Summary: Small change: replace mutex_.Lock/mutex_.Unlock() with scope guard
Test Plan: make all check
Reviewers: igor, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D21609
Summary:
Currently DBImpl::Flush() triggers flushes in all column families.
Instead we need to trigger just the column family specified.
Test Plan: make all check
Reviewers: igor, ljin, yhchiang, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20841
Summary:
Contains the following changes:
- Implementation of cuckoo_table_factory
- Adding cuckoo table into AdaptiveTableFactory
- Adding cuckoo_table_db_test, similar to lines of plain_table_db_test
- Minor fixes to Reader: When a key is found in the table, return the key found instead of the search key.
- Minor fixes to Builder: Add table properties that are required by Version::UpdateTemporaryStats() during Get operation. Don't define curr_node as a reference variable as the memory locations may get reassigned during tree.push_back operation, leading to invalid memory access.
Test Plan:
cuckoo_table_reader_test --enable_perf
cuckoo_table_builder_test
cuckoo_table_db_test
make check all
make valgrind_check
make asan_check
Reviewers: sdong, igor, yhchiang, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D21219
Changes to support unity build:
Script for building the unity.cc file via Makefile
Unity executable Makefile target for testing builds
Source code changes to fix compilation of unity build
* Script for building the unity.cc file via Makefile
* Unity executable Makefile target for testing builds
* Source code changes to fix compilation of unity build
Summary: In FindObsoleteFiles(), we don't scan db_log_dir. Add it.
Test Plan: make all check
Reviewers: ljin, igor, yhchiang
Reviewed By: yhchiang
Subscribers: leveldb, yhchiang
Differential Revision: https://reviews.facebook.net/D21429
Summary: If there is an outstanding compaction scheduled but at the time a manual compaction is triggered, the manual compaction will preempt. In the end of the manual compaction, we should try to schedule compactions to make sure those preempted ones are not skipped.
Test Plan: make all check
Reviewers: yhchiang, ljin
Reviewed By: ljin
Subscribers: leveldb, dhruba, igor
Differential Revision: https://reviews.facebook.net/D21321
Summary: Fix old issue with DBTest.Randomized with BlockBasedTableWithWholeKeyHashIndex + added printing in DBTest.Randomized.
Test Plan: make all check
Reviewers: zagfox, igor, ljin, yhchiang, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D21003
Summary:
Add a DB Property "rocksdb.estimate-table-readers-mem" to return estimated memory usage by all loaded table readers, other than allocated from block cache.
Refactor the property codes to allow getting property from a version, with DB mutex not acquired.
Test Plan: Add several checks of this new property in existing codes for various cases.
Reviewers: yhchiang, ljin
Reviewed By: ljin
Subscribers: xjin, igor, leveldb
Differential Revision: https://reviews.facebook.net/D20733
Summary:
1. logging when create and delete manifest file
2. fix formating in table/format.cc
Test Plan:
make all check
run db_bench, track the LOG file.
Reviewers: ljin, yhchiang, igor, yufei.zhu, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D21009
Summary: I was bit by this when developing SpatialDB. In case all files are at level 0, CompactRange() will output the compacted files to level 0. This is not ideal, since read amp. is much better at level 1 and higher.
Test Plan: Compacted data in SpatialDB, read manifest using ldb, verified that files are now at level 1 instead of 0.
Reviewers: sdong, ljin, yhchiang, dhruba
Reviewed By: dhruba
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D20901
Summary:
Fixed the following compilation error detected in mac:
db/db_test.cc:2524:3: note: in instantiation of function template
specialization 'rocksdb::test::Tester::IsEq<unsigned long long, int>' requested here
ASSERT_EQ(int_num, 0);
^
Test Plan:
make
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:
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: 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: 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:
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:
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:
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 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:
Add block_restart_interval in db_bench, default value 16
Test Plan:
make
Reviewers: sdong
Reviewed By: sdong
Differential Revision: https://reviews.facebook.net/D20331
Summary:
Adding option to save PlainTable index and bloom filter in SST file.
If there is no bloom block and/or index block, PlainTableReader builds
new ones. Otherwise PlainTableReader just use these blocks.
Test Plan: make all check
Reviewers: sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19527
Summary:
Since we have a lot of options for PlainTable, add a struct PlainTableOptions
to manage them
Test Plan: make all check
Reviewers: sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D20175
Summary:
Having if-then branch for different compaction strategies is considered
hacky and make CompactionPicker less pluggable. This diff removes two
of such if-then branches in version_set.cc by adding MaxInputLevel() to
CompactionPicker.
// Given the current number of levels, returns the lowest allowed level
// for compaction input.
virtual int MaxInputLevel(int current_num_levels) const;
Test Plan:
make db_test
export ROCKSDB_TESTS=Compaction
./db_test
Reviewers: igor, sdong, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19971
Summary: Adding guards to files_ attribute of FilePicker class. This attribute is used only in DEBUG mode. This fixes build of static_lib in mac.
Test Plan:
make static_lib in mac
make check all in devserver
Reviewers: ljin, igor, sdong
Reviewed By: sdong
Differential Revision: https://reviews.facebook.net/D20163
Summary:
Allow class Compaction to handle input files from multiple levels.
This diff is a subset of https://reviews.facebook.net/D19263 where
only db/compaction.cc and db/compaction.h are changed.
Test Plan:
make db_test
export ROCKSDB_TESTS=Compaction
./db_test
Reviewers: igor, sdong, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19923
Summary:
add a flag called use_hash_search in db_bench
Test Plan:
make all check
./db_bench --use_hash_search=1
Reviewers: ljin, haobo, yhchiang, sdong
Reviewed By: sdong
Subscribers: igor, dhruba
Differential Revision: https://reviews.facebook.net/D20067
Summary:
One line change to fix a bug in the LOG when flush memtable
Test Plan:
NONE
Reviewers: sdong
Reviewed By: sdong
Differential Revision: https://reviews.facebook.net/D20049
Summary: Refactoring Version::Get() method to move file picker logic to a separate class.
Test Plan: make check all
Reviewers: igor, sdong, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19713
Summary: Implement Prev() with merge operator for DBIterator. Request from mongoDB. Task 4673663.
Test Plan: make all check
Reviewers: sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19743
Summary:
This patch adds a target size parameter in options.db_paths and universal compaction will base it to determine which DB path to place a new file.
Level-style stays the same.
Test Plan: Add new unit tests
Reviewers: ljin, yhchiang
Reviewed By: yhchiang
Subscribers: MarkCallaghan, dhruba, igor, leveldb
Differential Revision: https://reviews.facebook.net/D19869
Summary: Browsing through the code, looks like StatsLogger is not used at all!
Test Plan: compiles
Reviewers: ljin, sdong, yhchiang, dhruba
Reviewed By: dhruba
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D19827
Summary: We should use PRIu64 instead of "%lu" for portability
Test Plan: compiles now
Reviewers: ljin, dhruba
Reviewed By: dhruba
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19809
Summary:
Use FileLevel in LevelFileNumIterator, thus use new version of findFile.
Old version of findFile function is deleted.
Write a function in version_set.cc to generate FileLevel from files_.
Add GenerateFileLevelTest in version_set_test.cc
Test Plan:
make all check
Reviewers: ljin, haobo, yhchiang, sdong
Reviewed By: sdong
Subscribers: igor, dhruba
Differential Revision: https://reviews.facebook.net/D19659
Summary:
If `NeedToSeekImmutable()` returns false, `SeekInternal()` won't reset the
contents of `immutable_min_heap_`. However, since it calls `UpdateCurrent()`
unconditionally, if `current_` is one of immutable iterators (previously popped
from `immutable_min_heap_`), `UpdateCurrent()` will overwrite it. As a result,
if old `current_` in fact pointed to the smallest entry, forward iterator will
skip some records.
Fix implemented in this diff pushes `current_` back to `immutable_min_heap_`
before calling `UpdateCurrent()`.
Test Plan:
New unit test (courtesy of @lovro):
$ ROCKSDB_TESTS=TailingIteratorSeekToSame ./db_test
Reviewers: igor, dhruba, haobo, ljin
Reviewed By: ljin
Subscribers: lovro, leveldb
Differential Revision: https://reviews.facebook.net/D19653
Summary:
Forward iterator only checked `status_` and `mutable_iter_->status()`, which is
not sufficient. For example, when reading exclusively from cache
(kBlockCacheTier), `mutable_iter_->status()` may return kOk (e.g. there's
nothing in the memtable), but one of immutable iterators could be in
kIncomplete. In this case, `ForwardIterator::status()` ought to return that
status instead of kOk.
This diff changes `status()` to also check `imm_iters_`, `l0_iters_`, and
`level_iters_`.
Test Plan:
ROCKSDB_TESTS=TailingIteratorIncomplete ./db_test
Reviewers: ljin, igor
Reviewed By: igor
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D19581
Summary: Add a function to return the perf level. It is to allow a wrapper of DB to increase the perf level and restore the original perf level after finishing the function call.
Test Plan: Add a verification in db_test
Reviewers: yhchiang, igor, ljin
Reviewed By: ljin
Subscribers: xjin, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D19551
Summary:
Seems like NewTotalOrderPlainTableFactory is useless and is semantically incorrect.
Total order mode indicator is prefix_extractor == nullptr,
but NewTotalOrderPlainTableFactory doesn't set it to be nullptr. That's why some tests
in plain_table_db_tests is incorrect.
Test Plan: make all check
Reviewers: sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19587
Summary:
This is a rough sketch of our new document API. Would like to get some thoughts and comments about the high-level architecture and API.
I didn't optimize for performance at all. Leaving some low-hanging fruit so that we can be happy when we fix them! :)
Currently, bunch of features are not supported at all. Indexes can be only specified when creating database. There is no query planner whatsoever. This will all be added in due time.
Test Plan: Added a simple unit test
Reviewers: haobo, yhchiang, dhruba, sdong, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D18747
Summary:
fix a bug in improve_file_key_search, change the parameter for FileDescriptor
Test Plan:
make all check
Reviewers: sdong
Reviewed By: sdong
Differential Revision: https://reviews.facebook.net/D19611
Summary:
The test is not stable because it relies on disk and only runs for a
short period of time. So misisng a compaction/flush would greatly affect
the rate. I am disabling it for now. What do you guys think?
Test Plan: make
Reviewers: yhchiang, igor, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19599
Summary:
Define CompressedFileMetaData that just contains fd, smallest_slice, largest_slice. Create compressed_levels_ in Version, the space is allocated using arena
Thus increase the file meta data locality, speed up "Get" and "FindFile"
benchmark with in-memory tmpfs, could have 4% improvement under "random read" and 2% improvement under "read while writing"
benchmark command:
./db_bench --db=/mnt/db/rocksdb --num_levels=6 --key_size=20 --prefix_size=20 --keys_per_prefix=0 --value_size=100 --block_size=4096 --cache_size=17179869184 --cache_numshardbits=6 --compression_type=none --compression_ratio=1 --min_level_to_compress=-1 --disable_seek_compaction=1 --hard_rate_limit=2 --write_buffer_size=134217728 --max_write_buffer_number=2 --level0_file_num_compaction_trigger=8 --target_file_size_base=33554432 --max_bytes_for_level_base=1073741824 --disable_wal=0 --sync=0 --disable_data_sync=1 --verify_checksum=1 --delete_obsolete_files_period_micros=314572800 --max_grandparent_overlap_factor=10 --max_background_compactions=4 --max_background_flushes=0 --level0_slowdown_writes_trigger=16 --level0_stop_writes_trigger=24 --statistics=0 --stats_per_interval=0 --stats_interval=1048576 --histogram=0 --use_plain_table=1 --open_files=-1 --mmap_read=1 --mmap_write=0 --memtablerep=prefix_hash --bloom_bits=10 --bloom_locality=1 --perf_level=0 --benchmarks=readwhilewriting,readwhilewriting,readwhilewriting --use_existing_db=1 --num=52428800 --threads=1 —writes_per_second=81920
Read Random:
From 1.8363 ms/op, improve to 1.7587 ms/op.
Read while writing:
From 2.985 ms/op, improve to 2.924 ms/op.
Test Plan:
make all check
Reviewers: ljin, haobo, yhchiang, sdong
Reviewed By: sdong
Subscribers: dhruba, igor
Differential Revision: https://reviews.facebook.net/D19419
Summary:
This patch include two fixes:
1. newly created Version will now takes the aggregated stats for average-value-size from the latest Version.
2. compensated size of a file is now computed only for newly created / loaded file, this addresses the issue where files are already sorted by their compensated file size but might sometimes observe some out-of-order due to later update on compensated file size.
Test Plan:
export ROCKSDB_TESTS=CompactionDele
./db_test
Reviewers: ljin, igor, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19557
Summary: stall count is wrong
Test Plan: make release
Reviewers: sdong, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19539
Summary:
Randomize keys so that compaction actually happens.
Change the config so that compaction happens more aggressively.
The test takes longer time, but the results are more stable shown by
iostat
Test Plan: ran it
Reviewers: igor, yhchiang
Reviewed By: yhchiang
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19533
Summary: as title
Test Plan: make release
Reviewers: sdong, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19515
Summary:
Add option and plugin rate limiter for PosixWritableFile. The rate
limiter only applies to flush and compaction. WAL and MANIFEST are
excluded from this enforcement.
Test Plan: db_test
Reviewers: igor, yhchiang, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19425
Summary:
Use search hint to reduce FindFile range thus avoid comparison
For a small DB with 50M keys, perf_context counter shows it reduces
comparison from 2B to 1.3B for a 15-minute run. No perf change was
observed for 1 seek thread, but quite good improvement was seen for 32
seek threads, when CPU was busy.
will post detail results when ready
Test Plan: db_bench and db_test
Reviewers: haobo, sdong, dhruba, igor
Reviewed By: igor
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D18879
Summary:
Changes:
- Adding numa_aware flag to db_bench.cc
- Using numa.h library to bind memory and cpu of threads to a fixed NUMA node
Result: There seems to be no significant change in the micros/op time with numa_aware enabled. I also tried this with other implementations, including a combination of pthread_setaffinity_np, sched_setaffinity and set_mempolicy methods. It'd be great if someone could point out where I'm going wrong and if we can achieve a better micors/op.
Test Plan:
Ran db_bench tests using following command:
./db_bench --db=/mnt/tmp --num_levels=6 --key_size=20 --prefix_size=20 --keys_per_prefix=0 --value_size=100 --block_size=4096 --cache_size=17179869184 --cache_numshardbits=6 --compression_type=none --compression_ratio=1 --min_level_to_compress=-1 --disable_seek_compaction=1 --hard_rate_limit=2 --write_buffer_size=134217728 --max_write_buffer_number=2 --level0_file_num_compaction_trigger=8 --target_file_size_base=134217728 --max_bytes_for_level_base=1073741824 --disable_wal=0 --wal_dir=/mnt/tmp --sync=0 --disable_data_sync=1 --verify_checksum=1 --delete_obsolete_files_period_micros=314572800 --max_grandparent_overlap_factor=10 --max_background_compactions=4 --max_background_flushes=0 --level0_slowdown_writes_trigger=16 --level0_stop_writes_trigger=24 --statistics=0 --stats_per_interval=0 --stats_interval=1048576 --histogram=0 --use_plain_table=1 --open_files=-1 --mmap_read=1 --mmap_write=0 --memtablerep=prefix_hash --bloom_bits=10 --bloom_locality=1 --perf_level=0 --duration=300 --benchmarks=readwhilewriting --use_existing_db=1 --num=157286400 --threads=24 --writes_per_second=10240 --numa_aware=[False/True]
The tests were run in private devserver with 24 cores and the db was prepopulated using filluniquerandom test. The tests resulted in 0.145 us/op with numa_aware=False and 0.161 us/op with numa_aware=True.
