Commit Graph

802 Commits

Author SHA1 Message Date
Yanqin Jin
729a617b5b Add listener to sample file io (#3933)
Summary:
We would like to collect file-system-level statistics including file name, offset, length, return code, latency, etc., which requires to add callbacks to intercept file IO function calls when RocksDB is running.
To collect file-system-level statistics, users can inherit the class `EventListener`, as in `TestFileOperationListener `. Note that `TestFileOperationListener::ShouldBeNotifiedOnFileIO()` returns true.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/3933

Differential Revision: D10219571

Pulled By: riversand963

fbshipit-source-id: 7acc577a2d31097766a27adb6f78eaf8b1e8ff15
2018-10-12 18:36:11 -07:00
jsteemann
517d3b8b77 fix typo in error message, twice (#4457)
Summary:
Fixes a typo in error messages returned by Iterator::GetProperty(...)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4457

Differential Revision: D10281965

Pulled By: sagar0

fbshipit-source-id: 1cd3c665f467ef06cdfd9f482692e6f8568f3d22
2018-10-09 17:07:27 -07:00
Dmitry Alimov
e13d8dcbbb Fix typos in comments (#4456)
Summary:
Fix some typos in the comments
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4456

Differential Revision: D10209214

Pulled By: miasantreble

fbshipit-source-id: dff857ba60396bc95126e635db96d7dc8330d2cb
2018-10-04 20:46:50 -07:00
Zhongyi Xie
ce1fc5af09 fix unused param allocator in compression.h (#4453)
Summary:
this should fix currently failing contrun test: rocksdb-contrun-no_compression, rocksdb-contrun-tsan, rocksdb-contrun-tsan_crash
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4453

Differential Revision: D10202626

Pulled By: miasantreble

fbshipit-source-id: 850b07f14f671b5998c22d8239e2a55b2fc1e355
2018-10-04 13:24:22 -07:00
Igor Canadi
1cf5deb8fd Introduce CacheAllocator, a custom allocator for cache blocks (#4437)
Summary:
This is a conceptually simple change, but it touches many files to
pass the allocator through function calls.

We introduce CacheAllocator, which can be used by clients to configure
custom allocator for cache blocks. Our motivation is to hook this up
with folly's `JemallocNodumpAllocator`
(f43ce6d686/folly/experimental/JemallocNodumpAllocator.h),
but there are many other possible use cases.

Additionally, this commit cleans up memory allocation in
`util/compression.h`, making sure that all allocations are wrapped in a
unique_ptr as soon as possible.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4437

Differential Revision: D10132814

Pulled By: yiwu-arbug

fbshipit-source-id: be1343a4b69f6048df127939fea9bbc96969f564
2018-10-02 17:24:58 -07:00
Maysam Yabandeh
65ac72edd9 Fix bug in partition filters with format_version=4 (#4381)
Summary:
Value delta encoding in format_version 4 requires the differences between the size of two consecutive handles to be sent to BlockBuilder::Add. This applies not only to indexes on blocks but also the indexes on indexes and filters in partitioned indexes and filters respectively. The patch fixes a bug where the partitioned filters would encode the entire size of the handle rather than the difference of the size with the last size.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4381

Differential Revision: D9879505

Pulled By: maysamyabandeh

fbshipit-source-id: 27a22e49b482b927fbd5629dc310c46d63d4b6d1
2018-09-17 17:28:15 -07:00
Sagar Vemuri
ac46790374 Fix sync-point comment in Block destructor (#4380)
Summary:
This is a follow up to #4370. The earlier comment is not correct.

