Commit Graph

673 Commits

Author SHA1 Message Date
Islam AbdelRahman
7c919deccc Reuse TimedFullMerge instead of FullMerge + instrumentation
Summary:
We have alot of code duplication whenever we call FullMerge we keep duplicating the instrumentation and statistics code
This is a simple diff to refactor the code to use TimedFullMerge instead of FullMerge

Test Plan: COMPILE_WITH_ASAN=1 make check -j64

Reviewers: andrewkr, yhchiang, sdong

Reviewed By: sdong

Subscribers: andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D59577
2016-06-13 16:17:26 -07:00
Nadav Rotem
7360db39e6 Add a check mode to verify compressed block can be decompressed back
Summary:
Try to decompress compressed blocks when a special flag is set.
assert and crash in debug builds if we can't decompress the just-compressed input.

Test Plan: Run unit-tests.

Reviewers: dhruba, andrewkr, sdong, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D59145
2016-06-10 18:20:54 -07:00
sdong
5009b5326b BlockBasedTable::FullFilterKeyMayMatch() Should skip prefix bloom if full key bloom exists
Summary: Currently, if users define both of full key bloom and prefix bloom in SST files. During Get(), if full key bloom shows the key may exist, we still go ahead and check prefix bloom. This is wasteful. If bloom filter for full keys exists, we should always ignore prefix bloom in Get().

Test Plan: Run existing tests

Reviewers: yhchiang, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: leveldb, andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D57825
2016-06-10 16:27:56 -07:00
Aaron Gao
e532877940 Add statistics field to show total size of index and filter blocks in block cache
Summary: With `table_options.cache_index_and_filter_blocks = true`, index and filter blocks are stored in block cache. Then people are curious how much of the block cache total size is used by indexes and bloom filters. It will be nice we have a way to report that. It can help people tune performance and plan for optimized hardware setting. We add several enum values for db Statistics. BLOCK_CACHE_INDEX/FILTER_BYTES_INSERT - BLOCK_CACHE_INDEX/FILTER_BYTES_ERASE = current INDEX/FILTER total block size in bytes.

Test Plan:
write a test case called `DBBlockCacheTest.IndexAndFilterBlocksStats`. The result is:
```
[gzh@dev9927.prn1 ~/local/rocksdb]  make db_block_cache_test -j64 && ./db_block_cache_test --gtest_filter=DBBlockCacheTest.IndexAndFilterBlocksStats
Makefile:101: Warning: Compiling in debug mode. Don't use the resulting binary in production
  GEN      util/build_version.cc
  make: `db_block_cache_test' is up to date.
  Note: Google Test filter = DBBlockCacheTest.IndexAndFilterBlocksStats
  [==========] Running 1 test from 1 test case.
  [----------] Global test environment set-up.
  [----------] 1 test from DBBlockCacheTest
  [ RUN      ] DBBlockCacheTest.IndexAndFilterBlocksStats
  [       OK ] DBBlockCacheTest.IndexAndFilterBlocksStats (689 ms)
  [----------] 1 test from DBBlockCacheTest (689 ms total)

  [----------] Global test environment tear-down
  [==========] 1 test from 1 test case ran. (689 ms total)
  [  PASSED  ] 1 test.
```

Reviewers: IslamAbdelRahman, andrewkr, sdong

Reviewed By: sdong

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D58677
2016-06-03 10:47:47 -07:00
sdong
1d725ca51d Deprecate BlockBasedTableOptions.hash_index_allow_collision=false.
Summary: Deprecate this one option and delete code and tests that are now superfluous.

Test Plan: all tests pass

Reviewers: igor, yhchiang, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: msalib, leveldb, andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D55317
2016-05-20 17:52:27 -07:00
Aaron Gao
43afd72bee [rocksdb] make more options dynamic
Summary:
make more ColumnFamilyOptions dynamic:
- compression
- soft_pending_compaction_bytes_limit
- hard_pending_compaction_bytes_limit
- min_partial_merge_operands
- report_bg_io_stats
- paranoid_file_checks

Test Plan:
Add sanity check in `db_test.cc` for all above options except for soft_pending_compaction_bytes_limit and hard_pending_compaction_bytes_limit.
All passed.

Reviewers: andrewkr, sdong, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D57519
2016-05-17 13:11:56 -07:00
krad
a08c8c851a Added PersistentCache abstraction
Summary:
Added a new abstraction to cache page to RocksDB designed for the read
cache use.

RocksDB current block cache is more of an object cache. For the persistent read cache
project, what we need is a page cache equivalent. This changes adds a cache
abstraction to RocksDB to cache pages called PersistentCache. PersistentCache can cache
uncompressed pages or raw pages (content as in filesystem). The user can
choose to operate PersistentCache either in  COMPRESSED or UNCOMPRESSED mode.

Blame Rev:

Test Plan: Run unit tests

Reviewers: sdong

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D55707
2016-05-15 22:17:18 -07:00
Ashish Shenoy
fa3536d202 Store SST file compression algorithm as a TableProperty
Summary: Store SST file compression algorithm as a TableProperty.

Test Plan: Modified and ran the table_test UT that checks for TableProperties

Reviewers: IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: lgalanis, andrewkr, dhruba, IslamAbdelRahman

Differential Revision: https://reviews.facebook.net/D58017
2016-05-12 09:47:16 -07:00
sdong
7ccb8d6ef3 BlockBasedTable::Get() not to use prefix bloom if read_options.total_order_seek = true
Summary: This is to provide a way for users to skip prefix bloom in point look-up.

Test Plan: Add a new unit test scenario.

Reviewers: IslamAbdelRahman

Subscribers: leveldb, andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D57747
2016-05-06 10:16:11 -07:00
Dmitri Smirnov
e7899c6618 Fix build issue. (#1103) 2016-04-28 11:39:12 -07:00
Li Peng
6d4832a998 Merge pull request #1101 from flyd1005/wip-fix-typo
fix typos and remove duplicated words
2016-04-28 02:30:44 -07:00
Andrew Kryczka
843d2e3137 Shared dictionary compression using reference block
Summary:
This adds a new metablock containing a shared dictionary that is used
to compress all data blocks in the SST file. The size of the shared dictionary
is configurable in CompressionOptions and defaults to 0. It's currently only
used for zlib/lz4/lz4hc, but the block will be stored in the SST regardless of
the compression type if the user chooses a nonzero dictionary size.

During compaction, computes the dictionary by randomly sampling the first
output file in each subcompaction. It pre-computes the intervals to sample
by assuming the output file will have the maximum allowable length. In case
the file is smaller, some of the pre-computed sampling intervals can be beyond
end-of-file, in which case we skip over those samples and the dictionary will
be a bit smaller. After the dictionary is generated using the first file in a
subcompaction, it is loaded into the compression library before writing each
block in each subsequent file of that subcompaction.

On the read path, gets the dictionary from the metablock, if it exists. Then,
loads that dictionary into the compression library before reading each block.

Test Plan: new unit test

Reviewers: yhchiang, IslamAbdelRahman, cyan, sdong

Reviewed By: sdong

Subscribers: andrewkr, yoshinorim, kradhakrishnan, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D52287
2016-04-27 17:36:03 -07:00
Islam AbdelRahman
d719b095dc Introduce PinnedIteratorsManager (Reduce PinData() overhead / Refactor PinData)
Summary:
While trying to reuse PinData() / ReleasePinnedData() .. to optimize away some memcpys I realized that there is a significant overhead for using PinData() / ReleasePinnedData if they were called many times.
This diff refactor the pinning logic by introducing PinnedIteratorsManager a centralized component that will be created once and will be notified whenever we need to Pin an Iterator. This implementation have much less overhead than the original implementation

Test Plan:
make check -j64
COMPILE_WITH_ASAN=1 make check -j64

Reviewers: yhchiang, sdong, andrewkr

Reviewed By: andrewkr

Subscribers: andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D56493
2016-04-26 12:41:07 -07:00
Dhruba Borthakur
995353e46a Fix null-pointer-dereference detected by Infer (https://github.com/facebook/infer)
Test Plan: make check

Reviewers: leveldb, sdong

Reviewed By: sdong

Subscribers: leveldb, andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D57165
2016-04-25 20:09:36 +01:00
Islam AbdelRahman
5bd4022fec Add comparator, merge operator, property collectors to SST file properties (again)
Summary:
This is the original diff that I have landed and reverted and now I want to land again https://reviews.facebook.net/D34269

For old SST files we will show
```
  comparator name: N/A
  merge operator name: N/A
  property collectors names: N/A
```

For new SST files with no merge operator name and with no property collectors
```
  comparator name: leveldb.BytewiseComparator
  merge operator name: nullptr
  property collectors names: []
```

for new SST files with these properties
```
  comparator name: leveldb.BytewiseComparator
  merge operator name: UInt64AddOperator
  property collectors names: [DummyPropertiesCollector1,DummyPropertiesCollector2]
```

Test Plan: unittests

Reviewers: andrewkr, yhchiang, sdong

Reviewed By: sdong

Subscribers: andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D56487
2016-04-21 10:16:28 -07:00
Dmitri Smirnov
ee221d2de0 Introduce XPRESS compresssion on Windows. (#1081)
Comparable with Snappy on comp ratio.
  Implemented using Windows API, does not require external package.
  Avaiable since Windows 8 and server 2012.
  Use -DXPRESS=1 with CMake to enable.
2016-04-19 22:54:24 -07:00
Islam AbdelRahman
6356b4d516 Fix nullptr dereference in adaptive_table
Summary:
@dulmarod Ran infer on RocksDB and found that we dereference nullptr in adaptive_table
https://fb.facebook.com/groups/rocksdb/permalink/1046374415411173/

Test Plan: make check -j64

Reviewers: sdong, yhchiang, andrewkr

Reviewed By: andrewkr

Subscribers: andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D56973
2016-04-19 13:57:05 -07:00
sdong
535af525d6 BlockBasedTable::PrefixMayMatch() to skip index checking if we can't find a filter block.
Summary:
In the case where we can't find a filter block, there is not much benefit of doing the binary search and see whether the index key has the prefix. With the change, we blindly return true if we can't get the filter.
It also fixes missing row cases for reverse comparator with full bloom.

Test Plan: Add a test case that used to fail.

Reviewers: yhchiang, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: kradhakrishnan, yiwu, hermanlee4, yoshinorim, leveldb, andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D56697
2016-04-13 19:06:48 -07:00
sdong
dff4c48ede BlockBasedTable::PrefixMayMatch: no need to find data block after full bloom checking
Summary:
Full block checking should be a good enough indication of prefix existance. No need to further check data block.
This also fixes wrong results when using prefix bloom and reverse bitwise comparator.

Test Plan: Will add a unit test.

Reviewers: yhchiang, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: hermanlee4, yoshinorim, yiwu, kradhakrishnan, leveldb, andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D56625
2016-04-12 16:25:54 -07:00
sdong
30d72ee43c PrefixTest.PrefixAndWholeKeyTest should run against a different directory from prefix_test
Summary: PrefixTest.PrefixAndWholeKeyTest runs against the same directory as prefix_test, which sometimes fail parallel tests. Fix it.

Test Plan: Run it in parallel and see it doesn't fail anymore.

Reviewers: andrewkr

Reviewed By: andrewkr

Subscribers: leveldb, andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D56541
2016-04-11 13:02:56 -07:00
Andrew Kryczka
0e3cc2cf1f Add column family info to TableProperties::ToString()
Summary: This is used at least by `sst_dump --show_properties`

Test Plan:
- default CF

```
  $ ./sst_dump --show_properties --file=./tmp-db/000007.sst | grep 'column family'
  column family ID: 0
  column family name: default
```

- custom CF

```
  $ ./sst_dump --show_properties --file=./tmp-db/000012.sst | grep 'column family'
  column family ID: 1
  column family name: col-fam-1
```

- no CF

```
  $ ./sst_dump --show_properties --file=./tmp-db/000017.sst | grep 'column family'
  column family ID: N/A
  column family name: N/A
```

Reviewers: IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D56499
2016-04-08 18:50:18 -07:00
sdong
1518b733eb Change default number of cache shard bit to be 6 and max_file_opening_threads to be 16.
Summary: Cache shard bit 4 is sometimes too small and 6 is a more common value picked by users. Make that default. It shouldn't hurt much to change options.max_file_opening_threads default to be 16, which will reduce the worst case DB open time.

Test Plan: Run all existing tests.

Reviewers: IslamAbdelRahman, yhchiang, kradhakrishnan, igor, andrewkr

Reviewed By: andrewkr

Subscribers: andrewkr, MarkCallaghan, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D55047
2016-04-07 13:55:10 -07:00
Andrew Kryczka
2391ef7214 Embed column family name in SST file
Summary:
Added the column family name to the properties block. This property
is omitted only if the property is unavailable, such as when RepairDB()
writes SST files.

In a next diff, I will change RepairDB to use this new property for
deciding to which column family an existing SST file belongs. If this
property is missing, it will add it to the "unknown" column family (same
as its existing behavior).

Test Plan:
New unit test:

  $ ./db_table_properties_test --gtest_filter=DBTablePropertiesTest.GetColumnFamilyNameProperty

Reviewers: IslamAbdelRahman, yhchiang, sdong

Reviewed By: sdong

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D55605
2016-04-06 23:10:32 -07:00
Marton Trencseni
9b51987521 Adding pin_l0_filter_and_index_blocks_in_cache feature and related fixes.
Summary:
When a block based table file is opened, if prefetch_index_and_filter is true, it will prefetch the index and filter blocks, putting them into the block cache.
What this feature adds: when a L0 block based table file is opened, if pin_l0_filter_and_index_blocks_in_cache is true in the options (and prefetch_index_and_filter is true), then the filter and index blocks aren't released back to the block cache at the end of BlockBasedTableReader::Open(). Instead the table reader takes ownership of them, hence pinning them, ie. the LRU cache will never push them out. Meanwhile in the table reader, further accesses will not hit the block cache, thus avoiding lock contention.