Reviewers: sdong, yhchiang, ljin, igor
Reviewed By: ljin, igor
Subscribers: igor, leveldb
Differential Revision: https://reviews.facebook.net/D19353
Summary:
SimpleWriteTimeoutTest has two parts: 1) insert two large key/values
to make memtable full and expect both of them are successful; 2) insert
another key / value and expect it to be timed-out. Previously we also
set a timeout in the first step, but this might sometimes cause
false alarm.
This diff makes the first two writes run without timeout setting.
Test Plan:
export ROCKSDB_TESTS=Time
make db_test
Reviewers: sdong, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19461
Summary: Removed a variable that is only used in assertion check.
Test Plan: make release
Reviewers: ljin, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19455
Summary:
This diff allows the I/O stats about Flush and Compaction to be reported
in a more accurate way. Instead of measuring the size of a file, it
measure I/O cost in per read / write basis.
Test Plan: make all check
Reviewers: sdong, igor, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19383
Summary:
This diff adds timeout_hint_us to WriteOptions. If it's non-zero, then
1) writes associated with this options MAY be aborted when it has been
waiting for longer than the specified time. If an abortion happens,
associated writes will return Status::TimeOut.
2) the stall time of the associated write caused by flush or compaction
will be limited by timeout_hint_us.
The default value of timeout_hint_us is 0 (i.e., OFF.)
The statistics of timeout writes will be recorded in WRITE_TIMEDOUT.
Test Plan:
export ROCKSDB_TESTS=WriteTimeoutAndDelayTest
make db_test
./db_test
Reviewers: igor, ljin, haobo, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D18837
Summary:
In this patch, we allow RocksDB to support multiple DB paths internally.
No user interface is supported yet so this patch is silent to users.
Test Plan: make all check
Reviewers: igor, haobo, ljin, yhchiang
Reviewed By: yhchiang
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D18921
Summary:
Before this diff, we're deciding enable_compression in CompactionPicker and then we're deciding final compression type in DBImpl. This is kind of confusing.
After the diff, the final compression type will be decided in CompactionPicker.
The reason for this is that I want CompactFiles() to specify output compression type, so that people can mix and match compression styles in their compaction algorithms. This diff makes it much easier to do that.
Test Plan: make check
Reviewers: dhruba, haobo, sdong, yhchiang, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19137
Commit 6634844dba by sdong
Two small fixes in db_test
Summary:
Two fixes:
(1) WalDir to pick a directory under TmpDir to allow two tests running in parallel without impacting each other
(2) kBlockBasedTableWithWholeKeyHashIndex is disabled by mistake (I assume). Enable it.
Test Plan: ./db_test
Reviewers: yhchiang, ljin
Reviewed By: ljin
Subscribers: nkg-, igor, dhruba, haobo, leveldb
Differential Revision: https://reviews.facebook.net/D19389
Summary:
In this patch, we enhance HashLinkList memtable to reduce performance outliers when a bucket contains too many entries. We switch to skip list for this case to enable binary search.
Add threshold_use_skiplist parameter to determine when a bucket needs to switch to skip list.
The new data structure is documented in comments in the codes.
Test Plan:
make all check
set threshold_use_skiplist in several tests
Reviewers: yhchiang, haobo, ljin
Reviewed By: yhchiang, ljin
Subscribers: nkg-, xjin, dhruba, yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D19299
Summary:
Two fixes:
(1) WalDir to pick a directory under TmpDir to allow two tests running in parallel without impacting each other
(2) kBlockBasedTableWithWholeKeyHashIndex is disabled by mistake (I assume). Enable it.
Test Plan: ./db_test
Reviewers: yhchiang, ljin
Reviewed By: ljin
Subscribers: nkg-, igor, dhruba, haobo, leveldb
Differential Revision: https://reviews.facebook.net/D19389
Summary: files_by_size_ is sorted by time in case of universal compaction. However, Version::files_ is also sorted by time. So no need for files_by_size_
Test Plan:
1) make check with the change
2) make check with `assert(last_index == c->input_version_->files_[level].size() - 1);` in compaction picker
Reviewers: dhruba, haobo, yhchiang, sdong, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19125
Summary:
Bloomfilter and hashskiplist's buckets_ allocated by memtable's arena
DynamicBloom: pass arena via constructor, allocate space in SetTotalBits
HashSkipListRep: allocate space of buckets_ using arena.
do not delete it in deconstructor because arena would take care of it.
Several test files are changed.
Test Plan:
make all check
Reviewers: ljin, haobo, yhchiang, sdong
Reviewed By: sdong
Subscribers: igor, dhruba
Differential Revision: https://reviews.facebook.net/D19335
Summary: Code cleaning up, since we are already using __STDC_FORMAT_MACROS in printing uint64_t, change other places. Only logging is changed.
Test Plan: make all check
Reviewers: ljin
Reviewed By: ljin
Subscribers: dhruba, yhchiang, haobo, leveldb
Differential Revision: https://reviews.facebook.net/D19113
Summary:
Task 4580155. Some conditions in DBImpl::MakeRoomForWrite can be cached in
ColumnFamilyData, because theirs value can be changed only during compaction,
adding new memtable and/or add recalculation of compaction score.
These conditions are:
cfd->imm()->size() == cfd->options()->max_write_buffer_number - 1
cfd->current()->NumLevelFiles(0) >= cfd->options()->level0_stop_writes_trigger
cfd->options()->soft_rate_limit > 0.0 &&
(score = cfd->current()->MaxCompactionScore()) > cfd->options()->soft_rate_limit
cfd->options()->hard_rate_limit > 1.0 &&
(score = cfd->current()->MaxCompactionScore()) > cfd->options()->hard_rate_limit
P.S.
As it's my first diff, Siying suggested to add everybody as a reviewers
for this diff. Sorry, if I forgot someone or add someone by mistake.
Test Plan: make all check
Reviewers: haobo, xjin, dhruba, yhchiang, zagfox, ljin, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19311
Summary: It seems to me that when ever function MemTableRep::GetIterator(const Slice& slice) is used, we can use MemTableRep::GetDynamicPrefixIterator() instead. Just delete it to simplify the codes.
Test Plan: make all check
Reviewers: yhchiang, ljin
Reviewed By: ljin
Subscribers: xjin, dhruba, haobo, leveldb
Differential Revision: https://reviews.facebook.net/D19281
Summary:
Move stats related member variables of FileMetaData to the bottom to
improve cache locality of normal DB operations.
Test Plan: make
Reviewers: haobo, ljin, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19287
Summary:
This diff allows compaction to reclaim storage more effectively.
In the current design, compactions are mainly triggered based on
the file sizes. However, since deletion entries does not have
value, files which have many deletion entries are less likely
to be compacted. As a result, it may took a while to make
deletion entries to be compacted.
This diff address issue by compensating the size of deletion
entries during compaction process: the size of each deletion
entry in the compaction process is augmented by 2x average
value size. The diff applies to both leveled and universal
compacitons.
Test Plan:
develop CompactionDeletionTrigger
make db_test
./db_test
Reviewers: haobo, igor, ljin, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19029
Summary:
RandomGenerator::Generate() currently has an assertion len < data_.size().
However, it is actually fine to have len == data_.size().
This diff change the assertion to len <= data_.size().
Test Plan:
make db_bench
./db_bench
Reviewers: haobo, sdong, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19269
Summary: as title
Test Plan: make release
Reviewers: haobo, sdong, yhchiang
Reviewed By: yhchiang
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19227
Summary: as requested by mark
Test Plan: make release
Reviewers: sdong, haobo
Reviewed By: haobo
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19221
Summary:
As discussed in our internal group, we don't get much use of seek compaction at the moment, while it's making code more complicated and slower in some cases.
This diff removes seek compaction and (hopefully) all code that was introduced to support seek compaction.
There is one test case that relied on didIO information. I'll try to find another way to implement it.
Test Plan: make check
Reviewers: sdong, haobo, yhchiang, ljin, dhruba
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19161
Summary:
We decided that one of the long term goals is to unify level and universal compaction.
As a small first step, I'm unifying level 0 sorting methods.
Previously, we used to sort level 0 files in level compaction by file number and in universal compaction by sequence number.
But it turns out that in level compaction, sorting by file number is exactly the same as sorting by sequence number.
Test Plan:
Ran make check with bunch of asserts to verify the sorting order is exactly the same.
Also, make check with this patch
Reviewers: haobo, yhchiang, ljin, dhruba, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19131
Summary: Currently, RocksDB returns error if a db written with prefix hash index, is later opened without providing a prefix extractor. This is uncessarily harsh. Without a prefix extractor, we could always fallback to the normal binary index.
Test Plan: unit test, also manually veried LOG that fallback did occur.
Reviewers: sdong, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19191
Summary:
Currently, when something badly happen in the DB::Write() while the write-queue
contains more than one element, the current design seems to forget to clean up
the queue as well as wake-up all the writers, this potentially makes rocksdb
hang on writes.
Test Plan: make all check
Reviewers: sdong, ljin, igor, haobo
Reviewed By: haobo
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19167
Summary: asan_crash_test is failing on segfault
Test Plan: running asan_crash_test
Reviewers: sdong, igor
Reviewed By: igor
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19149
Summary:
Add a encoding feature of PlainTable to encode PlainTable's keys to save some bytes for the same prefixes.
The data format is documented in table/plain_table_factory.h
Test Plan: Add unit test coverage in plain_table_db_test
Reviewers: yhchiang, igor, dhruba, ljin, haobo
Reviewed By: haobo
Subscribers: nkg-, leveldb
Differential Revision: https://reviews.facebook.net/D18735
Summary:
This is minor, but if we put the writing talbe factory as the third parameter, when we add a new table format, we'll have a situation:
1) block based factory
2) plain table factory
3) output factory
4) new format factory
I think it makes more sense to have output as the first parameter.
Also, fixed a NewAdaptiveTableFactory() call in unit test
Test Plan: unit test
Reviewers: sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19119
Summary: Add two parameters of hash linked list to log distribution of number of entries across all buckets, and a sample row when there are too many entries in one single bucket.
Test Plan: Turn it on in plain_table_db_test and see the logs.
Reviewers: haobo, ljin
Reviewed By: ljin
Subscribers: leveldb, nkg-, dhruba, yhchiang
Differential Revision: https://reviews.facebook.net/D19095
Summary: The new table factory is used if users want to convert a DB from one table format to the other. A user can use this table to open a DB written using one table format and write new files to another table format.
Test Plan: add a unit test
Reviewers: haobo, igor
Reviewed By: igor
Subscribers: dhruba, ljin, yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D19017
Summary: Include max_write_buffer_number >= 2 to SanitizeOptions.
Test Plan: make all check
Reviewers: haobo, sdong, igor, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D19077
Summary:
We added multiple fields to FileMetaData recently and are planning to add more.
This refactoring separate the minimum information for accessing the file. This object is copyable (FileMetaData is not copyable since the ref counter). I hope this refactoring can enable further improvements:
(1) use it to design a more efficient data structure to speed up read queries.
(2) in the future, when we add information of storage level, we can easily do the encoding, instead of enlarge this structure, which might expand memory work set for file meta data.
The definition is same as current EncodedFileMetaData used in two level iterator, so now the logic in two level iterator is easier to understand.
Test Plan: make all check
Reviewers: haobo, igor, ljin
Reviewed By: ljin
Subscribers: leveldb, dhruba, yhchiang
Differential Revision: https://reviews.facebook.net/D18933
Some platforms, particularly Windows, do not have a single method that can
release both a held reader lock and a held writer lock; instead, a
separate method (ReleaseSRWLockShared or ReleaseSRWLockExclusive) must be
called in each case.
This may also be necessary to back MutexRW with a shared_mutex in C++14;
the current language proposal includes both an unlock() and a
shared_unlock() method.
Summary:
https://reviews.facebook.net/D17205 removed the logic of skipping file key range check when there are less than 3 level 0 files. This patch brings it back.
Other than that, add another small optimization to avoid to check all the levels if most higher levels don't have any file.
Test Plan: make all check
Reviewers: ljin
Reviewed By: ljin
Subscribers: yhchiang, igor, haobo, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D19035
Summary: as title
Test Plan:
db_bench
the initial result is very promising. I will post results of complete
runs
Reviewers: dhruba, haobo, sdong, igor
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D18867
Summary:
Clean PlainTableReader's data structures:
(1) inline bloom_ (in order to do this, change DynamicBloom to allow lazy initialization)
(2) remove some variables only used when initialization from the class
(3) put variables not used in normal read code paths to the end of the class and reference prefix_extractor directly
(4) make Options a reference.
Test Plan: make all check
Reviewers: haobo, ljin
Reviewed By: ljin
Subscribers: igor, yhchiang, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D18891
Summary: Provide an convenience option to create column families if they are missing from the DB. Task #4460490
Test Plan: added unit test. also, stress test for some time
Reviewers: sdong, haobo, dhruba, ljin, yhchiang
Reviewed By: yhchiang
Subscribers: yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D18951
Summary: We have a perf regression of Write() even with one column family. Make fast path for single column family to avoid the perf regression. See task #4455480
Test Plan: make check
Reviewers: sdong, ljin
Reviewed By: sdong, ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D18963
Summary: Now sst_dump fails in block based tables if binary search index is used, as it requires a prefix extractor. Add it.
Test Plan: Run it against such a file to make sure it fixes the problem.
Reviewers: yhchiang, kailiu
Reviewed By: kailiu
Subscribers: ljin, igor, dhruba, haobo, leveldb
Differential Revision: https://reviews.facebook.net/D18927
Summary: In universal compaction, MaxFileSizeForLevel is ULLONG_MAX. We've been preallocation files to UULONG_MAX size all these time :)
Test Plan: make check
Reviewers: dhruba, haobo, ljin, sdong, yhchiang
Reviewed By: yhchiang
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D18915
Summary:
In this patch, try to allocate the whole iterator tree starting from DBIter from an arena
1. ArenaWrappedDBIter is created when serves as the entry point of an iterator tree, with an arena in it.
2. Add an option to create iterator from arena for following iterators: DBIter, MergingIterator, MemtableIterator, all mem table's iterators, all table reader's iterators and two level iterator.
3. MergeIteratorBuilder is created to incrementally build the tree of internal iterators. It is passed to mem table list and version set and add iterators to it.
Limitations:
(1) Only DB::NewIterator() without tailing uses the arena. Other cases, including readonly DB and compactions are still from malloc
(2) Two level iterator itself is allocated in arena, but not iterators inside it.
Test Plan: make all check
Reviewers: ljin, haobo
Reviewed By: haobo
Subscribers: leveldb, dhruba, yhchiang, igor
Differential Revision: https://reviews.facebook.net/D18513
Summary:
At the end of BackgroundCallCompaction(), we call SignalAll(), even though we don't need to. If compaction hasn't done anything and there's another compaction running, there is no need to signal on the condition variable. Doing so creates a tight feedback loop which results in log files like:
wait for memtable flush
compaction nothing to do
wait for memtable flush
compaction nothing to do
This change eliminates that
Test Plan:
make check
Also:
icanadi@dev1440 ~ $ grep "nothing to do" /fast-rocksdb-tmp/rocksdb_test/column_family_test/LOG | wc -l
7435
icanadi@dev1440 ~ $ grep "nothing to do" /fast-rocksdb-tmp/rocksdb_test/column_family_test/LOG | wc -l
372
First version is before the change, second version is after the change.
Reviewers: dhruba, ljin, haobo, yhchiang, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D18855
Summary:
We've seen some production issues where column family is detected as stale, although there is only one column family in the system. This is a quick fix that:
1) doesn't flush stale column families if there's only one of them
2) Use 4 as a coefficient instead of 2 for determening when a column family is stale. This will make flushing less aggressive, while still keep a nice dynamic flushing of very stale CFs.