Thanks to ajkr for pointing this out.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4380

Differential Revision: D9874667

Pulled By: sagar0

fbshipit-source-id: f4e092d86b29c715258210b770643d367e38caae
2018-09-17 11:58:11 -07:00
Sagar Vemuri
3db584059c Remove sync point from Block destructor (#4370)
Summary:
AddressSanitizer: heap-use-after-free in std::__atomic_base<bool>::load(std::memory_order) const
==1798517==ABORTING
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4370

Differential Revision: D9844146

Pulled By: sagar0

fbshipit-source-id: 18a2970b1d504b4f6c8fb04857f26e0f32124dd1
2018-09-15 00:12:57 -07:00
Maysam Yabandeh
9ea9007b50 Reduce IndexBlockIter size (#4358)
Summary:
With #3983 the size of IndexBlockIter was increased. This had resulted in a regression on P50 latencies in one of our benchmarks. The patch reduces IndexBlockIter size be eliminating active_comparator_ field from the class.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4358

Differential Revision: D9781737

Pulled By: maysamyabandeh

fbshipit-source-id: 71e2b28d90ff0813db9e04b737ae73e185583c52
2018-09-12 10:03:35 -07:00
Andrew Kryczka
2c14662213 Revert "Digest ZSTD compression dictionary once per SST file (#4251)" (#4347)
Summary:
Reverting is needed to unblock a user building against master, who is blocked for multiple days due to a thread-safety issue in `GetEmptyDict`. We haven't been able to fix it quickly, so reverting.

Simply ran `git revert 6c40806e51a89386d2b066fddf73d3fd03a36f65`. There were no merge conflicts.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4347

Differential Revision: D9668365

Pulled By: ajkr

fbshipit-source-id: 0c56334f0a23cf5ee0233d4e4679eae6709739cd
2018-09-06 09:58:34 -07:00
cngzhnp
64324e329e Support pragma once in all header files and cleanup some warnings (#4339)
Summary:
As you know, almost all compilers support "pragma once" keyword instead of using include guards. To be keep consistency between header files, all header files are edited.

Besides this, try to fix some warnings about loss of data.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4339

Differential Revision: D9654990

Pulled By: ajkr

fbshipit-source-id: c2cf3d2d03a599847684bed81378c401920ca848
2018-09-05 18:13:31 -07:00
Andrew Kryczka
6c40806e51 Digest ZSTD compression dictionary once per SST file (#4251)
Summary:
In RocksDB, for a given SST file, all data blocks are compressed with the same dictionary. When we compress a block using the dictionary's raw bytes, the compression library first has to digest the dictionary to get it into a usable form. This digestion work is redundant and ideally should be done once per file.

ZSTD offers APIs for the caller to create and reuse a digested dictionary object (`ZSTD_CDict`). In this PR, we call `ZSTD_createCDict` once per file to digest the raw bytes. Then we use `ZSTD_compress_usingCDict` to compress each data block using the pre-digested dictionary. Once the file's created `ZSTD_freeCDict` releases the resources held by the digested dictionary.

There are a couple other changes included in this PR:

- Changed the parameter object for (un)compression functions from `CompressionContext`/`UncompressionContext` to `CompressionInfo`/`UncompressionInfo`. This avoids the previous pattern, where `CompressionContext`/`UncompressionContext` had to be mutated before calling a (un)compression function depending on whether dictionary should be used. I felt that mutation was error-prone so eliminated it.
- Added support for digested uncompression dictionaries (`ZSTD_DDict`) as well. However, this PR does not support reusing them across uncompression calls for the same file. That work is deferred to a later PR when we will store the `ZSTD_DDict` objects in block cache.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4251

Differential Revision: D9257078

Pulled By: ajkr

fbshipit-source-id: 21b8cb6bbdd48e459f1c62343780ab66c0a64438
2018-08-23 19:28:18 -07:00
Fenggang Wu
da40d45267 DataBlockHashIndex: avoiding expensive iiter->Next when handling hash kNoEntry (#4296)
Summary:
When returning `kNoEntry` from HashIndex lookup, previously we invalidate the
`biter` by set `current_=restarts_`, so that the search can continue to the next
block in case the search result may reside in the next block.

There is one problem: when we are searching for a missing key, if the search
finds a `kNoEntry` and continue the search to the next block, there is also a
non-trivial possibility that the HashIndex return `kNoEntry` too, and the
expensive index iterator `Next()` will happen several times for nothing.

The solution is that if the hash table returns `kNoEntry`, `SeekForGetImpl()` just search the last restart interval for the key. It will stop at the first key that is large than the seek_key, or to the end of the block, and each case will be handled correctly.

