Summary:
Previously, builder.cc has a check for merge operator which prevents
RocksDB from crash when reopening a DB w/o properly specifying the merge
operator. However, currently we observed a memory leak on failing in
RocksDB recovery. This diff removes such check and let it crash instead of
causing memory leak for now before we have identified the real cause of
the memory leak.
Test Plan: make all check
Reviewers: sdong
Subscribers: ljin, igor
Differential Revision: https://reviews.facebook.net/D20913
Summary:
When compression is enabled, and blocksize is not too big, use the
space in stack to hold bytes read from block.
Bencmark:
base version: commit 8f09d53fd1
malloc: 1.30% -> 0.98%
free: 1.49% -> 1.07%
Test Plan:
make all check
Reviewers: ljin, yhchiang, dhruba, igor, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20679
Summary:
DBImplReadOnly::CompactRange wasn't override DBImpl::CompactRange;
this can cause problem when using StackableDB inheritors like
DbWithTtl.
P. S. Thanks C++11 for override :)
Test Plan: make all check
Reviewers: igor, sdong
Reviewed By: sdong
Subscribers: yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D20829
Summary:
Fixed the crash when merge_operator is not properly set after reopen
and added two test cases for this.
Test Plan:
make merge_test
./merge_test
Reviewers: igor, ljin, sdong
Reviewed By: sdong
Subscribers: benj, mvikjord, leveldb
Differential Revision: https://reviews.facebook.net/D20793
Summary:
Define Block::Iter to be an independent class to be used by block_based_table_reader
When creating data and index iterator, update an existing iterator rather than new one
Thus malloc and free could be reduced
Benchmark,
Base:
commit 76286ee67e
commands:
--db=/dev/shm/rocksdb --num_levels=6 --key_size=20 --prefix_size=20 --keys_per_prefix=0 --value_size=100 --write_buffer_size=134217728 --max_write_buffer_number=2 --target_file_size_base=33554432 --max_bytes_for_level_base=1073741824 --verify_checksum=false --max_background_compactions=4 --use_plain_table=0 --memtablerep=prefix_hash --open_files=-1 --mmap_read=1 --mmap_write=0 --bloom_bits=10 --bloom_locality=1 --memtable_bloom_bits=500000 --compression_type=lz4 --num=2621440 --use_hash_search=1 --block_size=1024 --block_restart_interval=1 --use_existing_db=1 --threads=1 --benchmarks=readrandom —disable_auto_compactions=1
malloc: 3.30% -> 1.42%
free: 3.59%->1.61%
Test Plan:
make all check
run db_stress
valgrind ./db_test ./table_test
Reviewers: ljin, yhchiang, dhruba, igor, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20655
Summary: const string& dbname parameter is not used
Test Plan: make all
Reviewers: sdong, igor
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20703
Summary:
We now reads table properties in VersionSet::LogAndApply(), which requires options.db_paths to be set. But since ldb_cmd directly creates VersionSet without initialization db_paths, causing a seg fault. This patch fix it by initializing db_paths.
log_and_apply_bench still shows segfault, because table cache is nullptr in VersionSet created.
Test Plan: Run ldb dump_manifest which used to fail.
Reviewers: yhchiang, ljin, igor
Reviewed By: igor
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20751
Summary:
- Copy the key and value to in-memory hash table during Add operation. Also modified cuckoo_table_reader_test to use this.
- Store only the user_key in in-memory hash table if it is last level file.
- Handle Carryover while chosing unused key in Finish() method in case unused key was never found before Finish() call.
Test Plan:
cuckoo_table_reader_test --enable_perf
cuckoo_table_builder_test
valgrind_check
asan_check
Reviewers: sdong, yhchiang, igor, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20715
Summary: We have quite some properties that are integers and we are adding more. Add a function to directly return them as an integer, instead of a string
Test Plan: Add several unit test checks
Reviewers: yhchiang, igor, dhruba, haobo, ljin
Reviewed By: ljin
Subscribers: yoshinorim, leveldb
Differential Revision: https://reviews.facebook.net/D20637
Summary: Add a DB property of estimated number of live keys, by adding number of entries of all mem tables and all files, subtracted by all deletions in all files.
