rocksdb/file/file_prefetch_buffer.h

179 lines
7.3 KiB
C
Raw Normal View History

// 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).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
#pragma once
#include <algorithm>
#include <atomic>
#include <sstream>
#include <string>
#include "file/readahead_file_info.h"
#include "port/port.h"
#include "rocksdb/env.h"
#include "rocksdb/options.h"
#include "util/aligned_buffer.h"
namespace ROCKSDB_NAMESPACE {
#define DEAFULT_DECREMENT 8 * 1024
struct IOOptions;
class RandomAccessFileReader;
// FilePrefetchBuffer is a smart buffer to store and read data from a file.
class FilePrefetchBuffer {
public:
static const int kMinNumFileReadsToStartAutoReadahead = 2;
Fix bug in rocksdb internal automatic prefetching (#9234) Summary: After introducing adaptive_readahead, the original flow got broken. Readahead size was set to 0 because of which rocksdb wasn't be able to do automatic prefetching which it enables after seeing sequential reads. This PR fixes it. ---------------------------------------------------------------------------------------------------- Before this patch: b_bench -use_existing_db=true -db=/tmp/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_size=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 Initializing RocksDB Options from the specified file Initializing RocksDB Options from command-line flags RocksDB: version 6.27 Date: Tue Nov 30 11:56:50 2021 CPU: 24 * Intel Core Processor (Broadwell) CPUCache: 16384 KB Keys: 32 bytes each (+ 0 bytes user-defined timestamp) Values: 512 bytes each (256 bytes after compression) Entries: 5000000 Prefix: 0 bytes Keys per prefix: 0 RawSize: 2594.0 MB (estimated) FileSize: 1373.3 MB (estimated) Write rate: 0 bytes/second Read rate: 0 ops/second Compression: Snappy Compression sampling rate: 0 Memtablerep: SkipListFactory Perf Level: 1 WARNING: Assertions are enabled; benchmarks unnecessarily slow ------------------------------------------------ DB path: [/tmp/prefix_scan] seekrandom : 5356367.174 micros/op 0 ops/sec; 29.4 MB/s (23 of 23 found) ---------------------------------------------------------------------------------------------------- After the patch: ./db_bench -use_existing_db=true -db=/tmp/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_size=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 Initializing RocksDB Options from the specified file Initializing RocksDB Options from command-line flags RocksDB: version 6.27 Date: Tue Nov 30 14:38:33 2021 CPU: 24 * Intel Core Processor (Broadwell) CPUCache: 16384 KB Keys: 32 bytes each (+ 0 bytes user-defined timestamp) Values: 512 bytes each (256 bytes after compression) Entries: 5000000 Prefix: 0 bytes Keys per prefix: 0 RawSize: 2594.0 MB (estimated) FileSize: 1373.3 MB (estimated) Write rate: 0 bytes/second Read rate: 0 ops/second Compression: Snappy Compression sampling rate: 0 Memtablerep: SkipListFactory Perf Level: 1 WARNING: Assertions are enabled; benchmarks unnecessarily slow ------------------------------------------------ DB path: [/tmp/prefix_scan] seekrandom : 456504.277 micros/op 2 ops/sec; 359.8 MB/s (264 of 264 found) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9234 Test Plan: Ran ./db_bench -db=/data/mysql/rocksdb/prefix_scan -benchmarks="fillseq" -key_size=32 -value_size=512 -num=5000000 -use_d irect_io_for_flush_and_compaction=true -target_file_size_base=16777216 and then ./db_bench -use_existing_db=true -db=/data/mysql/rocksdb/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_siz e=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 and compared the results. Reviewed By: anand1976 Differential Revision: D32743965 Pulled By: akankshamahajan15 fbshipit-source-id: b950fba68c91963b7deb5c20acdf471bc60251f5
2021-12-01 06:52:14 +00:00
static const size_t kInitAutoReadaheadSize = 8 * 1024;
// Constructor.
//
// All arguments are optional.
// readahead_size : the initial readahead size.
// max_readahead_size : the maximum readahead size.
// If max_readahead_size > readahead_size, the readahead size will be
// doubled on every IO until max_readahead_size is hit.
// Typically this is set as a multiple of readahead_size.
// max_readahead_size should be greater than equal to readahead_size.
// enable : controls whether reading from the buffer is enabled.