Microbenchmark script:
```
TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=fillseq,readtocache,readmissing \
          --cache_size=20000000000  --use_data_block_hash_index={true|false}
```

`readmissing` performance (lower is better):
```
binary:                      3.6098 micros/op
hash (before applying diff): 4.1048 micros/op
hash (after  applying diff): 3.3502 micros/op
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4296

Differential Revision: D9419159

Pulled By: fgwu

fbshipit-source-id: 21e3eedcccbc47a249aa8eb4bf405c9def0b8a05
2018-08-23 10:12:58 -07:00
Yanqin Jin
bb5dcea98e Add path to WritableFileWriter. (#4039)
Summary:
We want to sample the file I/O issued by RocksDB and report the function calls. This requires us to include the file paths otherwise it's hard to tell what has been going on.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4039

Differential Revision: D8670178

Pulled By: riversand963

fbshipit-source-id: 97ee806d1c583a2983e28e213ee764dc6ac28f7a
2018-08-23 10:12:58 -07:00
Fenggang Wu
640cfa7c33 DataBlockHashIndex: fix comment in NumRestarts() (#4286)
Summary:
Improve the description of the backward compatibility check in NumRestarts()
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4286

Differential Revision: D9412490

Pulled By: fgwu

fbshipit-source-id: ea7dd5c61d8ff8eacef623b729d4e4fd53cca066
2018-08-21 17:12:45 -07:00
Fenggang Wu
6d37fdb365 DataBlockHashIndex: Remove the division from EstimateSize() (#4293)
Summary:
`BlockBasedTableBuilder::Add()` eventually calls
`DataBlockHashIndexBuilder::EstimateSize()`. The previous implementation
divides the `num_keys` by the `util_ratio_` to get an estimizted `num_buckets`.
Such division is expensive as it happens in every
`BlockBasedTableBuilder::Add()`.

This diff estimates the `num_buckets` by double addition instead of double
division. Specifically, in each `Add()`, we add `bucket_per_key_`
(inverse of `util_ratio_`) to the current `estimiated_num_buckets_`. The cost is
that we are gonna have the `estimated_num_buckets_` stored as one extra field
in the DataBlockHashIndexBuilder.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4293

Differential Revision: D9412472

Pulled By: fgwu

fbshipit-source-id: 2925c8509a401e7bd3c1ab1d9e9c7244755c277a
2018-08-20 23:13:50 -07:00
Siying Dong
dc064f302e Suppress two CLANG Analyze warning (#4291)
Summary:
Suppress two CLANG analyze warnings. They don't seem to be real bugs
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4291

Differential Revision: D9407333

Pulled By: siying

fbshipit-source-id: 2ed63d88fa0b217fdccb1572d7508467c2203dc8
2018-08-20 16:57:38 -07:00
Andrey Zagrebin
fa4de6e30f #3865 followup for fix performance degression introduced by switching order of operands (#4284)
Summary:
Followup for #4266. There is one more place in **get_context.cc** where **MergeOperator::ShouldMerge** should be called with reversed list of operands.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4284

Differential Revision: D9380008

Pulled By: sagar0

fbshipit-source-id: 70ec26e607e5b88465e1acbdcd6c6171bd76b9f2
2018-08-17 10:57:25 -07:00
Fenggang Wu
9d646a6311 Add db_bench options of data block hash index (#4281)
Summary:
Add `--data_block_index_type` and `--data_block_hash_table_util_ratio` option to `db_bench`.

`--data_block_index_type` can be either of `binary` (default) or `binary_and_hash`;
`--data_block_hash_table_util_ratio` will be a double. The default value is `0.75`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4281

Differential Revision: D9361476

Pulled By: fgwu

fbshipit-source-id: dc53e01acef9db81b9eec5e8a96f3bc8ed718c10
2018-08-16 18:42:46 -07:00
Fenggang Wu
19ec44fd39 Improve point-lookup performance using a data block hash index (#4174)
Summary:
Add hash index support to data blocks, which helps to reduce the CPU utilization of point-lookup operations. This feature is backward compatible with the data block created without the hash index. It is disabled by default unless `BlockBasedTableOptions::data_block_index_type` is set to `data_block_index_type = kDataBlockBinaryAndHash.`