Test Plan: Add the case in unit tests
Reviewers: hobbymanyp, ljin
Reviewed By: ljin
Subscribers: MarkCallaghan, yoshinorim, leveldb, igor, dhruba
Differential Revision: https://reviews.facebook.net/D20631
Summary:
It has one-to-one relationship with CFD. Take a pointer to CFD on
constructor to avoid passing cfd through member functions.
Test Plan: make
Reviewers: sdong, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20565
Summary: So that we can avoid calling NowSecs() in MakeRoomForWrite twice
Test Plan: make all check
Reviewers: yhchiang, igor, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20529
Summary:
Make StatisticsImpl being able to forward stats to provided statistics
implementation. The main purpose is to allow us to collect internal
stats in the future even when user supplies custom statistics
implementation. It avoids intrumenting 2 sets of stats collection code.
One immediate use case is tuning advisor, which needs to collect some
internal stats, users may not be interested.
Test Plan:
ran db_bench and see stats show up at the end of run
Will run make all check since some tests rely on statistics
Reviewers: yhchiang, sdong, igor
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D20145
Summary:
Make StatisticsImpl being able to forward stats to provided statistics
implementation. The main purpose is to allow us to collect internal
stats in the future even when user supplies custom statistics
implementation. It avoids intrumenting 2 sets of stats collection code.
One immediate use case is tuning advisor, which needs to collect some
internal stats, users may not be interested.
Test Plan:
ran db_bench and see stats show up at the end of run
Will run make all check since some tests rely on statistics
Reviewers: yhchiang, sdong, igor
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D20145
Summary:
In block based table's hash index checking, when looking for a key that doesn't exist, there is a high chance that a false block is returned because of hash bucket conflicts. In this revision, another check is done to filter out some of those cases: comparing previous key of the block boundary to see whether the target block is what we are looking for.
In a favored test setting (bloom filter disabled, 8 L0 files), I saw about 80% improvements. In a non-favored test setting (bloom filter enabled, files are all in L1, files are all cached), I see the performance penalty is less than 3%.
Test Plan: make all check
Reviewers: haobo, ljin
Reviewed By: ljin
Subscribers: wuj, leveldb, zagfox, yhchiang
Differential Revision: https://reviews.facebook.net/D20595
Summary:
Contains:
- Implementation of TableReader based on Cuckoo Hashing
- Unittests for CuckooTableReader
- Performance test for TableReader
Test Plan:
make cuckoo_table_reader_test
./cuckoo_table_reader_test
make valgrind_check
make asan_check
Reviewers: yhchiang, sdong, igor, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20511
Summary:
User gets undefinied error since the definition is not exposed.
Also re-enable the db test with only upper bound check
Test Plan: db_test, rate_limit_test
Reviewers: igor, yhchiang, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20403
Summary:
Fixed compaction-related errors where number of input levels are hard-coded.
It's a bug found in compaction branch.
This diff will be pushed into master.
Test Plan:
export ROCKSDB_TESTS=Compact
make db_test -j32
./db_test
also passed the tests in compaction branch
Reviewers: igor, sdong, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20577
Summary: I changed SpatialDB API so that we only specify list of indexes when we create the database. That way, whoever is querying the DB doesn't need to know the full list of indexes and their options.
Test Plan: spatial_db_test
Reviewers: yinwang
Reviewed By: yinwang
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20571
Summary:
Contains the following changes in CuckooTableBuilder:
- Take an extra parameter in constructor to identify last level file.
- Implement a better way to identify if a bucket has been inserted into the tree already during BFS search.
- Minor typos
Test Plan:
make cuckoo_table_builder
./cuckoo_table_builder
make valgrind_check
Reviewers: sdong, igor, yhchiang, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20445
Summary:
Modify a functioin TrimAppend in dbformat.h: IterKey. Write a test for it in dbformat_test
Use IterKey in block::Iter to replace std::string to reduce malloc.