Test Plan: make check
Reviewers: dhruba, haobo, ljin, sdong
Reviewed By: sdong
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D18861
Summary:
Forward iterator puts everything together in a flat structure instead of
a hierarchy of nested iterators. this should simplify the code and
provide better performance. It also enables more optimization since all
information are accessiable in one place.
Init evaluation shows about 6% improvement
Test Plan: db_test and db_bench
Reviewers: dhruba, igor, tnovak, sdong, haobo
Reviewed By: haobo
Subscribers: sdong, leveldb
Differential Revision: https://reviews.facebook.net/D18795
Summary: One more option to allow iterator refreshing when using normal iterator
Test Plan: ran db_bench
Reviewers: haobo, sdong, igor
Reviewed By: igor
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D18849
Summary:
Introducing new compaction style -- FIFO.
FIFO compaction style has write amplification of 1 (+1 for WAL) and it deletes the oldest files when the total DB size exceeds pre-configured values.
FIFO compaction style is suited for storing high-frequency event logs.
Test Plan: Added a unit test
Reviewers: dhruba, haobo, sdong
Reviewed By: dhruba
Subscribers: alberts, leveldb
Differential Revision: https://reviews.facebook.net/D18765
Summary: Key size limit doesn't seem to be applicable anymore. Remove it.
Test Plan: run a couple of tests in db_bench
Reviewers: haobo, igor, yhchiang, dhruba
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18723
Summary: Cleaned up compaction logging a little bit. Now file sizes are easier to read. Also, removed the trailing space.
Test Plan:
verified that i'm happy with logging output:
files_size[#33(seq=101,sz=98KB,0) #31(seq=81,sz=159KB,0) #26(seq=0,sz=637KB,0)]
Reviewers: sdong, haobo, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18549
Summary:
In order to use arena to a use case that the total allocation size might be small (LogBuffer is already such a case), inline 1KB of data in it, so that it can be mostly in stack or inline in another class.
If always inlining 2KB is a concern, I could make it a template to determine what to inline. However, dependents need to changes. Doesn't go with it for now
Test Plan: make all check.
Reviewers: haobo, igor, yhchiang, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18609
Summary:
This diff addresses task #4296714 and rethinks how users provide us with TablePropertiesCollectors as part of Options.
Here's description of task #4296714:
I'm debugging #4295529 and noticed that our count of user properties kDeletedKeys is wrong. We're sharing one single InternalKeyPropertiesCollector with all Table Builders. In LOG Files, we're outputting number of kDeletedKeys as connected with a single table, while it's actually the total count of deleted keys since creation of the DB.
For example, this table has 3155 entries and 1391828 deleted keys.
The problem with current approach that we call methods on a single TablePropertiesCollector for all the tables we create. Even worse, we could do it from multiple threads at the same time and TablePropertiesCollector has no way of knowing which table we're calling it for.
Good part: Looks like nobody inside Facebook is using Options::table_properties_collectors. This means we should be able to painfully change the API.
In this change, I introduce TablePropertiesCollectorFactory. For every table we create, we call `CreateTablePropertiesCollector`, which creates a TablePropertiesCollector for a single table. We then use it sequentially from a single thread, which means it doesn't have to be thread-safe.
Test Plan:
Added a test in table_properties_collector_test that fails on master (build two tables, assert that kDeletedKeys count is correct for the second one).
Also, all other tests
Reviewers: sdong, dhruba, haobo, kailiu
Reviewed By: kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18579
Summary:
Fixed a file-not-found issue when a log file is moved to archive
by doing a missing retry.
Test Plan:
make db_test
export ROCKSDB_TEST=TransactionLogIteratorRace
./db_test
Reviewers: sdong, haobo
Reviewed By: sdong
CC: igor, leveldb
Differential Revision: https://reviews.facebook.net/D18669
Summary: as title
Test Plan: Still compile
Reviewers: haobo, igor, yhchiang
Reviewed By: igor
CC: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D18603
Summary:
Newer gflags switched from `google` namespace to `gflags` namespace. See: https://github.com/facebook/rocksdb/issues/139 and https://github.com/facebook/rocksdb/issues/102
Unfortunately, they don't define any macro with their namespace, so we need to actually try to compile gflags with two different namespace to figure out which one is the correct one.
Test Plan: works in fbcode environemnt. I'll also try in ubutnu with newer gflags
Reviewers: dhruba
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18537
Summary: We had a hypothesis in https://reviews.facebook.net/D18507 that empty-string internal keys might have been caused by compaction filter deleting all the entries. I added a unit test for that case. Unforutnately, everything works as expected.
Test Plan: this is a test
Reviewers: dhruba, haobo, sdong
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18519
Summary:
This was reported by our customers in task #4295529.
Cause:
* MANIFEST file contains a VersionEdit, which contains file entries whose 'smallest' and 'largest' internal keys are empty. String with zero characters. Root cause of corruption was not investigated. We should report corruption when this happens. However, we currently SIGSEGV.
Here's what happens:
* VersionEdit encodes zero-strings happily and stores them in smallest and largest InternalKeys. InternalKey::Encode() does assert when `rep_.empty()`, but we don't assert in production environemnts. Also, we should never assert as a result of DB corruption.
* As part of our ConsistencyCheck, we call GetLiveFilesMetaData()
* GetLiveFilesMetadata() calls `file->largest.user_key().ToString()`
* user_key() function does: 1. assert(size > 8) (ooops, no assert), 2. returns `Slice(internal_key.data(), internal_key.size() - 8)`
* since `internal_key.size()` is unsigned int, this call translates to `Slice(whatever, 1298471928561892576182756)`. Bazinga.
Fix:
* VersionEdit checks if InternalKey is valid in `VersionEdit::GetInternalKey()`. If it's invalid, returns corruption.
Lessons learned:
* Always keep in mind that even if you `assert()`, production code will continue execution even if assert fails.
* Never `assert` based on DB corruption. Assert only if the code should guarantee that assert can't fail.
Test Plan: dumped offending manifest. Before: assert. Now: corruption
Reviewers: dhruba, haobo, sdong
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18507
Summary: One of our users reported current file corruption. The machine was rebooted during the time. This is the only think I can think of which could cause current file corruption. Just add this paranoid check.
Test Plan: make all check
Reviewers: haobo, igor
Reviewed By: haobo
CC: yhchiang, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D18495
Summary:
TLB page allocation errors are now logged to info logs, instead of stderr.
In order to do that, mem table rep's factory functions take a info logger now.
Test Plan: make all check
Reviewers: haobo, igor, yhchiang
Reviewed By: yhchiang
CC: leveldb, yhchiang, dhruba
Differential Revision: https://reviews.facebook.net/D18471
Summary:
db_test includes Benchmark for LogAndApply. This diff removes it from db_test and puts it into a separate log_and_apply bench. I just wanted to play around with our new benchmark framework and figure out how it works.
I would also like to show you how great it is! I believe right set of microbenchmarks can speed up our productivity a lot and help catch early regressions.
Test Plan: no
Reviewers: dhruba, haobo, sdong, ljin, yhchiang
Reviewed By: yhchiang
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18261
Summary:
Added a new option `max_total_wal_size`. Once the total WAL size goes over that, we make an attempt to flush all column families that still have data in the earliest WAL file.
By default, I calculate `max_total_wal_size` dynamically, that should be good-enough for non-advanced customers.
Test Plan: Added a test
Reviewers: dhruba, haobo, sdong, ljin, yhchiang
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18345
Summary: Add an option to allocate a piece of memory from huge page TLB. Add options to trigger it in dynamic bloom, plain table indexes andhash linked list hash table.
Test Plan: make all check
Reviewers: haobo, ljin
Reviewed By: haobo
CC: nkg-, dhruba, leveldb, igor, yhchiang
Differential Revision: https://reviews.facebook.net/D18357
Summary:
= Major Changes =
* Add a new mem-table representation, HashCuckooRep, which is based cuckoo hash.
Cuckoo hash uses multiple hash functions. This allows each key to have multiple
possible locations in the mem-table.
- Put: When insert a key, it will try to find whether one of its possible
locations is vacant and store the key. If none of its possible
locations are available, then it will kick out a victim key and
store at that location. The kicked-out victim key will then be
stored at a vacant space of its possible locations or kick-out
another victim. In this diff, the kick-out path (known as
cuckoo-path) is found using BFS, which guarantees to be the shortest.
- Get: Simply tries all possible locations of a key --- this guarantees
worst-case constant time complexity.
- Time complexity: O(1) for Get, and average O(1) for Put if the
fullness of the mem-table is below 80%.
- Default using two hash functions, the number of hash functions used
by the cuckoo-hash may dynamically increase if it fails to find a
short-enough kick-out path.
- Currently, HashCuckooRep does not support iteration and snapshots,
as our current main purpose of this is to optimize point access.
= Minor Changes =
* Add IsSnapshotSupported() to DB to indicate whether the current DB
supports snapshots. If it returns false, then DB::GetSnapshot() will
always return nullptr.
Test Plan:
Run existing tests. Will develop a test specifically for cuckoo hash in
the next diff.
Reviewers: sdong, haobo
Reviewed By: sdong
CC: leveldb, dhruba, igor
Differential Revision: https://reviews.facebook.net/D16155
Summary:
ReadFirstRecord() reads the actual log file from disk on every call. This diff introduces a cache layer on top of ReadFirstRecord(), which should significantly speed up repeated calls to GetUpdatesSince().
I also cleaned up some stuff, but the whole TransactionLogIterator could use some refactoring, especially if we see increased usage.
Test Plan: make check
Reviewers: haobo, sdong, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18387
Summary:
When TransactionLogIterator comes to EOF, it calls UnmarkEOF and continues reading. However, if glibc cached the EOF status of the file, it will get EOF again, even though the new data might have been written to it.
This has been causing errors in Mac OS.
Test Plan: test passes, was failing before
Reviewers: dhruba, haobo, sdong
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18381
Summary:
As a follow-up diff for https://reviews.facebook.net/D17805, add
optimization to check PrefixMayMatch on Seek()
Test Plan: make all check
Reviewers: igor, haobo, sdong, yhchiang, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17853
Summary:
also add an override option total_order_iteration if you want to use full
iterator with prefix_extractor
Test Plan: make all check
Reviewers: igor, haobo, sdong, yhchiang
Reviewed By: haobo
CC: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D17805
Summary: As summary. Add two autovectors that get filled up in MakeRoomForWrite and they get deleted outside of mutex
Test Plan: make check
Reviewers: dhruba, haobo, ljin, sdong
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18249
Summary:
Now that we have column families involved, we need to add extra context to every log message. They now start with "[column family name] log message"
Also added some logging that I think would be useful, like level summary after every flush (I often needed that when going through the logs).
Test Plan: make check + ran db_bench to confirm I'm happy with log output
Reviewers: dhruba, haobo, ljin, yhchiang, sdong
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18303
Summary:
I'm getting lots of e-mails with CompactionInputErrorParanoid failing. Most recent example early morning today was: http://ci-builds.fb.com/job/rocksdb_valgrind/562/consoleFull
I'm putting a stop to these e-mails. I investigated why the test is flakey and it turns out it's because of non-determinsim of compaction scheduling. If there is a compaction after the last flush, CorruptFile will corrupt the compacted file instead of file at level 0 (as it assumes). That makes `Check(9, 9)` fail big time.
I also saw some errors with table file getting outputed to >= 1 levels instead of 0. Also fixed that.
Test Plan: Ran corruption_test 100 times without a failure. Previously it usually failed at 10th occurrence.
Reviewers: dhruba, haobo, ljin
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18285
Summary: IterKey set buffer_size_ to a wrong initial value, causing it to always allocate values from heap instead of stack if the key size is smaller. Fix it.
Test Plan: make all check
Reviewers: haobo, ljin
Reviewed By: haobo
CC: igor, dhruba, yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D18279
Summary: While debugging Mac-only issue with ThreadLocalPtr, this was very useful. Let's print out stack trace in MAC OS, too.
Test Plan: Verified that somewhat useful stack trace was generated on mac. Will run PrintStack() on linux, too.
Reviewers: ljin, haobo
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18189
Summary: In this patch, two new DB properties are defined: rocksdb.num-immutable-mem-table and rocksdb.num-entries-imm-mem-tables, from where number of entries in mem tables can be exposed to users
Test Plan:
Cover the codes in db_test
make all check
Reviewers: haobo, ljin, igor
Reviewed By: igor
CC: nkg-, igor, yhchiang, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D18207
Summary: Get rid of the devil. Probably won't impact anything on the perf side.
Test Plan: make all check
Reviewers: igor, haobo, sdong, yhchiang
Reviewed By: haobo
CC: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D18153
Summary:
This is a temp solution to expose index sizes to users from PlainTableReader before we persistent them to files.
In this patch, the memory consumption of indexes used by PlainTableReader will be reported as two user defined properties, so that users can monitor them.
Test Plan:
Add a unit test.
make all check`
Reviewers: haobo, ljin
Reviewed By: haobo
CC: nkg-, yhchiang, igor, ljin, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D18195
Summary:
Using ThreadLocalPtr as a flag to determine if a mutex is locked or not enables us to implement AssertNotHeld(). It also makes AssertHeld() actually correct.
I had to remove port::Mutex as a dependency for util/thread_local.h, but that's fine since we can just use std::mutex :)
Test Plan: make check
Reviewers: ljin, dhruba, haobo, sdong, yhchiang
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18171
Summary:
This will enable people using TTL DB to do so with multiple column families. They can also specify different TTLs for each one.
TODO: Implement CreateColumnFamily() in TTL world.
Test Plan: Added a very simple sanity test.
Reviewers: dhruba, haobo, ljin, sdong, yhchiang
Reviewed By: haobo
CC: leveldb, alberts
Differential Revision: https://reviews.facebook.net/D17859
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
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
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
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
Summary: Current behavior of creating new DB is, if there is existing log files, we will go ahead and replay them on top of empty DB. This is a behavior that no user would expect. With this patch, we will fail the creation if a user creates a DB with existing log files.
Test Plan: make all check
Reviewers: haobo, igor, ljin
Reviewed By: haobo
CC: nkg-, yhchiang, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D17817
Summary:
Introducing RocksDBLite! Removes all the non-essential features and reduces the binary size. This effort should help our adoption on mobile.
Binary size when compiling for IOS (`TARGET_OS=IOS m static_lib`) is down to 9MB from 15MB (without stripping)
Test Plan: compiles :)
Reviewers: dhruba, haobo, ljin, sdong, yhchiang
Reviewed By: yhchiang
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17835
Summary:
With multiple column families, especially when manual Flush is executed, we might roll the log file, although the current log file is empty (no data has been written to the log).
After the diff, we won't create new log file if current is empty.
Next, I will write an algorithm that will flush column families that reference old log files (i.e., that weren't flushed in a while)
Test Plan: Added an unit test. Confirmed that unit test failes in master
Reviewers: dhruba, haobo, ljin, sdong
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17631
Summary: multireadrandom is broken. Fix it
Test Plan: run it and see segfault has gone.
Reviewers: ljin
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17781
Summary:
Fix the following compile error
./db/tailing_iter.h:17:1: error: class 'SuperVersion' was previously declared as a struct [-Werror,-Wmismatched-tags]
class SuperVersion;
^
./db/column_family.h:77:8: note: previous use is here
struct SuperVersion {
^
./db/tailing_iter.h:17:1: note: did you mean struct here?
class SuperVersion;
^~~~~
struct
1 error generated.
Test Plan: make
Reviewers: ljin, igor, haobo, sdong
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17799
Summary:
replace the super version acquisision in tailing itrator with thread
local
Test Plan: will post results
Reviewers: igor, haobo, sdong, yhchiang, dhruba
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17757
Summary:
Similar to GetImp(), use SuperVersion from thread local instead of acquriing mutex.