The DB size would be bigger with the hash index option as a hash table is added at the end of each data block. If the hash utilization ratio is 1:1, the space overhead is one byte per key. The hash table utilization ratio is adjustable using `BlockBasedTableOptions::data_block_hash_table_util_ratio`. A lower utilization ratio will improve more on the point-lookup efficiency, but take more space too.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4174

Differential Revision: D8965914

Pulled By: fgwu

fbshipit-source-id: 1c6bae5d1fc39c80282d8890a72e9e67bc247198
2018-08-15 14:30:03 -07:00
Siying Dong
f3d91a0b57 Add a unit test to verify iterators release data blocks after using them (#4170)
Summary:
Add a unit test to check that iterators release data blocks after it has moved away from it. Verify the same for compaction input iterators.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4170

Differential Revision: D8962513

Pulled By: siying

fbshipit-source-id: 05a5b604d7d29887fb488f2cda7286f554a14407
2018-08-13 17:43:14 -07:00
Maysam Yabandeh
d511f35ea7 Fix wrong partitioned index size recorded in properties block (#4259)
Summary:
After refactoring in https://github.com/facebook/rocksdb/pull/4158 the properties block is written after the index block. This breaks the existing logic in estimating the index size in partitioned indexes. The patch fixes that by using the accurate index block size, which is available since by the time we write the properties block, the index block is already written.
The patch also fixes an issue in estimating the partition size with format_version=3 which was resulting into partitions smaller than the configured metadata_block_size.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4259

Differential Revision: D9274454

Pulled By: maysamyabandeh

fbshipit-source-id: c82d045505cca3e7ed1a44ee1eaa26e4f25a4272
2018-08-10 15:27:20 -07:00
Maysam Yabandeh
058026a885 Fix unity compile error (#4257)
Summary:
Fix the compile error in "make unity_test" caused by #3983.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4257

Differential Revision: D9271740

Pulled By: maysamyabandeh

fbshipit-source-id: 94e56d1675bf8bdc0e94439467eb4f40dd107517
2018-08-10 10:27:55 -07:00
Maysam Yabandeh
caf0f53a74 Index value delta encoding (#3983)
Summary:
Given that index value is a BlockHandle, which is basically an <offset, size> pair we can apply delta encoding on the values. The first value at each index restart interval encoded the full BlockHandle but the rest encode only the size. Refer to IndexBlockIter::DecodeCurrentValue for the detail of the encoding. This reduces the index size which helps using the  block cache more efficiently. The feature is enabled with using format_version 4.

The feature comes with a bit of cpu overhead which should be paid back by the higher cache hits due to smaller index block size.
Results with sysbench read-only using 4k blocks and using 16 index restart interval:
Format 2:
19585   rocksdb read-only range=100
Format 3:
19569   rocksdb read-only range=100
Format 4:
19352   rocksdb read-only range=100
Pull Request resolved: https://github.com/facebook/rocksdb/pull/3983

Differential Revision: D8361343

Pulled By: maysamyabandeh

fbshipit-source-id: f882ee082322acac32b0072e2bdbb0b5f854e651
2018-08-09 16:58:40 -07:00
Maysam Yabandeh
eb8885a08a Return correct usable_size for BlockContents (#4246)
Summary:
If jemalloc is disabled or the API is incorrectly referenced (jemalloc api on windows have a prefix je_) memory usage is incorrectly reported for all block sizes. This is because sizeof(char) is always 1. sizeof() is calculated at compile time and *(char*) is char. The patch uses the size of the slice to fix that.
Fixes #4245
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4246

Differential Revision: D9233958

Pulled By: maysamyabandeh

fbshipit-source-id: 9646933b24504e2814c7379f06a31148829c6b4e