Evaluate it using perf record.
malloc: 4.26% -> 2.91%
free: 3.61% -> 3.08%
Test Plan:
make all check
./valgrind db_test dbformat_test
Reviewers: ljin, haobo, yhchiang, dhruba, igor, sdong
Reviewed By: sdong
Differential Revision: https://reviews.facebook.net/D20433
Summary:
This diff is adding spatial index support to RocksDB.
When creating the DB user specifies a list of spatial indexes. Spatial indexes can cover different areas and have different resolution (i.e. number of tiles). This is useful for supporting different zoom levels.
Each element inserted into SpatialDB has:
* a bounding box, which determines how will the element be indexed
* string blob, which will usually be WKB representation of the polygon (http://en.wikipedia.org/wiki/Well-known_text)
* feature set, which is a map of key-value pairs, where value can be int, double, bool, null or a string. FeatureSet will be a set of tags associated with geo elements (for example, 'road': 'highway' and similar)
* a list of indexes to insert the element in. For example, small river element will be inserted in index for high zoom level, while country border will be inserted in all indexes (including the index for low zoom level).
Each query is executed on single spatial index. Query guarantees that it will return all elements intersecting the specified bounding box, but it might also return some extra non-intersecting elements.
Test Plan: Added bunch of unit tests in spatial_db_test
Reviewers: dhruba, yinwang
Reviewed By: yinwang
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20361
Summary:
Add the missing ROCKSDB_JAR variable in Makefile, which is mistakenly
removed in https://reviews.facebook.net/D20289.
Test Plan:
export ROCKSDB_JAR=
make rocksdbjava
Summary:
Update header inclusion as include/utilities/*.h has been moved to
include/rocksdb/utilities/*.h
Test Plan: make rocksdbjava
Reviewers: ljin, sdong, igor
Reviewed By: igor
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20517
Summary:
Fixed the following compile error by replacing pow by shift, as it computes
power of 2.
util/options_builder.cc:133:14: error: no member named 'pow' in namespace 'std'
std::pow(2, std::max(0, std::min(3, level0_stop_writes_trigger -
~~~~~^
1 error generated.
make: *** [util/options_builder.o] Error 1
Test Plan: make success in mac and linux
Reviewers: ljin, igor, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20475
Summary:
Fixed a bug in Compaction.cc where input_levels_ was not properly resized.
Without this fix, there would be invalid access in input_levels_ when more
than two levels are involved in one compaction run.
This fix will go to master instead of compaction branch.
Test Plan: tested in compaction branch.
Reviewers: ljin, sdong, igor
Reviewed By: igor
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20481
Summary:
All public headers need to be under `include/rocksdb` directory. Otherwise, clients include our header files like this:
#include <rocksdb/db.h>
#include <utilities/backupable_db.h> // still our public header!
Also, internally, we include:
#include "utilities/backupable/backupable_db.h" // internal header
#include "utilities/backupable_db.h" // public header
which is confusing.
This way, when we install rocksdb as a system library, we can just copy `include/rocksdb` directory to system's header files. We can't really copy `utilities` directory to system's header files.
Test Plan: compiles
Reviewers: dhruba, ljin, yhchiang, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20409
Summary:
Add a function GetOptions(), where based on four parameters users give: read/write amplification threshold, memory budget for mem tables and target DB size, it picks up a compaction style and parameters for them. Background threads are not touched yet.
One limit of this algorithm: since compression rate and key/value size are hard to predict, it's hard to predict level 0 file size from write buffer size. Simply make 1:1 ratio here.
Sample results: https://reviews.facebook.net/P477
Test Plan: Will add some a unit test where some sample scenarios are given and see they pick the results that make sense
Reviewers: yhchiang, dhruba, haobo, igor, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D18741
Summary:
This diff merges pull request 208. Contributor: ankgup87
[Java] Optimize statistics collector
* Optimize statistics collector by collecting statistics of multiple DBs in a single thread rather than starting up a new thread for each DB.
