- 04 2月, 2014 3 次提交
-
-
由 Igor Canadi 提交于
Summary: RocksDB doesn't compile on 32-bit architecture apparently. This is attempt to fix some of 32-bit errors. They are reported here: https://gist.github.com/paxos/8789697 Test Plan: RocksDB still compiles on 64-bit :) Reviewers: kailiu Reviewed By: kailiu CC: leveldb Differential Revision: https://reviews.facebook.net/D15825
-
由 Lei Jin 提交于
Summary: Use super_version insider NewIterator to avoid Ref() each component separately under mutex The new added bench shows NewIterator QPS increases from 515K to 719K No meaningful improvement for multiget I guess due to its relatively small cost comparing to 90 keys fetch in the test. Test Plan: unit test and db_bench Reviewers: igor, sdong Reviewed By: igor CC: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D15609
-
由 Igor Canadi 提交于
-
- 03 2月, 2014 1 次提交
-
-
由 Kai Liu 提交于
Eliminate stdout message when launching a posix thread.
-
- 01 2月, 2014 3 次提交
-
-
由 Dhruba Borthakur 提交于
Summary: Patch https://reviews.facebook.net/D15591 enabled checksum verification by default. This caused the unit test to fail. Test Plan: ./corruption_test Reviewers: igor, kailiu Reviewed By: igor CC: leveldb Differential Revision: https://reviews.facebook.net/D15795
-
由 Igor Canadi 提交于
Summary: VersionSet::next_file_number_ is always assumed to be strictly greater than VersionSet::log_number_. In our new recovery code, we artificially set log_number_ to be (log_number + 1), so that once we flush, we don't recover from the same log file again (this is important because of merge operator non-idempotence) When we set VersionSet::log_number_ to (log_number + 1), we also have to mark that file number used, such that next_file_number_ is increased to a legal level. Otherwise, VersionSet might assert. This has not be a problem so far because here's what happens: 1. assume next_file_number is 5, we're recovering log_number 10 2. in DBImpl::Recover() we call MarkFileNumberUsed with 10. This will set VersionSet::next_file_number_ to 11. 3. If there are some updates, we will call WriteTable0ForRecovery(), which will use file number 11 as a new table file and advance VersionSet::next_file_number_ to 12. 4. When we LogAndApply() with log_number 11, assertion is true: assert(11 <= 12); However, this was a lucky occurrence. Even though this diff doesn't cause a bug, I think the issue is important to fix. Test Plan: In column families I have different recovery logic and this code path asserted. When adding MarkFileNumberUsed(log_number + 1) assert is gone. Reviewers: dhruba, kailiu Reviewed By: kailiu CC: leveldb Differential Revision: https://reviews.facebook.net/D15783
-
由 Siying Dong 提交于
Summary: I didn't figure out the reason why the feature of zeroing out earlier sequence ID is disabled in universal compaction. I do see bottommost_level is set correctly. It should simply work if we remove the constraint of universal compaction. Test Plan: make all check Reviewers: haobo, dhruba, kailiu, igor Reviewed By: dhruba CC: leveldb Differential Revision: https://reviews.facebook.net/D15423
-
- 31 1月, 2014 1 次提交
-
-
由 Dhruba Borthakur 提交于
Summary: The default settings enable checksum verification on every read. Test Plan: make check Reviewers: haobo Reviewed By: haobo CC: leveldb Differential Revision: https://reviews.facebook.net/D15591
-
- 30 1月, 2014 8 次提交
-
-
由 Igor Canadi 提交于
Summary: In DBImpl we keep track of some statistics internally and expose them via GetProperty(). This diff encapsulates all the internal statistics into a class InternalStatisics. Most of it is copy/paste. Apart from cleaning up db_impl.cc, this diff is also necessary for Column families, since every column family should have its own CompactionStats, MakeRoomForWrite-stall stats, etc. It's much easier to keep track of it in every column family if it's nicely encapsulated in its own class. Test Plan: make check Reviewers: dhruba, kailiu, haobo, sdong, emayanke Reviewed By: haobo CC: leveldb Differential Revision: https://reviews.facebook.net/D15273