I don't expect this change will make a dent on NewIterator() performance
because the bottleneck seems to be on the rest part of the API
Test Plan:
make asan_check
will post perf numbers
Reviewers: haobo, igor, sdong, dhruba, yhchiang
Reviewed By: sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17643
Summary: This patch introduces a new parameter num_multi_db in db_bench. When this parameter is larger than 1, multiple DBs will be created. In all benchmarks, any operation applies to a random DB among them. This is to benchmark the performance of similar applications.
Test Plan: run db_bench on both of num_multi_db=0 and more.
Reviewers: haobo, ljin, igor
Reviewed By: igor
CC: igor, yhchiang, dhruba, nkg-, leveldb
Differential Revision: https://reviews.facebook.net/D17769
Summary:
it writes ~10M data, default L0 compaction trigger is 4, plus 2 writer
buffer, so that can accommodate ~6M data before compaction happens for
sure. I guess encoding is doing a good job to shrink the data so that
sometime, compaction does not get triggered. I get test failure quite
often.
Test Plan: ran it multiple times and all got pass
Reviewers: igor, sdong
Reviewed By: sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17775
Summary: as title
Test Plan: ran it
Reviewers: igor, haobo, yhchiang
Reviewed By: yhchiang
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17751
Summary: XCode for some reason injects `#define DEBUG 1` into our code, which makes compile fail because we use `DEBUG` keyword for other stuff. This diff fixes the issue by renaming `DEBUG` to `DEBUG_LEVEL`.
Test Plan: compiles
Reviewers: dhruba, haobo, sdong, yhchiang, ljin
Reviewed By: yhchiang
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17709
Summary: Based on previous patches, this diff eventually provides the end-to-end mechanism for users to specify the hash-index.
Test Plan: Wrote several new unit tests.
Reviewers: sdong, haobo, dhruba
Reviewed By: sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16539
Summary: as title
Test Plan: ran it
Reviewers: igor, haobo, yhchiang
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17655
Summary: Compiling for iOS has by default turned on -Wmissing-prototypes, which causes rocksdb to fail compiling. This diff turns on -Wmissing-prototypes in our compile options and cleans up all functions with missing prototypes.
Test Plan: compiles
Reviewers: dhruba, haobo, ljin, sdong
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17649
Summary:
1. Polish IterKey a little bit.
2. Turn to use it in local parameter of current_user_key in DBImpl::ProcessKeyValueCompaction(). Our profile showing that DBImpl::ProcessKeyValueCompaction() has about 14% costs in std::string (the base including reading and writing data but excluding compaction filtering), which is higher than it should be. There are two std::string used in DBImpl::ProcessKeyValueCompaction(), compaction_filter_value and current_user_key and it's hard to distinguish the two.
Test Plan: make all check
Reviewers: haobo, ljin
Reviewed By: haobo
CC: igor, yhchiang, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D17613
Summary:
This is testing behavior that was reported in https://github.com/facebook/rocksdb/issues/111
No issue was found, but it still good to commit this and make CompressedCache more robust.
Test Plan: this is a plan
Reviewers: ljin, dhruba
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17625
Summary:
filluniquerandom is painfully slow due to the naive bitmap check to find
out if a key has been seen before. Majority of time is spent on searching
the last few keys. Split a giant BitSet to smaller ones so that we can
quickly check if a BitSet is full and thus can skip quickly.
It used to take over one hour to filluniquerandom for 100M keys, now it
takes about 10 mins.
Test Plan:
unit test
also verified correctness in db_bench and make sure all keys are
generated
Reviewers: igor, haobo, yhchiang
Reviewed By: igor
CC: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D17607
Summary: When opening DB in read-only mode, client can choose to only specify a subset of column families ("default" column family can't be omitted, though)
Test Plan: added a unit test in column_family_test
Reviewers: haobo, sdong, ljin, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17565
Summary:
GetProperty test is flakey.
Before this diff: P8635927
After: P8635945
We need to make sure the thread is done before we destruct sleeping tasks. Otherwise, bad things happen.
Test Plan: See summary
Reviewers: ljin, sdong, haobo, dhruba
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17595
Summary:
clean up the db_bench a little bit. also avoid allocating memory for key
in the loop
Test Plan:
I verified a run with filluniquerandom & readrandom. Iterator seek will be used lot
to measure performance. Will fix whatever comes up
Reviewers: haobo, igor, yhchiang
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17559
Summary: ToString() is expensive. Profiling shows that most compaction threads are stuck in jemalloc, allocating a new string. This will help out a litte.
Test Plan: make check
Reviewers: haobo, danguo
Reviewed By: danguo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17583
Summary: This will allow us to disable them completely for iOS or for better performance
Test Plan: will run make all check
Reviewers: igor, haobo, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17511
Summary:
Move PlainTableIterator's copied key from std::string local buffer to avoid paying the extra costs in std::string related to sharing. Reuse the same buffer class in DbIter. Move the class to dbformat.h.
This patch improves iterator performance significantly. Running this benchmark:
./table_reader_bench --num_keys2=17 --iterator --plain_table --time_unit=nanosecond
The average latency is improved to about 750 nanoseconds from 1100 nanoseconds.
Test Plan:
Add a unit test.
make all check
Reviewers: haobo, ljin
Reviewed By: haobo
CC: igor, yhchiang, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D17547
Summary: If a client specifies wal_dir with trailing '/', we will fail in deleting obsolete log files. See task #4083746
Test Plan: make check
Reviewers: haobo, sdong
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17535
Summary: Our measurement shows that sometimes new log::Write's constructor can take hundreds of milliseconds. It's unclear why but just simply move it out of DB mutex.
Test Plan: make all check
Reviewers: haobo, ljin, igor
Reviewed By: haobo
CC: nkg-, yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D17487
Summary: per sdong's request, this will help processor prefetch on n->key case.
Test Plan: make all check
Reviewers: sdong, haobo, igor
Reviewed By: sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17415
Summary: Flushing log buffer earlier to avoid confusion of time holding the locks.
Test Plan: Should be safe as long as several related db test passes
Reviewers: haobo, igor, ljin
Reviewed By: igor
CC: nkg-, leveldb
Differential Revision: https://reviews.facebook.net/D17493
Summary: Move several some common logging still in DB mutex to log buffer.
Test Plan: make all check
Reviewers: haobo, igor, ljin, nkg-
Reviewed By: nkg-
CC: nkg-, yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D17439
Summary: This patch fixed a race condition where a log file is moved to archived dir in the middle of GetSortedWalFiles. Without the fix, the log file would be missed in the result, which leads to transaction log iterator gap. A test utility SyncPoint is added to help reproducing the race condition.
Test Plan: TransactionLogIteratorRace; make check
Reviewers: dhruba, ljin
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17121
Summary: As we know, logging can be slow, or even hang for some file systems. Move one more logging out of DB mutex.
Test Plan: make all check
Reviewers: haobo, igor, ljin
Reviewed By: igor
CC: yhchiang, nkg-, leveldb
Differential Revision: https://reviews.facebook.net/D17427
Summary: The previous change D15087 changed existing compaction filter, which makes the commonly used class not backward compatible. Revert the older interface. Use a new interface for V2 instead.
Test Plan: make all check
Reviewers: haobo, yhchiang, igor
CC: danguo, dhruba, ljin, igor, leveldb
Differential Revision: https://reviews.facebook.net/D17223
Summary: It is a regression valgrind bug caused by using FileMetaData as index block handle. One of the fields of FileMetaData is not initialized after being contructed and copied, but I'm not able to find which one. Also, I realized that it's not a good idea to use FileMetaData as in TwoLevelIterator::InitDataBlock(), a copied FileMetaData can be compared with the one in version set byte by byte, but the refs can be changed. Also comparing such a large structure is slightly more expensive. Use a simpler structure instead
Test Plan:
Run the failing valgrind test (Harness.RandomizedLongDB)
make all check
Reviewers: igor, haobo, ljin
Reviewed By: igor
CC: yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D17409
Summary: DBIter now uses a std::string for saved_key. Based on some profiling, it could be more expensive than we though. Optimize it with the same technique as LookupKey -- if it is short, we copy it to a static allocated char. Otherwise, dynamically allocate memory for it.
Test Plan: make all check
Reviewers: haobo, ljin
Reviewed By: haobo
CC: dhruba, igor, yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D17289
Summary:
In total order mode, iterator's seek() shouldn't check total order.
Also some cleaning up about checking null for shared pointers. I don't know the behavior before it.
This bug was reported by @igor.
Test Plan: test plain_table_db_test
Reviewers: ljin, haobo, igor
Reviewed By: igor
CC: yhchiang, dhruba, igor, leveldb
Differential Revision: https://reviews.facebook.net/D17391
Summary: Talked to <insert internal project name> folks and they found it really scary that they won't be able to roll back once they upgrade to 2.8. We should fix this.
Test Plan: make check
Reviewers: haobo, ljin
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17343
Summary: Fix some more CompactionFilterV2 valgrind issues. Maybe it would make sense for CompactionFilterV2 to delete its prefix_extractor?
Test Plan: ran CompactionFilterV2* tests with valgrind. issues before patch -> no issues after
Reviewers: haobo, sdong, ljin, dhruba
Reviewed By: dhruba
CC: leveldb, danguo
Differential Revision: https://reviews.facebook.net/D17337
Summary: Since we are optimizing for server workloads, some default values are not optimized any more. We change some of those values that I feel it's less prone to regression bugs.
Test Plan: make all check
Reviewers: dhruba, haobo, ljin, igor, yhchiang
Reviewed By: igor
CC: leveldb, MarkCallaghan
Differential Revision: https://reviews.facebook.net/D16995
Summary: In one of the perf, I shows 10%-25% CPU costs of MemTableIterator.Seek(), when doing dynamic prefix seek, are spent on checking whether we need to do bloom filter check or finding out the prefix extractor. Seems that more level of pointer checking makes CPU cache miss more likely. This patch makes things slightly simpler by copying pointer of bloom of prefix extractor into the iterator.
Test Plan: make all check
Reviewers: haobo, ljin
Reviewed By: ljin
CC: igor, dhruba, yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D17247
Summary:
By constraining the probes within cache line(s), we can improve the
cache miss rate thus performance. This probably only makes sense for
in-memory workload so defaults the option to off.
Numbers and comparision can be found in wiki:
https://our.intern.facebook.com/intern/wiki/index.php/Ljin/rocksdb_perf/2014_03_17#Bloom_Filter_Study
Test Plan: benchmarked this change substantially. Will run make all check as well
Reviewers: haobo, igor, dhruba, sdong, yhchiang
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17133
Summary: Fix the bug in MergeUtil which causes mixing values of different keys.
Test Plan:
stringappend_test
make all check
Reviewers: haobo, igor
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17235
Summary:
NewFixedPrefixTransform is leaked in default options. Broken by b47812fba6
Also included in the diff some code cleanup
Test Plan:
valgrind env_test
also make check
Reviewers: haobo, danguo, yhchiang
Reviewed By: danguo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17211
Summary:
Previously, we used to sort all files by BySmallestFirst comparator and then re-sort level0 files in the Finalize() (recently moved to end of SaveTo).
In this diff, I chose the correct comparator at the beginning and sort the files correctly in Builder::SaveTo.
I also added a verification that all files are sorted correctly in CheckConsistency()
NOTE: This diff depends on D17037
Test Plan: make check. Will also run db_stress
Reviewers: dhruba, haobo, sdong, ljin
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17049
Summary:
AssertHeld() was a no-op before. Now it does things.
Also, this change caught a bad bug in SuperVersion::Init(). The method is calling db->mutex.AssertHeld(), but db variable is not initialized yet! I also fixed that issue.
Test Plan: make check
Reviewers: dhruba, haobo, ljin, sdong, yhchiang
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17193
Summary: We don't preallocate MANIFEST file, even though we have an option for that. This diff preallocates manifest file every time we create it
Test Plan: make check
Reviewers: dhruba, haobo
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17163
Summary:
This is the part that was not finished when doing the Options.max_num_files=-1 feature. For iterating non level0 SST files (which was done using two level iterator), table cache is not bypassed. With this patch, the leftover feature is done.
Test Plan: make all check; change Options.max_num_files=-1 in one of the tests to cover the codes.
Reviewers: haobo, igor, dhruba, ljin, yhchiang
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17001
Summary:
Add assert(operands_list.size() >= 2) in MergeOperator::PartialMergeMulti
to ensure it's only be called when we have at least two merge operands.
Test Plan: run merge_test and stringappend_test.
Reviewers: haobo, igor
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17169
Summary:
Currently if client uses kNULLString as the prefix, it will confuse
compaction filter v2. This diff added a bool to indicate if the prefix
has been intialized. I also added a unit test to cover this case and
make sure the new code path is hit.
Test Plan: db_test
Reviewers: igor, haobo
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17151
Summary:
Fix a bug that PartialMergeMulti will try to merge the first operand
with an empty slice.
Test Plan: run stringappend_test and merge_test.
Reviewers: haobo, igor
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17157
Summary:
This diff adds a new CompactionFilterV2 API that roll up the
decisions of kv pairs during compactions. These kv pairs must share the
same key prefix. They are buffered inside the db.
typedef std::vector<Slice> SliceVector;
virtual std::vector<bool> Filter(int level,
const SliceVector& keys,
const SliceVector& existing_values,
std::vector<std::string>* new_values,
std::vector<bool>* values_changed
) const = 0;
Application can override the Filter() function to operate
on the buffered kv pairs. More details in the inline documentation.
Test Plan:
make check. Added unit tests to make sure Keep, Delete,
Change all works.
Reviewers: haobo
CCs: leveldb
Differential Revision: https://reviews.facebook.net/D15087
Summary:
* PartialMerge api now takes a list of operands instead of two operands.
* Add min_pertial_merge_operands to Options, indicating the minimum
number of operands to trigger partial merge.
* This diff is based on Schalk's previous diff (D14601), but it also
includes necessary changes such as updating the pure C api for
partial merge.
Test Plan:
* make check all
* develop tests for cases where partial merge takes more than two
operands.
TODOs (from Schalk):
* Add test with min_partial_merge_operands > 2.
* Perform benchmarks to measure the performance improvements (can probably
use results of task #2837810.)
* Add description of problem to doc/index.html.
* Change wiki pages to reflect the interface changes.
Reviewers: haobo, igor, vamsi
Reviewed By: haobo
CC: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D16815
Summary:
Everytime a client opens a DB, we do a sanity check that:
* checks the existance of all the necessary files
* verifies that file sizes are correct
Some of the code was stolen from https://reviews.facebook.net/D16935
Test Plan: added a unit test
Reviewers: dhruba, haobo, sdong
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17097
Summary: Added a function/command to check the consistency of live files' meta data
Test Plan:
Manual test (size mismatch, file not exist).
Command test script.
Reviewers: haobo
Reviewed By: haobo
CC: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D16935
Summary:
Whenever we get an IOError from GetImpl() or NewIterator(), we should immediatelly mark the DB read-only. The same check already exists in Write() and Compaction().
This should help with clients that are somehow missing a file.
Test Plan: make check
Reviewers: dhruba, haobo, sdong, ljin
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17061
Summary: D17067 breaks DBTest.UniversalCompactionTrigger because of wrong location of the checking. Fix it.
Test Plan: Run the test and make sure it passes.
Reviewers: igor, haobo
Reviewed By: igor
CC: dhruba, ljin, yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D17079
Summary: Add unit tests to make sure CompactionFilterContext::is_manual_compaction_ and CompactionFilterContext::is_full_compaction_ are set correctly.
Test Plan: run the new tests.