2018-08-08 17:43:00 -07:00
Yanqin Jin
54de56844d Remove random writes from SST file ingestion (#4172)
Summary:
RocksDB used to store global_seqno in external SST files written by
SstFileWriter. During file ingestion, RocksDB uses `pwrite` to update the
`global_seqno`. Since random write is not supported in some non-POSIX compliant
file systems, external SST file ingestion is not supported on these file
systems. To address this limitation, we no longer update `global_seqno` during
file ingestion. Later RocksDB uses the MANIFEST and other information in table
properties to deduce global seqno for externally-ingested SST files.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4172

Differential Revision: D8961465

Pulled By: riversand963

fbshipit-source-id: 4382ec85270a96be5bc0cf33758ca2b167b05071
2018-07-27 16:12:23 -07:00
Fenggang Wu
a11df583ec Add DataBlockIndexType option in BlockBasedTableOptions (#4150)
Summary:
Added DataBlockIndexType option in BlockBasedTableOptions.
```
enum DataBlockIndexType : char {
    kDataBlockBinarySearch = 0, // traditional block type
    kDataBlockHashIndex = 1, // additional hash index appended to the end.
};
```
The default type is the traditional binary seek option: `kDataBlockBinarySearch`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4150

Differential Revision: D8895958

Pulled By: fgwu

fbshipit-source-id: 480adef48104cf11d30db3bad9a73f98b4a80c10
2018-07-27 15:42:27 -07:00
Siying Dong
2a81633da2 Fix bug when seeking backward against an out-of-bound iterator (#4187)
Summary:
92ee3350e0 introduces an out-of-bound check in BlockBasedTableIterator::Valid(). However, this flag is not reset when re-seeking in backward direction. This caused the iterator to be invalide by mistake. Fix it by always resetting the out-of-bound flag in every seek.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4187

Differential Revision: D8996600

Pulled By: siying

fbshipit-source-id: b6235ea614f71381e50e7904c4fb036300604ac1
2018-07-25 17:14:01 -07:00
Fenggang Wu
8805ec2f49 DataBlockHashIndex: Standalone Implementation with Unit Test (#4139)
Summary:
The first step of the `DataBlockHashIndex` implementation. A string based hash table is implemented and unit-tested.

`DataBlockHashIndexBuilder`: `Add()` takes pairs of `<key, restart_index>`, and formats it into a string when `Finish()` is called.
`DataBlockHashIndex`: initialized by the formatted string, and can interpret it as a hash table. Lookup for a key is supported by iterator operation.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4139

Reviewed By: sagar0

Differential Revision: D8866764

Pulled By: fgwu

fbshipit-source-id: 7f015f0098632c65979a22898a50424384730b10
2018-07-24 11:43:37 -07:00
Zhongyi Xie
f95a5b2464 Avoid unnecessary big for-loop when reporting ticker stats stored in GetContext (#3490)
Summary:
Currently in `Version::Get` when reporting ticker stats stored in `GetContext`, there is a big for-loop through all `Ticker` which adds unnecessary cost to overall CPU usage. We can optimize by storing only ticker values that are used in `Get()` calls in a new struct `GetContextStats` since only a small fraction of all tickers are used in `Get()` calls. For comparison, with the new approach we only need to visit 17 values while old approach will require visiting 100+ `Ticker`
Pull Request resolved: https://github.com/facebook/rocksdb/pull/3490

Differential Revision: D6969154

Pulled By: miasantreble

fbshipit-source-id: fc27072965a3a94125a3e6883d20dafcf5b84029
2018-07-20 16:58:13 -07:00
Siying Dong
a5e851e113 Reformatting some recent changes (#4161)
Summary:
Lint is not happy with some new code recently committed. Format them.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4161

Differential Revision: D8940582

Pulled By: siying

fbshipit-source-id: c9b43b1ef8c88b5e923911058b44eb77234b36b7
2018-07-20 14:43:38 -07:00
Siying Dong
8425c8bd4d BlockBasedTableReader: automatically adjust tail prefetch size (#4156)
Summary:
Right now we use one hard-coded prefetch size to prefetch data from the tail of the SST files. However, this may introduce a waste for some use cases, while not efficient for others.
Introduce a way to adjust this prefetch size by tracking 32 recent times, and pick a value with which the wasted read is less than 10%
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4156

Differential Revision: D8916847

Pulled By: siying

fbshipit-source-id: 8413f9eb3987e0033ed0bd910f83fc2eeaaf5758
2018-07-20 14:43:37 -07:00
Andrew Kryczka
ab35505e21 Write properties metablock last in block-based tables (#4158)
Summary:
The properties meta-block should come at the end since we always need to
read it when opening a file, unlike index/filter/other meta-blocks, which
are sometimes read depending on the user's configuration. This ordering
will allow us to (in a future PR) do a small readahead on the end of the file
to read properties and meta-index blocks with one I/O.

The bulk of this PR is a refactoring of the `BlockBasedTableBuilder::Finish`
function. It was previously too large with inconsistent error handling, which
made it difficult to change. So I broke it up into one function per meta-block
write, and tried to make error handling consistent within those functions.
Then reordering the metablocks was trivial -- just reorder the calls to these
helper functions.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4158

Differential Revision: D8921705

Pulled By: ajkr

fbshipit-source-id: 96c9cc3182eb1adf11af46adab79dbeba7b12fcc
2018-07-20 09:11:59 -07:00
Andrew Kryczka
b5613227a9 Smaller tail readahead when not reading index/filters (#4159)
Summary:
In all cases during `BlockBasedTable::Open`, we issue at least three read requests to the file's tail: (1) footer, (2) metaindex block, and (3) properties block. Depending on the config, we may also read other metablocks like filter and index.

This PR issues smaller readahead when we expect to do only the three necessary reads mentioned above. Then, 4KB should be enough (ignoring the case where there are lots of user-defined properties). We can keep doing 512KB readahead when additional reads are expected.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4159

Differential Revision: D8924002

Pulled By: ajkr

fbshipit-source-id: cfc713275de4d05ce11f18571f1d72e27ccd3356
2018-07-19 16:13:22 -07:00
Maysam Yabandeh
b55da012f6 Refactor IndexBlockIter (#4141)
Summary:
Refactor IndexBlockIter to reduce conditional branches on key_includes_seq_. IndexBlockIter::Prev is also separated from DataBlockIter::Prev, not to cache the prev entries as they are of less importance when iterating over the index block.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4141

Differential Revision: D8866437

Pulled By: maysamyabandeh

fbshipit-source-id: fdac76880426fc2be7d3c6354c09ab98f6657d4b
2018-07-16 17:13:10 -07:00
Siying Dong
8f06b4fa01 Separate some IndexBlockIter logic from BlockIter (#4136)
Summary:
Some logic only related to IndexBlockIter is separated from BlockIter to IndexBlockIter. This is done by writing an exclusive Seek() and SeekForPrev() for DataBlockIter, and all metadata block iter and tombstone block iter now use data block iter. Dealing with the BinarySeek() sharing problem by passing in the comparator to use.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4136

Reviewed By: maysamyabandeh

Differential Revision: D8859673

Pulled By: siying

fbshipit-source-id: 703e5e6824b82b7cbf4721f3594b94127797ca9e
2018-07-16 10:13:18 -07:00
Nathan VanBenschoten
ef7815b803 Support range deletion tombstones in IngestExternalFile SSTs (#3778)
Summary:
Fixes #3391.

This change adds a `DeleteRange` method to `SstFileWriter` and adds
support for ingesting SSTs with range deletion tombstones. This is
important for applications that need to atomically ingest SSTs while
clearing out any existing keys in a given key range.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/3778

Differential Revision: D8821836

Pulled By: anand1976

fbshipit-source-id: ca7786c1947ff129afa703dab011d524c7883844