-
由 Lei Jin 提交于
Summary: as title Test Plan: unit test Reviewers: haobo, igor, sdong, kailiu, dhruba Reviewed By: dhruba CC: leveldb Differential Revision: https://reviews.facebook.net/D15435
-
由 Lei Jin 提交于
Summary: Pad each Ticker structure to be 64 bytes and make them align on 64 bytes boundary to avoid cache line false sharing issue. Please refer to task 3615553 for more details Test Plan: db_bench LevelDB: version 2.0s Date: Wed Jan 29 12:23:17 2014 CPU: 32 * Intel(R) Xeon(R) CPU E5-2660 0 @ 2.20GHz CPUCache: 20480 KB rocksdb.build.overwrite.qps 49638 rocksdb.build.overwrite.p50_micros 58.73 rocksdb.build.overwrite.p75_micros 210.56 rocksdb.build.overwrite.p99_micros 733.28 rocksdb.build.fillseq.qps 366729 rocksdb.build.fillseq.p50_micros 1.00 rocksdb.build.fillseq.p75_micros 1.00 rocksdb.build.fillseq.p99_micros 2.65 rocksdb.build.readrandom.qps 1152995 rocksdb.build.readrandom.p50_micros 11.27 rocksdb.build.readrandom.p75_micros 15.69 rocksdb.build.readrandom.p99_micros 33.59 rocksdb.build.readrandom_smallblockcache.qps 956047 rocksdb.build.readrandom_smallblockcache.p50_micros 15.23 rocksdb.build.readrandom_smallblockcache.p75_micros 17.31 rocksdb.build.readrandom_smallblockcache.p99_micros 31.49 rocksdb.build.readrandom_memtable_sst.qps 1105183 rocksdb.build.readrandom_memtable_sst.p50_micros 12.04 rocksdb.build.readrandom_memtable_sst.p75_micros 15.78 rocksdb.build.readrandom_memtable_sst.p99_micros 32.49 rocksdb.build.readrandom_fillunique_random.qps 487856 rocksdb.build.readrandom_fillunique_random.p50_micros 29.65 rocksdb.build.readrandom_fillunique_random.p75_micros 40.93 rocksdb.build.readrandom_fillunique_random.p99_micros 78.68 rocksdb.build.memtablefillrandom.qps 91304 rocksdb.build.memtablefillrandom.p50_micros 171.05 rocksdb.build.memtablefillrandom.p75_micros 196.12 rocksdb.build.memtablefillrandom.p99_micros 291.73 rocksdb.build.memtablereadrandom.qps 1340411 rocksdb.build.memtablereadrandom.p50_micros 9.48 rocksdb.build.memtablereadrandom.p75_micros 13.95 rocksdb.build.memtablereadrandom.p99_micros 30.36 rocksdb.build.readwhilewriting.qps 491004 rocksdb.build.readwhilewriting.p50_micros 29.58 rocksdb.build.readwhilewriting.p75_micros 40.34 rocksdb.build.readwhilewriting.p99_micros 76.78 Reviewers: igor, haobo Reviewed By: igor CC: leveldb Differential Revision: https://reviews.facebook.net/D15573
-
由 Kai Liu 提交于
Summary: In new third-party release tool, `LIBNAME=<customized_library> make` will not really change the LIBNAME. However it's very odd that the same approach works with old third-party release tools. I checked previous rocksdb version and both librocksdb.a and librocksdb_debug.a were correctly generated and copied to the right place. Test Plan: `LIBNAME=hello make -j32` generates hello.a `make -j32` generates librocksdb.a Reviewers: igor, sdong, haobo, dhruba Reviewed By: igor CC: leveldb Differential Revision: https://reviews.facebook.net/D15555
-
由 kailiu 提交于
Summary: Change all occurrences of "rocksdb" to its canonical form "RocksDB". Test Plan: N/A Reviewers: igor Reviewed By: igor CC: leveldb Differential Revision: https://reviews.facebook.net/D15549
-
由 kailiu 提交于
-
由 Igor Canadi 提交于
-
由 Igor Canadi 提交于
-
- 29 1月, 2014 6 次提交
-
-
由 kailiu 提交于
Summary: * Add a change log for rocksdb releases. * Remove the hacky parts of make_new_version.sh, which are either no longer useful or will be done in our dedicated 3rd-party release tool. Test Plan: N/A Reviewers: igor, haobo, sdong, dhruba CC: leveldb Differential Revision: https://reviews.facebook.net/D15543
-
由 Lei Jin 提交于