* Also, fix packaging of jnilib file on OS_X platform.
* Diff review: https://reviews.facebook.net/D20265
[Java] Add documentation on interdependency of dispose call of RocksObjects
* Remove transferCppRawPointersOwnershipFrom function.
- This function was setting opt.filter_ and thus filter_ to be null. This way there is no
one holding reference for filter object and can thus be GC'd which is not the intention.
Replaced it with storeOptionsInstace which stores options instance. Options class
internally holds Filter instance. Thus when Options is GC'd, filter reference
will be GC'd automatically.
* Added documentation explaining interdependency of Filter, Options and DB.
* Diff review: https://reviews.facebook.net/D20379
Test Plan:
described in their diff reviews
Reviewers: haobo sdong swapnilghike zzbennett rsumbaly yhchiang
Reviewed by: yhchiang
Summary:
This diff merges pull request #208. Contributor: ankgup87
[Java] Optimize statistics collector
* Optimize statistics collector by collecting statistics of multiple DBs in a single thread rather than starting up a new thread for each DB.
* Also, fix packaging of jnilib file on OS_X platform.
* Diff review: https://reviews.facebook.net/D20265
[Java] Add documentation on interdependency of dispose call of RocksObjects
* Remove transferCppRawPointersOwnershipFrom function.
- This function was setting opt.filter_ and thus filter_ to be null. This way there is no
one holding reference for filter object and can thus be GC'd which is not the intention.
Replaced it with storeOptionsInstace which stores options instance. Options class
internally holds Filter instance. Thus when Options is GC'd, filter reference
will be GC'd automatically.
* Added documentation explaining interdependency of Filter, Options and DB.
* Diff review: https://reviews.facebook.net/D20379
Test Plan:
described in their diff reviews
Reviewers: haobo sdong swapnilghike zzbennett rsumbaly yhchiang
Reviewed by: yhchiang
Summary: Fixes some memory leaks in cuckoo_builder_test.cc. This also fixed broken valgrind_check tests
Test Plan:
make valgrind_check
./cuckoo_builder_test
Currently running make check all. I shall update once it is done.
Reviewers: ljin, sdong, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20385
Summary:
Add setCacheNumShardBits() and cacheNumShardBits() to Options. This allows
developers to control the number of shards for the block cache.
Test Plan:
make rocksdbjava
cd java
make db_bench
./jdb_bench.sh --cache_size=1048576 --cache_numshardbits=6
Reviewers: sdong, ljin, ankgup87
Reviewed By: ankgup87
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19347
Summary:
Fixed some make and linking issues of RocksDBJava. Specifically:
* Add JAVA_LDFLAGS, which does not include gflags
* rocksdbjava library now uses JAVA_LDFLAGS instead of LDFLAGS
* java/Makefile now includes build_config.mk
* rearrange make rocksdbjava workflow to ensure the library file is correctly
included in the jar file.
Test Plan:
make rocksdbjava
make jdb_bench
java/jdb_bench.sh
Reviewers: dhruba, swapnilghike, zzbennett, rsumbaly, ankgup87
Reviewed By: ankgup87
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20289
Summary: Add a parameter path_id to DB::CompactRange(), to indicate where the output file should be placed to.
Test Plan: add a unit test
Reviewers: yhchiang, ljin
Reviewed By: ljin
Subscribers: xjin, igor, dhruba, MarkCallaghan, leveldb
Differential Revision: https://reviews.facebook.net/D20085
Summary:
Fixed the following compile error.
./table/cuckoo_table_builder.h:72:22: error: private field 'key_length_' is not used [-Werror,-Wunused-private-field]
const unsigned int key_length_;
^
1 error generated.
Test Plan: make
Reviewers: sdong, ljin, radheshyamb, igor
Reviewed By: igor
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20349
Yueh-Hsuan Chiang