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
Yueh-Hsuan Chiang