Summary: if it happens (randomly) to corrupt shared file in the test, then the checksum will be inconsistent between meta files from different backup. BackupEngine will then detect this issue and fail. But in reality, this does not happen since the checksum is checked on every backup. So here, only corrupt checksum of private file to let BackupEngine to construct properly (but fail during restore). Test Plan: run test with valgrind Reviewers: igor Reviewed By: igor CC: leveldb Differential Revision: https://reviews.facebook.net/D15531
-
由 Igor Canadi 提交于
Summary: I came across this while working on column families. CorruptionTest::RecoverWriteError threw a SIGSEG because the descriptor_log_->file() was nullptr. I'm not sure why it doesn't happen in master, but better safe than sorry. @kailiu, can we get this in release, too? Test Plan: make check Reviewers: kailiu, dhruba, haobo Reviewed By: haobo CC: leveldb, kailiu Differential Revision: https://reviews.facebook.net/D15513
-
由 Igor Canadi 提交于
Summary: I think it looks nicer. In RocksDB we have both styles, but I think that static method is the more common version. Test Plan: backupable_db_test Reviewers: ljin, benj, swk Reviewed By: ljin CC: leveldb Differential Revision: https://reviews.facebook.net/D15519
-
由 Igor Canadi 提交于
Summary: Lots of clients have problems with using StackableDB interface. It's nice to have BackupableDB as a layer on top of DB, but not necessary. This diff exports BackupEngine, which can be used to create backups without forcing clients to use StackableDB interface. Test Plan: backupable_db_test Reviewers: dhruba, ljin, swk Reviewed By: ljin CC: leveldb, benj Differential Revision: https://reviews.facebook.net/D15477
-
由 Lei Jin 提交于
Summary: Keep checksum of each backuped file in meta file. When it restores these files, compute their checksum on the fly and compare against what is in the meta file. Fail the restore process if checksum mismatch. Test Plan: unit test Reviewers: haobo, igor, sdong, kailiu Reviewed By: igor CC: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D15381
-
- 28 1月, 2014 4 次提交
-
-
由 Mark Callaghan 提交于
Summary: The new columns are msComp and msStall that provide average time per compaction and stall for that level in milliseconds. Level Files Size(MB) Score Time(sec) Read(MB) Write(MB) Rn(MB) Rnp1(MB) Wnew(MB) RW-Amplify Read(MB/s) Write(MB/s) Rn Rnp1 Wnp1 NewW Count msComp msStall Ln-stall Stall-cnt ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ 0 8 15 1.5 2 0 30 0 0 30 0.0 0.0 15.5 0 0 0 0 16 112 0.2 1.3 7568 1 8 16 1.6 1 26 26 15 11 16 3.5 17.6 18.1 8 6 13 7 3 362 0.0 0.0 0 2 1 2 0.0 0 0 2 0 0 2 0.0 0.0 18.4 0 0 0 0 1 50 0.0 0.0 0 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: haobo Reviewed By: haobo CC: leveldb Differential Revision: https://reviews.facebook.net/D15345
-
由 Schalk-Willem Kruger 提交于
Summary: Blocks in the transaction log are a fixed size, but the last block in the transaction log file is usually a partial block. When a new record is added after the reader hit the end of the file, a new physical record will be appended to the last block. ReadPhysicalRecord can only read full blocks and assumes that the file position indicator is aligned to the start of a block. If the reader is forced to read further by simply clearing the EOF flag, ReadPhysicalRecord will read a full block starting from somewhere in the middle of a real block, causing it to lose alignment and to have a partial physical record at the end of the read buffer. This will result in length mismatches and checksum failures. When the log file is tailed for replication this will cause the log iterator to become invalid, necessitating the creation of a new iterator which will have to read the log file from scratch. This diff fixes this issue by reading the remaining portion of the last block we read from. This is done when the reader is forced to read further (UnmarkEOF is called). Test Plan: - Added unit tests - Stress test (with replication). Check dbdir/LOG file for corruptions. - Test on test tier Reviewers: emayanke, haobo, dhruba Reviewed By: haobo CC: vamsi, sheki, dhruba, kailiu, igor Differential Revision: https://reviews.facebook.net/D15249