// If false, TryReadFromCache() always return false, and we only take stats
// for the minimum offset if track_min_offset = true.
// track_min_offset : Track the minimum offset ever read and collect stats on
// it. Used for adaptable readahead of the file footer/metadata.
// implicit_auto_readahead : Readahead is enabled implicitly by rocksdb after
// doing sequential scans for two times.
//
// Automatic readhead is enabled for a file if readahead_size
// and max_readahead_size are passed in.
// A user can construct a FilePrefetchBuffer without any arguments, but use
// `Prefetch` to load data into the buffer.
FilePrefetchBuffer(size_t readahead_size = 0, size_t max_readahead_size = 0,
bool enable = true, bool track_min_offset = false,
bool implicit_auto_readahead = false)
: buffer_offset_(0),
readahead_size_(readahead_size),
max_readahead_size_(max_readahead_size),
min_offset_read_(port::kMaxSizet),
enable_(enable),
track_min_offset_(track_min_offset),
implicit_auto_readahead_(implicit_auto_readahead),
prev_offset_(0),
prev_len_(0),
num_file_reads_(kMinNumFileReadsToStartAutoReadahead + 1) {}
// Load data into the buffer from a file.
Add rate limiter priority to ReadOptions (#9424) 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
2022-02-17 07:17:03 +00:00
// reader : the file reader.
// offset : the file offset to start reading from.
// n : the number of bytes to read.
// rate_limiter_priority : rate limiting priority, or `Env::IO_TOTAL` to
// bypass.
Status Prefetch(const IOOptions& opts, RandomAccessFileReader* reader,
Add rate limiter priority to ReadOptions (#9424) 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
2022-02-17 07:17:03 +00:00
uint64_t offset, size_t n,
Env::IOPriority rate_limiter_priority);
// Tries returning the data for a file read from this buffer if that data is
// in the buffer.
// It handles tracking the minimum read offset if track_min_offset = true.
// It also does the exponential readahead when readahead_size is set as part
// of the constructor.
//
Add rate limiter priority to ReadOptions (#9424) 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
2022-02-17 07:17:03 +00:00
// opts : the IO options to use.
// reader : the file reader.
// offset : the file offset.
// n : the number of bytes.
// result : output buffer to put the data into.
// s : output status.
// rate_limiter_priority : rate limiting priority, or `Env::IO_TOTAL` to
// bypass.
// for_compaction : true if cache read is done for compaction read.
bool TryReadFromCache(const IOOptions& opts, RandomAccessFileReader* reader,
uint64_t offset, size_t n, Slice* result, Status* s,
Add rate limiter priority to ReadOptions (#9424) 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
2022-02-17 07:17:03 +00:00
Env::IOPriority rate_limiter_priority,
bool for_compaction = false);
// The minimum `offset` ever passed to TryReadFromCache(). This will nly be
// tracked if track_min_offset = true.
size_t min_offset_read() const { return min_offset_read_; }
Fix bug in rocksdb internal automatic prefetching (#9234) Summary: After introducing adaptive_readahead, the original flow got broken. Readahead size was set to 0 because of which rocksdb wasn't be able to do automatic prefetching which it enables after seeing sequential reads. This PR fixes it. ---------------------------------------------------------------------------------------------------- Before this patch: b_bench -use_existing_db=true -db=/tmp/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_size=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 Initializing RocksDB Options from the specified file Initializing RocksDB Options from command-line flags RocksDB: version 6.27 Date: Tue Nov 30 11:56:50 2021 CPU: 24 * Intel Core Processor (Broadwell) CPUCache: 16384 KB Keys: 32 bytes each (+ 0 bytes user-defined timestamp) Values: 512 bytes each (256 bytes after compression) Entries: 5000000 Prefix: 0 bytes Keys per prefix: 0 RawSize: 2594.0 MB (estimated) FileSize: 1373.3 MB (estimated) Write rate: 0 bytes/second Read rate: 0 ops/second Compression: Snappy Compression sampling rate: 0 Memtablerep: SkipListFactory Perf Level: 1 WARNING: Assertions are enabled; benchmarks unnecessarily slow ------------------------------------------------ DB path: [/tmp/prefix_scan] seekrandom : 5356367.174 micros/op 0 ops/sec; 29.4 MB/s (23 of 23 found) ---------------------------------------------------------------------------------------------------- After the patch: ./db_bench -use_existing_db=true -db=/tmp/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_size=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 Initializing RocksDB Options from the specified file Initializing RocksDB Options from command-line flags RocksDB: version 6.27 Date: Tue Nov 30 14:38:33 2021 CPU: 24 * Intel Core Processor (Broadwell) CPUCache: 16384 KB Keys: 32 