Reviewers: haobo, igor, dhruba, yhchiang, ljin
Reviewed By: haobo
CC: nkg-, leveldb
Differential Revision: https://reviews.facebook.net/D17067
Summary:
As it turns out, we need the call to ComputeCompactionScore (previously: Finalize) in CompactionPicker.
The issue caused a deadlock in db_stress: http://ci-builds.fb.com/job/rocksdb_crashtest/290/console
The last two lines before a deadlock were:
2014/03/18-22:43:41.481029 7facafbee700 (Original Log Time 2014/03/18-22:43:41.480989) Compaction nothing to do
2014/03/18-22:43:41.481041 7faccf7fc700 wait for fewer level0 files...
"Compaction nothing to do" and other thread waiting for fewer level0 files. Hm hm.
I moved the pre-sorting to SaveTo, which should fix both the original and the new issue.
Test Plan: make check for now, will run db_stress in jenkins
Reviewers: dhruba, haobo, sdong
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17037
Summary:
We have an issue with internal service trying to run compaction with zero input files:
2014/02/07-02:26:58.386531 7f79117ec700 Compaction start summary: Base version 1420 Base level 3, seek compaction:0, inputs:[Ï›~^Qy^?],[]
2014/02/07-02:26:58.386539 7f79117ec700 Compacted 0@3 + 0@4 files => 0 bytes
There are two issues:
* inputsummary is printing out junk
* it's constantly retrying (since I guess madeProgress is true), so it prints out a lot of data in the LOG file (40GB in one day).
I read through the Level compaction picker and added some failure condition if input[0] is empty. I think PickCompaction() should not return compaction with zero input files with this change. I'm not confident enough to add an assertion though :)
Test Plan: make check
Reviewers: dhruba, haobo, sdong, kailiu
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16005
Summary:
This is a 500ns operation while the whole Get() call takes only a few
micro!
Test Plan: ran db_bench, for a DB with 50M keys, QPS jumps from 5.2M/s to 7.2M/s
Reviewers: haobo, igor, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D17007
Summary: Add a property to calculate number of background errors encountered to help users build their monitoring
Test Plan: Add a unit test. make all check
Reviewers: haobo, igor, dhruba
Reviewed By: igor
CC: ljin, nkg-, yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D16959
Summary: To partly address the request @nkg- raised, add three easy-to-add properties to compactions and flushes.
Test Plan: run unit tests and add a new unit test to cover new properties.
Reviewers: haobo, dhruba
Reviewed By: dhruba
CC: nkg-, leveldb
Differential Revision: https://reviews.facebook.net/D13677
Summary:
Finalize re-sorts (read: mutates) the files_ in Version* and it is called by CompactionPicker during normal runtime. At the same time, this same Version* lives in the SuperVersion* and is accessed without the mutex in GetImpl() code path.
Mutating the files_ in one thread and reading the same files_ in another thread is a bad idea. It caused this issue: http://ci-builds.fb.com/job/rocksdb_crashtest/285/console
Long-term, we need to be more careful with method contracts and clearly document what state can be mutated when. Now that we are much faster because we don't lock in GetImpl(), we keep running into data races that were not a problem before when we were slower. db_stress has been very helpful in detecting those.
Short-term, I removed Finalize() from CompactionPicker.
Note: I believe this is an issue in current 2.7 version running in production.
Test Plan:
make check
Will also run db_stress to see if issue is gone
Reviewers: sdong, ljin, dhruba, haobo
Reviewed By: sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16983
Summary:
There is a chance that an old MANIFEST is corrupted in 2.7 but just not noticed.
This check would fail them. Change it to log instead of returning a
Corruption status.
Test Plan: make
Reviewers: haobo, igor
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16923
Summary:
Based on my recent findings (posted in our internal group), if we use fallocate without KEEP_SIZE flag, we get superior performance of fdatasync() in append-only workloads.
This diff provides an option for user to not use KEEP_SIZE flag, thus optimizing his sync performance by up to 2x-3x.
At one point we also just called posix_fallocate instead of fallocate, which isn't very fast: http://code.woboq.org/userspace/glibc/sysdeps/posix/posix_fallocate.c.html (tl;dr it manually writes out zero bytes to allocate storage). This diff also fixes that, by first calling fallocate and then posix_fallocate if fallocate is not supported.
Test Plan: make check
Reviewers: dhruba, sdong, haobo, ljin
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16761
Summary:
When the manifest is getting rolled the following happens:
1) manifest_file_number_ is assigned to a new manifest number (even though the old one is still current)
2) mutex is unlocked
3) SetCurrentFile() creates temporary file manifest_file_number_.dbtmp
4) SetCurrentFile() renames manifest_file_number_.dbtmp to CURRENT
5) mutex is locked
If FindObsoleteFiles happens between (3) and (4) it will:
1) Delete manifest_file_number_.dbtmp (because it's not in pending_outputs_)
2) Delete old manifest (because the manifest_file_number_ already points to a new one)
I introduce the concept of prev_manifest_file_number_ that will avoid the race condition.
However, we should discuss the future of MANIFEST file rolling. We found some race conditions with it last week and who knows how many more are there. Nobody is using it in production because we don't trust the implementation. Should we even support it?
Test Plan: make check
Reviewers: ljin, dhruba, haobo, sdong
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16929
Summary:
Memtable will now be forced to flush if the one of the following
conditions is met:
1. Already allocated more than write_buffer_size + 60% arena block size.
(the overflowing condition)
2. Unable to safely allocate one more arena block without hitting the
overflowing condition AND the unused allocated memory < 25% arena
block size.
Test Plan: make all check
Reviewers: sdong, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16893
Summary: Prev() now can hang when there is a key with more than max_skipped number of appearance internally but all of them are newer than the sequence ID to seek. Add unit tests to confirm the bug and fix it.
Test Plan: make all check
Reviewers: igor, haobo
Reviewed By: igor
CC: ljin, yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D16899
Summary:
In the last fix, I forgot to point to the writer when comparing edit,
which is apparently not correct.
Test Plan: still running make whitebox_crash_test
Reviewers: igor, haobo, igor2
Reviewed By: igor2
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16911
Summary:
Here is what it can cause probelm:
There is one memtable flush and one compaction. Both call LogAndApply(). If both edits are applied in the same batch with flush edit first and the compaction edit followed. LogAndApplyHelper() will assign compaction edit current VersionSet's log number(which should be smaller than the log number from flush edit). It cause log_numbers in MANIFEST to be not monotonic increasing, which violates the assume Recover() makes. What is more is after comitting to MANIFEST file, log_number_ in VersionSet is updated to the log_number from the last edit, which is the compaction one. It ends up not updating the log_number.
Test Plan:
make whitebox_crash_test
got another assertion about iter->valid(), not sure if that is related
to this.
Reviewers: igor, haobo
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16875
Summary: Client doesn't need to know anything about ColumnFamily ID. By making WriteBatch take ColumnFamilyHandle as a parameter, we can eliminate method GetID() from ColumnFamilyHandle
Test Plan: column_family_test
Reviewers: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16887
Summary:
Original Summary:
Yesterday, @ljin and I were debugging various db_stress issues. We suspected one of them happens when we concurrently call NewIterator without prefix_seek on HashSkipList. This test demonstrates it.
Update:
Arena is not thread-safe!! When creating a new full iterator, we *have* to create a new arena, otherwise we're doomed.
Test Plan: SIGSEGV and assertion-throwing test now works!
Reviewers: ljin, haobo, sdong
Reviewed By: sdong
CC: leveldb, ljin
Differential Revision: https://reviews.facebook.net/D16857
Summary:
With D16767, there is a case compaction tasks are scheduled infinitely:
(1) no flush thread is configured and more than 1 compaction threads
(2) a flush is going on by one compaction hread
(3) the state of SST files is in the state that versions_->current()->NeedsCompaction() will generate a false positive (return true actually there is no work to be done)
In that case, a infinite loop will be formed.
This patch would fix it.
Test Plan: make all check
Reviewers: haobo, igor, ljin
Reviewed By: igor
CC: dhruba, yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D16863
Summary:
This is is based on https://reviews.facebook.net/D15027. It's not finished but I would like to give a prototype to avoid arena over-allocation while making better use of the already allocated memory blocks.
Instead of check approximate memtable size, we will take a deeper look at the arena, which incorporate essential idea that @sdong suggests: flush when arena has allocated its last and the last is "almost full"
Test Plan: N/A
Reviewers: haobo, sdong
Reviewed By: sdong
CC: leveldb, sdong
Differential Revision: https://reviews.facebook.net/D15051
Summary:
I'm cleaning up some code preparing for the big diff review tomorrow. This is the first part of the cleanup.
Changes are mostly cosmetic. The goal is to decrease amount of code difference between columnfamilies and master branch.
This diff also fixes race condition when dropping column family.
Test Plan: Ran db_stress with variety of parameters
Reviewers: dhruba, haobo
Differential Revision: https://reviews.facebook.net/D16833
Summary: A bad Auto-Merge caused log buffer is flushed twice. Remove the unintended one.
Test Plan: Should already be tested (the code looks the same as when I ran unit tests).
Reviewers: haobo, igor
Reviewed By: haobo
CC: ljin, yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D16821
Summary:
@igor pointed out that there is a potential data race because of the way we use the newly introduced LogBuffer. After "bg_compaction_scheduled_--" or "bg_flush_scheduled_--", they can both become 0. As soon as the lock is released after that, DBImpl's deconstructor can go ahead and deconstruct all the states inside DB, including the info_log object hold in a shared pointer of the options object it keeps. At that point it is not safe anymore to continue using the info logger to write the delayed logs.
With the patch, lock is released temporarily for log buffer to be flushed before "bg_compaction_scheduled_--" or "bg_flush_scheduled_--". In order to make sure we don't miss any pending flush or compaction, a new flag bg_schedule_needed_ is added, which is set to be true if there is a pending flush or compaction but not scheduled because of the max thread limit. If the flag is set to be true, the scheduling function will be called before compaction or flush thread finishes.
Thanks @igor for this finding!
Test Plan: make all check
Reviewers: haobo, igor
Reviewed By: haobo
CC: dhruba, ljin, yhchiang, igor, leveldb
Differential Revision: https://reviews.facebook.net/D16767
Summary:
I had this diff for a while to test column families implementation. Last night, I ran it sucessfully for 10 hours with the command:
time ./db_stress --threads=30 --ops_per_thread=200000000 --max_key=5000 --column_families=20 --clear_column_family_one_in=3000000 --verify_before_write=1 --reopen=50 --max_background_compactions=10 --max_background_flushes=10 --db=/tmp/db_stress
It is ready to be committed :)
Test Plan: Ran it for 10 hours
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16797
Summary: To temp fix the log buffer flushing. Flush the buffer inside the lock. Clean the trunk before we find an eventual fix.
Test Plan: make all check
Reviewers: haobo, igor
Reviewed By: igor
CC: ljin, leveldb, yhchiang
Differential Revision: https://reviews.facebook.net/D16791
Summary: Having code after SignalAll has already caused 2 bugs. Let's make sure this doesn't happen again.
Test Plan: no test
Reviewers: sdong, dhruba, haobo
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16785
Summary: Column family should be dropped after the change has been commited
Test Plan: db stress
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16779
Summary: as title. also made info log output of file deletion a bit more descriptive.
Test Plan: make check; db_bench and look at LOG output
Reviewers: igor
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16731
Summary:
(1) Fix SanitizeOptions() to also check HashLinkList. The current
dynamic case just happens to work because the 2 classes have the same
layout.
(2) Do not delete SliceTransform object in HashSkipListFactory and
HashLinkListFactory destructor. Reason: SanitizeOptions() enforces
prefix_extractor and SliceTransform to be the same object when
Hash**Factory is used. This makes the behavior strange: when
Hash**Factory is used, prefix_extractor will be released by RocksDB. If
other memtable factory is used, prefix_extractor should be released by
user.
Test Plan: db_bench && make asan_check
Reviewers: haobo, igor, sdong
Reviewed By: igor
CC: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D16587
Summary: KSVObsolete is no longer nullptr and needs to be checked explicitly. Also did some minor code cleanup and added a stat counter to track superversion cleanups incurred in the foreground.
Test Plan: make check
Reviewers: ljin
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16701
Summary: Moved LogBuffer class to an internal header. Removed some unneccesary indirection. Enabled log buffer for BackgroundCallFlush. Forced log buffer flush right after Unlock to improve time ordering of info log.
Test Plan: make check; db_bench compare LOG output
Reviewers: sdong
Reviewed By: sdong
CC: leveldb, igor
Differential Revision: https://reviews.facebook.net/D16707
Summary:
If verify_checksums_in_compaction is true, compaction will verify checksums. This is default.
If it's false, compaction doesn't verify checksums. This is useful for in-memory workloads.
Test Plan: corruption_test
Reviewers: dhruba
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16695
Summary: Adding the last missing function -- NewIterators(). Pretty simple implementation
Test Plan: added a unit test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16689
Summary:
Add a check at the end of GetImpl to release SuperVersion if it becomes
obsolete. Also do Scrape() inside InstallSuperVersion so it happens more
frequent.
Test Plan:
make all check
running asan_check now
Reviewers: igor, haobo, sdong, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16641
Summary: Now while the background thread is picking compactions, it writes out multiple info_logs, especially for universal compaction, which introduces a chance of waiting log writing in mutex, which is bad. To remove this risk, write all those info logs to a buffer and flush it after releasing the mutex.
Test Plan:
make all check
check the log lines while running some tests that trigger compactions.
Reviewers: haobo, igor, dhruba
Reviewed By: dhruba
CC: i.am.jin.lei, dhruba, yhchiang, leveldb, nkg-
Differential Revision: https://reviews.facebook.net/D16515
Summary:
Column family IDs should be unique, even if column family is dropped. To achieve this, we save max column family in manifest.
Note that the diff is still not ready. I'm only using differential to move the patch to my Mac machine.
Test Plan: added a test to column_family_test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16581
Summary:
Add helper function to print perf context data in db_bench if enabled.
I didn't find any code that actually exports perf context data. Not sure
if I missed anything
Test Plan: ran db_bench
Reviewers: haobo, sdong, igor
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16575
Summary:
For HashSkipList case, DBImpl has sanity check to see if prefix_extractor in
options is the same as the one in memtable factory. If not, it falls
back to SkipList. As result, I was experimenting with SkipList
performance. No wonder it is much worse than LinkedList
Test Plan: ran benchmark
Reviewers: haobo, sdong, igor
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16569
Summary: as title
Test Plan: make release
Reviewers: haobo, sdong, igor
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16437
Summary: I wrote a test that triggers assertion in MergingIterator. I have not touched that code ever, so I'm looking for somebody with good understanding of the MergingIterator code to fix this. The solution is probably a one-liner. Let me know if you're willing to take a look.
Test Plan: This test fails with an assertion `use_heap_ == false`
Reviewers: dhruba, haobo, sdong, kailiu
Reviewed By: sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16521
Summary:
Two changes:
1. DeletionState is only constructed when cleaning up is needed
2. Fix the bug of deletion state construction bug. A change was made in a previous patch: https://reviews.facebook.net/rROCKSDB774ed89c2405ee058086b099cbc8b29e243739cc#71a34e2e However, it somehow got lost when merging
Test Plan: make all check
Reviewers: kailiu, haobo, igor
Reviewed By: igor
CC: igor, dhruba, i.am.jin.lei, yhchiang, leveldb
Differential Revision: https://reviews.facebook.net/D16233
Summary: When column family is dropped, we want to delete all WALs that refer to it. To do that, we need to make them obsolete by flushing all the memtables
Test Plan: column_family_test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16557
Summary:
The issue is that when FLAGS_num is small, the leading bytes of the key
are padded with 0s. This makes all keys have the same prefix 00000000
Most of the changes are just to make lint happy
Test Plan: ran db_bench
Reviewers: sdong, haobo, igor
Reviewed By: sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16317
Summary: Added a function DeleteSuperVersion that can be called in DBImpl destructor before PurgingObsoleteFiles. That way, PurgeObsoleteFiles will be able to delete all files held by alive super versions.