Test Plan:
'export TEST_TMPDIR=/dev/shm/ && DISABLE_JEMALLOC=1 OPT=-g make all valgrind_check -j32' is OK.
I didn't run the Java tests, I don't have Java set up on my devserver.

Reviewers: sdong

Reviewed By: sdong

Subscribers: andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D56133
2016-04-01 10:42:39 -07:00
Laurent Demailly
21700a5106 to/from hex refactor
Summary:
Expose the inverse of ToString(hex=true) on Slice: Slice::DecodeHex
Refactor the other implementation of to/from hex in ldb_cmd.h to use the Slice
version
(Difference between the 2 is whether 0x is expected/produced in front of the hex
string or not)
Eliminated support for invalid odd length hex string - this is now invalid
instead of having 1/2 byte set
Added (inverse of HexToString) test for LDBCommand::StringToHex which also
indirectly tests Slice::ToString(true)

After moving the original implementation from ldb_cmd.h, updated it to much simpler/efficient version
(originally/inspired from https://github.com/facebook/wdt/blob/master/util/EncryptionUtils.cpp#L140-L169 )

Test Plan: run tests

Reviewers: uddipta, sdong

Reviewed By: sdong

Subscribers: andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D56121
2016-03-30 14:36:48 -07:00
sdong
b1fafcaca6 Revert "Adding pin_l0_filter_and_index_blocks_in_cache feature."
This reverts commit 522de4f59e.

It has bug of index block cleaning up.
2016-03-21 11:50:42 -07:00
Marton Trencseni
522de4f59e Adding pin_l0_filter_and_index_blocks_in_cache feature.
Summary:
When a block based table file is opened, if prefetch_index_and_filter is true, it will prefetch the index and filter blocks, putting them into the block cache.
What this feature adds: when a L0 block based table file is opened, if pin_l0_filter_and_index_blocks_in_cache is true in the options (and prefetch_index_and_filter is true), then the filter and index blocks aren't released back to the block cache at the end of BlockBasedTableReader::Open(). Instead the table reader takes ownership of them, hence pinning them, ie. the LRU cache will never push them out. Meanwhile in the table reader, further accesses will not hit the block cache, thus avoiding lock contention.
When the table reader is destroyed, it releases the pinned blocks (if there were any). This has to happen before the cache is destroyed, so I had to introduce a TableReader::Close(), to guarantee the order of destruction.

Test Plan:
Added two unit tests for this. Existing unit tests run fine (default is pin_l0_filter_and_index_blocks_in_cache=false).

DISABLE_JEMALLOC=1 OPT=-g make all valgrind_check -j32
  Mac: OK.
  Linux: with D55287 patched in it's OK.

Reviewers: sdong

Reviewed By: sdong

Subscribers: andrewkr, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D54801
2016-03-17 22:40:01 +00:00
Edouard A
02e62ebbc8 Fixes warnings and ensure correct int behavior on 32-bit platforms. 2016-03-16 22:57:57 +01:00
sdong
b2ae5950ba Index Reader should not be reused after DB restart
Summary:
In block based table reader, wow we put index reader to block cache, which can be retrieved after DB restart. However, index reader may reference internal comparator, which can be destroyed after DB restarts, causing problems.
Fix it by making cache key identical per table reader.

Test Plan: Add a new test which failed with out the commit but now pass.

Reviewers: IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: maro, yhchiang, kradhakrishnan, leveldb, andrewkr, dhruba

Differential Revision: https://reviews.facebook.net/D55287
2016-03-14 10:04:09 -07:00
Yi Wu
f71fc77b7c Cache to have an option to fail Cache::Insert() when full
Summary:
Cache to have an option to fail Cache::Insert() when full. Update call sites to check status and handle error.

I totally have no idea what's correct behavior of all the call sites when they encounter error. Please let me know if you see something wrong or more unit test is needed.

Test Plan: make check -j32, see tests pass.

Reviewers: anthony, yhchiang, andrewkr, IslamAbdelRahman, kradhakrishnan, sdong

Reviewed By: sdong

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D54705
2016-03-10 17:35:19 -08:00
sdong
e79ad9e184 Add Iterator Property rocksdb.iterator.version_number
Summary: We want to provide a way to detect whether an iterator is stale and needs to be recreated. Add a iterator property to return version number.

Test Plan: Add two unit tests for it.

Reviewers: IslamAbdelRahman, yhchiang, anthony, kradhakrishnan, andrewkr

Reviewed By: andrewkr

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D54921
2016-03-02 16:23:59 -08:00
sdong
74b660702e Rename iterator property "rocksdb.iterator.is.key.pinned" => "rocksdb.iterator.is-key-pinned"
Summary: Rename iterator property to folow property naming convention.

Test Plan: Run all existing tests.

Reviewers: andrewkr, anthony, yhchiang, kradhakrishnan, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D54957
2016-03-01 13:47:12 -08:00
sdong
1f5954147b Introduce Iterator::GetProperty() and replace Iterator::IsKeyPinned()
Summary:
Add Iterator::GetProperty(), a way for users to communicate with iterator, and turn Iterator::IsKeyPinned() with it.
As a follow-up, I'll ask a property as the version number attached to the iterator

Test Plan: Rerun existing tests and add a negative test case.

Reviewers: yhchiang, andrewkr, kradhakrishnan, anthony, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D54783
2016-02-29 14:01:31 -08:00
Yueh-Hsuan Chiang
291ae4c206 Revert "Revert "Fixed the bug when both whole_key_filtering and prefix_extractor are set.""
Summary:
This reverts commit 73c31377bb, which mistakenly
reverts 73c31377bb that fixes a bug when both
whole_key_filtering and prefix_extractor are set

Test Plan: revert the patch

Reviewers: anthony, IslamAbdelRahman, rven, kradhakrishnan, sdong

Reviewed By: sdong

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D52707
2016-02-22 16:33:26 -08:00
Baraa Hamodi
21e95811d1 Updated all copyright headers to the new format. 2016-02-09 15:12:00 -08:00
Yueh-Hsuan Chiang
4a8cbf4e31 Allows Get and MultiGet to read directly from SST files.
Summary:
Add kSstFileTier to ReadTier, which allows Get and MultiGet to
read only directly from SST files and skip mem-tables.

    kSstFileTier = 0x2      // data in SST files.
                          // Note that this ReadTier currently only supports
                          // Get and MultiGet and does not support iterators.

Test Plan: add new test in db_test.

Reviewers: anthony, IslamAbdelRahman, rven, kradhakrishnan, sdong

Reviewed By: sdong

Subscribers: igor, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D53511
2016-02-09 11:20:22 -08:00
Islam AbdelRahman
8e6172bc57 Add BlockBasedTableOptions::index_block_restart_interval
Summary: Add a new option to BlockBasedTableOptions that will allow us to change the restart interval for the index block

Test Plan: unit tests

Reviewers: yhchiang, anthony, andrewkr, sdong

Reviewed By: sdong

Subscribers: march, dhruba

Differential Revision: https://reviews.facebook.net/D53721
2016-02-05 10:22:37 -08:00
Islam AbdelRahman
0c433cd1eb Fix issue in Iterator::Seek when using Block based filter block with prefix_extractor
Summary: Similar to D53385 we need to check InDomain before checking the filter block.

Test Plan: unit tests

Reviewers: yhchiang, rven, sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D53421
2016-01-26 14:47:42 -08:00
Islam AbdelRahman
b0afcdeeac Fix bug in block based tables with full filter block and prefix_extractor
Summary:
Right now when we are creating a BlockBasedTable with fill filter block
we add to the filter all the prefixes that are InDomain() based on the prefix_extractor

the problem is that when we read a key from the file, we check the filter block for the prefix whether or not it's InDomain()

Test Plan: unit tests

Reviewers: yhchiang, rven, anthony, kradhakrishnan, sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D53385
2016-01-26 11:07:08 -08:00
Islam AbdelRahman
2fbc59a348 Disallow SstFileWriter from creating empty sst files
Summary:
SstFileWriter may create an sst file with no entries
Right now this will fail when being ingested using DB::AddFile() saying that the keys are corrupted

Test Plan: make check

Reviewers: yhchiang, rven, anthony, sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D52815
2016-01-25 13:47:07 -08:00
Islam AbdelRahman
d9bca1e14c Reduce iterator deletion overhead
Summary:
After introducing Iterator::PinData(), we have extra overhead of deleting the pinned iterators that we track in a std::set
This patch avoid inserting to the std::set if we have only one iterator (normal use case when no iterators are pinned)

Before this change
```
DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="newiterator" --db="/tmp/rocksdbtest-8616/dbbench" --use_existing_db --disable_auto_compactions
newiterator  :       1.006 micros/op 994013 ops/sec;
newiterator  :       0.994 micros/op 1006295 ops/sec;
newiterator  :       0.990 micros/op 1010422 ops/sec;
```

After change

```
DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="newiterator" --db="/tmp/rocksdbtest-8616/dbbench" --use_existing_db --disable_auto_compactions
newiterator  :       0.754 micros/op 1326588 ops/sec;
newiterator  :       0.759 micros/op 1317394 ops/sec;
newiterator  :       0.691 micros/op 1446704 ops/sec;
```

Test Plan: make check -j64

Reviewers: yhchiang, rven, anthony, sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D52761
2016-01-11 16:48:15 -08:00
sdong
df7e3b6229 Include <array> in table/plain_table_key_coding.h
Summary: <array> is not included in table/plain_table_key_coding.h. It may be the cause of one CLANG build failure.

Test Plan: Build it

Reviewers: yhchiang, rven, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D52725
2016-01-08 17:34:53 -08:00
sdong
9a8e3f73ed plain table reader: non-mmap mode to keep two recent buffers
Summary: In plain table reader's non-mmap mode, we only keep the most recent read buffer. However, for binary search, it is likely we come back to a location to read. To avoid one pread in such a case, we keep two read buffers. It should cover most of the cases.

Test Plan:
1. run tests
2. check the optimization works through strace when running
./table_reader_bench -mmap_read=false --num_keys2=1 -num_keys1=5000 -table_factory=plain_table --iterator --through_db

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

Reviewed By: IslamAbdelRahman

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D51171
2016-01-08 10:53:57 -08:00
Islam AbdelRahman
f3fb39814d Fix BlockBasedTableTest.NoopTransformSeek failure
Summary:
table_test is failing because we are creating a temp InternalComparator

14:27:28 [ RUN      ] BlockBasedTableTest.NoopTransformSeek
14:27:28 pure virtual method called
14:27:28 terminate called without an active exception
14:27:28 /bin/sh: line 7: 2346261 Aborted                 (core dumped) ./$t

Test Plan: make table_test -j64 && ./table_test --gtest_filter="BlockBasedTableTest.NoopTransformSeek"

Reviewers: igor, sdong, anthony, rven

Reviewed By: rven

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D52671
2016-01-07 09:48:29 -08:00
Yueh-Hsuan Chiang
73c31377bb Revert "Fixed the bug when both whole_key_filtering and prefix_extractor are set."
Summary:
This patch reverts commit 57605d7ef3 as it will
cause BlockBasedTableTest.NoopTransformSeek test crashes in some environment.

Test Plan: revert the patch

Reviewers: anthony, IslamAbdelRahman, rven, kradhakrishnan, sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D52623
2016-01-06 23:33:41 -08:00
Yueh-Hsuan Chiang
57605d7ef3 Fixed the bug when both whole_key_filtering and prefix_extractor are set.
Summary:
When both whole_key_filtering and prefix_extractor are set, RocksDB will
mistakenly encode prefix + whole key into the database instead of
simply whole key when BlockBasedTable is used.  This patch fixes this bug.

Test Plan: Add a test in table_test

Reviewers: anthony, IslamAbdelRahman, rven, kradhakrishnan, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D52233
2016-01-06 23:01:23 -08:00
Igor Canadi
ba83447363 Merge pull request #923 from petermattis/pmattis/prefix-may-match
Fix index seeking in BlockTableReader::PrefixMayMatch.
2016-01-06 14:02:10 -08:00
Reid Horuff
da032495d3 Optimize GetLatestSequenceForKey
Summary: DBImpl::GetLatestSequenceForKey() can do memcpy's to load a value that will never be used.  This can be optimized by changing all the Get() functions called to optionally not fetch the value (and only fetch the sequencenumber).

Test Plan: optimistic_transaction_test and transaction_test

Reviewers: anthony

Reviewed By: anthony

Subscribers: leveldb, dhruba, hermanlee4

Differential Revision: https://reviews.facebook.net/D52227
2016-01-06 13:43:22 -08:00
Peter Mattis
260c29762a Fix index seeking in BlockTableReader::PrefixMayMatch.
PrefixMayMatch previously seeked in the prefix index using an internal
key with a sequence number of 0. This would cause the prefix index seek
to fall off the end if the last key in the index had a user-key greater
than or equal to the key being looked for. Falling off the end of the
index in turn results in PrefixMayMatch returning false if the index is
in memory.
2016-01-06 16:39:56 -05:00
Jay Edgar
7699439b7c Prevent the user from setting block_restart_interval to less than 1
Summary: If block_restart_interval gets set to less than 1 an assert will be triggered in BlockBuilder::BlockBuilder().  This prevents the user from doing this by silently setting any value less than 1 to 1.

