dolysis/rocksdb
3
0
Fork 0
mirror of https://github.com/facebook/rocksdb.git synced 2024-11-25 22:44:05 +00:00
Code Issues Packages Projects Releases Wiki Activity
11217 commits 196 branches 277 tags 392 MiB
Commit graph

2 commits

Author SHA1 Message Date
Jaepil Jeong 4eb7b35f6d Fix compile error in Clang 13 (#10033) 
Summary:
This PR fixes the following compilation error in Clang 13, which was tested on macOS 12.4.

```
❯ ninja clean && ninja
[1/1] Cleaning all built files...
Cleaning... 0 files.
[198/315] Building CXX object CMakeFiles/rocksdb.dir/util/cleanable.cc.o
FAILED: CMakeFiles/rocksdb.dir/util/cleanable.cc.o
ccache /opt/homebrew/opt/llvm/bin/clang++ -DGFLAGS=1 -DGFLAGS_IS_A_DLL=0 -DHAVE_FULLFSYNC -DJEMALLOC_NO_DEMANGLE -DLZ4 -DOS_MACOSX -DROCKSDB_JEMALLOC -DROCKSDB_LIB_IO_POSIX -DROCKSDB_NO_DYNAMIC_EXTENSION -DROCKSDB_PLATFORM_POSIX -DSNAPPY -DTBB -DZLIB -DZSTD -I/Users/jaepil/work/deepsearch/deps/cpp/rocksdb -I/Users/jaepil/work/deepsearch/deps/cpp/rocksdb/include -I/Users/jaepil/app/include -I/opt/homebrew/include -I/opt/homebrew/opt/llvm/include -W -Wextra -Wall -pthread -Wsign-compare -Wshadow -Wno-unused-parameter -Wno-unused-variable -Woverloaded-virtual -Wnon-virtual-dtor -Wno-missing-field-initializers -Wno-strict-aliasing -Wno-invalid-offsetof -fno-omit-frame-pointer -momit-leaf-frame-pointer -march=armv8-a+crc+crypto -Wno-unused-function -Werror -O3 -DNDEBUG -DROCKSDB_USE_RTTI -arch arm64 -isysroot /Library/Developer/CommandLineTools/SDKs/MacOSX12.3.sdk -std=gnu++17 -MD -MT CMakeFiles/rocksdb.dir/util/cleanable.cc.o -MF CMakeFiles/rocksdb.dir/util/cleanable.cc.o.d -o CMakeFiles/rocksdb.dir/util/cleanable.cc.o -c /Users/jaepil/work/deepsearch/deps/cpp/rocksdb/util/cleanable.cc
/Users/jaepil/work/deepsearch/deps/cpp/rocksdb/util/cleanable.cc:24:65: error: no member named 'move' in namespace 'std'
Cleanable::Cleanable(Cleanable&& other) noexcept { *this = std::move(other); }
                                                           ~~~~~^
/Users/jaepil/work/deepsearch/deps/cpp/rocksdb/util/cleanable.cc:126:16: error: no member named 'move' in namespace 'std'
  *this = std::move(from);
          ~~~~~^
2 errors generated.
[209/315] Building CXX object CMakeFiles/rocksdb.dir/tools/block_cache_analyzer/block_cache_trace_analyzer.cc.o
ninja: build stopped: subcommand failed.
```

Pull Request resolved: https://github.com/facebook/rocksdb/pull/10033

Reviewed By: jay-zhuang

Differential Revision: D36580562

Pulled By: ajkr

fbshipit-source-id: 0f6b241d186ed528ad62d259af2857d2c2b4ded1
 2022-05-28 00:15:28 -07:00
Peter Dillinger 9d0cae7104 Eliminate unnecessary (slow) block cache Ref()ing in MultiGet (#9899) 
Summary:
When MultiGet() determines that multiple query keys can be
served by examining the same data block in block cache (one Lookup()),
each PinnableSlice referring to data in that data block needs to hold
on to the block in cache so that they can be released at arbitrary
times by the API user. Historically this is accomplished with extra
calls to Ref() on the Handle from Lookup(), with each PinnableSlice
cleanup calling Release() on the Handle, but this creates extra
contention on the block cache for the extra Ref()s and Release()es,
especially because they hit the same cache shard repeatedly.

