Summary:
This patch fixes a race condition in DBTEst.DynamicMemtableOptions. In rare cases,
it was possible that the main thread would fill up both memtables before the flush
job acquired its work. Then, the flush job was flushing both memtables together,
producing only one L0 file while the test expected two. Now, the test waits for
flushes to finish earlier, to make sure that the memtables are flushed in separate
flush jobs.

Test Plan:
Insert "usleep(10000);" after "IOSTATS_SET_THREAD_POOL_ID(Env::Priority::HIGH);" in BGWorkFlush()
to make the issue more likely. Then test with:
make db_test && time while ./db_test --gtest_filter=*DynamicMemtableOptions; do true; done

Reviewers: rven, sdong, yhchiang, anthony, igor

Reviewed By: igor

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D45429

Summary: As title

Test Plan: make check

Reviewers: yhchiang

Reviewed By: yhchiang

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D45447

Summary:
Currently, we only purge duplicate keys and deletions during flush if `earliest_seqno_in_memtable <= newest_snapshot`. This means that the newest snapshot happened before we first created the memtable. This is almost never true for MyRocks and MongoRocks.

This patch makes purging during flush able to understand snapshots. The main logic is copied from compaction_job.cc, although the logic over there is much more complicated and extensive. However, we should try to merge the common functionality at some point.

I need this patch to implement no_overwrite_i_promise functionality for flush. We'll also need this to support SingleDelete() during Flush(). @yoshinorim requested the feature.

Test Plan:
make check
I had to adjust some unit tests to understand this new behavior

Reviewers: yhchiang, yoshinorim, anthony, sdong, noetzli

Reviewed By: noetzli

Subscribers: yoshinorim, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D42087

Summary:
db_bench output now displays Percentile many times with --statistics after
read IO latency histograms were added. So I only need the last one in the report output.

Task ID: #

Blame Rev:

Test Plan:
run run_flash_bench.sh

Revert Plan:

Database Impact:

Memcache Impact:

Other Notes:

EImportant:

- begin *PUBLIC* platform impact section -
Bugzilla: #
- end platform impact -

Reviewers: igor

Reviewed By: igor

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D45093

Summary:
Up until this point we had DbOptions.num_subcompactions, but
it is semantically more correct to call this max_subcompactions since
we will schedule *up to* DbOptions.max_subcompactions smaller compactions
at a time during a compaction job.

I also added a --subcompactions option to db_bench

Test Plan: make all   make check

Reviewers: sdong, igor, anthony, yhchiang

Reviewed By: yhchiang

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D45069

Summary: Add more test cases of data race causing wrong iterating results. Tag tests not passing as DISABLED_

Test Plan: Run the tests

Reviewers: igor, rven, IslamAbdelRahman, anthony, kradhakrishnan, yhchiang

Reviewed By: yhchiang

Subscribers: tnovak, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D44907

Summary: Currently compaction inputs share the same file descriptor and table reader as other foreground threads. It makes fadvise works less predictable. Add options.new_table_reader_for_compaction_inputs to enforce to create a new file descriptor and new table reader for it.

Test Plan: Add the option.

Reviewers: rven, anthony, kradhakrishnan, IslamAbdelRahman, igor, yhchiang

Reviewed By: igor

Subscribers: igor, MarkCallaghan, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D43311

Summary:
Add a counter of estimated bytes the DB needs to compact for all the compactions to finish. Expose it as a DB Property.
In the future, we can use threshold of this counter to replace soft rate limit and hard rate limit. A single threshold of estimated compaction debt in bytes will be easier for users to reason about when should slow down and stopping than more abstract soft and hard rate limits.

Test Plan: Add unit tests

Reviewers: IslamAbdelRahman, yhchiang, rven, kradhakrishnan, anthony, igor

Reviewed By: igor

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D44205

Summary:
Changes include:
* don't sync-on-commit for single writer thread in readwhile... tests
* make default block size 8kb rather than 4kb to avoid too small blocks after compression
* use snappy instead of zlib to avoid stalls from compression latency
* disable statistics
* use bytes_per_sync=8M to reduce throughput loss on disk
* use open_files=-1 to reduce mutex contention

Task ID: #

Blame Rev:

Test Plan:
run benchmark

Revert Plan:

Database Impact:

Memcache Impact:

Other Notes:

EImportant:

- begin *PUBLIC* platform impact section -
Bugzilla: #
- end platform impact -

Reviewers: igor

Reviewed By: igor

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D44961

Summary:
Currently, ThreadStatusFlush uses two sync-points to ensure
there's a flush currently running when calling GetThreadList().
However, one of the sync-point is inside db-mutex, which could
cause deadlock in case there's a DB::Get() call.

This patch fix this issue by moving the sync-point to a better
place where the flush job does not hold the mutex.