Test Plan: Added a test (in BlockBasedTableTest in table_test) that checks invalid values to make sure that they are reset to the expected values.  The block_restart_interval value is checked along with block_size_deviation which also silently sets the value if it is outside a specific range.

Reviewers: yoshinorim, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D52509
2016-01-04 14:13:18 -08:00
Nathan Bronson
ac16663bd6 use -Werror=missing-field-initializers, to closer match MyRocks build
Summary:
myrocks seems to build rocksdb using
-Wmissing-field-initializers (and treats warnings as errors).  This diff
adds that flag to the rocksdb build, and fixes the compilation failures
that result.  I have not checked for any other differences in the build
flags for rocksdb build as part of myrocks.

Test Plan: make check

Reviewers: sdong, rven

Reviewed By: rven

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D52443
2015-12-30 14:56:18 -08:00
Nathan Bronson
7d87f02799 support for concurrent adds to memtable
Summary:
This diff adds support for concurrent adds to the skiplist memtable
implementations.  Memory allocation is made thread-safe by the addition of
a spinlock, with small per-core buffers to avoid contention.  Concurrent
memtable writes are made via an additional method and don't impose a
performance overhead on the non-concurrent case, so parallelism can be
selected on a per-batch basis.

Write thread synchronization is an increasing bottleneck for higher levels
of concurrency, so this diff adds --enable_write_thread_adaptive_yield
(default off).  This feature causes threads joining a write batch
group to spin for a short time (default 100 usec) using sched_yield,
rather than going to sleep on a mutex.  If the timing of the yield calls
indicates that another thread has actually run during the yield then
spinning is avoided.  This option improves performance for concurrent
situations even without parallel adds, although it has the potential to
increase CPU usage (and the heuristic adaptation is not yet mature).

Parallel writes are not currently compatible with
inplace updates, update callbacks, or delete filtering.
Enable it with --allow_concurrent_memtable_write (and
--enable_write_thread_adaptive_yield).  Parallel memtable writes
are performance neutral when there is no actual parallelism, and in
my experiments (SSD server-class Linux and varying contention and key
sizes for fillrandom) they are always a performance win when there is
more than one thread.

Statistics are updated earlier in the write path, dropping the number
of DB mutex acquisitions from 2 to 1 for almost all cases.

This diff was motivated and inspired by Yahoo's cLSM work.  It is more
conservative than cLSM: RocksDB's write batch group leader role is
preserved (along with all of the existing flush and write throttling
logic) and concurrent writers are blocked until all memtable insertions
have completed and the sequence number has been advanced, to preserve
linearizability.

My test config is "db_bench -benchmarks=fillrandom -threads=$T
-batch_size=1 -memtablerep=skip_list -value_size=100 --num=1000000/$T
-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
--block_size=16384 --allow_concurrent_memtable_write" on a two-socket
Xeon E5-2660 @ 2.2Ghz with lots of memory and an SSD hard drive.  With 1
thread I get ~440Kops/sec.  Peak performance for 1 socket (numactl
-N1) is slightly more than 1Mops/sec, at 16 threads.  Peak performance
across both sockets happens at 30 threads, and is ~900Kops/sec, although
with fewer threads there is less performance loss when the system has
background work.

Test Plan:
1. concurrent stress tests for InlineSkipList and DynamicBloom
2. make clean; make check
3. make clean; DISABLE_JEMALLOC=1 make valgrind_check; valgrind db_bench
4. make clean; COMPILE_WITH_TSAN=1 make all check; db_bench
5. make clean; COMPILE_WITH_ASAN=1 make all check; db_bench
6. make clean; OPT=-DROCKSDB_LITE make check
7. verify no perf regressions when disabled

Reviewers: igor, sdong

Reviewed By: sdong

Subscribers: MarkCallaghan, IslamAbdelRahman, anthony, yhchiang, rven, sdong, guyg8, kradhakrishnan, dhruba

Differential Revision: https://reviews.facebook.net/D50589
2015-12-25 11:03:40 -08:00
Siying Dong
298ba27ae2 Merge pull request #846 from yuslepukhin/enble_c4244_lossofdata
Enable MS compiler warning c4244.
2015-12-23 22:59:42 -08:00
Andrew Kryczka
e089db40f9 Skip bottom-level filter block caching when hit-optimized
Summary:
When Get() or NewIterator() trigger file loads, skip caching the filter block if
(1) optimize_filters_for_hits is set and (2) the file is on the bottommost
level. Also skip checking filters under the same conditions, which means that
for a preloaded file or a file that was trivially-moved to the bottom level, its
filter block will eventually expire from the cache.

- added parameters/instance variables in various places in order to propagate the config ("skip_filters") from version_set to block_based_table_reader
- in BlockBasedTable::Rep, this optimization prevents filter from being loaded when the file is opened simply by setting filter_policy = nullptr
- in BlockBasedTable::Get/BlockBasedTable::NewIterator, this optimization prevents filter from being used (even if it was loaded already) by setting filter = nullptr

Test Plan:
updated unit test:

  $ ./db_test --gtest_filter=DBTest.OptimizeFiltersForHits

will also run 'make check'

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

Reviewed By: yhchiang

Subscribers: leveldb

Differential Revision: https://reviews.facebook.net/D51633
2015-12-23 10:15:07 -08:00
Reid Horuff
97ea8afaaf compaction assertion triggering test fix for sequence zeroing assertion trip 2015-12-18 16:08:31 -08:00
Islam AbdelRahman
521da3abb3 Fix BlockBasedTableTest.BlockCacheLeak valgrind failure
Summary:
I added this line in my previous patch D48999 (which is incorrect)
We should not release the iterator since releasing it will evict the blocks from cache

Test Plan:
Run the test under valgrind
make check

Reviewers: rven, yhchiang, sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D52161
2015-12-18 11:17:21 -08:00
Islam AbdelRahman
aececc209e Introduce ReadOptions::pin_data (support zero copy for keys)
Summary:
This patch update the Iterator API to introduce new functions that allow users to keep the Slices returned by key() valid as long as the Iterator is not deleted

ReadOptions::pin_data : If true keep loaded blocks in memory as long as the iterator is not deleted
Iterator::IsKeyPinned() : If true, this mean that the Slice returned by key() is valid as long as the iterator is not deleted

Also add a new option BlockBasedTableOptions::use_delta_encoding to allow users to disable delta_encoding if needed.

Benchmark results (using https://phabricator.fb.com/P20083553)

```
// $ du -h /home/tec/local/normal.4K.Snappy/db10077
// 6.1G    /home/tec/local/normal.4K.Snappy/db10077

// $ du -h /home/tec/local/zero.8K.LZ4/db10077
// 6.4G    /home/tec/local/zero.8K.LZ4/db10077

// Benchmarks for shard db10077
// _build/opt/rocks/benchmark/rocks_copy_benchmark \
//      --normal_db_path="/home/tec/local/normal.4K.Snappy/db10077" \
//      --zero_db_path="/home/tec/local/zero.8K.LZ4/db10077"

// First run
// ============================================================================
// rocks/benchmark/RocksCopyBenchmark.cpp          relative  time/iter  iters/s
// ============================================================================
// BM_StringCopy                                                 1.73s  576.97m
// BM_StringPiece                                   103.74%      1.67s  598.55m
// ============================================================================
// Match rate : 1000000 / 1000000

// Second run
// ============================================================================
// rocks/benchmark/RocksCopyBenchmark.cpp          relative  time/iter  iters/s
// ============================================================================
// BM_StringCopy                                              611.99ms     1.63
// BM_StringPiece                                   203.76%   300.35ms     3.33
// ============================================================================
// Match rate : 1000000 / 1000000
```

Test Plan: Unit tests

Reviewers: sdong, igor, anthony, yhchiang, rven

Reviewed By: rven

Subscribers: dhruba, lovro, adsharma

Differential Revision: https://reviews.facebook.net/D48999
2015-12-16 12:08:30 -08:00
Dmitri Smirnov
236fe21c92 Enable MS compiler warning c4244.
Mostly due to the fact that there are differences in sizes of int,long
  on 64 bit systems vs GNU.
2015-12-11 16:47:34 -08:00
agiardullo
3bfd3d39a3 Use SST files for Transaction conflict detection
Summary:
Currently, transactions can fail even if there is no actual write conflict.  This is due to relying on only the memtables to check for write-conflicts.  Users have to tune memtable settings to try to avoid this, but it's hard to figure out exactly how to tune these settings.

With this diff, TransactionDB will use both memtables and SST files to determine if there are any write conflicts.  This relies on the fact that BlockBasedTable stores sequence numbers for all writes that happen after any open snapshot.  Also, D50295 is needed to prevent SingleDelete from disappearing writes (the TODOs in this test code will be fixed once the other diff is approved and merged).

Note that Optimistic transactions will still rely on tuning memtable settings as we do not want to read from SST while on the write thread.  Also, memtable settings can still be used to reduce how often TransactionDB needs to read SST files.

Test Plan: unit tests, db bench

Reviewers: rven, yhchiang, kradhakrishnan, IslamAbdelRahman, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb, yoshinorim

Differential Revision: https://reviews.facebook.net/D50475
2015-12-11 12:34:11 -08:00
sdong
9d0b8f19d9 plain table reader: avoid re-read the same position for index and data in non-mmap mode
Summary: In non-mmap mode, plain table reader can issue two pread() for index checking and reading the actual data, although it's for the same location. By reusing the key decoder, we reuse the buffer used for the two to avoid it.

Test Plan: Run unit tests. Run table_reader_bench and see from strace the repeat read cases to disappear.

Reviewers: anthony, yhchiang, rven, kradhakrishnan, IslamAbdelRahman

Reviewed By: IslamAbdelRahman

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D50949
2015-11-18 16:49:08 -08:00
sdong
6170fec251 Fix build broken by previous commit of "option helper refactor"
Summary:
The commit of option helper refactor broken the build:
(1) a git merge problem
(2) some uncaught compiler warning
Fix it.

Test Plan: Make sure "make all" passes

Reviewers: anthony, IslamAbdelRahman, rven, kradhakrishnan, yhchiang

Reviewed By: yhchiang

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D50943
2015-11-17 16:52:54 -08:00
Siying Dong
3a6643c2fd Merge pull request #805 from SherlockNoMad/OptionHelperFix
Option Helper Refactoring
2015-11-17 16:24:52 -08:00
Islam AbdelRahman
a163cc2d5a Lint everything
Summary:
```
arc2 lint --everything
```

run the linter on the whole code repo to fix exisitng lint issues

Test Plan: make check -j64

Reviewers: sdong, rven, anthony, kradhakrishnan, yhchiang

Reviewed By: yhchiang

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D50769
2015-11-16 12:56:21 -08:00
Yueh-Hsuan Chiang
e11f676e34 Add OptionsUtil::LoadOptionsFromFile() API
Summary:
This patch adds OptionsUtil::LoadOptionsFromFile() and
OptionsUtil::LoadLatestOptionsFromDB(), which allow developers
to construct DBOptions and ColumnFamilyOptions from a RocksDB
options file.  Note that most pointer-typed options such as
merge_operator will not be constructed.

With this API, developers no longer need to remember all the
options in order to reopen an existing rocksdb instance like
the following:

  DBOptions db_options;
  std::vector<std::string> cf_names;
  std::vector<ColumnFamilyOptions> cf_opts;

  // Load primitive-typed options from an existing DB
  OptionsUtil::LoadLatestOptionsFromDB(
      dbname, &db_options, &cf_names, &cf_opts);

  // Initialize necessary pointer-typed options
  cf_opts[0].merge_operator.reset(new MyMergeOperator());
  ...

  // Construct the vector of ColumnFamilyDescriptor
  std::vector<ColumnFamilyDescriptor> cf_descs;
  for (size_t i = 0; i < cf_opts.size(); ++i) {
    cf_descs.emplace_back(cf_names[i], cf_opts[i]);
  }

  // Open the DB
  DB* db = nullptr;
  std::vector<ColumnFamilyHandle*> cf_handles;
  auto s = DB::Open(db_options, dbname, cf_descs,
                    &handles, &db);

Test Plan:
Augment existing tests in column_family_test
options_test
db_test

Reviewers: igor, IslamAbdelRahman, sdong, anthony

Reviewed By: anthony

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D49095
2015-11-12 06:52:43 -08:00
Islam AbdelRahman
838676c17b Revert "Adding new table properties"
Summary:
Reverting https://reviews.facebook.net/D34269 for now
after I landed it a flaky test started continuously failing, I am almost sure this patch is not related to the test but I will revert it until I figure out why it's failing

Test Plan: make check

Reviewers: kradhakrishnan

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D50385
2015-11-06 16:49:38 -08:00
Islam AbdelRahman
5b9ce1a323 Merge pull request #820 from yuslepukhin/enable_compiler_warnings
Enable Windows warnings C4307 C4309 C4512 C4701
2015-11-06 12:08:25 -08:00
Dmitri Smirnov
20f57b1715 Enable Windows warnings C4307 C4309 C4512 C4701
Enable C4307 'operator' : integral constant overflow
  Longs and ints on Windows are 32-bit hence the overflow
  Enable C4309 'conversion' : truncation of constant value
  Enable C4512 'class' : assignment operator could not be generated
  Enable C4701 Potentially uninitialized local variable 'name' used
2015-11-06 11:34:06 -08:00
Islam AbdelRahman
8be568a9c2 Adding new table properties
Summary:
This diff introduce new table properties that will be written for block based tables
These properties are
  - comparator name
  - merge operator name
  - property collectors names

Test Plan:
  - Added a new unit test to verify that these tests are written/read correctly
  - Running all other tests right now (wont land until all tests finish)

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

Reviewed By: yhchiang

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D34269
2015-11-06 11:19:01 -08:00
Islam AbdelRahman
f31442fb5c Merge pull request #803 from SherlockNoMad/SkipFlush
Add Option to Skip Flushing in TableBuilder
2015-11-02 14:56:11 -08:00
SherlockNoMad
df7ed91ef9 Fix white space at end of line 2015-11-02 14:12:29 -08:00
SherlockNoMad
ccc8c10c0c Move skip_table_builder_flush to BlockBasedTableOption 2015-10-30 18:33:01 -07:00
SherlockNoMad
84992d6475 Option Helper Refactoring 2015-10-30 15:58:46 -07:00
SherlockNoMad
550af4ee68 Fix Travis Build Error 2015-10-29 22:41:57 -07:00
SherlockNoMad
a6dd0831d5 Add Option to Skip Flushing in TableBuilder 2015-10-29 22:10:25 -07:00
SherlockNoMad
b69b9b624e Support PlainTableOption in option_helper 2015-10-28 23:01:33 -07:00
Dmitri Smirnov
5c8f2ee786 Fix MockTable ID storage
On Windows two tests fail that use MockTable:
  flush_job_test and compaction_job_test with the following message:
  compaction_job_test_je.exe : Assertion failed: result.size() == 4,
  file c:\dev\rocksdb\rocksdb\table\mock_table.cc, line 110

  Investigation reveals that this failure occurs when a 4 byte
  ID written to a beginning of the physically open file (main
  contents remains in a in-memory map) can not be read back.

