretter, ankgup87 Subscribers: dhruba Differential Revision: https://reviews.facebook.net/D32151 | 31 January 2015, 14:15:48 UTC |
caedd40 | fyrz | 25 January 2015, 21:47:29 UTC | [RocksJava] Adjusted auto pointer | 31 January 2015, 14:15:47 UTC |
b39006e | fyrz | 25 January 2015, 21:46:11 UTC | [RocksJava] enable/disable File deletions | 31 January 2015, 14:15:47 UTC |
9a456fb | fyrz | 25 January 2015, 21:05:29 UTC | [RocksJava] GetUpdatesSince support | 31 January 2015, 14:15:46 UTC |
d3a7367 | Adam Retter | 31 January 2015, 14:11:13 UTC | Merge pull request #482 from fyrz/RocksJava-TTL-Fix [RocksJava] Fix ColumnFamily name alloc in TTL DB | 31 January 2015, 14:11:13 UTC |
939bb36 | fyrz | 31 January 2015, 13:43:21 UTC | [RocksJava] Fix ColumnFamily name alloc in TTL DB While fixing the RocksDB ColumnFamily name the TTL DB wasn`t touched. This commit resolves this. | 31 January 2015, 13:43:21 UTC |
86e2a1e | Marko Kevac | 31 January 2015, 12:47:49 UTC | Allow creating backups from C | 31 January 2015, 12:47:49 UTC |
db9ed5f | sdong | 31 January 2015, 00:07:35 UTC | Unaddressed comment in previous diff. Change only in code comments. | 31 January 2015, 00:07:35 UTC |
5917de0 | sdong | 21 January 2015, 19:09:56 UTC | CappedFixTransform: return fixed length prefix, or full key if key is shorter than the fixed length Summary: Add CappedFixTransform, which is the same as fixed length prefix extractor, except that when slice is shorter than the fixed length, it will use the full key. Test Plan: Add a test case for db_test options_test and a new test Reviewers: yhchiang, rven, igor Reviewed By: igor Subscribers: MarkCallaghan, leveldb, dhruba, yoshinorim Differential Revision: https://reviews.facebook.net/D31887 | 31 January 2015, 00:04:30 UTC |
6c6037f | Igor Canadi | 30 January 2015, 02:22:43 UTC | Expose Snapshot's SequenceNumber Summary: Requested here: https://www.facebook.com/groups/rocksdb.dev/permalink/705524519546065/ It might also help with mongo. I don't see a reason why we shouldn't expose this info. Test Plan: make check Reviewers: sdong, yhchiang, rven Reviewed By: rven Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D32547 | 30 January 2015, 02:22:43 UTC |