Test Plan: db_test

Reviewers: igor, sdong, anthony, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D45045

Address windows build issues caused by introducing Subcompaction

Merge branch 'address_windows_build' of https://github.com/yuslepukhin/rocksdb into address_windows_build

 Intro SubCompactionState move functionality
 =delete copy functionality
 #ifdef SyncPoint in tests for Windows Release builds

  Intro SubCompactionState move functionality
  =delete copy functionality
  #ifdef SyncPoint in tests for Windows Release builds

Summary: Add a new DB property that calculate the total size of files used by all RocksDB Versions

Test Plan: Unittests for the new property

Reviewers: igor, yhchiang, anthony, rven, kradhakrishnan, sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D44799

Summary: Removing two unused variables that prevented compilation.

Test Plan: make all

Reviewers: rven, sdong, yhchiang, anthony, igor

Reviewed By: igor

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D44991

Summary:
This diff improves the memory utilization for tailing iterators RocksDB,
by freeing file iterators which are over the upper bound.
It is an updating on Siying's original diff for improving the memory usage for
tailing iterators. The changes for the seek and next path are now complete
and a test has been added to exercise these paths while deleting file iterators
which are above the upper bound.

Test Plan: db_tailing_iter_test.TailingIteratorTrimSeekToNext

Reviewers: march, tnovak, sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D43833

Summary: Update DestroyDB so that all SST files in the first path id go through DeleteScheduler instead of being deleted immediately

Test Plan: added a unittest

Reviewers: igor, yhchiang, anthony, kradhakrishnan, rven, sdong

Reviewed By: sdong

Subscribers: jeanxu2012, dhruba

Differential Revision: https://reviews.facebook.net/D44955

Summary:
Currently, GetIntProperty("rocksdb.cur-size-all-mem-tables") only returns
the memory usage by those memtables which have not yet been flushed.

This patch introduces GetIntProperty("rocksdb.size-all-mem-tables"),
which includes the memory usage by all the memtables, includes those
have been flushed but pinned by iterators.

Test Plan: Added a test in db_test

Reviewers: igor, anthony, IslamAbdelRahman, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D44229

Summary: There is a check to fail the iterator if prefix extractor is specified but upper bound is out of the prefix for the seek key. Relax this constraint to allow users to set upper bound to the next prefix of the current one.

Test Plan: make commit-prereq

Reviewers: igor, anthony, kradhakrishnan, yhchiang, rven

Reviewed By: rven

Subscribers: tnovak, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D44949

Summary:
A couple variables were declared but only used in assertions
which causes issues when building in fbcode.

Test Plan: make dbg  and   make release

Reviewers: yhchiang, sdong, igor, anthony, MarkCallaghan

Reviewed By: MarkCallaghan

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D44937

Summary:
In D43239 (https://reviews.facebook.net/D43239) the number
of subcompactions is set based on the number of L1 files with
unique starting keys. In certain cases when this number is very large
this causes issues, particularly with the overlap between files since
very small output files can be generated. This diff bounds the number
of subcompactions to the user option DBOption.num_subcompactions.

Test Plan: ./db_test ./db_compaction_test

Reviewers: sdong, igor, anthony, yhchiang

Reviewed By: yhchiang

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D44883

Summary:
Reseek mutable_iter if it is invalid in Next and immutable_iter
is invalid.

Test Plan: DBTestTailingIterator.TailingIteratorSeekToNext

Reviewers: tnovak, march, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D44865

Summary:
This patch implements DBOptions deserialization and improve
the current implementation of DBOptions serialization by
using a static structure that stores the offset of each
DBOptions member variables to perform serialization and
deserialization instead of using tons of if-then-branch
to determine the mapping between string and variables.

Test Plan: Added test in options_test.cc

Reviewers: igor, anthony, sdong, IslamAbdelRahman

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D44097

Summary:
HashCuckooRep::ApproximateMemoryUsage() previously return
std::numeric_limits<size_t>::max() when it cannot accept more
entries.  This patch makes it return a more reasonable estimation.

This change is necessary in order to make GetIntProperty("rocksdb.cur-size-all-mem-tables")
handles HashCuckooRep properly in diff https://reviews.facebook.net/D44229.

Test Plan: db_test

Reviewers: sdong, anthony, IslamAbdelRahman, igor

Reviewed By: igor

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D44241

Summary:
In D43239 (https://reviews.facebook.net/D43239) there is an
assertion to make sure a subcompaction's output is never empty at the
end of execution. This assertion however breaks the build because some
tests lead to exactly that scenario. So instead I have altered the logic
to handle this case instead of just failing the assertion.

The reason that it is possible for a subcompaction's output to be empty is
that during a sequential execution of subcompactions, if a user aborts the
compaction job then some of the later subcompactions to be executed may
have yet to process any keys and therefore have yet to generate output files.
This becomes very rare once the subcompactions are executed in parallel,
but for now they are still sequential so the case is possible when there is an
early termination, as in some of the tests.

Test Plan: ./db_test  ./db_compaction_test

Reviewers: sdong, igor, anthony, yhchiang

Reviewed By: yhchiang

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D44877

Summary:
In prepration for running multiple threads at the same time during
a compaction job, this patch assigns each subcompaction its own state
(instead of sharing the one global CompactionState). Each subcompaction then
uses this state to update its statistics, keep track of its snapshots, etc.
during the course of execution. Then at the end of all the executions the
statistics are aggregated across the subcompactions so that the final result
is the same as if only one larger compaction had run.