  The reason for the failure is that the ID is written directly
  to a WritableFile bypassing WritableFileWriter. The side effect of that
  is that pending_sync_ never becomes true so the file is never flushed,
  however, the direct cause of the failure is that the filesize_ member
  of the WritableFileWriter remains zero. At Close() the file is truncated
  to that size and the file becomes empty so the ID can not be read back.
2015-10-28 10:53:14 -07:00
Venkatesh Radhakrishnan
a98fbacfa0 Moving memtable related files from util to a new directory memtable
Summary:
We are cleaning up dependencies.
This diff takes a first step at moving memtable files to their own
directory called memtable. In future diffs, we will move other memtable
files from db to memtable.

Test Plan: make check

Reviewers: sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D48915
2015-10-16 14:10:33 -07:00
sdong
35ad531be3 Seperate InternalIterator from Iterator
Summary:
Separate a new class InternalIterator from class Iterator, when the look-up is done internally, which also means they operate on key with sequence ID and type.

This change will enable potential future optimizations but for now InternalIterator's functions are still the same as Iterator's.
At the same time, separate the cleanup function to a separate class and let both of InternalIterator and Iterator inherit from it.

Test Plan: Run all existing tests.

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

Reviewed By: rven

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D48549
2015-10-13 15:32:13 -07:00
Islam AbdelRahman
1fe78a4073 Fix tests failing in ROCKSDB_LITE
Summary:
Fix tests that compile under ROCKSDB_LITE but currently failing.

table_test:
RandomizedLongDB test is using internal stats which is not supported in ROCKSDB_LITE

compaction_job_test:
Using CompactionJobStats which is not supported

perf_context_test:
KeyComparisonCount test try to open DB in ReadOnly mode which is not supported

Test Plan: run the tests under ROCKSDB_LITE

Reviewers: yhchiang, sdong, igor

Reviewed By: igor

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D48585
2015-10-13 10:32:05 -07:00
Alexey Maykov
3d07b815f6 Passing table properties to compaction callback
Summary: It would be nice to have and access to table properties in compaction callbacks. In MyRocks project, it will make possible to update optimizer statistics online.

Test Plan: ran the unit test. Ran myrocks with the new way of collecting stats.

Reviewers: igor, rven, yhchiang

Reviewed By: yhchiang

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D48267
2015-10-09 18:10:55 -07:00
sdong
776bd8d5eb Pass column family ID to table property collector
Summary: Pass column family ID through TablePropertiesCollectorFactory::CreateTablePropertiesCollector() so that users can identify which column family this file is for and handle it differently.

Test Plan: Add unit test scenarios in tests related to table properties collectors to verify the information passed in is correct.

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

Reviewed By: IslamAbdelRahman

Subscribers: yoshinorim, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D48411
2015-10-09 14:36:51 -07:00
Islam AbdelRahman
51fa7ecec5 Bytes read/written from cache statistics
Summary: Add 2 new counters BLOCK_CACHE_BYTES_WRITE, BLOCK_CACHE_BYTES_READ to keep track of how many bytes were written to the cache and how many bytes that we read from cache

Test Plan: make check

Reviewers: sdong, yhchiang, igor

Reviewed By: igor

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D48195
2015-10-07 15:17:20 -07:00
dyniusz
a065cdb388 bloom hit/miss stats for SST and memtable
Summary:
	hit and miss bloom filter stats for memtable and SST
	stats added to perf_context struct
	key matches and prefix matches combined into one stat

Test Plan: unit test veryfing the functionality added, see BloomStatsTest in db_test.cc for details

Reviewers: yhchiang, igor, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D47859
2015-10-07 11:23:20 -07:00
Igor Canadi
d80ce7f99a Compaction filter on merge operands
Summary:
Since Andres' internship is over, I took over https://reviews.facebook.net/D42555 and rebased and simplified it a bit.

The behavior in this diff is a bit simpler than in D42555:
* only merge operators are passed through FilterMergeValue(). If fitler function returns true, the merge operator is ignored
* compaction filter is *not* called on: 1) results of merge operations and 2) base values that are getting merged with merge operands (the second case was also true in previous diff)

Do we also need a compaction filter to get called on merge results?

Test Plan: make && make check

Reviewers: lovro, tnovak, rven, yhchiang, sdong

Reviewed By: sdong

Subscribers: noetzli, kolmike, leveldb, dhruba, sdong

Differential Revision: https://reviews.facebook.net/D47847
2015-10-07 09:30:03 -07:00
sdong
a70d08ec07 Fix the bug of using freed memory introduced by recent plain table reader patch
Summary: Recent patch introduced a bug that if non-mmap mode is used, in prefix encoding case, there is a resizing of cur_key_ within the same prefix, we still read prefix from the released buffer. It fails ASAN tests and this commit fixes it.

Test Plan: Run the ASAN tests for the failing test case.

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

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D47457
2015-09-23 16:16:26 -07:00
Islam AbdelRahman
f03b5c987b Add experimental DB::AddFile() to plug sst files into empty DB
Summary:
This is an initial version of bulk load feature

This diff allow us to create sst files, and then bulk load them later, right now the restrictions for loading an sst file are
(1) Memtables are empty
(2) Added sst files have sequence number = 0, and existing values in database have sequence number = 0
(3) Added sst files values are not overlapping

Test Plan: unit testing

Reviewers: igor, ott, sdong

Reviewed By: sdong

Subscribers: leveldb, ott, dhruba

Differential Revision: https://reviews.facebook.net/D39081
2015-09-23 12:42:43 -07:00
sdong
df34aea331 PlainTableReader to support non-mmap mode
Summary:
PlainTableReader now only allows mmap-mode. Add the support to non-mmap mode for more flexibility.
Refactor the codes to move all logic of reading data to PlainTableKeyDecoder, and consolidate the calls to Read() call and ReadVarint32() call. Implement the calls for both of mmap and non-mmap case seperately. For non-mmap mode, make copy of keys in several places when we need to move the buffer after reading the keys.

Test Plan: Add the mode of non-mmap case in plain_table_db_test. Run it in valgrind mode too.

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D47187
2015-09-23 11:41:07 -07:00
sdong
d746eaad5e RandomAccessFileReader should not inherit RandomAccessFile
Summary: RandomAccessFileReader unnecessarily inherited RandomAccessFile, which can introduce unnecessarily extra costs. Remove it.

Test Plan: Run all existing tests

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

Reviewed By: IslamAbdelRahman

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D47409
2015-09-23 11:00:41 -07:00
Andres Noetzli
014fd55adc Support for SingleDelete()
Summary:
This patch fixes #7460559. It introduces SingleDelete as a new database
operation. This operation can be used to delete keys that were never
overwritten (no put following another put of the same key). If an overwritten
key is single deleted the behavior is undefined. Single deletion of a
non-existent key has no effect but multiple consecutive single deletions are
not allowed (see limitations).

In contrast to the conventional Delete() operation, the deletion entry is
removed along with the value when the two are lined up in a compaction. Note:
The semantics are similar to @igor's prototype that allowed to have this
behavior on the granularity of a column family (
https://reviews.facebook.net/D42093 ). This new patch, however, is more
aggressive when it comes to removing tombstones: It removes the SingleDelete
together with the value whenever there is no snapshot between them while the
older patch only did this when the sequence number of the deletion was older
than the earliest snapshot.

Most of the complex additions are in the Compaction Iterator, all other changes
should be relatively straightforward. The patch also includes basic support for
single deletions in db_stress and db_bench.

Limitations:
- Not compatible with cuckoo hash tables
- Single deletions cannot be used in combination with merges and normal
  deletions on the same key (other keys are not affected by this)
- Consecutive single deletions are currently not allowed (and older version of
  this patch supported this so it could be resurrected if needed)

Test Plan: make all check

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

Reviewed By: igor

Subscribers: maykov, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 11:42:56 -07:00
Igor Canadi
81a61d75dc Skipped tests shouldn't be failures [part 2]
Summary: Missed one file in the previous commit

Test Plan: compiles

Reviewers: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D47055
2015-09-15 22:59:53 -07:00
Islam AbdelRahman
45e9e4f0bb Refactor NewTableReader to accept TableReaderOptions
Summary:
Refactoring NewTableReader to accept TableReaderOptions
This will make it easier to add new options in the future, for example in this diff https://reviews.facebook.net/D46071

Test Plan: run existing tests

Reviewers: igor, yhchiang, anthony, rven, sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D46179
2015-09-11 11:36:33 -07:00
Andres Noetzli
6bdc484fd8 Added Equal method to Comparator interface
Summary:
In some cases, equality comparisons can be done more efficiently than three-way
comparisons. There are quite a few places in the code where we only care about
equality. This patch adds an Equal() method that defaults to using the
Compare() method.

Test Plan: make clean all check

Reviewers: rven, anthony, yhchiang, igor, sdong

Reviewed By: igor

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D46233
2015-09-08 15:30:49 -07:00
Igor Canadi
14456aea52 Fix compile
Summary: There was a merge conflict with https://reviews.facebook.net/D45993

Test Plan: make check

Reviewers: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D46065
2015-09-02 16:05:53 -07:00
Igor Canadi
76f286cc82 Optimize bloom filter cache misses
Summary:
This optimizes the case when (cache_index_and_filter_blocks=1) and bloom filter is not present in the cache.

Previously we did:
1. Read meta block from file
2. Read the filter position from the meta block
3. Read the filter

Now, we pre-load the filter position on Table::Open(), so we can skip steps (1) and (2) on bloom filter cache miss. Instead of 2 IOs, we do only 1.

Test Plan: make check

Reviewers: sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D46047
2015-09-02 15:36:47 -07:00
Andres Noetzli
3c9cef1eed Unified maps with Comparator for sorting, other cleanup
Summary:
This diff is a collection of cleanups that were initially part of D43179.
Additionally it adds a unified way of defining key-value maps that use a
Comparator for sorting (this was previously implemented in four different
places).

Test Plan: make clean check all

Reviewers: rven, anthony, yhchiang, sdong, igor

Reviewed By: igor

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D45993
2015-09-02 13:58:22 -07:00
sdong
7a0dbdf3ac Add ZSTD (not final format) compression type
Summary: Add ZSTD compression type. The same way as adding LZ4.

Test Plan: run all tests. Generate files in db_bench. Make sure reads succeed. But the SST files cannot be opened in older versions. Also some other adhoc tests.

Reviewers: rven, anthony, IslamAbdelRahman, kradhakrishnan, igor

Reviewed By: igor

Subscribers: MarkCallaghan, maykov, yoshinorim, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D45747
2015-08-28 11:01:13 -07:00
Yueh-Hsuan Chiang
6996de87af Expose per-level aggregated table properties via GetProperty()
Summary:
This patch adds "rocksdb.aggregated-table-properties"
and "rocksdb.aggregated-table-properties-at-levelN", the former
returns the aggreated table properties of a column family,
while the later returns the aggregated table properties
of the specified level N.

Test Plan: Added tests in db_test

Reviewers: igor, sdong, IslamAbdelRahman, anthony

Reviewed By: anthony

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D45087
2015-08-25 12:03:54 -07:00
sdong
c852968465 db_iter_test: add more test cases for the data race bug
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
2015-08-21 12:14:12 -07:00
sdong
4637207120 Add test case to repro the mispositional iterator in a low-chance data race case
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
2015-08-12 10:50:52 -07:00
Andres Notzli
68f934355a Better CompactionJob testing
Summary:
Changed compaction_job_test to support better/more thorough
tests and added two tests. Also changed MockFileContents
to order using InternalKeyComparator.

Test Plan: make compaction_job_test && ./compaction_job_test; make all && make check

Reviewers: sdong, rven, igor, yhchiang, anthony

Reviewed By: anthony

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D42837
2015-08-07 21:59:51 -07:00
Andres Notzli
c465071029 Removing duplicate code
Summary:
While working on https://reviews.facebook.net/D43179 , I found
duplicate code in the tests. This patch removes it.