In the case of merge operands (possibly more cases?), the problem was
compounded by doing an extra Ref()+eventual Release() for each merge
operand for a key reusing a block (which could be the same key!), rather
than one Ref() per key. (Note: the non-shared case with `biter` was
already one per key.)

This change optimizes MultiGet not to rely on these extra, contentious
Ref()+Release() calls by instead, in the shared block case, wrapping
the cache Release() cleanup in a refcounted object referenced by the
PinnableSlices, such that after the last wrapped reference is released,
the cache entry is Release()ed. Relaxed atomic refcounts should be
much faster than mutex-guarded Ref() and Release(), and much less prone
to a performance cliff when MultiGet() does a lot of block sharing.

Note that I did not use std::shared_ptr, because that would require an
extra indirection object (shared_ptr itself new/delete) in order to
associate a ref increment/decrement with a Cleanable cleanup entry. (If
I assumed it was the size of two pointers, I could do some hackery to
make it work without the extra indirection, but that's too fragile.)

Some details:
* Fixed (removed) extra block cache tracing entries in cases of cache
entry reuse in MultiGet, but it's likely that in some other cases traces
are missing (XXX comment inserted)
* Moved existing implementations for cleanable.h from iterator.cc to
new cleanable.cc
* Improved API comments on Cleanable
* Added a public SharedCleanablePtr class to cleanable.h in case others
could benefit from the same pattern (potentially many Cleanables and/or
smart pointers referencing a shared Cleanable)
* Add a typedef for MultiGetContext::Mask
* Some variable renaming for clarity

Pull Request resolved: https://github.com/facebook/rocksdb/pull/9899

Test Plan:
Added unit tests for SharedCleanablePtr.

Greatly enhanced ability of existing tests to detect cache use-after-free.
* Release PinnableSlices from MultiGet as they are read rather than in
bulk (in db_test_util wrapper).
* In ASAN build, default to using a trivially small LRUCache for block_cache
so that entries are immediately erased when unreferenced. (Updated two
tests that depend on caching.) New ASAN testsuite running time seems
OK to me.

If I introduce a bug into my implementation where we skip the shared
cleanups on block reuse, ASAN detects the bug in
`db_basic_test *MultiGet*`. If I remove either of the above testing
enhancements, the bug is not detected.

Consider for follow-up work: manipulate or randomize ordering of
PinnableSlice use and release from MultiGet db_test_util wrapper. But in
typical cases, natural ordering gives pretty good functional coverage.

Performance test:
In the extreme (but possible) case of MultiGetting the same or adjacent keys
in a batch, throughput can improve by an order of magnitude.
`./db_bench -benchmarks=multireadrandom -db=/dev/shm/testdb -readonly -num=5 -duration=10 -threads=20 -multiread_batched -batch_size=200`
Before ops/sec, num=5: 1,384,394
Before ops/sec, num=500: 6,423,720
After ops/sec, num=500: 10,658,794
After ops/sec, num=5: 16,027,257

Also note that previously, with high parallelism, having query keys
concentrated in a single block was worse than spreading them out a bit. Now
concentrated in a single block is faster than spread out, which is hopefully
consistent with natural expectation.

Random query performance: with num=1000000, over 999 x 10s runs running before & after simultaneously (each -threads=12):
Before: multireadrandom [AVG    999 runs] : 1088699 (± 7344) ops/sec;  120.4 (± 0.8 ) MB/sec
After: multireadrandom [AVG    999 runs] : 1090402 (± 7230) ops/sec;  120.6 (± 0.8 ) MB/sec
Possibly better, possibly in the noise.

Reviewed By: anand1976

Differential Revision: D35907003

Pulled By: pdillinger

fbshipit-source-id: bbd244d703649a8ca12d476f2d03853ed9d1a17e
 2022-04-26 21:59:24 -07:00