bytes each (+ 0 bytes user-defined timestamp) Values: 512 bytes each (256 bytes after compression) Entries: 5000000 Prefix: 0 bytes Keys per prefix: 0 RawSize: 2594.0 MB (estimated) FileSize: 1373.3 MB (estimated) Write rate: 0 bytes/second Read rate: 0 ops/second Compression: Snappy Compression sampling rate: 0 Memtablerep: SkipListFactory Perf Level: 1 WARNING: Assertions are enabled; benchmarks unnecessarily slow ------------------------------------------------ DB path: [/tmp/prefix_scan] seekrandom : 456504.277 micros/op 2 ops/sec; 359.8 MB/s (264 of 264 found) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9234 Test Plan: Ran ./db_bench -db=/data/mysql/rocksdb/prefix_scan -benchmarks="fillseq" -key_size=32 -value_size=512 -num=5000000 -use_d irect_io_for_flush_and_compaction=true -target_file_size_base=16777216 and then ./db_bench -use_existing_db=true -db=/data/mysql/rocksdb/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_siz e=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 and compared the results. Reviewed By: anand1976 Differential Revision: D32743965 Pulled By: akankshamahajan15 fbshipit-source-id: b950fba68c91963b7deb5c20acdf471bc60251f5
2021-12-01 06:52:14 +00:00
// Called in case of implicit auto prefetching.
void UpdateReadPattern(const uint64_t& offset, const size_t& len,
bool is_adaptive_readahead = false) {
if (is_adaptive_readahead) {
// Since this block was eligible for prefetch but it was found in
// cache, so check and decrease the readahead_size by 8KB (default)
// if eligible.
DecreaseReadAheadIfEligible(offset, len);
}
prev_offset_ = offset;
prev_len_ = len;
}
bool IsBlockSequential(const size_t& offset) {
return (prev_len_ == 0 || (prev_offset_ + prev_len_ == offset));
}
Fix bug in rocksdb internal automatic prefetching (#9234) Summary: After introducing adaptive_readahead, the original flow got broken. Readahead size was set to 0 because of which rocksdb wasn't be able to do automatic prefetching which it enables after seeing sequential reads. This PR fixes it. ---------------------------------------------------------------------------------------------------- Before this patch: b_bench -use_existing_db=true -db=/tmp/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_size=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 Initializing RocksDB Options from the specified file Initializing RocksDB Options from command-line flags RocksDB: version 6.27 Date: Tue Nov 30 11:56:50 2021 CPU: 24 * Intel Core Processor (Broadwell) CPUCache: 16384 KB Keys: 32 bytes each (+ 0 bytes user-defined timestamp) Values: 512 bytes each (256 bytes after compression) Entries: 5000000 Prefix: 0 bytes Keys per prefix: 0 RawSize: 2594.0 MB (estimated) FileSize: 1373.3 MB (estimated) Write rate: 0 bytes/second Read rate: 0 ops/second Compression: Snappy Compression sampling rate: 0 Memtablerep: SkipListFactory Perf Level: 1 WARNING: Assertions are enabled; benchmarks unnecessarily slow ------------------------------------------------ DB path: [/tmp/prefix_scan] seekrandom : 5356367.174 micros/op 0 ops/sec; 29.4 MB/s (23 of 23 found) ---------------------------------------------------------------------------------------------------- After the patch: ./db_bench -use_existing_db=true -db=/tmp/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_size=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 Initializing RocksDB Options from the specified file Initializing RocksDB Options from command-line flags RocksDB: version 6.27 Date: Tue Nov 30 14:38:33 2021 CPU: 24 * Intel Core Processor (Broadwell) CPUCache: 16384 KB Keys: 32 bytes each (+ 0 bytes user-defined timestamp) Values: 512 bytes each (256 bytes after compression) Entries: 5000000 Prefix: 0 bytes Keys per prefix: 0 RawSize: 2594.0 MB (estimated) FileSize: 1373.3 MB (estimated) Write rate: 0 bytes/second Read rate: 0 ops/second Compression: Snappy Compression sampling rate: 0 Memtablerep: SkipListFactory Perf Level: 1 WARNING: Assertions are enabled; benchmarks unnecessarily slow ------------------------------------------------ DB path: [/tmp/prefix_scan] seekrandom : 456504.277 micros/op 2 ops/sec; 359.8 MB/s (264 of 264 found) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9234 Test Plan: Ran ./db_bench -db=/data/mysql/rocksdb/prefix_scan -benchmarks="fillseq" -key_size=32 -value_size=512 -num=5000000 -use_d irect_io_for_flush_and_compaction=true -target_file_size_base=16777216 and then ./db_bench -use_existing_db=true -db=/data/mysql/rocksdb/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_siz e=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 and compared the results. Reviewed By: anand1976 Differential Revision: D32743965 Pulled By: akankshamahajan15 fbshipit-source-id: b950fba68c91963b7deb5c20acdf471bc60251f5
2021-12-01 06:52:14 +00:00
// Called in case of implicit auto prefetching.