Test Plan: make clean all check

Reviewers: igor, sdong, rven, anthony, yhchiang

Reviewed By: yhchiang

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D43263
2015-08-05 07:33:27 -07:00
agiardullo
064294081b Improved FileExists API
Summary: Add new CheckFileExists method.  Considered changing the FileExists api but didn't want to break anyone's builds.

Test Plan: unit tests

Reviewers: yhchiang, igor, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D42003
2015-07-20 17:20:40 -07:00
Islam AbdelRahman
4853e228ef Make table_test runnable in ROCKSDB_LITE
Summary: Remove plain table tests from table_test since plain table is not supported in ROCKSDB_LITE

Test Plan: table_test

Reviewers: igor, sdong, yhchiang

Reviewed By: yhchiang

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D42153
2015-07-20 11:09:14 -07:00
Islam AbdelRahman
cf6a7bebc8 Block cuckoo table tests in ROCKSDB_LITE
Summary: Cuckoo table is not supported in ROCKSDB_LITE, blocking it's tests

Test Plan:
cuckoo_table_builder_test
cuckoo_table_db_test
cuckoo_table_reader_test

Reviewers: sdong, igor, yhchiang

Reviewed By: yhchiang

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D42141
2015-07-20 10:50:46 -07:00
sdong
6e9fbeb27c Move rate_limiter, write buffering, most perf context instrumentation and most random kill out of Env
Summary: We want to keep Env a think layer for better portability. Less platform dependent codes should be moved out of Env. In this patch, I create a wrapper of file readers and writers, and put rate limiting, write buffering, as well as most perf context instrumentation and random kill out of Env. It will make it easier to maintain multiple Env in the future.

Test Plan: Run all existing unit tests.

Reviewers: anthony, kradhakrishnan, IslamAbdelRahman, yhchiang, igor

Reviewed By: igor

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D42321
2015-07-17 16:58:18 -07:00
Andres Notzli
1d20fa9d0f Fixed and simplified merge_helper
Summary:
MergeUntil was not reporting a success when merging an operand with
a Value/Deletion despite the comments in MergeHelper and CompactionJob
indicating otherwise. This lead to operands being written to the compaction
output unnecessarily:

M1 M2 M3 P M4 M5 --> (P+M1+M2+M3) M2 M3 M4 M5 (before the diff)
M1 M2 M3 P M4 M5 --> (P+M1+M2+M3) M4 M5 (after the diff)

In addition, the code handling Values/Deletion was basically identical.
This patch unifies the code. Finally, this patch also adds testing for
merge_helper.

Test Plan: make && make check

Reviewers: sdong, rven, yhchiang, tnovak, igor

Reviewed By: igor

Subscribers: tnovak, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D42351
2015-07-17 09:27:24 -07:00
Dmitri Smirnov
d1a457181d Ensure Windows build w/o port/port.h in public headers
- Remove make file defines from public headers and use _WIN32 because it is compiler defined
 - use __GNUC__ and __clang__ to guard non-portable attributes
 - add #include "port/port.h" to some new .cc files.
 - minor changes in CMakeLists to reflect recent changes
2015-07-16 12:10:16 -07:00
lovro
e1c99e10c1 Replace std::priority_queue in MergingIterator with custom heap, take 2
Summary: Repeat of b6655a679d (reverted in b7a2369fb2) with a proper fix for the issue that 57d216ea65 was trying to fix.

Test Plan:
make check

for i in $(seq 100); do ./db_stress --test_batches_snapshots=1 --threads=32 --write_buffer_size=4194304 --destroy_db_initially=0 --reopen=20 --readpercent=45 --prefixpercent=5 --writepercent=35 --delpercent=5 --iterpercent=10 --db=/tmp/rocksdb_crashtest_KdCI5F --max_key=100000000 --mmap_read=0 --block_size=16384 --cache_size=1048576 --open_files=500000 --verify_checksum=1 --sync=0 --progress_reports=0 --disable_wal=0 --disable_data_sync=1 --target_file_size_base=2097152 --target_file_size_multiplier=2 --max_write_buffer_number=3 --max_background_compactions=20 --max_bytes_for_level_base=10485760 --filter_deletes=0 --memtablerep=prefix_hash --prefix_size=7 --ops_per_thread=200 || break; done

Reviewers: anthony, sdong, igor, yhchiang

Reviewed By: igor, yhchiang

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D41391
2015-07-15 03:34:40 -07:00
sdong
f9728640f3 "make format" against last 10 commits
Summary: This helps Windows port to format their changes, as discussed. Might have formatted some other codes too becasue last 10 commits include more.

Test Plan: Build it.

Reviewers: anthony, IslamAbdelRahman, kradhakrishnan, yhchiang, igor

Reviewed By: igor

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D41961
2015-07-13 13:50:18 -07:00
sdong
76d3cd3286 Fix public API dependency on internal codes and dependency on MAX_INT32
Summary:
Public API depends on port/port.h which is wrong. Fix it.
Also with gcc 4.8.1 build was broken as MAX_INT32 was not recognized. Fix it by using ::max in linux.

Test Plan: Build it and try to build an external project on top of it.

Reviewers: anthony, yhchiang, kradhakrishnan, igor

Reviewed By: igor

Subscribers: yoshinorim, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D41745
2015-07-11 10:32:11 -07:00
Siying Dong
e41cbd9c2f Merge pull request #646 from yuslepukhin/ms_win_port
Windows Port from Microsoft
2015-07-10 15:53:39 -07:00
sdong
041b6f95a2 perf_context: report time spent on reading index and bloom blocks
Summary: Add a perf context counter to help users figure out time spent on reading indexes and bloom filter blocks.

Test Plan: Will write a unit test

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D41433
2015-07-10 14:45:42 -07:00
Dmitri Smirnov
c903ccc4c2 Merge from github/master 2015-07-09 18:01:08 -07:00
unknown
5c79132335 Revert the changes related to Options, as requested to seperate them into
a different patch.
2015-07-09 11:31:42 -07:00
Dmitri Smirnov
ef4b87f1b2 Commit both PR and internal code review changes 2015-07-07 16:58:20 -07:00
Yueh-Hsuan Chiang
b7a2369fb2 Revert "Replace std::priority_queue in MergingIterator with custom heap"
Summary:
This patch reverts "Replace std::priority_queue in MergingIterator
with custom heap" (commit commit b6655a679d)
as it causes db_stress failure.

Test Plan: ./db_stress --test_batches_snapshots=1 --threads=32 --write_buffer_size=4194304 --destroy_db_initially=0 --reopen=20 --readpercent=45 --prefixpercent=5 --writepercent=35 --delpercent=5 --iterpercent=10 --db=/tmp/rocksdb_crashtest_KdCI5F --max_key=100000000 --mmap_read=0 --block_size=16384 --cache_size=1048576 --open_files=500000 --verify_checksum=1 --sync=0 --progress_reports=0 --disable_wal=0 --disable_data_sync=1 --target_file_size_base=2097152 --target_file_size_multiplier=2 --max_write_buffer_number=3 --max_background_compactions=20 --max_bytes_for_level_base=10485760 --filter_deletes=0 --memtablerep=prefix_hash --prefix_size=7 --ops_per_thread=200 --kill_random_test=97

Reviewers: igor, anthony, lovro, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D41343
2015-07-07 14:45:20 -07:00
Yueh-Hsuan Chiang
57d216ea65 Remove assert(current_ == CurrentReverse()) in MergingIterator::Prev()
Summary:
Remove assert(current_ == CurrentReverse()) in MergingIterator::Prev()
because it is possible to have some keys larger than the seek-key
inserted between Seek() and SeekToLast(), which makes current_ not
equal to CurrentReverse().

Test Plan: db_stress

Reviewers: igor, sdong, IslamAbdelRahman, anthony

Reviewed By: anthony

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D41331
2015-07-07 12:45:06 -07:00
Yueh-Hsuan Chiang
685582a0b4 Revert two diffs related to DBIter::FindPrevUserKey()
Summary:
This diff reverts the following two previous diffs related to
DBIter::FindPrevUserKey(), which makes db_stress unstable.
We should bake a better fix for this.

* "Fix a comparison in DBIter::FindPrevUserKey()"
  ec70fea4c4.

* "Fixed endless loop in DBIter::FindPrevUserKey()"
  acee2b08a2.

Test Plan: db_stress

Reviewers: anthony, igor, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D41301
2015-07-07 11:36:24 -07:00
lovro
b6655a679d Replace std::priority_queue in MergingIterator with custom heap
Summary:
While profiling compaction in our service I noticed a lot of CPU (~15% of compaction) being spent in MergingIterator and key comparison.  Looking at the code I found MergingIterator was (understandably) using std::priority_queue for the multiway merge.

Keys in our dataset include sequence numbers that increase with time.  Adjacent keys in an L0 file are very likely to be adjacent in the full database.  Consequently, compaction will often pick a chunk of rows from the same L0 file before switching to another one.  It would be great to avoid the O(log K) operation per row while compacting.

This diff replaces std::priority_queue with a custom binary heap implementation.  It has a "replace top" operation that is cheap when the new top is the same as the old one (i.e. the priority of the top entry is decreased but it still stays on top).

Test Plan:
make check

To test the effect on performance, I generated databases with data patterns that mimic what I describe in the summary (rows have a mostly increasing sequence number).  I see a 10-15% CPU decrease for compaction (and a matching throughput improvement on tmpfs).  The exact improvement depends on the number of L0 files and the amount of locality.  Performance on randomly distributed keys seems on par with the old code.

Reviewers: kailiu, sdong, igor

Reviewed By: igor

Subscribers: yoshinorim, dhruba, tnovak

Differential Revision: https://reviews.facebook.net/D29133
2015-07-06 04:24:09 -07:00
Yueh-Hsuan Chiang
acee2b08a2 Fixed endless loop in DBIter::FindPrevUserKey()
Summary: Fixed endless loop in DBIter::FindPrevUserKey()

Test Plan: ./db_stress --test_batches_snapshots=1 --threads=32 --write_buffer_size=4194304 --destroy_db_initially=0 --reopen=20 --readpercent=45 --prefixpercent=5 --writepercent=35 --delpercent=5 --iterpercent=10 --db=/tmp/rocksdb_crashtest_KdCI5F --max_key=100000000 --mmap_read=0 --block_size=16384 --cache_size=1048576 --open_files=500000 --verify_checksum=1 --sync=0 --progress_reports=0 --disable_wal=0 --disable_data_sync=1 --target_file_size_base=2097152 --target_file_size_multiplier=2 --max_write_buffer_number=3 --max_background_compactions=20 --max_bytes_for_level_base=10485760 --filter_deletes=0 --memtablerep=prefix_hash --prefix_size=7 --ops_per_thread=200 --kill_random_test=97

Reviewers: tnovak, igor, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D41085
2015-07-02 16:10:31 -07:00
Dmitri Smirnov
9dbde7277c Merge remote-tracking branch 'origin' into ms_win_port 2015-07-02 11:34:22 -07:00
Dmitri Smirnov
18285c1e2f Windows Port from Microsoft
Summary: Make RocksDb build and run on Windows to be functionally
 complete and performant. All existing test cases run with no
 regressions. Performance numbers are in the pull-request.

 Test plan: make all of the existing unit tests pass, obtain perf numbers.

 Co-authored-by: Praveen Rao praveensinghrao@outlook.com
 Co-authored-by: Sherlock Huang baihan.huang@gmail.com
 Co-authored-by: Alex Zinoviev alexander.zinoviev@me.com
 Co-authored-by: Dmitri Smirnov dmitrism@microsoft.com
2015-07-01 16:13:56 -07:00
sdong
05e2831966 Allocate LevelFileIteratorState and LevelFileNumIterator from DB iterator's arena
Summary: Try to allocate LevelFileIteratorState and LevelFileNumIterator from DB iterator's arena, instead of calling malloc and free.

Test Plan: valgrind check

Reviewers: rven, yhchiang, anthony, kradhakrishnan, igor

Reviewed By: igor

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D40929
2015-06-30 17:30:38 -07:00
Igor Canadi
0a019d74a0 Use malloc_usable_size() for accounting block cache size
Summary:
Currently, when we insert something into block cache, we say that the block cache capacity decreased by the size of the block. However, size of the block might be less than the actual memory used by this object. For example, 4.5KB block will actually use 8KB of memory. So even if we configure block cache to 10GB, our actually memory usage of block cache will be 20GB!

This problem showed up a lot in testing and just recently also showed up in MongoRocks production where we were using 30GB more memory than expected.

This diff will fix the problem. Instead of counting the block size, we will count memory used by the block. That way, a block cache configured to be 10GB will actually use only 10GB of memory.

I'm using non-portable function and I couldn't find info on portability on Google. However, it seems to work on Linux, which will cover majority of our use-cases.

Test Plan:
1. fill up mongo instance with 80GB of data
2. restart mongo with block cache size configured to 10GB
3. do a table scan in mongo
4. memory usage before the diff: 12GB. memory usage after the diff: 10.5GB

Reviewers: sdong, MarkCallaghan, rven, yhchiang

Reviewed By: yhchiang

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D40635
2015-06-26 11:48:09 -07:00
Giuseppe Ottaviano
782a1590f9 Implement a table-level row cache
Summary:
Implementation of a table-level row cache.
It only caches point queries done through the `DB::Get` interface, queries done through the `Iterator` interface will completely skip the cache.

Supports snapshots and merge operations.