Test Plan: column_family_test with valgrind
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16545
Summary:
this is the key component extracted from diff: https://reviews.facebook.net/D14271
I separate it to a dedicated patch to make the review easier.
Test Plan: added a unit test and passed it.
Reviewers: haobo, sdong, dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16245
Summary:
EncodeTo(&record) does not overwrite, it appends to it.
This means that group commit log and apply will look something like:
record1
record1record2
record1record2record3
I'm surprised this didn't show up in production, but I think the reason is that MANIFEST group commit almost never happens.
This bug turned up in column family work, where opening a database failed with "adding a same column family twice".
Test Plan: Tested the change in column family branch and observed that the problem is gone (with db_stress)
Reviewers: dhruba, haobo
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16461
Summary:
This diff fixes two bugs:
* Increase sequence number even if WriteBatch fails. This is important because WriteBatches in WAL logs have implictly increasing sequence number, even if one update in a write batch fails. This caused some writes to get lost in my CF stress testing
* Tolerate 'invalid column family' errors on recovery. When a column family is dropped, processing WAL logs can have some WriteBatches that still refer to the dropped column family. In recovery environment, we want to ignore those errors. In client's Write() code path, however, we want to return the failure to the client if he's trying to add data to invalid column family.
Test Plan: db_stress's verification works now
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16533
Summary:
Previous code is too convoluted and I must be drunk for letting
such code to be written without a second thought.
Thanks to the discussion with @sdong, I added the `Options` when
generating the flusher, thus avoiding the tricks.
Just FYI: I resisted to add Options in flush_block_policy.h since I
wanted to avoid cyclic dependencies: FlushBlockPolicy dpends on Options
and Options also depends FlushBlockPolicy... While I appreciate my
effort to prevent it, the old design turns out creating more troubles than
it tried to avoid.
Test Plan: ran ./table_test
Reviewers: sdong
Reviewed By: sdong
CC: sdong, leveldb
Differential Revision: https://reviews.facebook.net/D16503
Summary:
I though I might get away with as little changes to LogAndApply() as possible. It turns out this is not the case.
This diff introduces different behavior of LogAndApply() for three cases:
1. column family add
2. column family drop
3. no-column family manipulation
(1) and (2) don't support group commit yet.
There were a lot of problems with old version od LogAndApply, detected by db_stress. The biggest was non-atomicity of manifest writes and metadata changes (i.e. if column family add is in manifest, it also has to be in in-memory data structure).
Test Plan: db_stress
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16491
Summary:
This diff does two things:
(1) Log::Reader does not report a corruption when the last record in a log or manifest file is truncated (meaning that log writer died in the middle of the write). Inherited the code from LevelDB: https://code.google.com/p/leveldb/source/detail?r=269fc6ca9416129248db5ca57050cd5d39d177c8#
(2) Turn off mmap writes for all writes to log and manifest files
(2) is necessary because if we use mmap writes, the last record is not truncated, but is actually filled with zeros, making checksum fail. It is hard to recover from checksum failing.
Test Plan:
Added unit tests from LevelDB
Actually recovered a "corrupted" MANIFEST file.
Reviewers: dhruba, haobo
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16119
Summary:
Add an optional input parameter ReadOptions to DB::GetUpdateSince(),
which allows the verification of checksums to be disabled by setting
ReadOptions::verify_checksums to false.
Test Plan: Tests are done off-line and will not be included in the regular unit test.
Reviewers: igor
Reviewed By: igor
CC: leveldb, xjin, dhruba
Differential Revision: https://reviews.facebook.net/D16305
Summary:
This fixes few bugs with CreateColumnFamily
* We first have to LogAndApply and then call VersionSet::CreateColumnFamily. Otherwise, WriteSnapshot might be invoked, writing out column family add inside of LogAndApply, even though it's not really committed
* Fix LogAndApplyHelper() to not apply log number to column_family_data, which is in case of column family add, just a dummy (default) column family
* Create SuperVerion when creating column family
Test Plan: column_family_test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16443
Summary:
Previously, we first wrote to the manifest and then created internal data structure.
Now, we first create internal data structure. That way, we can write out internal comparator to the manifest
Test Plan: column_family_test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16425
Summary: Added list_column_family command and also updated dump_manifest
Test Plan: no
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16419
Summary: as title
Test Plan:
asan_check
will post results later
Reviewers: haobo, igor, dhruba, sdong
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16257
Summary: If we sleep for 300ms the test fails in valgrind because it takes more than 300ms to flush. This way we WaitForFlush() when we're expecting flush, but still sleep and check if the flush happens even though it's not supposed to.
Test Plan: notest
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16401
Summary:
Two new column family tests:
* DifferentMergeOperators -- three column families, one without merge operator, one with add operator and one with append operator. verify that operations work as expected.
* DifferentCompactionStyles -- three column families, two with level compactions and one with universal compaction. trigger the compactions and verify they work as expected.
Test Plan: nope
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16377
Summary: Retry GetSortedWalFiles() and also wait 20ms before counting number of log files. WaitForFlush() doesn't necessarily wait for logs to be deleted, since logs are deleted outside of the mutex.
Test Plan: column_family_test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16371
Summary: New unit tests for column families
Test Plan: this is a test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16359
Summary: Big CF diff uncovered some lint errors. This diff fixes some of them. Not much to see here
Test Plan: make check
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16347
Summary:
* Add ColumnFamilyHandle::GetID() function. Client needs to know column family's ID to be able to construct WriteBatch
* Handle WriteBatch::Handler failure gracefully. Since WriteBatch is not a very smart function (it takes raw CF id), client can add data to WriteBatch for column family that doesn't exist. In that case, we need to gracefully return failure status from DB::Write(). To do that, I added a return Status to WriteBatch functions PutCF, DeleteCF and MergeCF.
Test Plan: Added test to column_family_test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16323
Summary:
* Added unit test that verifies that obsolete files are deleted.
* Advance log number for empty column family when cutting log file.
* MinLogNumber() bug fix! (caught by the new unit test)
Test Plan: unit test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16311
Summary: Even if user flushes the memtables before getting live files, we still can't guarantee that new data didn't come in (to already-flushed memtables). If we want backups to provide consistent view of the database, we still need to get WAL files.
Test Plan: backupable_db_test
Reviewers: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16299
Summary:
This will also help with avoiding the deadlock. If a flush failed and we're waiting for a memtable to be flushed, we should schedule a new flush and hope a new one succeedes.
If paranoid_checks = false, Wait() will still hang on ENOSPC, but at least it will automatically continue when the space frees up. Current behavior both hangs and deadlocks.
Also, I renamed some 'compaction' to 'flush'. 'compaction' was leveldb way of saying things.
Test Plan: make check
Reviewers: dhruba, haobo, ljin
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16281
Summary: as title
Test Plan: ran db_bench
Reviewers: dhruba, haobo
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16269
Summary: DBImpl now keeps a list of alive_log_files_. On every FindObsoleteFiles, it deletes all alive log files that are smaller than versions_->MinLogNumber()
Test Plan:
make check passes
no specific unit tests yet, will add
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16293
Summary:
More info here: https://github.com/facebook/rocksdb/issues/89
If flush fails because of ENOSPC, we have a deadlock problem. This is a quick fix that will continue the normal operation when user deletes the file and frees up the space on the device.
We need to address the issue more broadly with bg_error_ cleanup.
Test Plan: make check
Reviewers: dhruba, haobo, ljin
Reviewed By: ljin
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16275
Summary:
Add a test to verify HashLinkList and HashSkipList (mainly for the former one) returns the correct results when inserting the same bucket in the different orders.
Some other changes:
(1) add the test to test list
(2) fix compile error
(3) add header
Test Plan: ./prefix_test
Reviewers: haobo, kailiu
Reviewed By: haobo
CC: igor, yhchiang, i.am.jin.lei, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D16143
Summary: This bug caused server crash issues because the filter block is too big and kept purging out of cache.
Test Plan: Wrote a new unit tests to make sure it works.
Reviewers: dhruba, haobo, igor, sdong
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16221
Summary: Currently, the first transaction log file ignore bytes_per_sync and other storage-related options. It is not consistent. Fix it.
Test Plan: make all check. See the options set in GDB.
Reviewers: haobo, kailiu
Reviewed By: haobo
CC: igor, ljin, yhchiang, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D16215
Summary: Adapt table properties to column family world
Test Plan: make check
Reviewers: kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16161
Summary:
This is a huge diff and it was hectic, but the idea is actually quite simple. Every operation (Put, Get, etc.) done on default column family in DBTest is now forwarded to non-default ("pikachu"). The good news is that we had zero test failures! Column families look stable so far.
One interesting test that I adapted for column families is MultiThreadedTest. I replaced every Put() with a WriteBatch writing to all column families concurrently. Every Put in the write batch contains unique_id. Instead of Get() I do a multiget across all column families with the same key. If atomicity holds, I expect to see the same unique_id in all column families.
Test Plan: This is a test!
Reviewers: dhruba, haobo, kailiu, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16149
Summary: Provide a public API for users to access the table properties for each SSTable.
Test Plan: Added a unit tests to test the function correctness under differnet conditions.
Reviewers: haobo, dhruba, sdong
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16083
Summary:
1. Add some more implementation-aware tests for PlainTable
2. move from a hard-coded one index per 16 rows in one prefix to a configurable number. Also, make hash table ratio = 0 means binary search only. Also fixes some divide 0 risks.
3. Explicitly support total order (only use binary search)
4. some code cleaning up.
Test Plan: make all check
Reviewers: haobo, kailiu
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16023
Summary:
The change to the public behavior:
* When opening a DB or creating new column family client gets a ColumnFamilyHandle.
* As long as column family handle is alive, client can do whatever he wants with it, even drop it
* Dropped column family can still be read from (using the column family handle)
* Added a new call CloseColumnFamily(). Client has to close all column families that he has opened before deleting the DB
* As soon as column family is closed, any calls to DB using that column family handle will fail (also any outstanding calls)
Internally:
* Ref-counting ColumnFamilyData
* New thread-safety for ColumnFamilySet
* Dropped column families are now completely dropped and their memory cleaned-up
Test Plan: added some tests to column_family_test
Reviewers: dhruba, haobo, kailiu, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16101
Summary: Added a bit more information to compaction context, requested by internal team at FB.
Test Plan: Modified CompactionFilter test to make sure is_manual_compaction is properly set.
Reviewers: haobo
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16095
Summary: Clean up IOErrors so that it only indicates errors talking to device.
Test Plan: make all check
Reviewers: igor, haobo, dhruba, emayanke
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15831
Summary: This covers existing table files before DB open happens and avoids contention on table cache
Test Plan: db_test
Reviewers: haobo, sdong, igor, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16089
Summary: as title
Test Plan: ran db_bench to gather stats
Reviewers: haobo, sdong
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16059
Summary:
This patch optimized Get() code paths by avoiding malloc of iterators. Iterator creation is moved to mem table rep implementations, where a callback is called when any key is found. This is the same practice as what we do in (SST) table readers.
db_bench result for readrandom following a writeseq, with no compression, single thread and tmpfs, we see throughput improved to 144958 from 139027, about 3%.
Test Plan: make all check
Reviewers: dhruba, haobo, igor
Reviewed By: haobo
CC: leveldb, yhchiang
Differential Revision: https://reviews.facebook.net/D14685
Summary:
We are going to expose properties of all tables to end users through "some" db interface.
However, current design doesn't naturally fit for this need, which is because:
1. If a table presents in table cache, we cannot simply return the reference to its table properties, because the table may be destroy after compaction (and we don't want to hold the ref of the version).
2. Copy table properties is OK, but it's slow.
Thus in this diff, I change the table reader's interface to return a shared pointer (for const table properties), instead a const refernce.
Test Plan: `make check` passed
Reviewers: haobo, sdong, dhruba
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15999
Summary: By discussion with @dhruba, overloading Open makes more sense
Test Plan: compiles!
Reviewers: dhruba
CC: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D16017
Summary: When we open a DB, we should dump only DBOptions and then when we create a new column family, we dump ColumnFamilyOptions for each one.
Test Plan: make check, confirm contents of the LOG
Reviewers: dhruba, haobo, sdong, kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D16011
Summary:
Added an option for readrandom benchmark to run with tailing iterator instead of Get. Benefit of tailing iterator is that it doesn't require locking DB mutex on access.
I also have some results when running on my machine. The results highly depend on number of cache shards. With our current benchmark setting of 4 table cache shards and 6 block cache shards, I don't see much improvements of using tailing iterator. In that case, we're probably seeing cache mutex contention.
Here are the results for different number of shards
cache shards tailing iterator get
6 1.38M 1.16M
10 1.58M 1.15M
As soon as we get rid of cache mutex contention, we're seeing big improvements in using tailing iterator vs. ordinary get.
Test Plan: ran regression test
Reviewers: dhruba, haobo, ljin, kailiu, sding
Reviewed By: haobo
CC: tnovak
Differential Revision: https://reviews.facebook.net/D15867
Summary:
This is not column-family related diff. It is in columnfamily branch because the change is significant and we want to push it with next major release (3.0).
It removes the leveldb notion of one thread pool and expands it to two thread pools by default (HIGH and LOW). Flush process is removed from compaction process and all flush threads are executed on HIGH thread pool, since we don't want long-running compactions to influence flush latency.
Test Plan: make check
Reviewers: dhruba, haobo, kailiu, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15987
Summary: Revised thread-safety guarantees and implemented a way to spinlock the object.
Test Plan: make check
Reviewers: dhruba, haobo, sdong, kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15975
Summary:
WriteBatch can have multiple column families in one batch. Every column family has different options. So we have to add a way for write batch to get options for an arbitrary column family.
This required a bit more acrobatics since lots of interfaces had to be changed.
Test Plan: make check
Reviewers: dhruba, haobo, sdong, kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15957
Summary: Replaced most of occurrences of Options with more specific DBOptions. This brings us very close to supporting different configuration options for each column family.
Test Plan: make check
Reviewers: dhruba, haobo, kailiu, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15933
Summary:
Lots of code expects Options on construction/function call. My original idea was to split Options argument into ColumnFamilyOptions and DBOptions (the latter only if needed). However, this will require huge code changes very deep in the stack.
The better idea is to have ColumnFamilyData hold both ColumnFamilyOptions and Options. ColumnFamilyData::Options would be constructed from DBOptions (same for each column family) and ColumnFamilyOptions (different for each column family)
Now when we construct a class or call any method that requires Options, we can just push him ColumnFamilyData::Options and be sure that it's using column-family-specific settings.
Test Plan: make check
Reviewers: dhruba, haobo, kailiu, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15927
Summary:
Adapting table cache to column families is interesting. We want table cache to be global LRU, so if some column families are use not as often as others, we want them to be evicted from cache. However, current TableCache object also constructs tables on its own. If table is not found in the cache, TableCache automatically creates new table. We want each column family to be able to specify different table factory.
To solve the problem, we still have a single LRU, but we provide the LRUCache object to TableCache on construction. We have one TableCache per column family, but the underyling cache is shared by all TableCache objects.
This allows us to have a global LRU, but still be able to support different table factories for different column families. Also, in the future it will also be able to support different directories for different column families.
Test Plan: make check
Reviewers: dhruba, haobo, kailiu, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15915
Summary: InternalStats is a messy thing, keeping both DB data and column family data. However, it's better off living in ColumnFamilyData than in DBImpl. For now, at least.
