babe56ddba
Summary: Users can set the priority for file reads associated with their operation by setting `ReadOptions::rate_limiter_priority` to something other than `Env::IO_TOTAL`. Rate limiting `VerifyChecksum()` and `VerifyFileChecksums()` is the motivation for this PR, so it also includes benchmarks and minor bug fixes to get that working. `RandomAccessFileReader::Read()` already had support for rate limiting compaction reads. I changed that rate limiting to be non-specific to compaction, but rather performed according to the passed in `Env::IOPriority`. Now the compaction read rate limiting is supported by setting `rate_limiter_priority = Env::IO_LOW` on its `ReadOptions`. There is no default value for the new `Env::IOPriority` parameter to `RandomAccessFileReader::Read()`. That means this PR goes through all callers (in some cases multiple layers up the call stack) to find a `ReadOptions` to provide the priority. There are TODOs for cases I believe it would be good to let user control the priority some day (e.g., file footer reads), and no TODO in cases I believe it doesn't matter (e.g., trace file reads). The API doc only lists the missing cases where a file read associated with a provided `ReadOptions` cannot be rate limited. For cases like file ingestion checksum calculation, there is no API to provide `ReadOptions` or `Env::IOPriority`, so I didn't count that as missing. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9424 Test Plan: - new unit tests - new benchmarks on ~50MB database with 1MB/s read rate limit and 100ms refill interval; verified with strace reads are chunked (at 0.1MB per chunk) and spaced roughly 100ms apart. - setup command: `./db_bench -benchmarks=fillrandom,compact -db=/tmp/testdb -target_file_size_base=1048576 -disable_auto_compactions=true -file_checksum=true` - benchmarks command: `strace -ttfe pread64 ./db_bench -benchmarks=verifychecksum,verifyfilechecksums -use_existing_db=true -db=/tmp/testdb -rate_limiter_bytes_per_sec=1048576 -rate_limit_bg_reads=1 -rate_limit_user_ops=true -file_checksum=true` - crash test using IO_USER priority on non-validation reads with https://github.com/facebook/rocksdb/issues/9567 reverted: `python3 tools/db_crashtest.py blackbox --max_key=1000000 --write_buffer_size=524288 --target_file_size_base=524288 --level_compaction_dynamic_level_bytes=true --duration=3600 --rate_limit_bg_reads=true --rate_limit_user_ops=true --rate_limiter_bytes_per_sec=10485760 --interval=10` Reviewed By: hx235 Differential Revision: D33747386 Pulled By: ajkr fbshipit-source-id: a2d985e97912fba8c54763798e04f006ccc56e0c
82 lines
3.1 KiB
C++
82 lines
3.1 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).
|
|
//
|
|
|
|
#ifndef ROCKSDB_LITE
|
|
|
|
#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) {
|
|
return VerifySstFileChecksum(options, env_options, ReadOptions(), file_path);
|
|
}
|
|
Status VerifySstFileChecksum(const Options& options,
|
|
const EnvOptions& env_options,
|
|
const ReadOptions& read_options,
|
|
const std::string& file_path) {
|
|
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 */,
|
|
nullptr /* stats */, 0 /* hist_type */, nullptr /* file_read_hist */,
|
|
ioptions.rate_limiter.get()));
|
|
const bool kImmortal = true;
|
|
s = ioptions.table_factory->NewTableReader(
|
|
TableReaderOptions(ioptions, options.prefix_extractor, env_options,
|
|
internal_comparator, false /* skip_filters */,
|
|
!kImmortal, false /* force_direct_prefetch */,
|
|
-1 /* level */),
|
|
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
|
|
|
|
#endif // ROCKSDB_LITE
|