Test Plan: Ran `make valgrind_check commit-prereq`

Reviewers: igor, philipp, sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D39849
2015-06-23 10:25:45 -07:00
sdong
6df589b446 Add TablePropertiesCollector::NeedCompact() to suggest DB to further compact output files
Summary:
It is experimental. Allow users to return from a call back function TablePropertiesCollector::NeedCompact(), based on the data in the file.
It can be used to allow users to suggest DB to clear up delete tombstones faster.

Test Plan: Add a unit test.

Reviewers: igor, yhchiang, kradhakrishnan, rven

Reviewed By: rven

Subscribers: yoshinorim, MarkCallaghan, maykov, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D39585
2015-06-05 20:18:21 -07:00
agiardullo
dc9d70de65 Optimistic Transactions
Summary: Optimistic transactions supporting begin/commit/rollback semantics.  Currently relies on checking the memtable to determine if there are any collisions at commit time.  Not yet implemented would be a way of enuring the memtable has some minimum amount of history so that we won't fail to commit when the memtable is empty.  You should probably start with transaction.h to get an overview of what is currently supported.

Test Plan: Added a new test, but still need to look into stress testing.

Reviewers: yhchiang, igor, rven, sdong

Reviewed By: sdong

Subscribers: adamretter, MarkCallaghan, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D33435
2015-05-29 14:36:35 -07:00
Igor Canadi
dbd95b7532 Add more table properties to EventLogger
Summary:
Example output:

    {"time_micros": 1431463794310521, "job": 353, "event": "table_file_creation", "file_number": 387, "file_size": 86937, "table_info": {"data_size": "81801", "index_size": "9751", "filter_size": "0", "raw_key_size": "23448", "raw_average_key_size": "24.000000", "raw_value_size": "990571", "raw_average_value_size": "1013.890481", "num_data_blocks": "245", "num_entries": "977", "filter_policy_name": "", "kDeletedKeys": "0"}}

Also fixed a bug where BuildTable() in recovery was passing Env::IOHigh argument into paranoid_checks_file parameter.

Test Plan: make check + check out the output in the log

Reviewers: sdong, rven, yhchiang

Reviewed By: yhchiang

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D38343
2015-05-12 15:53:55 -07:00
clark.kang
6ede020dc4 fix typos 2015-04-25 18:14:27 +09:00
sdong
98a44559d5 Build for CYGWIN
Summary:
Make it build for CYGWIN.
Need to define "-std=gnu++11" instead of "-std=c++11" and use some replacement functions.

Test Plan: Build it and run some unit tests in CYGWIN

Reviewers: yhchiang, rven, anthony, kradhakrishnan, igor

Reviewed By: igor

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D37605
2015-04-23 21:33:44 -07:00
sdong
fcb206b667 SyncPoint to allow a callback with an argument and use it to get DBTest.DynamicLevelCompressionPerLevel2 more straight-forward
Summary:
Allow users to give a callback function with parameter using sync point, so more complicated verification can be done in tests.
Use it in DBTest.DynamicLevelCompressionPerLevel2 so that failures will be more easy to debug.

Test Plan: Run all tests. Run DBTest.DynamicLevelCompressionPerLevel2 with valgrind check.

Reviewers: rven, yhchiang, anthony, kradhakrishnan, igor

Reviewed By: igor

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D36999
2015-04-14 16:18:50 -07:00
Igor Canadi
5e067a7b19 Clean up compression logging
Summary: Now we add warnings when user configures compression and the compression is not supported.

Test Plan:
Configured compression to non-supported values. Observed messages in my log:

    2015/03/26-12:17:57.586341 7ffb8a496840 [WARN] Compression type chosen for level 2 is not supported: LZ4. RocksDB will not compress data on level 2.

    2015/03/26-12:19:10.768045 7f36f15c5840 [WARN] Compression type chosen is not supported: LZ4. RocksDB will not compress data.

Reviewers: rven, sdong, yhchiang

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D35979
2015-04-06 12:50:44 -07:00
sdong
a45e7581b7 Avoid naming conflict of EntryType
Summary:
Fix build break on travis build:

$ OPT=-DTRAVIS V=1 make unity && make clean && OPT=-DTRAVIS V=1 make db_test && ./db_test

......

In file included from unity.cc:65:0:
./table/plain_table_key_coding.cc: In member function ‘rocksdb::Status rocksdb::PlainTableKeyDecoder::NextPrefixEncodingKey(const char*, const char*, rocksdb::ParsedInternalKey*, rocksdb::Slice*, size_t*, bool*)’:
./table/plain_table_key_coding.cc:224:3: error: reference to ‘EntryType’ is ambiguous
   EntryType entry_type;
   ^
In file included from ./db/table_properties_collector.h:9:0,
                 from ./db/builder.h:11,
                 from ./db/builder.cc:10,
                 from unity.cc:1:
./include/rocksdb/table_properties.h:81:6: note: candidates are: enum rocksdb::EntryType
 enum EntryType {
      ^
In file included from unity.cc:65:0:
./table/plain_table_key_coding.cc:16:6: note:                 enum rocksdb::{anonymous}::EntryType
 enum EntryType : unsigned char {
      ^
./table/plain_table_key_coding.cc:231:51: error: ‘entry_type’ was not declared in this scope
     const char* pos = DecodeSize(key_ptr, limit, &entry_type, &size);
                                                   ^
make: *** [unity.o] Error 1

Test Plan:
OPT=-DTRAVIS V=1 make unity

And make sure it doesn't break anymore.

Reviewers: yhchiang, kradhakrishnan, igor

Reviewed By: igor

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D36549
2015-04-06 11:49:13 -07:00
sdong
953a885ebf A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.

Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties

Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.

Reviewers: yhchiang, igor.sugak, rven, igor

Reviewed By: rven, igor

Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D35373
2015-04-06 10:27:21 -07:00
Anurag Indu
1e57f2bf2b Fix build
Test Plan: Running make all

Reviewers: sdong

Reviewed By: sdong

Subscribers: rven, yhchiang, igor, meyering, dhruba

Differential Revision: https://reviews.facebook.net/D35889
2015-03-24 17:00:28 -07:00
Anurag Indu
211ca26aee Fixing build issue
Summary: Fixing issues with get context function.

Test Plan: Run make commit-prereq

Reviewers: sdong, meyering, yhchiang

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D35853
2015-03-24 16:27:24 -07:00
Anurag Indu
3d1a924ff3 Adding stats for the merge and filter operation
Summary:
We have addded new stats and perf_context for measuring the merge and filter operation time consumption.
We have bounded all the merge operations within the GUARD statment and collected the total time for these operations in the DB.

Test Plan: WIP

Reviewers: rven, yhchiang, kradhakrishnan, igor, sdong

Reviewed By: sdong

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D34377
2015-03-24 14:42:04 -07:00
Igor Sugak
9405b5ef8f rocksdb: Remove #include "util/string_util.h" from util/testharness.h
Summary:
1. Manually deleted #include "util/string_util.h" from util/testharness.h
2.
```
% USE_CLANG=1 make all -j55 -k 2> build.log
% perl -naF: -E 'say $F[0] if /: error:/' build.log | sort -u | xargs sed -i '/#include "util\/testharness.h"/i #include "util\/string_util.h"'
```

Test Plan:
Make sure make all completes with no errors.
```
% make all -j55
```

Reviewers: meyering, igor, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D35493
2015-03-19 17:29:37 -07:00
Igor Sugak
b4b69e4f77 rocksdb: switch to gtest
Summary:
Our existing test notation is very similar to what is used in gtest. It makes it easy to adopt what is different.
In this diff I modify existing [[ https://code.google.com/p/googletest/wiki/Primer#Test_Fixtures:_Using_the_Same_Data_Configuration_for_Multiple_Te | test fixture ]] classes to inherit from `testing::Test`. Also for unit tests that use fixture class, `TEST` is replaced with `TEST_F` as required in gtest.

There are several custom `main` functions in our existing tests. To make this transition easier, I modify all `main` functions to fallow gtest notation. But eventually we can remove them and use implementation of `main` that gtest provides.

```lang=bash
% cat ~/transform
#!/bin/sh
files=$(git ls-files '*test\.cc')
for file in $files
do
  if grep -q "rocksdb::test::RunAllTests()" $file
  then
    if grep -Eq '^class \w+Test {' $file
    then
      perl -pi -e 's/^(class \w+Test) {/${1}: public testing::Test {/g' $file
      perl -pi -e 's/^(TEST)/${1}_F/g' $file
    fi
    perl -pi -e 's/(int main.*\{)/${1}::testing::InitGoogleTest(&argc, argv);/g' $file
    perl -pi -e 's/rocksdb::test::RunAllTests/RUN_ALL_TESTS/g' $file
  fi
done
% sh ~/transform
% make format
```

Second iteration of this diff contains only scripted changes.

Third iteration contains manual changes to fix last errors and make it compilable.

Test Plan:
Build and notice no errors.
```lang=bash
% USE_CLANG=1 make check -j55
```
Tests are still testing.

Reviewers: meyering, sdong, rven, igor

Reviewed By: igor

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D35157
2015-03-17 14:08:00 -07:00
Igor Sugak
9fd6edf81c rocksdb: Replace ASSERT* with EXPECT* in functions that does not return void value
Summary:
gtest does not use exceptions to fail a unit test by design, and `ASSERT*`s are implemented using `return`. As a consequence we cannot use `ASSERT*` in a function that does not return `void` value ([[ https://code.google.com/p/googletest/wiki/AdvancedGuide#Assertion_Placement | 1]]), and have to fix our existing code. This diff does this in a generic way, with no manual changes.

In order to detect all existing `ASSERT*` that are used in functions that doesn't return void value, I change the code to generate compile errors for such cases.

In `util/testharness.h` I defined `EXPECT*` assertions, the same way as `ASSERT*`, and redefined `ASSERT*` to return `void`. Then executed:

```lang=bash
% USE_CLANG=1 make all -j55 -k 2> build.log
% perl -naF: -e 'print "-- -number=".$F[1]." ".$F[0]."\n" if  /: error:/' \
build.log | xargs -L 1 perl -spi -e 's/ASSERT/EXPECT/g if $. == $number'
% make format
```
After that I reverted back change to `ASSERT*` in `util/testharness.h`. But preserved introduced `EXPECT*`, which is the same as `ASSERT*`. This will be deleted once switched to gtest.

This diff is independent and contains manual changes only in `util/testharness.h`.

Test Plan:
Make sure all tests are passing.
```lang=bash
% USE_CLANG=1 make check
```

Reviewers: igor, lgalanis, sdong, yufei.zhu, rven, meyering

Reviewed By: meyering

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D33333
2015-03-16 20:52:32 -07:00
Igor Sugak
95344346af rocksdb: Small refactoring before migrating to gtest
Summary: These changes are necessary to make tests look more generic, and avoid feature conflicts with gtest.

Test Plan:
Make sure no build errors, and all test are passing.
```
% make check
```

Reviewers: igor, meyering

Reviewed By: meyering

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D35145
2015-03-16 18:08:59 -07:00
sdong
e9de8b65a6 Change the way options.compression_per_level is used when options.level_compaction_dynamic_level_bytes=true
Summary:
Change the way options.compression_per_level is used when options.level_compaction_dynamic_level_bytes=true so that options.compression_per_level[1] determines compression for the level L0 is merged to, options.compression_per_level[2] to the level after that, etc.

Test Plan: run all tests

Reviewers: rven, yhchiang, kradhakrishnan, igor

Reviewed By: igor

Subscribers: yoshinorim, leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D34431
2015-03-11 13:14:52 -07:00
krad
f29b33c73b Add functionality to pre-fetch blocks specified by a key range to BlockBasedTable implementation.
Summary:
Pre-fetching is a common operation performed by data stores for
disk/flash based systems as part of database startup.

This is part of task 5197184.

Test Plan: Run the newly added unit test

Reviewers: rven, igor, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D33933
2015-03-02 17:07:03 -08:00
Sameet Agarwal
e7c434c364 Add columnfamily option optimize_filters_for_hits to optimize for key hits only
Summary:
    Summary:
    Added a new option to ColumnFamllyOptions  - optimize_filters_for_hits. This option can be used in the case where most
    accesses to the store are key hits and we dont need to optimize performance for key misses.
    This is useful when you have a very large database and most of your lookups succeed.  The option allows the store to
     not store and use filters in the last level (the largest level which contains data). These filters can take a large amount of
     space for large databases (in memory and on-disk). For the last level, these filters are only useful for key misses and not
     for key hits. If we are not optimizing for key misses, we can choose to not store these filters for that level.

    This option is only provided for BlockBasedTable. We skip the filters when we are compacting

Test Plan:
1. Modified db_test toalso run tests with an additonal option (skip_filters_on_last_level)
 2. Added another unit test to db_test which specifically tests that filters are being skipped

Reviewers: rven, igor, sdong

Reviewed By: sdong

Subscribers: lgalanis, yoshinorim, MarkCallaghan, rven, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D33717
2015-02-26 16:25:56 -08:00
Igor Sugak
62247ffa3b rocksdb: Add missing override
Summary:
When using latest clang (3.6 or 3.7/trunck) rocksdb is failing with many errors. Almost all of them are missing override errors. This diff adds missing override keyword. No manual changes.

