- 22 4月, 2014 16 次提交
-
-
由 Ankit Gupta 提交于
-
由 Ankit Gupta 提交于
-
由 Ankit Gupta 提交于
-
由 Yueh-Hsuan Chiang 提交于
Summary: Fix the sigfault when running sst_dump on v2.6 db. Test Plan: git checkout bba6595b make clean make db_bench ./db_bench --db=/tmp/some/db --benchmarks=fillseq arc patch D18039 make clean make sst_dump ./sst_dump --file=/tmp/some/db --command=check Reviewers: igor, haobo, sdong Reviewed By: sdong CC: leveldb Differential Revision: https://reviews.facebook.net/D18039
-
由 Igor Canadi 提交于
Summary: Calling Fsync()/Sync() on a file should give the guarantee that whatever you written to the file is now persisted. This is currently not the case, since we might have some data left in application cache as we do Fsync()/Sync(). For example, BuildTable() calls Fsync() without the flush, assuming all sst data is now persisted, but it's actually not. This may result in big inconsistencies. Test Plan: no test Reviewers: sdong, dhruba, haobo, ljin, yhchiang Reviewed By: sdong CC: leveldb Differential Revision: https://reviews.facebook.net/D18159
-
由 Igor Canadi 提交于
-
由 Yueh-Hsuan Chiang 提交于
Summary: Add Java binding and test for rocksdb::ReadOptions. Test Plan: make rocksdbjava make jtest Reviewers: haobo, dhruba, sdong, ankgup87, rsumbaly, swapnilghike, zzbennett Reviewed By: haobo CC: leveldb Differential Revision: https://reviews.facebook.net/D18129
-
由 Igor Canadi 提交于
-
由 Yueh-Hsuan Chiang 提交于
Summary: Add Java bindings for memtables and sst format. Specifically, add two abstract Java classses --- MemTableConfig and SstFormatConfig. Each MemTable / SST implementation should has its own config class extends MemTableConfig / SstFormatConfig respectively and pass it to Options via setMemTableConfig / setSstConfig. Test Plan: make rocksdbjava make jdb_test make jdb_bench java/jdb_bench.sh \ --benchmarks=fillseq,readrandom,readwhilewriting \ --memtablerep=hash_skiplist \ --use_plain_table=1 \ --key_size=20 \ --prefix_size=12 \ --value_size=100 \ --cache_size=17179869184 \ --disable_wal=0 \ --sync=0 \ Reviewers: haobo, ankgup87, sdong Reviewed By: haobo CC: leveldb, dhruba Differential Revision: https://reviews.facebook.net/D17997
-
由 Igor Canadi 提交于
Also, make `benchharness.cc` not compiled into rocksdb library.
-
由 Igor Canadi 提交于
-
由 Pratyush Seth 提交于
Summary: Added benchmark functionality on the lines of folly/Benchmark.h Test Plan: Added unit tests Reviewers: igor, haobo, sdong, ljin, yhchiang, dhruba Reviewed By: igor CC: leveldb Differential Revision: https://reviews.facebook.net/D17973
-
由 Igor Canadi 提交于
Summary: For some reason, on a subset of our continuous build machines, preallocation is allocating 8 block more than it should be. Let's relax the test a little bit -- now we require the test to allocate *at least* the number of blocks as we told them to. Test Plan: no Reviewers: ljin, haobo, sdong Reviewed By: ljin CC: leveldb Differential Revision: https://reviews.facebook.net/D18141
-
由 Igor Canadi 提交于
-
由 Igor Canadi 提交于
[Java] Add iterator JNI bindings
-
由 Lei Jin 提交于
Summary: The file tree structure in Version is prebuilt and the range of each file is known. On the Get() code path, we do binary search in FindFile() by comparing target key with each file's largest key and also check the range for each L0 file. With some pre-calculated knowledge, each key comparision that has been done can serve as a hint to narrow down further searches: (1) If a key falls within a L0 file's range, we can safely skip the next file if its range does not overlap with the current one. (2) If a key falls within a file's range in level L0 - Ln-1, we should only need to binary search in the next level for files that overlap with the current one. (1) will be able to skip some files depending one the key distribution. (2) can greatly reduce the range of binary search, especially for bottom levels, given that one file most likely only overlaps with N files from the level below (where N is max_bytes_for_level_multiplier). So on level L, we will only look at ~N files instead of N^L files. Some inital results: measured with 500M key DB, when write is light (10k/s = 1.2M/s), this improves QPS ~7% on top of blocked bloom. When write is heavier (80k/s = 9.6M/s), it gives us ~13% improvement. Test Plan: make all check Reviewers: haobo, igor, dhruba, sdong, yhchiang Reviewed By: haobo CC: leveldb Differential Revision: https://reviews.facebook.net/D17205
-
- 20 4月, 2014 5 次提交
-
-
由 Ankit Gupta 提交于
-
由 Ankit Gupta 提交于
-
由 Ankit Gupta 提交于
-
由 Ankit Gupta 提交于
-
由 Ankit Gupta 提交于
-
- 19 4月, 2014 9 次提交
-
-
由 Ankit Gupta 提交于
-
由 Ankit Gupta 提交于
-
由 sdong 提交于