2018-07-13 22:43:09 -07:00
Maysam Yabandeh
8581a93a6b Per-thread unique test db names (#4135)
Summary:
The patch makes sure that two parallel test threads will operate on different db paths. This enables using open source tools such as gtest-parallel to run the tests of a file in parallel.
Example: ``` ~/gtest-parallel/gtest-parallel ./table_test```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4135

Differential Revision: D8846653

Pulled By: maysamyabandeh

fbshipit-source-id: 799bad1abb260e3d346bcb680d2ae207a852ba84
2018-07-13 17:27:39 -07:00
Tamir Duberstein
7bee48bdbd Add GCC 8 to Travis (#3433)
Summary:
- Avoid `strdup` to use jemalloc on Windows
- Use `size_t` for consistency
- Add GCC 8 to Travis
- Add CMAKE_BUILD_TYPE=Release to Travis
Pull Request resolved: https://github.com/facebook/rocksdb/pull/3433

Differential Revision: D6837948

Pulled By: sagar0

fbshipit-source-id: b8543c3a4da9cd07ee9a33f9f4623188e233261f
2018-07-13 10:58:06 -07:00
Maysam Yabandeh
d4ad32d7bd Refactor BlockIter (#4121)
Summary:
BlockIter is getting crowded including details that specific only to either index or data blocks. The patch moves down such details to DataBlockIter and IndexBlockIter, both inheriting from BlockIter.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4121

Differential Revision: D8816832

Pulled By: maysamyabandeh

fbshipit-source-id: d492e74155c11d8a0c1c85cd7ee33d24c7456197
2018-07-12 17:27:31 -07:00
Nikhil Benesch
5cd8240b86 Test range deletions with more configurations (#4021)
Summary:
Run the basic range deletion tests against the standard set of
configurations. This testing exposed that files with hash indexes and
partitioned indexes were not handling the case where the file contained
only range deletions--i.e., where the index was empty.

Additionally file a TODO about the fact that range deletions are broken
when allow_mmap_reads = true is set.

/cc ajkr nvanbenschoten

Best viewed with ?w=1: https://github.com/facebook/rocksdb/pull/4021/files?w=1
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4021

Differential Revision: D8811860

Pulled By: ajkr

fbshipit-source-id: 3cc07e6d6210a2a00b932866481b3d5c59775343
2018-07-11 15:57:49 -07:00
Yanqin Jin
d4d9fe8e57 Fix a bug caused by not copying the block trailer. (#4096)
Summary:
This was caught by crash test, and the following is a simple way to reproduce it and verify the fix.
One way to trigger this code path is to use the following configuration:
- Compress SST file
- Enable direct IO and prefetch buffer
- Do NOT use compressed block cache
Closes https://github.com/facebook/rocksdb/pull/4096

Differential Revision: D8742009

Pulled By: riversand963

fbshipit-source-id: f13381078bbb0dce92f60bd313a78ab602bcacd2
2018-07-06 13:12:39 -07:00
Yanqin Jin
39218a72a4 Increase the size of LRU cache. (#4090)
Summary:
Increase the size of each shard so that the number of cache hit/miss match
expectation. Otherwise FilterBlockInBlockCache test will fail.
Closes https://github.com/facebook/rocksdb/pull/4090

Differential Revision: D8736158

Pulled By: riversand963

fbshipit-source-id: 5cdbc06b02390389fd5b72a6d251d88949ad3d91
2018-07-05 11:45:11 -07:00
Maysam Yabandeh
2462763b2e Fix mis-spoken assert on prefetch_filter and prefetch_index (#4077)
Summary:
We can have prefetch_index without prefetch_filter but not the other way around. The assert statement is fixed.
Closes https://github.com/facebook/rocksdb/pull/4077

Differential Revision: D8694472

Pulled By: maysamyabandeh

fbshipit-source-id: ccd2804d9d9cdafb1c3e65062c7bc38603e69004
2018-06-29 09:28:12 -07:00
Maysam Yabandeh
29ffbb8a50 Charging block cache more accurately (#4073)
Summary:
Currently the block cache is charged only by the size of the raw data block and excludes the overhead of the c++ objects that contain the raw data block. The patch improves the accuracy of the charge by including the c++ object overhead into it.
Closes https://github.com/facebook/rocksdb/pull/4073

Differential Revision: D8686552