Prerequisites: bear and clang 3.5 build with extra tools

```lang=bash
% USE_CLANG=1 bear make all # generate a compilation database http://clang.llvm.org/docs/JSONCompilationDatabase.html
% clang-modernize -p . -include . -add-override
% make format
```

Test Plan:
Make sure all tests are passing.
```lang=bash
% #Use default fb code clang.
% make check
```
Verify less error and no missing override errors.
```lang=bash
% # Have trunk clang present in path.
% ROCKSDB_NO_FBCODE=1 CC=clang CXX=clang++ make
```

Reviewers: igor, kradhakrishnan, rven, meyering, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D34077
2015-02-26 11:28:41 -08:00
krad
d9f4875e52 Disable pre-fetching of index and filter blocks for sst_dump_tool.
Summary:
BlockBasedTable pre-fetches the filter and index blocks on Open call.
This is an optimistic optimization targeted for runtime scenario. The
optimization is unnecessary for sst_dump_tool

- Added a provision to disable pre-fetching of index and filter blocks
  in BlockBasedTable
- Disabled pre-fetching for the sst_dump tool

Stack for reference :

#01  0x00000000005ed944 in snappy::InternalUncompress<snappy::SnappyArrayWriter> () from /home/engshare/third-party2/snappy/1.0.3/src/snappy-1.0.3/snappy.cc:148
#02  0x00000000005edeee in snappy::RawUncompress () from /home/engshare/third-party2/snappy/1.0.3/src/snappy-1.0.3/snappy.cc:947
#03  0x00000000004e0b4d in rocksdb::UncompressBlockContents () from /data/users/paultuckfield/rocksdb/./util/compression.h:69
#04  0x00000000004e145c in rocksdb::ReadBlockContents () from /data/users/paultuckfield/rocksdb/table/format.cc:334
#05  0x00000000004ca424 in rocksdb::(anonymous namespace)::ReadBlockFromFile () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:70
#06  0x00000000004cccad in rocksdb::BlockBasedTable::CreateIndexReader () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:173
#07  0x00000000004d17e5 in rocksdb::BlockBasedTable::Open () from /data/users/paultuckfield/rocksdb/table/block_based_table_reader.cc:553
#08  0x00000000004c8184 in rocksdb::BlockBasedTableFactory::NewTableReader () from /data/users/paultuckfield/rocksdb/table/block_based_table_factory.cc:51
#09  0x0000000000598463 in rocksdb::SstFileReader::NewTableReader () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:69
#10  0x00000000005986c2 in rocksdb::SstFileReader::SstFileReader () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:26
#11  0x0000000000599047 in rocksdb::SSTDumpTool::Run () from /data/users/paultuckfield/rocksdb/util/sst_dump_tool.cc:332
#12  0x0000000000409b06 in main () from /data/users/paultuckfield/rocksdb/tools/sst_dump.cc:12

Test Plan:
- Added a unit test to trigger the code.
- Also did some manual verification.
- Passed all unit tests

task #6296048

Reviewers: igor, rven, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D34041
2015-02-25 16:34:26 -08:00
Igor Sugak
62f7a1be4f rocksdb: Fixed 'Dead assignment' and 'Dead initialization' scan-build warnings
Summary:
This diff contains trivial fixes for 6 scan-build warnings:

**db/c_test.c**
`db` variable is never read. Removed assignment.
scan-build report:
http://home.fburl.com/~sugak/latest20/report-9b77d2.html#EndPath

**db/db_iter.cc**
`skipping` local variable is assigned to false. Then in the next switch block the only "non return" case assign `skipping` to true, the rest cases don't use it and all do return.
scan-build report:
http://home.fburl.com/~sugak/latest20/report-13fca7.html#EndPath

**db/log_reader.cc**
In `bool Reader::SkipToInitialBlock()` `offset_in_block` local variable is assigned to 0 `if (offset_in_block > kBlockSize - 6)` and then never used. Removed the assignment and renamed it to `initial_offset_in_block` to avoid confusion.
scan-build report:
http://home.fburl.com/~sugak/latest20/report-a618dd.html#EndPath

In `bool Reader::ReadRecord(Slice* record, std::string* scratch)` local variable `in_fragmented_record` in switch case `kFullType` block is assigned to false and then does `return` without use. In the other switch case `kFirstType` block the same `in_fragmented_record` is assigned to false, but later assigned to true without prior use. Removed assignment for both cases.
scan-build reprots:
http://home.fburl.com/~sugak/latest20/report-bb86b0.html#EndPath
http://home.fburl.com/~sugak/latest20/report-a975be.html#EndPath

**table/plain_table_key_coding.cc**
Local variable `user_key_size` is assigned when declared. But then in both places where it is used assigned to `static_cast<uint32_t>(key.size() - 8)`. Changed to initialize the variable to the proper value in declaration.
scan-build report:
http://home.fburl.com/~sugak/latest20/report-9e6b86.html#EndPath

**tools/db_stress.cc**
Missing `break` in switch case block. This seems to be a bug. Added missing `break`.

Test Plan:
Make sure all tests are passing and scan-build does not report 'Dead assignment' and 'Dead initialization' bugs.
```lang=bash
% make check
% make analyze
```

Reviewers: meyering, igor, kradhakrishnan, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D33795
2015-02-23 14:10:09 -08:00
Jim Meyering
aa5d8e6d95 table_test.cc: add missing 5th arg in TestArgs initializer
Summary:
Adding -W and -Wextra to CXXFLAGS provoked this failure:

	  table/table_test.cc:1854:56: error: missing initializer for member ‘rocksdb::TestArgs::format_version’ [-Werror=missing-field-initializers]
	     TestArgs args = { DB_TEST, false, 16, kNoCompression };
	                                                          ^

Add the missing, 5th value (format_version).

Test Plan:
  Run "make EXTRA_CXXFLAGS='-W -Wextra'" and see fewer errors.

Reviewers: ljin, sdong, igor.sugak, igor

Reviewed By: igor

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D33765
2015-02-20 11:07:11 -08:00
Jim Meyering
9283c7afd2 build: remove always-true assertions
Summary:
Remove some always-true assertions.
They provoke these compilation failures:

  table/plain_table_key_coding.cc:279:20: error: comparison of unsigned expression >= 0 is always true [-Werror=type-limits]
  db/version_set.cc:336:15: error: comparison of unsigned expression >= 0 is always true [-Werror=type-limits]

* table/plain_table_key_coding.cc (rocksdb): Remove assertion that
unsigned type variable is >= 0.
* db/version_set.cc (DoGenerateLevelFilesBrief): Likewise.

Test Plan:
  Run "make EXTRA_CXXFLAGS='-W -Wextra'" and see fewer errors.

Reviewers: ljin, sdong, igor.sugak, igor

Reviewed By: igor

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D33747
2015-02-20 11:07:03 -08:00
Igor Sugak
98870c7b9c rocksdb: Fix scan-build memory warning in table/block_based_table_reader.cc
Summary:
scan-build is reporting two memory leak bugs in `table/block_based_table_reader.cc`. They are both false positives. In both cases we allocate memory in `ReadBlockFromFile` if `s.ok()`. Then after the function `ReadBlockFromFile` returns we check for the same variable if `s.ok()` and then use the memory that was allocated. The bugs reported by scan-build is if `ReadBlockFromFile` allocates memory and returns, but for some reason status `s` is not the same and `s.ok() != true`.

In this case scan-build is concerned that memory owner transfer is not explicit. I modified `ReadBlockFromFile` to accept `std::unique_ptr<Block>*` as a parameter, instead of raw pointer.

scan-build reports:
http://home.fburl.com/~sugak/latest2/report-a4b3fa.html#EndPath
http://home.fburl.com/~sugak/latest2/report-29adbf.html#EndPath

Test Plan:
Make sure scan-build does not report these bugs and all tests are passing.
```lang=bash
% make check
% make analyze
```

Reviewers: sdong, lgalanis, meyering, igor

Reviewed By: igor

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D33681
2015-02-19 14:07:38 -08:00
sdong
68af7811ea Remember whole key/prefix filtering on/off in SST file
Summary: Remember whole key or prefix filtering on/off in SST files. If user opens the DB with a different setting that cannot be satisfied while reading the SST file, ignore the bloom filter.

Test Plan: Add a unit test for it

Reviewers: yhchiang, igor, rven

Reviewed By: rven

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D32889
2015-02-11 11:20:04 -08:00
sdong
e63140d52b Get() to use prefix bloom filter when filter is not block based
Summary:
Get() now doesn't make use of bloom filter if it is prefix based. Add the check.
Didn't touch block based bloom filter. I can't fully reason whether it is correct to do that. But it's straight-forward to for full bloom filter.

Test Plan:
make all check
Add a test case in DBTest

Reviewers: rven, yhchiang, igor

Reviewed By: igor

Subscribers: MarkCallaghan, leveldb, dhruba, yoshinorim

Differential Revision: https://reviews.facebook.net/D31941
2015-02-04 15:15:41 -08:00
Igor Canadi
9ab5adfc59 New BlockBasedTable version -- better compressed block format
Summary:
This diff adds BlockBasedTable format_version = 2. New format version brings better compressed block format for these compressions:
1) Zlib -- encode decompressed size in compressed block header
2) BZip2 -- encode decompressed size in compressed block header
3) LZ4 and LZ4HC -- instead of doing memcpy of size_t encode size as varint32. memcpy is very bad because the DB is not portable accross big/little endian machines or even platforms where size_t might be 8 or 4 bytes.

It does not affect format for snappy.

If you write a new database with format_version = 2, it will not be readable by RocksDB versions before 3.10. DB::Open() will return corruption in that case.

Test Plan:
Added a new test in db_test.
I will also run db_bench and verify VSIZE when block_cache == 1GB

Reviewers: yhchiang, rven, MarkCallaghan, dhruba, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D31461
2015-01-14 16:24:24 -08:00
Igor Canadi
96b8240bc5 Support footer versions bigger than 1
Summary:
In this diff I add another parameter to BlockBasedTableOptions that will let users specify block based table's format. This will greatly simplify block based table's format changes in the future.

First format change that this will support is encoding decompressed size in Zlib and BZip2 blocks. This diff is blocking https://reviews.facebook.net/D31311.

Test Plan: Added a unit tests. More tests to come as part of https://reviews.facebook.net/D31311.

Reviewers: dhruba, MarkCallaghan, yhchiang, rven, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D31383
2015-01-13 14:33:04 -08:00
Igor Canadi
15d2abbec3 Fix build issues 2015-01-09 13:04:06 -08:00
Igor Canadi
abb9b95ffe Move compression functions from port/ to util/
Summary: We keep checksum functions in util/, there is no reason for compression to be in port/

Test Plan: compiles

Reviewers: sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D31281
2015-01-09 12:57:11 -08:00
Manish Patil
7ea7bdf04d Dump routine to BlockBasedTableReader
Summary: Added necessary routines for dumping block based SST with block filter

Test Plan: Added "raw" mode to utility sst_dump

Reviewers: sdong, rven

Reviewed By: rven

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D29679
2014-12-23 13:24:07 -08:00
Jonah Cohen
a14b7873ee Enforce write buffer memory limit across column families
Summary:
Introduces a new class for managing write buffer memory across column
families.  We supplement ColumnFamilyOptions::write_buffer_size with
ColumnFamilyOptions::write_buffer, a shared pointer to a WriteBuffer
instance that enforces memory limits before flushing out to disk.

Test Plan: Added SharedWriteBuffer unit test to db_test.cc

Reviewers: sdong, rven, ljin, igor

Reviewed By: igor

Subscribers: tnovak, yhchiang, dhruba, xjin, MarkCallaghan, yoshinorim

Differential Revision: https://reviews.facebook.net/D22581
2014-12-02 12:09:20 -08:00
Yueh-Hsuan Chiang
7e608e2fe3 Block plain_table_index.cc in ROCKSDB_LITE
Summary: Block plain_table_index.cc in ROCKSDB_LITE

Test Plan:
make clean
make OPT=-DROCKSDB_LITE shared_lib -j32
make clean
make shared_lib -j32

Reviewers: ljin, igor

Reviewed By: igor

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D29535
2014-11-24 20:47:27 -08:00
Yueh-Hsuan Chiang
13de000f07 Add rocksdb::ToString() to address cases where std::to_string is not available.
Summary:
In some environment such as android, the c++ library does not have
std::to_string.  This path adds rocksdb::ToString(), which wraps std::to_string
when std::to_string is not available, and implements std::to_string
in the other case.

Test Plan:
make dbg -j32
./db_test
make clean
make dbg OPT=-DOS_ANDROID -j32
./db_test

Reviewers: ljin, sdong, igor

Reviewed By: igor

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D29181
2014-11-24 20:44:49 -08:00
Bryan Rosario
9e285d4238 Added CompatibleOptions for compatibility with LevelDB Options
Summary: Created a CompatibleOptions object that can be used as a LevelDB Options object and then converted to a RocksDB Options object using the ConvertOptions() method.

Test Plan: Unit test included in diff.

Reviewers: ljin

Reviewed By: ljin

Subscribers: sdong, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D28893
2014-11-20 19:24:39 -08:00
Lei Jin
8d3f8f9696 remove all remaining references to cfd->options()
Summary:
The very last reference happens in DBImpl::GetOptions()
I built with both DBImpl::GetOptions() and ColumnFamilyData::options() commented out

Test Plan: make all check

Reviewers: sdong, yhchiang, igor

Reviewed By: igor

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D29073
2014-11-18 10:20:10 -08:00
Igor Canadi
9be338cf9d CompactionJobTest
Summary:
This is just a simple test that passes two files though a compaction. It shows the framework so that people can continue building new compaction *unit* tests.
In the future we might want to move some Compaction* tests from DBTest here. For example, CompactBetweenSnapshot seems a good candidate.

Hopefully this test can be simpler when we mock out VersionSet.

Test Plan: this is a test

Reviewers: ljin, rven, yhchiang, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D28449
2014-11-14 11:35:48 -08:00
sdong
a177742a9b Make db_stress built for ROCKSDB_LITE
Summary:
Make db_stress built for ROCKSDB_LITE.
The test doesn't pass tough. It seg fault quickly. But I took a look and it doesn't seem to be related to lite version. Likely to be a bug inside RocksDB.

