mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-26 16:30:56 +00:00
9a034801ce
Summary:
**Context/Summary:**
- Similar to https://github.com/facebook/rocksdb/pull/11288 but for user read such as `Get(), MultiGet(), DBIterator::XXX(), Verify(File)Checksum()`.
- For this, I refactored some user-facing `MultiGet` calls in `TransactionBase` and various types of `DB` so that it does not call a user-facing `Get()` but `GetImpl()` for passing the `ReadOptions::io_activity` check (see PR conversation)
- New user read stats breakdown are guarded by `kExceptDetailedTimers` since measurement shows they have 4-5% regression to the upstream/main.
- Misc
- More refactoring: with https://github.com/facebook/rocksdb/pull/11288, we complete passing `ReadOptions/IOOptions` to FS level. So we can now replace the previously [added](https://github.com/facebook/rocksdb/pull/9424) `rate_limiter_priority` parameter in `RandomAccessFileReader`'s `Read/MultiRead/Prefetch()` with `IOOptions::rate_limiter_priority`
- Also, `ReadAsync()` call time is measured in `SST_READ_MICRO` now
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11444
Test Plan:
- CI fake db crash/stress test
- Microbenchmarking
**Build** `make clean && ROCKSDB_NO_FBCODE=1 DEBUG_LEVEL=0 make -jN db_basic_bench`
- google benchmark version: 604f6fd3f4
- db_basic_bench_base: upstream
- db_basic_bench_pr: db_basic_bench_base + this PR
- asyncread_db_basic_bench_base: upstream + [db basic bench patch for IteratorNext](https://github.com/facebook/rocksdb/compare/main...hx235:rocksdb:micro_bench_async_read)
- asyncread_db_basic_bench_pr: asyncread_db_basic_bench_base + this PR
**Test**
Get
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_{null_stat|base|pr} --benchmark_filter=DBGet/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1/negative_query:0/enable_filter:0/mmap:1/threads:1 --benchmark_repetitions=1000
```
Result
```
Coming soon
```
AsyncRead
```
TEST_TMPDIR=/dev/shm ./asyncread_db_basic_bench_{base|pr} --benchmark_filter=IteratorNext/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1/async_io:1/include_detailed_timers:0 --benchmark_repetitions=1000 > syncread_db_basic_bench_{base|pr}.out
```
Result
```
Base:
1956,1956,1968,1977,1979,1986,1988,1988,1988,1990,1991,1991,1993,1993,1993,1993,1994,1996,1997,1997,1997,1998,1999,2001,2001,2002,2004,2007,2007,2008,
PR (2.3% regression, due to measuring `SST_READ_MICRO` that wasn't measured before):
1993,2014,2016,2022,2024,2027,2027,2028,2028,2030,2031,2031,2032,2032,2038,2039,2042,2044,2044,2047,2047,2047,2048,2049,2050,2052,2052,2052,2053,2053,
```
Reviewed By: ajkr
Differential Revision: D45918925
Pulled By: hx235
fbshipit-source-id: 58a54560d9ebeb3a59b6d807639692614dad058a
99 lines
3.9 KiB
C++
99 lines
3.9 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/convenience_impl.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) {
|
|
if (_read_options.io_activity != Env::IOActivity::kUnknown) {
|
|
return Status::InvalidArgument(
|
|
"Can only call VerifySstFileChecksum with `ReadOptions::io_activity` "
|
|
"is "
|
|
"`Env::IOActivity::kUnknown`");
|
|
}
|
|
ReadOptions read_options(_read_options);
|
|
return VerifySstFileChecksumInternal(options, env_options, read_options,
|
|
file_path, largest_seqno);
|
|
}
|
|
|
|
Status VerifySstFileChecksumInternal(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(
|
|
read_options, 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
|