-
由 Igor Canadi 提交于
Summary: @dhruba, I'm not sure where we need to sync the directory. I implemented the function in Env() and added the dir sync just after we close the newly created file in the builder. Should I also add FsyncDir() to new files that get created by a compaction? Test Plan: Confirmed that FsyncDir is returning Status::OK() Reviewers: dhruba, haobo Reviewed By: dhruba CC: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D14751
-
由 Igor Canadi 提交于
Summary: There is no reason to have functions NeedCompaction(), MaxCompactionScore() and MaxCompactionScoreLevel() in VersionSet, since they don't access any data in VersionSet. Test Plan: make check Reviewers: kailiu, haobo, sdong Reviewed By: kailiu CC: leveldb Differential Revision: https://reviews.facebook.net/D15333
-
- 27 1月, 2014 1 次提交
-
-
由 Igor Canadi 提交于
-
- 26 1月, 2014 1 次提交
-
-
由 Igor Canadi 提交于
-
- 25 1月, 2014 11 次提交
-
-
由 Igor Canadi 提交于
ReduceNumberOfLevels had segmentation fault in WriteSnapshot() since we didn't change the number of levels in VersionSet (we consider them immutable from now on). This fixes the problem.
-
由 Siying Dong 提交于
Summary: By removing some includes form options.h and reply on forward declaration, we can more easily reason the dependencies. Test Plan: make all check Reviewers: kailiu, haobo, igor, dhruba Reviewed By: kailiu CC: leveldb Differential Revision: https://reviews.facebook.net/D15411
-
由 Igor Canadi 提交于
Immutable tailing iterator doesn't set CleanupState::mem, so we don't have to unref it.
-
由 Igor Canadi 提交于
Summary: On a shutdown, freeing memory takes a long time. If we're shutting down, we don't really care about memory leaks. I added a call to Cache that will avoid freeing all objects in cache. Test Plan: I created a script to test the speedup and demonstrate how to use the call: https://phabricator.fb.com/P3864368 Clean shutdown took 7.2 seconds, while fast and dirty one took 6.3 seconds. Unfortunately, the speedup is not that big, but should be bigger with bigger block_cache. I have set up the capacity to 80GB, but the script filled up only ~7GB. Reviewers: dhruba, haobo, MarkCallaghan, xjin Reviewed By: dhruba CC: leveldb Differential Revision: https://reviews.facebook.net/D15069
-
由 Igor Canadi 提交于
Summary: A lot of our code implicitly assumes number_levels to be static. ReduceNumberOfLevels() breaks that assumption. For example, after calling ReduceNumberOfLevels(), DBImpl::NumberLevels() will be different from VersionSet::NumberLevels(). This is dangerous. Thankfully, it's not in public headers and is only used from LDB cmd tool. LDB tool is only using it statically, i.e. it never calls it with running DB instance. With this diff, we make it explicitly static. This way, we can assume number_levels to be immutable and not break assumption that lot of our code is relying upon. LDB tool can still use the method. Also, I removed the method from a separate file since it breaks filename completition. version_se<TAB> now completes to "version_set." instead of "version_set" (without the dot). I don't see a big reason that the function should be in a different file. Test Plan: reduce_levels_test Reviewers: dhruba, haobo, kailiu, sdong Reviewed By: kailiu CC: leveldb Differential Revision: https://reviews.facebook.net/D15303
-
由 Igor Canadi 提交于