Test Plan: make check
Reviewers: dhruba, kailiu, haobo, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15879
Summary:
There are three SanitizeOption-s now : one for DBOptions, one for ColumnFamilyOptions and one for Options (which just calls the other two)
I have also reshuffled some options -- table_cache options and info_log should live in DBOptions, for example.
Test Plan: make check doesn't complain
Reviewers: dhruba, haobo, kailiu, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15873
Summary:
Previous I am too ambitious to hide every detail about table factory
to internal api. However, we cannot pass the compilatoin for external
users since we use table factory as the shared_ptr, which requires
the definition of table factory's destructor.
Test Plan: make check;
Reviewers: sdong, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15861
Summary: user_comparator() is a Column Family property, not DBImpl
Test Plan: make check
Reviewers: dhruba, haobo, kailiu, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15855
Summary: Support for different column families in Iterator and MultiGet code path.
Test Plan: make check
Reviewers: dhruba, haobo, kailiu, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15849
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
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
Summary: In PlainTable, use one single byte to represent 8 bytes of internal bytes, if seqID = 0 and it is value type (which should be common for bottom most files). It is to save 7 bytes for uncompressed cases.
Test Plan: make all check
Reviewers: haobo, dhruba, kailiu
Reviewed By: haobo
CC: igor, leveldb
Differential Revision: https://reviews.facebook.net/D15489
Summary: This diff enables non-default column families to get compacted both automatically and also by calling CompactRange()
Test Plan: make check
Reviewers: dhruba, haobo, kailiu, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15813
Summary: Compaction picker and internal key comparator are different for each column family (not global), so they should live in ColumnFamilyData
Test Plan: make check
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15801
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
Summary: Removed default_cfd_ from all flush code paths. This means we can now flush memtables from arbitrary column families!
Test Plan: Added a new unit test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15789
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
Summary:
Easy thing goes first. This patch moves arena to internal dir; based
on which, the coming patch will deal with memtable_rep.
Test Plan: make check
Reviewers: haobo, sdong, dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15615
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
Summary:
Sometimes we iterate through column families, and unlock the mutex in the body of the iteration. While mutex is unlocked, some column family might be created or dropped. We need to be able to continue iterating through column families even though our current column family got dropped.
This diff implements circular linked lists that connect all column families. It then uses the link list to enable iterating through linked lists. Even if the column family is dropped, its next_ pointer still can be used to advance to another alive column family.
Test Plan: make check
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15603
Summary: Making room for write will be the hardest part of the column family implementation. For now, I just iterate through all column families and run MakeRoomForWrite() for every one.
Test Plan: make check does not complain
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15597
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
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
Summary: ColumnFamilyData grew a lot, there's much more data that it holds now. It makes more sense to encapsulate it better by making it a class.
Test Plan: make check
Reviewers: dhruba, haobo, kailiu, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15579
Summary: When we drop the column family, we want to delete all the files from that column family.
Test Plan: make check
Reviewers: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15561
Summary: This one is big. It adds ability to write to and read from different column families (see the unit test). It also supports recovery of different column families from log, which was the hardest part to reason about. We need to make sure to never delete the log file which has unflushed data from any column family. To support that, I added another concept, which is versions_->MinLogNumber()
Test Plan: Added a unit test in column_family_test
Reviewers: dhruba, haobo, sdong, kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15537
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
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
Summary: This removes the default implementation of LogAndApply that applied the changed to the default column family by default. It is mostly simple reformatting.
Test Plan: make check
Reviewers: dhruba, kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15465
Summary: All memtables and immutable memtables are moved from DBImpl to ColumnFamilyData. For now, they are all referenced from default column family in DBImpl. It shouldn't be hard to get them from custom column family.
Test Plan: make check
Reviewers: dhruba, kailiu, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15459
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
Summary: Converting from length prefixed buffer back to internal key costs some CPU but it is not necessary. In this patch, internal keys are pass though the functions so that we don't need to convert back to it.
Test Plan: make all check
Reviewers: haobo, kailiu
Reviewed By: kailiu
CC: igor, leveldb
Differential Revision: https://reviews.facebook.net/D15393
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
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.
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
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
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
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
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
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
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
Summary:
This diff implements a special type of iterator that doesn't create a snapshot
(can be used to read newly inserted data) and is optimized for doing sequential
reads.
TailingIterator uses current superversion number to determine whether to
invalidate its internal iterators. If the version hasn't changed, it can often
avoid doing expensive seeks over immutable structures (sst files and immutable
memtables).
Test Plan:
* new unit tests
* running LD with this patch
Reviewers: igor, dhruba, haobo, sdong, kailiu
Reviewed By: sdong
CC: leveldb, lovro, march
Differential Revision: https://reviews.facebook.net/D15285
Summary:
I created a separate class ColumnFamilySet to keep track of column families. Before we did this in VersionSet and I believe this approach is cleaner.
Let me know if you have any comments. I will commit tomorrow.
Test Plan: make check
Reviewers: dhruba, haobo, kailiu, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15357
Summary:
In this diff I made some effort to reduce usage of friending. To do that, I had to expose Compaction::inputs_ through a method inputs(). Not sure if this is a good idea, there is a trade-off. I think it's less confusing than having lots of friends.
I also thought about other friendship relationships, but they are too much tangled at this point. Once you friend two classes, it's very hard to unfriend them :)
Test Plan: make check
Reviewers: haobo, kailiu, sdong, dhruba
Reviewed By: kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15267
Summary:
This diff does two things:
* Rethinks how we call Recover() with read_only option. Before, we call it with pointer to memtable where we'd like to apply those changes to. This memtable is set in db_impl_readonly.cc and it's actually DBImpl::mem_. Why don't we just apply updates to mem_ right away? It seems more intuitive.
* Changes when we apply updates to manifest. Before, the process is to recover all the logs, flush it to sst files and then do one giant commit that atomically adds all recovered sst files and sets the next log number. This works good enough, but causes some small troubles for my column family approach, since I can't have one VersionEdit apply to more than single column family[1]. The change here is to commit the files recovered from logs right away. Here is the state of the world before the change:
1. Recover log 5, add new sst files to edit
2. Recover log 7, add new sst files to edit
3. Recover log 8, add new sst files to edit
4. Commit all added sst files to manifest and mark log files 5, 7 and 8 as recoverd (via SetLogNumber(9) function)
After the change, we'll do:
1. Recover log 5, commit the new sst files and set log 5 as recovered
2. Recover log 7, commit the new sst files and set log 7 as recovered
3. Recover log 8, commit the new sst files and set log 8 as recovered
The added (small) benefit is that if we fail after (2), the new recovery will only have to recover log 8. In previous case, we'll have to restart the recovery from the beginning. The bigger benefit will be to enable easier integration of multiple column families in Recovery code path.
[1] I'm happy to dicuss this decison, but I believe this is the cleanest way to go. It also makes backward compatibility much easier. We don't have a requirement of adding multiple column families atomically.
Test Plan: make check
Reviewers: dhruba, haobo, kailiu, sdong
Reviewed By: kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15237
Summary: Commit "1304d8c8cefe66be1a3caa5e93413211ba2486f2" (Merge branch 'master' into performance) removes a line in performance branch by mistake. This patch fixes it.
Test Plan: make all check
Reviewers: haobo, kailiu, igor
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15297
Summary:
This moves the use of versions_ to before the mutex is unlocked
to avoid a possible race.
Task ID: #
Blame Rev:
Test Plan:
make check
Revert Plan:
Database Impact:
Memcache Impact:
Other Notes:
EImportant:
- begin *PUBLIC* platform impact section -
Bugzilla: #
- end platform impact -
Reviewers: haobo, dhruba
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15279
Summary: I'm separating code-cleanup part of https://reviews.facebook.net/D14517. This will make D14517 easier to understand and this diff easier to review.
Test Plan: make check
Reviewers: haobo, kailiu, sdong, dhruba, tnovak
Reviewed By: tnovak
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15099
Summary:
The SIGSEGV was introduced by https://reviews.facebook.net/D15171
I also fixed ExpandWhileOverlapping() which returned the failure by setting it's own stack variable to nullptr (!). This bug is present in 2.6 release, so I guess ExpandWhileOverlapping never fails :)
Test Plan: `make check`. Also MarkCallaghan confirmed it fixed the SIGSEGV he reported.
Reviewers: MarkCallaghan, kailiu, sdong, dhruba, haobo
Reviewed By: kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15261
Summary:
This had a few bugs.
1) bottom and top were reversed. top is for the max value but the callers were passing the max
value to bottom. The result is that the max sleep is used when n >= bottom.
2) one of the callers passed values with type double and these values are frequently between
1.0 and 2.0 so rounding will do some bad things
3) sometimes the function returned 0 when there should be a stall
With this change and one other diff (out for review soon) there are slightly fewer stalls on one workload.
With the fix.
Stalls(secs): 160.166 level0_slowdown, 0.000 level0_numfiles, 0.000 memtable_compaction, 58.495 leveln_slowdown
Stalls(count): 910261 level0_slowdown, 0 level0_numfiles, 0 memtable_compaction, 54526 leveln_slowdown
Without the fix.
Stalls(secs): 172.227 level0_slowdown, 0.000 level0_numfiles, 0.000 memtable_compaction, 56.538 leveln_slowdown
Stalls(count): 160831 level0_slowdown, 0 level0_numfiles, 0 memtable_compaction, 52845 leveln_slowdown
Task ID: #
Blame Rev:
Test Plan:
run db_bench for --benchmarks=overwrite with IO-bound database
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/D15243
Summary:
This diff fixes 2 hacks:
* The callback function can modify the existing value inplace, if the merged value fits within the existing buffer size. But currently the existing buffer size is not being modified. Now the callback recieves a int* allowing the size to be modified. Since size is encoded as a varint in the internal key for memtable. It might happen that the entire value might have be copied to the new location if the new size varint is smaller than the existing size varint.
* The callback function has 3 functionalities
1. Modify existing buffer inplace, and update size correspondingly. Now to indicate that, Returns 1.
2. Generate a new buffer indicating merged value. Returns 2.
3. Fails to do either of above, based on whatever application logic. Returns 0.
Test Plan: Just make all for now. I'm adding another unit test to test each scenario.
Reviewers: dhruba, haobo
Reviewed By: haobo
CC: leveldb, sdong, kailiu, xinyaohu, sumeet, danguo
Differential Revision: https://reviews.facebook.net/D15195
Summary: The only thing we do with compaction pointers is set them to some values, we never actually read them. I don't know what we used them for, but it doesn't look like we use them anymore.
Test Plan: make check
Reviewers: dhruba, haobo, kailiu, sdong
Reviewed By: kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15225
Summary:
This is a big one. This diff moves all the code related to picking compactions from VersionSet to new class CompactionPicker. Column families' compactions will be completely separate processes, so we need to have multiple CompactionPickers.
To make this easier to review, most of the code change is just copy/paste. There is also a small change not to use VersionSet::current_, but rather to take `Version* version` as a parameter. Most of the other code is exactly the same.
In future diffs, I will also make some improvements to CompactionPickers. I think the most important part will be encapsulating it better. Currently Version, VersionSet, Compaction and CompactionPicker are all friend classes, which makes it harder to change the implementation.
This diff depends on D15171, D15183, D15189 and D15201
Test Plan: `make check`
Reviewers: kailiu, sdong, dhruba, haobo
Reviewed By: kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15207
Summary:
shared_ptr is slower than unique_ptr (which literally comes with no performance cost compare with raw pointers).
In memtable and memtable rep, we use shared_ptr when we'd actually should use unique_ptr.
According to igor's previous work, we are likely to make quite some performance gain from this diff.
Test Plan: make check
Reviewers: dhruba, igor, sdong, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15213
Summary:
I'm sure we'll all agree that version_set.cc needs simplifying. This diff moves Compaction class to a separate file.
The diff depends on D15171 and D15183
Test Plan: make check
Reviewers: dhruba, haobo, kailiu, sdong
Reviewed By: kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15189
Summary:
There were some functions in VersionSet that had no reason to be there instead of Version. Moving them to Version will make column families implementation easier.
The functions moved are:
* NumLevelBytes
* LevelSummary
* LevelFileSummary
* MaxNextLevelOverlappingBytes
* AddLiveFiles (previously AddLiveFilesCurrentVersion())
* NeedSlowdownForNumLevel0Files
The diff continues on (and depends on) D15171
Test Plan: make check
Reviewers: dhruba, haobo, kailiu, sdong, emayanke
Reviewed By: sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15183
Summary:
With column families VersionSet will not have a constant number of levels (each CF can have different options), so we'll need to eliminate call to VersionSet::NumberLevels()
This diff decreases number of callsites, but we're not there yet. It associates number of levels with Version (each version is associated with single CF) instead of VersionSet.
I have also slightly changed how VersionSet keeps track of manifest size.
This diff also modifies constructor of Compaction such that it takes input_version and automatically Ref()s it. Before this was done outside of constructor.
In next diffs I will continue to decrease number of callsites of VersionSet::NumberLevels() and also references to current_
Test Plan: make check
Reviewers: haobo, dhruba, kailiu, sdong
Reviewed By: sdong
Differential Revision: https://reviews.facebook.net/D15171
Summary: To reduce mutex contention caused by DBImpl.NewInternalIterator(), in this function, move all the iteration creation works out of mutex, only leaving object ref and get.
Test Plan:
make all check
will run db_stress for a while too to make sure no problem.
Reviewers: haobo, dhruba, kailiu
Reviewed By: haobo
CC: igor, leveldb
Differential Revision: https://reviews.facebook.net/D14589
Conflicts:
db/db_impl.cc
Summary:
When doing CompactRange(), we should first flush the memtable and then calculate max_level_with_files. Also, we want to compact all the levels that have files, including level `max_level_with_files`.
This patch fixed the unit test.
Test Plan: Added a failing unit test and a fix, so it's not failing anymore.
Reviewers: dhruba, haobo, sdong
Reviewed By: haobo
CC: leveldb, xjin
Differential Revision: https://reviews.facebook.net/D14421
Summary:
I will submit a sequence of diffs that are preparing master branch for column families. There are a lot of implicit assumptions in the code that are making column family implementation hard. If I make the change only in column family branch, it will make merging back to master impossible.
Most of the diffs will be simple code refactorings, so I hope we can have fast turnaround time. Feel free to grab me in person to discuss any of them.
This diff removes number of level check from VersionEdit. It is used only when VersionEdit is read, not written, but has to be set when it is written. I believe it is a right thing to make VersionEdit dumb and check consistency on the caller side. This will also make it much easier to implement Column Families, since different column families can have different number of levels.
Test Plan: make check
Reviewers: dhruba, haobo, sdong, kailiu
Reviewed By: kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15159
Summary: When building batch group, don't actually build a new batch since it requires heavy-weight mem copy and malloc. Only store references to the batches and build the batch group without lock held.
Test Plan:
`make check`
I am also planning to run performance tests. The workload that will benefit from this change is readwhilewriting. I will post the results once I have them.
Reviewers: dhruba, haobo, kailiu
Reviewed By: haobo
CC: leveldb, xjin
Differential Revision: https://reviews.facebook.net/D15063
Summary: We use SanitizeOptions() to set appropriate values for some options, based on other options. So we should use the sanitized options by default. Luckily it hasn't caused a bug yet, but can result in a bug in the fugture.
Test Plan: make check
Reviewers: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14103
Summary:
In one of CPU profiles, we see some CPU costs of string::reserve() inside Batch.Put(). This patch should be able to reduce some of the costs by allocating sufficient buffer before hand.
Since it is a trivial percentage of CPU costs, I didn't find a way to show the improvement in one of the benchmarks. I'll deploy it to same application and do the same CPU profiling to make sure those CPU costs are reduced.