Pulled By: maysamyabandeh

fbshipit-source-id: 8472f7fc163c0644533bc6942e20cdd5725f520f
2018-06-29 08:57:20 -07:00
Zhongyi Xie
14f409c0f1 PrefixMayMatch: remove unnecessary check for prefix_extractor_ (#4067)
Summary:
with https://github.com/facebook/rocksdb/pull/3601 and https://github.com/facebook/rocksdb/pull/3899, `prefix_extractor_` is not really being used in block based filter and full filter's version of `PrefixMayMatch` because now `prefix_extractor` is passed as an argument. Also it is now possible that prefix_extractor_ may be initialized to nullptr when a non-standard prefix_extractor is used and also for ROCKSDB_LITE. Removing these checks should not break any existing tests.
Closes https://github.com/facebook/rocksdb/pull/4067

Differential Revision: D8669002

Pulled By: miasantreble

fbshipit-source-id: 0e701ba912b8a26734fadb72d15bb1b266b6176a
2018-06-27 20:42:43 -07:00
Zhichao Cao
1f6efabe23 Add bottommost_compression_opts to for bottommost_compression (#3985)
Summary:
…ression

 For `CompressionType` we have options `compression` and `bottommost_compression`. Thus, to make the compression options consitent with the compression type when bottommost_compression is enabled, we add the bottommost_compression_opts
Closes https://github.com/facebook/rocksdb/pull/3985

Reviewed By: riversand963

Differential Revision: D8385911

Pulled By: zhichao-cao

fbshipit-source-id: 07bc533dd61bcf1cef5927d8d62901c13d38d5fc
2018-06-27 17:42:38 -07:00
Maysam Yabandeh
235ab9dd32 Pin mmap files in ReadOnlyDB (#4053)
Summary:
https://github.com/facebook/rocksdb/pull/3881 fixed a bug where PinnableSlice pin mmap files which could be deleted with background compaction. This is however a non-issue for ReadOnlyDB when there is no compaction running and max_open_files is -1. This patch reenables the pinning feature for that case.
Closes https://github.com/facebook/rocksdb/pull/4053

Differential Revision: D8662546

Pulled By: maysamyabandeh

fbshipit-source-id: 402962602eb0f644e17822748332999c3af029fd
2018-06-27 17:13:34 -07:00
Manuel Ung
a16e00b7b9 WriteUnPrepared Txn: Disable seek to snapshot optimization (#3955)
Summary:
This is implemented by extending ReadCallback with another function `MaxUnpreparedSequenceNumber` which returns the largest visible sequence number for the current transaction, if there is uncommitted data written to DB. Otherwise, it returns zero, indicating no uncommitted data.

There are the places where reads had to be modified.
- Get and Seek/Next was just updated to seek to max(snapshot_seq, MaxUnpreparedSequenceNumber()) instead, and iterate until a key was visible.
- Prev did not need need updates since it did not use the Seek to sequence number optimization. Assuming that locks were held when writing unprepared keys, and ValidateSnapshot runs, there should only be committed keys and unprepared keys of the current transaction, all of which are visible. Prev will simply iterate to get the last visible key.
- Reseeking to skip keys optimization was also disabled for write unprepared, since it's possible to hit the max_skip condition even while reseeking. There needs to be some way to resolve infinite looping in this case.
Closes https://github.com/facebook/rocksdb/pull/3955

Differential Revision: D8286688

Pulled By: lth

fbshipit-source-id: 25e42f47fdeb5f7accea0f4fd350ef35198caafe
2018-06-27 12:23:07 -07:00
Nikhil Benesch
17339dc2f3 Add table property tracking number of range deletions (#4016)
Summary:
Add a new table property, rocksdb.num.range-deletions, which tracks the
number of range deletions in a block-based table. Range deletions are no
longer counted in rocksdb.num.entries; as discovered in PR #3778, there
are various code paths that implicitly assume that rocksdb.num.entries
counts only true keys, not range deletions.

/cc ajkr nvanbenschoten
Closes https://github.com/facebook/rocksdb/pull/4016

Differential Revision: D8527575

Pulled By: ajkr

fbshipit-source-id: 92e7edbe78fda53756a558013c9fb496e7764fd7
2018-06-26 20:27:35 -07:00