Summary: MemTableListVersion is to MemTableList what Version is to VersionSet. I took almost the same ideas to develop MemTableListVersion. The reason is to have copying std::list done in background, while flushing, rather than in foreground (MultiGet() and NewIterator()) under a mutex! Also, whenever we copied MemTableList, we copied also some MemTableList metadata (flush_requested_, commit_in_progress_, etc.), which was wasteful. This diff avoids std::list copy under a mutex in both MultiGet() and NewIterator(). I created a small database with some number of immutable memtables, and creating 100.000 iterators in a single-thread (!) decreased from {188739, 215703, 198028} to {154352, 164035, 159817}. A lot of the savings come from code under a mutex, so we should see much higher savings with multiple threads. Creating new iterator is very important to LogDevice team. I also think this diff will make SuperVersion obsolete for performance reasons. I will try it in the next diff. SuperVersion gave us huge savings on Get() code path, but I think that most of the savings came from copying MemTableList under a mutex. If we had MemTableListVersion, we would never need to copy the entire object (like we still do in NewIterator() and MultiGet()) Test Plan: `make check` works. I will also do `make valgrind_check` before commit Reviewers: dhruba, haobo, kailiu, sdong, emayanke, tnovak Reviewed By: kailiu CC: leveldb Differential Revision: https://reviews.facebook.net/D15255
-
由 kailiu 提交于
Summary: Previous we made `make release` also compile shared library. However it takes a long time to complete. To make our development process more efficient. I added a new make target shared_lib. User can of course run `make <library_name>` for direct compilation. However the <library_name> changed under certain condition. Thus we need `make shared_lib` to get rid of the memorization from users' side. Test Plan: make shared_lib Reviewers: igor, sdong, haobo, dhruba Reviewed By: igor CC: leveldb Differential Revision: https://reviews.facebook.net/D15309
-
由 Igor Canadi 提交于
This reverts commit d24961b6. For some reason, glibc2.17-fb breaks gflags. Reverting for now
-
由 kailiu 提交于
Summary: Mixing index/filter blocks with data blocks resulted in some known issues. To make sure in next release our users won't be affected, we added a new option in BlockBasedTableFactory::TableOption to conceal this functionality for now. This patch also introduced a BlockBasedTableReader::OpenOptions, which avoids the "infinite" growth of parameters in BlockBasedTableReader::Open(). Test Plan: make check Reviewers: haobo, sdong, igor, dhruba Reviewed By: igor CC: leveldb, tnovak Differential Revision: https://reviews.facebook.net/D15327
-
由 Igor Canadi 提交于
Summary: It looks like we might have some trouble when building the new release with 4.8, since fbcode is using glibc2.17-fb by default and we are using glibc2.17. It was reported by Benjamin Renard in our internal group. This diff moves our fbcode build to use glibc2.17-fb by default. I got some linker errors when compiling, complaining that `google::SetUsageMessage()` was undefined. After deleting all offending lines, the compile was successful and everything works. Test Plan: Compiled Ran ./db_bench ./db_stress ./db_repl_stress Reviewers: kailiu Reviewed By: kailiu CC: leveldb Differential Revision: https://reviews.facebook.net/D15405
-
由 Siying Dong 提交于
Summary: Currently, compaction multipliers can overflow and cause unexpected behaviors. In this patch, we detect those overflows and use multiplier 1 for them. Test Plan: make all check Reviewers: dhruba, haobo, igor, kailiu Reviewed By: kailiu CC: leveldb Differential Revision: https://reviews.facebook.net/D15321
-
- 24 1月, 2014 1 次提交
-
-
由 Lei Jin 提交于
Summary: as title Test Plan: make all check What else tests shall I cover? Reviewers: igor, haobo CC: Differential Revision: https://reviews.facebook.net/D15339
-