Test Plan: make all check
Reviewers: haobo, kailiu, igor
Reviewed By: haobo
CC: leveldb, nkg-
Differential Revision: https://reviews.facebook.net/D15135
Summary: Currently in DBImpl::MakeRoomForWrite(), we do "versions_->NumLevelFiles(0) >= options_.level0_slowdown_writes_trigger" to check whether the writer thread needs to slow down. However, versions_->NumLevelFiles(0) is slightly more expensive than we expected. By caching the result of the comparison when installing a new version, we can avoid this function call every time.
Test Plan:
make all check
Manually trigger this behavior by applying universal compaction style and make sure inserts are made slow after there are certain number of files.
Reviewers: haobo, kailiu, igor
Reviewed By: kailiu
CC: nkg-, leveldb
Differential Revision: https://reviews.facebook.net/D15141
Summary:
In one of CPU profiles, we see some CPU costs of string::reserve() inside Batch.Put(). This patch should be able to reduce some of the costs by allocating sufficient buffer before hand.
Since it is a trivial percentage of CPU costs, I didn't find a way to show the improvement in one of the benchmarks. I'll deploy it to same application and do the same CPU profiling to make sure those CPU costs are reduced.
Test Plan: make all check
Reviewers: haobo, kailiu, igor
Reviewed By: haobo
CC: leveldb, nkg-
Differential Revision: https://reviews.facebook.net/D15135
Summary: The application can set a callback function, which is applied on the previous value. And calculates the new value. This new value can be set, either inplace, if the previous value existed in memtable, and new value is smaller than previous value. Otherwise the new value is added normally.
Test Plan: fbmake. Added unit tests. All unit tests pass.
Reviewers: dhruba, haobo
Reviewed By: haobo
CC: sdong, kailiu, xinyaohu, sumeet, leveldb
Differential Revision: https://reviews.facebook.net/D14745
Summary: We don't want to delete ColumnFamilyData object if somebody has references to it.
Test Plan: `make check` for now, but will need to implement bigger column family test case
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15111
Summary:
The biggest change here is getting rid of current_ Version and adding a column_family_data->current Version to each column family.
I have also fixed some smaller things in VersionSet that made it easier to implement Column family support.
Test Plan: make check
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15105
Summary:
Added an option (max_successive_merges) that can be used to specify the
maximum number of successive merge operations on a key in the memtable.
This can be used to improve performance of the "get" operation. If many
successive merge operations are performed on a key, the performance of "get"
operations on the key deteriorates, as the value has to be computed for each
"get" operation by applying all the successive merge operations.
FB Task ID: #3428853
Test Plan:
make all check
db_bench --benchmarks=readrandommergerandom
counter_stress_test
Reviewers: haobo, vamsi, dhruba, sdong
Reviewed By: haobo
CC: zshao
Differential Revision: https://reviews.facebook.net/D14991
Summary:
In some use cases, table readers for all live files should always be cached. In that case, there will be an opportunity to avoid the table cache look-up while Get() and NewIterator().
We define options.max_open_files = -1 to be the mode that table readers for live files will always be kept. In that mode, table readers are cached in FileMetaData (with a reference count hold in table cache). So that when executing table_cache.Get() and table_cache.newInterator(), LRU cache checking can be by-passed, to reduce latency.
Test Plan: add a test case in db_test
Reviewers: haobo, kailiu
Reviewed By: haobo
CC: dhruba, igor, leveldb
Differential Revision: https://reviews.facebook.net/D15039
Summary: Full list constructed for full iterator can be leaked. This was a bug introduced when I copy the full iterator codes from hash skip list to hash link list. This patch fixes it.
Test Plan: Run valgrind test against db_test and make sure the memory leak is fixed
Reviewers: kailiu, haobo
Reviewed By: kailiu
CC: igor, leveldb
Differential Revision: https://reviews.facebook.net/D15093
Summary: Currently, even if statistics is not enabled, StopWatch only for the stats still gets the time of the day, which is wasteful. This patch adds a new option to StopWatch to disable this get in this case.
Test Plan: make all check
Reviewers: dhruba, haobo, igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14703
Conflicts:
db/db_impl.cc
Summary:
Implement a mem table, in which keys are hashed based on prefixes. In each bucket, entries are organized in a sorted linked list. It has the same thread safety guarantee as skip list.
The motivation is to optimize memory usage for the case that prefix hashing is primary way of seeking to the entry. Compared to hash skip list implementation, this implementation is more memory efficient, but inside each bucket, search is always linear. The target scenario is that there are only very limited number of records in each hash bucket.
Test Plan: Add a test case in db_test
Reviewers: haobo, kailiu, dhruba
Reviewed By: haobo
CC: igor, nkg-, leveldb
Differential Revision: https://reviews.facebook.net/D14979
Summary: Currently, even if statistics is not enabled, StopWatch only for the stats still gets the time of the day, which is wasteful. This patch adds a new option to StopWatch to disable this get in this case.
Test Plan: make all check
Reviewers: dhruba, haobo, igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14703
Summary:
I have added three new value types:
* kTypeColumnFamilyDeletion
* kTypeColumnFamilyValue
* kTypeColumnFamilyMerge
which include column family Varint32 before the data (value, deletion and merge). These values are used only in WAL (not in memtables yet).
This endeavour required changing some WriteBatch internals.
Test Plan: Added a unittest
Reviewers: dhruba, haobo, sdong, kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15045
Summary:
Code was always compressing L0 files written by a memtable flush
when compression was enabled. Now this is done when
min_level_to_compress=0 for leveled compaction and when
universal_compaction_size_percent=-1 for universal compaction.
Task ID: #3416472
Blame Rev:
Test Plan:
ran db_bench with compression options
Revert Plan:
Database Impact:
Memcache Impact:
Other Notes:
EImportant:
- begin *PUBLIC* platform impact section -
Bugzilla: #
- end platform impact -
Reviewers: dhruba, igor, sdong
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14757
Summary:
In addition to implementing OpenWithColumnFamilies, this diff also includes some minor changes:
* Changed all column family names from Slice() to std::string. The performance of column family name handling is not critical, and it's more convenient and cleaner to have names as std::strings
* Implemented ColumnFamilyOptions(const Options&) and DBOptions(const Options&)
* Added ColumnFamilyOptions to VersionSet::ColumnFamilyData. ColumnFamilyOptions are specified on OpenWithColumnFamilies() and CreateColumnFamily()
I will keep the diff in the Phabricator for a day or two and will push to the branch then. Feel free to comment even after the diff has been pushed.
Test Plan: Added a simple unit test
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15033
Summary:
The way DBImpl::TEST_CompactRange() throttles down the number of bg compactions
can cause it to deadlock when CompactRange() is called concurrently from
multiple threads. Imagine a following scenario with only two threads
(max_background_compactions is 10 and bg_compaction_scheduled_ is initially 0):
1. Thread #1 increments bg_compaction_scheduled_ (to LargeNumber), sets
bg_compaction_scheduled_ to 9 (newvalue), schedules the compaction
(bg_compaction_scheduled_ is now 10) and waits for it to complete.
2. Thread #2 calls TEST_CompactRange(), increments bg_compaction_scheduled_
(now LargeNumber + 10) and waits on a cv for bg_compaction_scheduled_ to
drop to LargeNumber.
3. BG thread completes the first manual compaction, decrements
bg_compaction_scheduled_ and wakes up all threads waiting on bg_cv_.
Thread #1 runs, increments bg_compaction_scheduled_ by LargeNumber again
(now 2*LargeNumber + 9). Since that's more than LargeNumber + newvalue,
thread #2 also goes to sleep (waiting on bg_cv_), without resetting
bg_compaction_scheduled_.
This diff attempts to address the problem by introducing a new counter
bg_manual_only_ (when positive, MaybeScheduleFlushOrCompaction() will only
schedule manual compactions).
Test Plan:
I could pretty much consistently reproduce the deadlock with a program that
calls CompactRange(nullptr, nullptr) immediately after Write() from multiple
threads. This no longer happens with this patch.
Tests (make check) pass.
Reviewers: dhruba, igor, sdong, haobo
Reviewed By: igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14799
Summary:
This diff provides basic implementations of CreateColumnFamily(), DropColumnFamily() and ListColumnFamilies(). It builds on top of https://reviews.facebook.net/D14733
It also includes a bug fix for DBImplReadOnly, where Get implementation would be redirected to DBImpl instead of DBImplReadOnly.
Test Plan: Added unit test
Reviewers: dhruba, haobo, kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15021
Summary: this diff only replace the cases when we need to frequently create vector with small amount of entries. This diff doesn't aim to improve performance of a specific area, but more like a small scale test for the autovector and see how it works in real life.
Test Plan:
make check
I also ran the performance tests, however there is no performance gain/loss. All performance numbers are pretty much the same before/after the change.
Reviewers: dhruba, haobo, sdong, igor
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14985
Summary: I made some cleanup while reading the source code in `db`. Most changes are about style, naming or C++ 11 new features.
Test Plan: ran `make check`
Reviewers: haobo, dhruba, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D15009
Summary:
<This diff is for Column Family branch>
Added fields in manifest file to support adding and deleting column families.
Pretty simple change, each version edit record can be:
1. add column family
2. drop column family
3. add and delete N files from a single column family (compactions and flushes will generate such records)
Test Plan: make check works, the code is backward compatible
Reviewers: dhruba, haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14733
Summary:
We don't want two threads to clash if they concurrently call DisableFileDeletions() and EnableFileDeletions(). I'm adding a counter that will enable file deletions only after all DisableFileDeletions() calls have been negated with EnableFileDeletions().
However, we also don't want to break the old behavior, so I added a parameter force to EnableFileDeletions(). If force is true, we will still enable file deletions after every call to EnableFileDeletions(), which is what is happening now.
Test Plan: make check
Reviewers: dhruba, haobo, sanketh
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14781
Summary: I'm not sure what's the purpose of encoding file number to a new buffer for looking up the table cache. It seems to be unnecessary to me. With this patch, we point the lookup key to the address of the int64 of the file number.
Test Plan: make all check
Reviewers: dhruba, haobo, igor, kailiu
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14811
Summary:
In some places we have NotFound status created with empty message, but it doesn't avoid a malloc. With this patch, the malloc is avoided for that case.
The motivation of it is that I found in db_bench readrandom test when all keys are not existing, about 4% of the total running time is spent on malloc of Status, plus a similar amount of CPU spent on free of them, which is not necessary.
Test Plan: make all check
Reviewers: dhruba, haobo, igor
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14691
Summary: The previous patch is wrong. rep_.resize(kHeader) just resets the header portion to zero, and should not cause a re-allocation if g++ does it right. I will go ahead and revert it.
Test Plan: make check
Reviewers: dhruba, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14793
Summary: tmp_batch_ will get re-allocated for every merged write batch because of the existing resize in WriteBatch::Clear. Note that in DBImpl::BuildBatchGroup, we have a hard coded upper limit of batch size 1<<20 = 1MB already.
Test Plan: make check
Reviewers: dhruba, sdong
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14787
Summary:
Some changes to PlainTable format:
(1) support variable key length
(2) use user defined slice transformer to extract prefixes
(3) Run some test cases against PlainTable in db_test and table_test
Test Plan: test db_test
Reviewers: haobo, kailiu
CC: dhruba, igor, leveldb, nkg-
Differential Revision: https://reviews.facebook.net/D14457
Summary:
Instead of locking and saving a DB state, we can cache a DB state and update it only when it changes. This change reduces lock contention and speeds up read operations on the DB.
Performance improvements are substantial, although there is some cost in no-read workloads. I ran the regression tests on my devserver and here are the numbers:
overwrite 56345 -> 63001
fillseq 193730 -> 185296
readrandom 771301 -> 1219803 (58% improvement!)
readrandom_smallblockcache 677609 -> 862850
readrandom_memtable_sst 710440 -> 1109223
readrandom_fillunique_random 221589 -> 247869
memtablefillrandom 105286 -> 92643
memtablereadrandom 763033 -> 1288862
Test Plan:
make asan_check
I am also running db_stress
Reviewers: dhruba, haobo, sdong, kailiu
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14679
Summary:
For some tests I want to cache the database prior to running other tests on the same invocation
of db_bench. The readtocache test ignores --threads and --reads so those can be used by other tests
and it will still do a full read of --num rows with one thread. It might be invoked like:
db_bench --benchmarks=readtocache,readrandom --reads 100 --num 10000 --threads 8
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: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14739
Summary:
<This diff is for Column Family branch>
Sharing some of the work I've done so far. This diff compiles and passes the tests.
The biggest change is in options.h - I broke down Options into two parts - DBOptions and ColumnFamilyOptions. DBOptions is DB-specific (env, create_if_missing, block_cache, etc.) and ColumnFamilyOptions is column family-specific (all compaction options, compresion options, etc.). Note that this does not break backwards compatibility at all.
Further, I created DBWithColumnFamily which inherits DB interface and adds new functions with column family support. Clients can transparently switch to DBWithColumnFamily and it will not break their backwards compatibility.
There are few methods worth checking out: ListColumnFamilies(), MultiNewIterator(), MultiGet() and GetSnapshot(). [GetSnapshot() returns the snapshot across all column families for now - I think that's what we agreed on]
Finally, I made small changes to WriteBatch so we are able to atomically insert data across column families.
Please provide feedback.
Test Plan: make check works, the code is backward compatible
Reviewers: dhruba, haobo, sdong, kailiu, emayanke
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14445
Summary: I realized that "D14409 Avoid sorting in Version::Get() by presorting them in VersionSet::Builder::SaveTo()" is not done in an optimized place. SaveTo() is usually inside mutex. Move it to Finalize(), which is called out of mutex.
Test Plan: make all check
Reviewers: dhruba, haobo, kailiu
Reviewed By: dhruba
CC: igor, leveldb
Differential Revision: https://reviews.facebook.net/D14607
Summary: It seems to be a decision tradeoff in current codes: we make a malloc for every Get() to reduce one malloc for a flush inside mutex. It takes about 5% of CPU time in readrandom tests. We might consider the tradeoff to be the other way around.
Test Plan: make all check
Reviewers: dhruba, haobo, igor
Reviewed By: dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14697
Summary:
This is the last diff that adds the property block to plain table.
The format resembles that of the block-based table: https://github.com/facebook/rocksdb/wiki/Rocksdb-table-format
[data block]
[meta block 1: stats block]
[meta block 2: future extended block]
...
[meta block K: future extended block] (we may add more meta blocks in the future)
[metaindex block]
[index block: we only have the placeholder here, we can add persistent index block in the future]
[Footer: contains magic number, handle to metaindex block and index block]
<end_of_file>
Test Plan: extended existing property block test.
Reviewers: haobo, sdong, dhruba
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14523
Summary: To reduce mutex contention caused by DBImpl.NewInternalIterator(), in this function, move all the iteration creation works out of mutex, only leaving object ref and get.
Test Plan:
make all check
will run db_stress for a while too to make sure no problem.
Reviewers: haobo, dhruba, kailiu
Reviewed By: haobo
CC: igor, leveldb
Differential Revision: https://reviews.facebook.net/D14589
Summary: When deconstructing an iterator, no need to check obsolete file if it doesn't hold last reference of any version.
Test Plan: make all check
Reviewers: haobo, igor, dhruba, kailiu
Reviewed By: haobo
CC: leveldb
Differential Revision: https://reviews.facebook.net/D14595
Summary: In get operations, merge_operands is only used in few cases. Lazily initialize it can reduce average latency in some cases
Test Plan: make all check
Reviewers: haobo, kailiu, dhruba
Reviewed By: haobo
CC: igor, nkg-, leveldb
Differential Revision: https://reviews.facebook.net/D14415
Conflicts:
db/db_impl.cc
db/memtable.cc