Test Plan: make db_stress

Reviewers: yhchiang, rven, ljin, igor

Reviewed By: igor

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D28797
2014-11-14 10:20:51 -08:00
Igor Canadi
25f273027b Fix iOS compile with -Wshorten-64-to-32
Summary: So iOS size_t is 32-bit, so we need to static_cast<size_t> any uint64_t :(

Test Plan: TARGET_OS=IOS make static_lib

Reviewers: dhruba, ljin, yhchiang, rven, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D28743
2014-11-13 14:39:30 -05:00
Igor Canadi
767777c2bd Turn on -Wshorten-64-to-32 and fix all the errors
Summary:
We need to turn on -Wshorten-64-to-32 for mobile. See D1671432 (internal phabricator) for details.

This diff turns on the warning flag and fixes all the errors. There were also some interesting errors that I might call bugs, especially in plain table. Going forward, I think it makes sense to have this flag turned on and be very very careful when converting 64-bit to 32-bit variables.

Test Plan: compiles

Reviewers: ljin, rven, yhchiang, sdong

Reviewed By: yhchiang

Subscribers: bobbaldwin, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D28689
2014-11-11 16:47:22 -05:00
Igor Canadi
68effa0348 Fix -Wshadow for tools
Summary: Previously I made `make check` work with -Wshadow, but there are some tools that are not compiled using `make check`.

Test Plan: make all

Reviewers: yhchiang, rven, ljin, sdong

Reviewed By: ljin, sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D28497
2014-11-07 15:04:30 -08:00
Igor Canadi
9f20395cd6 Turn -Wshadow back on
Summary: It turns out that -Wshadow has different rules for gcc than clang. Previous commit fixed clang. This commits fixes the rest of the warnings for gcc.

Test Plan: compiles

Reviewers: ljin, yhchiang, rven, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D28131
2014-11-06 11:14:28 -08:00
Igor Canadi
9f7fc3ac45 Turn on -Wshadow
Summary:
...and fix all the errors :)

Jim suggested turning on -Wshadow because it helped him fix number of critical bugs in fbcode. I think it's a good idea to be -Wshadow clean.

Test Plan: compiles

Reviewers: yhchiang, rven, sdong, ljin

Reviewed By: ljin

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D27711
2014-10-31 11:59:54 -07:00
Yueh-Hsuan Chiang
98849a35fa Apply InfoLogLevel to the logs in table/block_based_table_reader.cc
Summary:
Apply InfoLogLevel to the logs in table/block_based_table_reader.cc

Also, add missing checks for the returned status in BlockBasedTable::Open

Test Plan: make

Reviewers: sdong, ljin, igor

Reviewed By: igor

Subscribers: dhruba

Differential Revision: https://reviews.facebook.net/D28005
2014-10-31 11:41:15 -07:00
Yueh-Hsuan Chiang
217cc217d7 Apply InfoLogLevel to the logs in table/meta_blocks.cc
Summary: Apply InfoLogLevel to the logs in table/meta_blocks.cc

Test Plan: make

Reviewers: ljin, sdong, igor

Reviewed By: igor

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D27903
2014-10-29 17:55:19 -07:00
Yueh-Hsuan Chiang
fd95745a59 Fix compile error in table/plain_table_index.cc
Summary:
Fix compile error in table/plain_table_index.cc

Test Plan:
make
2014-10-29 17:42:38 -07:00
Yueh-Hsuan Chiang
e7ad69b9fe Apply InfoLogLevel to the logs in table/plain_table_index.cc
Summary: Apply InfoLogLevel to the logs in table/plain_table_index.cc

Test Plan: make

Reviewers: ljin, sdong, igor

Reviewed By: igor

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D27909
2014-10-29 17:08:40 -07:00
Yueh-Hsuan Chiang
bbd9c53457 Apply InfoLogLevel to the logs in table/block_based_table_builder.cc
Summary: Apply InfoLogLevel to the logs in table/block_based_table_builder.cc

Test Plan: make

Reviewers: igor, ljin, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D27921
2014-10-29 17:08:20 -07:00
Igor Canadi
412b7f85bb Include atomic in mock_table.h 2014-10-28 18:10:55 -07:00
Igor Canadi
abac3d6476 TableMock + framework for mock classes
Summary:
This diff replaces BlockBasedTable in flush_job_test with TableMock, making it depend on less things and making it closer to an unit test than integration test.

It also introduces a framework to compile mock classes -- Any file named *mock.cc will not be compiled into the build. It will only get compiled into the tests. What way we can mock out most other classes, Version, VersionSet, DBImpl, etc.

Test Plan: flush_job_test

Reviewers: ljin, rven, yhchiang, sdong

Reviewed By: sdong

Subscribers: dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D27681
2014-10-28 17:52:32 -07:00
Igor Canadi
c1c68bce43 remove atomic_pointer.h references 2014-10-27 15:12:20 -07:00
Lei Jin
f1841985e4 dynamic inplace_update options
Summary:
Make inplace_update_support and inplace_update_num_locks dynamic.
inplace_callback becomes immutable
We are almost free of references to cfd->options() in db_impl

Test Plan: unit test

Reviewers: igor, yhchiang, rven, sdong

Reviewed By: sdong

Subscribers: leveldb

Differential Revision: https://reviews.facebook.net/D25293
2014-10-27 12:10:13 -07:00
Lei Jin
839c376bd1 fix table_test
Summary:
SaveValue expects an internal key but I previously added to table a
user key

Test Plan:
ran the test
2014-10-22 13:53:35 -07:00
Lei Jin
0fd985f427 Avoid reloading filter on Get() if cache_index_and_filter_blocks == false
Summary:
This fixes the case that filter policy is missing in SST file, but we
open the table with filter policy on and cache_index_and_filter_blocks =
false. The current behavior is that we will try to load it every time on
Get() but fail.

Test Plan: unit test

Reviewers: yhchiang, igor, rven, sdong

Reviewed By: sdong

Subscribers: leveldb

Differential Revision: https://reviews.facebook.net/D25455
2014-10-22 11:52:35 -07:00
Lei Jin
2dd9bfe3a8 Sanitize block-based table index type and check prefix_extractor
Summary:
Respond to issue reported
https://www.facebook.com/groups/rocksdb.dev/permalink/651090261656158/
Change the Sanitize signature to take both DBOptions and CFOptions

Test Plan: unit test

Reviewers: sdong, yhchiang, igor

Reviewed By: igor

Subscribers: leveldb

Differential Revision: https://reviews.facebook.net/D25041
2014-10-17 21:18:36 -07:00
Igor Canadi
d6987216c9 Merge pull request #327 from dalgaaf/wip-da-SCA-20141001
Fix some issues from SCA
2014-10-02 10:59:52 -07:00
Lei Jin
5ec53f3edf make compaction related options changeable
Summary:
make compaction related options changeable. Most of changes are tedious,
following the same convention: grabs MutableCFOptions at the beginning
of compaction under mutex, then pass it throughout the job and register
it in SuperVersion at the end.

Test Plan: make all check

Reviewers: igor, yhchiang, sdong

Reviewed By: sdong

Subscribers: leveldb

Differential Revision: https://reviews.facebook.net/D23349
2014-10-01 16:19:16 -07:00
Danny Al-Gaaf
28a6e31583 table/block_based_table_builder.cc: remove unused variable
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-10-01 10:49:09 +02:00
Danny Al-Gaaf
6b6cedbb1b table/format.cc: reduce scope of some variables
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-10-01 10:49:08 +02:00
Danny Al-Gaaf
55652043c8 table/cuckoo_table_reader.cc: pass func parameter by reference
Fix for:

[table/cuckoo_table_reader.cc:196]: (performance) Function
 parameter 'target' should be passed by reference.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-10-01 10:49:08 +02:00
Danny Al-Gaaf
d517c83648 in_table_factory.cc: use correct format specifier
Use %zu instead of %zd since size_t and uint32_t are unsigned.

Fix for:

[table/plain_table_factory.cc:55]: (warning) %zd in format string (no. 1)
 requires 'ssize_t' but the argument type is 'size_t {aka unsigned long}'.
[table/plain_table_factory.cc:58]: (warning) %zd in format string (no. 1)
 requires 'ssize_t' but the argument type is 'size_t {aka unsigned long}'.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-09-30 23:30:32 +02:00
Danny Al-Gaaf
063471bf76 table/table_test.cc: pass func parameter by reference
Fix for:

[table/table_test.cc:1218]: (performance) Function parameter
 'prefix' should be passed by reference.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-09-30 23:30:32 +02:00
Danny Al-Gaaf
93548ce8f4 table/cuckoo_table_reader.cc: pass func parameter by ref
Fix for:

[table/cuckoo_table_reader.cc:198]: (performance) Function
 parameter 'file_data' should be passed by reference.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-09-30 23:30:32 +02:00
Danny Al-Gaaf
8ce050b51b table/bloom_block.*: pass func parameter by reference
[table/bloom_block.h:29]: (performance) Function parameter
 'keys_hashes' should be passed by reference.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
2014-09-30 23:30:31 +02:00
Lei Jin
2faf49d5f1 use GetContext to replace callback function pointer
Summary:
Intead of passing callback function pointer and its arg on Table::Get()
interface, passing GetContext. This makes the interface cleaner and
possible better perf. Also adding a fast pass for SaveValue()

Test Plan: make all check

Reviewers: igor, yhchiang, sdong

Reviewed By: sdong

Subscribers: leveldb

Differential Revision: https://reviews.facebook.net/D24057
2014-09-29 11:09:09 -07:00
Lei Jin
2dc6f62bb9 handle kDelete type in cuckoo builder
Summary:
when I changed std::vector<std::string, std::string> to std::string to
store key/value pairs in builder, I missed the handling for kDeletion
type. As a result, value_size_ can be wrong if the first add key is for
deletion.
The is captured by ./cuckoo_table_db_test

Test Plan:
./cuckoo_table_db_test
./cuckoo_table_reader_test
./cuckoo_table_builder_test

Reviewers: sdong, yhchiang, igor

Reviewed By: igor

Subscribers: leveldb

Differential Revision: https://reviews.facebook.net/D24045
2014-09-29 10:25:21 -07:00
Lei Jin
d439451fab delay initialization of cuckoo table iterator
Summary:
cuckoo table iterator creation is quite expensive since it needs to load
all data and sort them. After compaction, RocksDB creates a new iterator
of the new file to make sure it is in good state. That makes the DB
creation quite slow. Delay the iterator db sort to the seek time to
speed it up.

Test Plan: db_bench

Reviewers: igor, yhchiang, sdong

Reviewed By: sdong

Subscribers: leveldb

Differential Revision: https://reviews.facebook.net/D23775
2014-09-25 16:45:37 -07:00
Lei Jin
94997eab5e reduce memory usage of cuckoo table builder
Summary:
builder currently buffers all key value pairs as a vector of
pair<string, string>. That is too much due to std::string
overhead. It wasn't able to fit 1B key/values (12bytes total) in 100GB
of ram. Switch to use a plain string to store the key/value sequence and
use only 12GB of ram as a result.

Test Plan: db_bench

Reviewers: igor, sdong, yhchiang

Reviewed By: sdong

Subscribers: leveldb

Differential Revision: https://reviews.facebook.net/D23763
2014-09-25 16:34:24 -07:00
Lei Jin
c6275956e2 improve memory efficiency of cuckoo reader
Summary:
When creating a new iterator, instead of storing mapping from key to
bucket id for sorting, store only bucket id and read key from mmap file
based on the id. This reduces from 20 bytes per entry to only 4 bytes.

Test Plan: db_bench

Reviewers: igor, yhchiang, sdong

Reviewed By: sdong

Subscribers: leveldb

Differential Revision: https://reviews.facebook.net/D23757
2014-09-25 16:15:23 -07:00
Lei Jin
581442d446 option to choose module when calculating CuckooTable hash
Summary:
Using module to calculate hash makes lookup ~8% slower. But it has its
benefit: file size is more predictable, more space enffient

Test Plan: db_bench

Reviewers: igor, yhchiang, sdong

Reviewed By: sdong

Subscribers: leveldb

Differential Revision: https://reviews.facebook.net/D23691
2014-09-25 13:53:27 -07:00
Lei Jin
3c68006109 CompactedDBImpl
Summary:
Add a CompactedDBImpl that will enabled when calling OpenForReadOnly()
and the DB only has one level (>0) of files. As a performan comparison,
CuckooTable performs 2.1M/s with CompactedDBImpl vs. 1.78M/s with
ReadOnlyDBImpl.

Test Plan: db_bench

Reviewers: yhchiang, igor, sdong

Reviewed By: sdong

Subscribers: leveldb

Differential Revision: https://reviews.facebook.net/D23553
2014-09-25 11:14:01 -07:00
Lei Jin
0a29ce5393 re-enable BlockBasedTable::SetupForCompaction()
Summary:
It was commented out in D22545 by accident. Keep the option in
ImmutableOptions for now. I can make it dynamic in
https://reviews.facebook.net/D23349

Test Plan: make release

Reviewers: sdong, yhchiang, igor

Reviewed By: igor

Subscribers: leveldb

Differential Revision: https://reviews.facebook.net/D23865
2014-09-23 14:18:57 -07:00
Igor Canadi
55af370756 Remove TODO for checking index checksums 2014-09-23 13:02:23 -07:00
Igor Canadi
3d74f09979 Fix compile 2014-09-22 15:19:20 -07:00