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

create compressed_levels_ in Version, allocate its space using arena. Make Version::Get, Version::FindFile faster

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:
External contribution caused some valgrind errors: https://github.com/facebook/rocksdb/commit/1a34aaaef0900785c2de7e55b55d8c48d1201300

This diff fixes them

Test Plan: ran valgrind

Reviewers: sdong, yhchiang, ljin

Reviewed By: ljin

Subscribers: leveldb

Differential Revision: https://reviews.facebook.net/D19485

Also refactored the compaction filter tests to share some code and ensure that
options were getting reset so future test results aren't confused.

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 6634844d 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

This reverts commit 6634844d.

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