Summary: A recent commit https://github.com/facebook/rocksdb/commit/e37dd216f9384bfdabc6760fa296e8ee28c79d30 makes sure hash index can be used when reading existing files. This patch uses another way to achieve the approach: (1) Currently, always writing kBinarySearch to files, despite of BlockBasedTableOptions.IndexType setting. (2) When reading a file, read out the field, and make sure it is kBinarySearch, while always use index type by users. The reason for doing it is, to reserve kHashSearch property on disk to future. If now we write out binary index for both of kHashSearch and kBinarySearch. We have to use a new flag in the future for hash index on disk, otherwise compatibility would break. Also, we want the real index type and type shown in properties block to be consistent. Test Plan: make all check Reviewers: haobo, kailiu Reviewed By: kailiu CC: igor, ljin, yhchiang, xjin, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D18009
-
由 Igor Canadi 提交于
[Java] Add statistics JNI bindings
-
由 Ankit Gupta 提交于
-
由 Ankit Gupta 提交于
-
https://github.com/facebook/rocksdb由 Ankit Gupta 提交于
Conflicts: Makefile java/Makefile java/org/rocksdb/Options.java java/rocksjni/portal.h
-
由 Igor Canadi 提交于
Added period
-
由 James Pearce 提交于
This is a PR to test some tooling; please do not merge without talking to @jamesgpearce :)
-
- 18 4月, 2014 9 次提交
-
-
由 Yueh-Hsuan Chiang 提交于
Summary: 1. Add Java bindings for 30 options for rocksdb::DBOptions. 2. Add org.rocksdb.test.OptionsTest 3. Codes are semi-auto generated, JavaDocs are manually polished. Test Plan: make rocksdbjava make jtest Reviewers: haobo, ankgup87, sdong, dhruba Reviewed By: dhruba CC: leveldb Differential Revision: https://reviews.facebook.net/D18015
-
由 Yueh-Hsuan Chiang 提交于
Summary: Add a skeleton binding and test for BackupableDB which shows that BackupableDB and RocksDB can share the same JNI calls. Test Plan: make rocksdbjava make jtest Reviewers: haobo, ankgup87, sdong, dhruba Reviewed By: haobo CC: leveldb Differential Revision: https://reviews.facebook.net/D17793
-
由 sdong 提交于
Summary: D17961 has two bugs: (1) two level iterator fails to populate FileMetaData.table_reader, causing performance regression. (2) table cache handle the !status.ok() case in the wrong place, causing seg fault which shouldn't happen. Test Plan: make all check Reviewers: ljin, igor, haobo Reviewed By: ljin CC: yhchiang, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D17991
-
由 Igor Canadi 提交于
Summary: We don't use or build this code Test Plan: builds Reviewers: dhruba Reviewed By: dhruba CC: leveldb Differential Revision: https://reviews.facebook.net/D17979
-
由 Igor Canadi 提交于
-
由 sdong 提交于
Summary: One of our profilings shows that Version::Get() sometimes is slow when getting pointer of user comparators or other global objects. In this patch: (1) we keep pointers of immutable objects in Version to avoid accesses them though option objects or cfd objects (2) table_reader is directly cached in FileMetaData so that table cache don't have to go through handle first to fetch it (3) If level 0 has less than 3 files, skip the filtering logic based on SST tables' key range. Smallest and largest key are stored in separated memory locations, which has potential cache misses Test Plan: make all check Reviewers: haobo, ljin Reviewed By: haobo CC: igor, yhchiang, nkg-, leveldb Differential Revision: https://reviews.facebook.net/D17739
-
由 Kai Liu 提交于
Summary: With the recent changes, there is no need to check the property block about the index block type. If user want to use it, they don't really need any disk format change; everything happens in the fly. Also another team encountered an error while reading the index type from properties. Test Plan: ran all the tests Reviewers: sdong CC: Task ID: # Blame Rev:
-
由 Igor Canadi 提交于
Summary: We don't really need sync_point.o if we're compiling with NDEBUG. This diff depends on D17823 Test Plan: compiles Reviewers: haobo, ljin, sdong Reviewed By: haobo CC: leveldb Differential Revision: https://reviews.facebook.net/D17829
-
由 sdong 提交于
Summary: From 2.6 to 2.7, property block name is renamed from rocksdb.stats to rocksdb.properties. Older properties were not able to be loaded. In 2.8, we seem to have added some logic that uses property block without checking null pointers, which create segment faults. In this patch, we fix it by: (1) try rocksdb.stats if rocksdb.properties is not found (2) add some null checking before consuming rep->table_properties Test Plan: make sure a file generated in 2.7 couldn't be opened now can be opened. Reviewers: haobo, igor, yhchiang Reviewed By: igor CC: ljin, xjin, dhruba, kailiu, leveldb Differential Revision: https://reviews.facebook.net/D17961
-
- 17 4月, 2014 1 次提交
-
-
由 Ankit Gupta 提交于
-