mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-26 16:30:56 +00:00
62fc15f009
Summary: add option `block_protection_bytes_per_key` and implementation for block per key-value checksum. The main changes are 1. checksum construction and verification in block.cc/h 2. pass the option `block_protection_bytes_per_key` around (mainly for methods defined in table_cache.h) 3. unit tests/crash test updates Tests: * Added unit tests * Crash test: `python3 tools/db_crashtest.py blackbox --simple --block_protection_bytes_per_key=1 --write_buffer_size=1048576` Follow up (maybe as a separate PR): make sure corruption status returned from BlockIters are correctly handled. Performance: Turning on block per KV protection has a non-trivial negative impact on read performance and costs additional memory. For memory, each block includes additional 24 bytes for checksum-related states beside checksum itself. For CPU, I set up a DB of size ~1.2GB with 5M keys (32 bytes key and 200 bytes value) which compacts to ~5 SST files (target file size 256 MB) in L6 without compression. I tested readrandom performance with various block cache size (to mimic various cache hit rates): ``` SETUP make OPTIMIZE_LEVEL="-O3" USE_LTO=1 DEBUG_LEVEL=0 -j32 db_bench ./db_bench -benchmarks=fillseq,compact0,waitforcompaction,compact,waitforcompaction -write_buffer_size=33554432 -level_compaction_dynamic_level_bytes=true -max_background_jobs=8 -target_file_size_base=268435456 --num=5000000 --key_size=32 --value_size=200 --compression_type=none BENCHMARK ./db_bench --use_existing_db -benchmarks=readtocache,readrandom[-X10] --num=5000000 --key_size=32 --disable_auto_compactions --reads=1000000 --block_protection_bytes_per_key=[0|1] --cache_size=$CACHESIZE The readrandom ops/sec looks like the following: Block cache size: 2GB 1.2GB * 0.9 1.2GB * 0.8 1.2GB * 0.5 8MB Main 240805 223604 198176 161653 139040 PR prot_bytes=0 238691 226693 200127 161082 141153 PR prot_bytes=1 214983 193199 178532 137013 108211 prot_bytes=1 vs -10% -15% -10.8% -15% -23% prot_bytes=0 ``` The benchmark has a lot of variance, but there was a 5% to 25% regression in this benchmark with different cache hit rates. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11287 Reviewed By: ajkr Differential Revision: D43970708 Pulled By: cbi42 fbshipit-source-id: ef98d898b71779846fa74212b9ec9e08b7183940
82 lines
3.2 KiB
C++
82 lines
3.2 KiB
C++
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
// (found in the LICENSE.Apache file in the root directory).
|
|
//
|
|
|
|
|
|
#include "rocksdb/convenience.h"
|
|
|
|
#include "db/db_impl/db_impl.h"
|
|
#include "util/cast_util.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
void CancelAllBackgroundWork(DB* db, bool wait) {
|
|
(static_cast_with_check<DBImpl>(db->GetRootDB()))
|
|
->CancelAllBackgroundWork(wait);
|
|
}
|
|
|
|
Status DeleteFilesInRange(DB* db, ColumnFamilyHandle* column_family,
|
|
const Slice* begin, const Slice* end,
|
|
bool include_end) {
|
|
RangePtr range(begin, end);
|
|
return DeleteFilesInRanges(db, column_family, &range, 1, include_end);
|
|
}
|
|
|
|
Status DeleteFilesInRanges(DB* db, ColumnFamilyHandle* column_family,
|
|
const RangePtr* ranges, size_t n, bool include_end) {
|
|
return (static_cast_with_check<DBImpl>(db->GetRootDB()))
|
|
->DeleteFilesInRanges(column_family, ranges, n, include_end);
|
|
}
|
|
|
|
Status VerifySstFileChecksum(const Options& options,
|
|
const EnvOptions& env_options,
|
|
const std::string& file_path) {
|
|
// TODO: plumb Env::IOActivity
|
|
const ReadOptions read_options;
|
|
return VerifySstFileChecksum(options, env_options, read_options, file_path);
|
|
}
|
|
Status VerifySstFileChecksum(const Options& options,
|
|
const EnvOptions& env_options,
|
|
const ReadOptions& read_options,
|
|
const std::string& file_path,
|
|
const SequenceNumber& largest_seqno) {
|
|
std::unique_ptr<FSRandomAccessFile> file;
|
|
uint64_t file_size;
|
|
InternalKeyComparator internal_comparator(options.comparator);
|
|
ImmutableOptions ioptions(options);
|
|
|
|
Status s = ioptions.fs->NewRandomAccessFile(
|
|
file_path, FileOptions(env_options), &file, nullptr);
|
|
if (s.ok()) {
|
|
s = ioptions.fs->GetFileSize(file_path, IOOptions(), &file_size, nullptr);
|
|
} else {
|
|
return s;
|
|
}
|
|
std::unique_ptr<TableReader> table_reader;
|
|
std::unique_ptr<RandomAccessFileReader> file_reader(
|
|
new RandomAccessFileReader(
|
|
std::move(file), file_path, ioptions.clock, nullptr /* io_tracer */,
|
|
ioptions.stats /* stats */,
|
|
Histograms::SST_READ_MICROS /* hist_type */,
|
|
nullptr /* file_read_hist */, ioptions.rate_limiter.get()));
|
|
const bool kImmortal = true;
|
|
auto reader_options = TableReaderOptions(
|
|
ioptions, options.prefix_extractor, env_options, internal_comparator,
|
|
options.block_protection_bytes_per_key, false /* skip_filters */,
|
|
!kImmortal, false /* force_direct_prefetch */, -1 /* level */);
|
|
reader_options.largest_seqno = largest_seqno;
|
|
s = ioptions.table_factory->NewTableReader(
|
|
reader_options, std::move(file_reader), file_size, &table_reader,
|
|
false /* prefetch_index_and_filter_in_cache */);
|
|
if (!s.ok()) {
|
|
return s;
|
|
}
|
|
s = table_reader->VerifyChecksum(read_options,
|
|
TableReaderCaller::kUserVerifyChecksum);
|
|
return s;
|
|
}
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|