Test Plan: ./db_test  ./db_compaction_test  ./compaction_job_test

Reviewers: sdong, anthony, igor, noetzli, yhchiang

Reviewed By: yhchiang

Subscribers: MarkCallaghan, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D43239

Summary:
While working on supporting mixing merge operators with
single deletes ( https://reviews.facebook.net/D43179 ),
I realized that returning and dealing with merge results
can be made simpler. Submitting this as a separate diff
because it is not directly related to single deletes.

Before, callers of merge helper had to retrieve the merge
result in one of two ways depending on whether the merge
was successful or not (success = result of merge was single
kTypeValue). For successful merges, the caller could query
the resulting key/value pair and for unsuccessful merges,
the result could be retrieved in the form of two deques of
keys and values. However, with single deletes, a successful merge
does not return a single key/value pair (if merge
operands are merged with a single delete, we have to generate
a value and keep the original single delete around to make
sure that we are not accidentially producing a key overwrite).
In addition, the two existing call sites of the merge
helper were taking the same actions independently from whether
the merge was successful or not, so this patch simplifies that.

Test Plan: make clean all check

Reviewers: rven, sdong, yhchiang, anthony, igor

Reviewed By: igor

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D43353

Summary: In internal stats, remember read latency histogram, if statistics is enabled. It can be retrieved from DB::GetProperty() with "rocksdb.dbstats" property, if it is enabled.

Test Plan: Manually run db_bench and prints out "rocksdb.dbstats" by hand and make sure it prints out as expected

Reviewers: igor, IslamAbdelRahman, rven, kradhakrishnan, anthony, yhchiang

Reviewed By: yhchiang

Subscribers: MarkCallaghan, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D44193

Summary:
This diff allows a Writer to join the next write batch group
without acquiring any locks. Waiting is performed via a per-Writer mutex,
so all of the non-leader writers never need to acquire the db mutex.
It is now possible to join a write batch group after the leader has been
chosen but before the batch has been constructed. This diff doesn't
increase parallelism, but reduces synchronization overheads.

For some CPU-bound workloads (no WAL, RAM-sized working set) this can
substantially reduce contention on the db mutex in a multi-threaded
environment.  With T=8 N=500000 in a CPU-bound scenario (see the test
plan) this is good for a 33% perf win.  Not all scenarios see such a
win, but none show a loss.  This code is slightly faster even for the
single-threaded case (about 2% for the CPU-bound scenario below).

Test Plan:
1. unit tests
2. COMPILE_WITH_TSAN=1 make check
3. stress high-contention scenarios with db_bench -benchmarks=fillrandom -threads=$T -batch_size=1 -memtablerep=skip_list -value_size=0 --num=$N -level0_slowdown_writes_trigger=9999 -level0_stop_writes_trigger=9999 -disable_auto_compactions --max_write_buffer_number=8 -max_background_flushes=8 --disable_wal --write_buffer_size=160000000

Reviewers: sdong, igor, rven, ljin, yhchiang

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D43887

Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:

2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}

Add two more counters in iostats_context.

Also add a parameter of db_bench.

Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D44115

Summary: Change master version to 3.14

Test Plan: simple change

Reviewers: sdong, yhchiang, kradhakrishnan, rven, anthony, igor

Reviewed By: igor

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D44187

Add a 'tools' target.

My use case is to build the rocksdb static library and tools, and
ideally I'd like to not spend time building the shared library and other
targets that I won't use.

Summary: Iterator has a bug: if a child iterator reaches its end, and user issues a Prev(), and just before SeekToLast() of the child iterator is called, some extra rows is added in the end, the position of iterator can be misplaced.

Test Plan: Run the tests with or without valgrind

Reviewers: rven, yhchiang, IslamAbdelRahman, anthony

Reviewed By: anthony

Subscribers: tnovak, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D43671

Summary: RandomRWFile is not used anywhere in out code base, this patch remove RandomRWFile

Test Plan:
make check -j64
USE_CLANG=1 make all -j64
OPT=-DROCKSDB_LITE make release -j64

Reviewers: sdong, yhchiang, anthony, kradhakrishnan, rven, igor

Reviewed By: igor

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D44091

Summary:
Clean up transactions to use the new RollbackToSavePoint api in WriteBatchWithIndex.

Note, this diff depends on Pessimistic Transactions diff and ManagedSnapshot diff (D40869 and D43293).

Test Plan: unit tests

Reviewers: rven, yhchiang, kradhakrishnan, spetrunia, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D43371

Summary:
Based on feedback from spetrunia, we should better differentiate error statuses for transaction failures.

https://github.com/MySQLOnRocksDB/mysql-5.6/issues/86#issuecomment-124605954

Test Plan: unit tests

Reviewers: rven, kradhakrishnan, spetrunia, yhchiang, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D43323