void ResetValues() {
num_file_reads_ = 1;
Fix bug in rocksdb internal automatic prefetching (#9234) Summary: After introducing adaptive_readahead, the original flow got broken. Readahead size was set to 0 because of which rocksdb wasn't be able to do automatic prefetching which it enables after seeing sequential reads. This PR fixes it. ---------------------------------------------------------------------------------------------------- Before this patch: b_bench -use_existing_db=true -db=/tmp/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_size=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 Initializing RocksDB Options from the specified file Initializing RocksDB Options from command-line flags RocksDB: version 6.27 Date: Tue Nov 30 11:56:50 2021 CPU: 24 * Intel Core Processor (Broadwell) CPUCache: 16384 KB Keys: 32 bytes each (+ 0 bytes user-defined timestamp) Values: 512 bytes each (256 bytes after compression) Entries: 5000000 Prefix: 0 bytes Keys per prefix: 0 RawSize: 2594.0 MB (estimated) FileSize: 1373.3 MB (estimated) Write rate: 0 bytes/second Read rate: 0 ops/second Compression: Snappy Compression sampling rate: 0 Memtablerep: SkipListFactory Perf Level: 1 WARNING: Assertions are enabled; benchmarks unnecessarily slow ------------------------------------------------ DB path: [/tmp/prefix_scan] seekrandom : 5356367.174 micros/op 0 ops/sec; 29.4 MB/s (23 of 23 found) ---------------------------------------------------------------------------------------------------- After the patch: ./db_bench -use_existing_db=true -db=/tmp/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_size=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 Initializing RocksDB Options from the specified file Initializing RocksDB Options from command-line flags RocksDB: version 6.27 Date: Tue Nov 30 14:38:33 2021 CPU: 24 * Intel Core Processor (Broadwell) CPUCache: 16384 KB Keys: 32 bytes each (+ 0 bytes user-defined timestamp) Values: 512 bytes each (256 bytes after compression) Entries: 5000000 Prefix: 0 bytes Keys per prefix: 0 RawSize: 2594.0 MB (estimated) FileSize: 1373.3 MB (estimated) Write rate: 0 bytes/second Read rate: 0 ops/second Compression: Snappy Compression sampling rate: 0 Memtablerep: SkipListFactory Perf Level: 1 WARNING: Assertions are enabled; benchmarks unnecessarily slow ------------------------------------------------ DB path: [/tmp/prefix_scan] seekrandom : 456504.277 micros/op 2 ops/sec; 359.8 MB/s (264 of 264 found) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9234 Test Plan: Ran ./db_bench -db=/data/mysql/rocksdb/prefix_scan -benchmarks="fillseq" -key_size=32 -value_size=512 -num=5000000 -use_d irect_io_for_flush_and_compaction=true -target_file_size_base=16777216 and then ./db_bench -use_existing_db=true -db=/data/mysql/rocksdb/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_siz e=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 and compared the results. Reviewed By: anand1976 Differential Revision: D32743965 Pulled By: akankshamahajan15 fbshipit-source-id: b950fba68c91963b7deb5c20acdf471bc60251f5
2021-12-01 06:52:14 +00:00
readahead_size_ = kInitAutoReadaheadSize;
}
void GetReadaheadState(ReadaheadFileInfo::ReadaheadInfo* readahead_info) {
readahead_info->readahead_size = readahead_size_;
readahead_info->num_file_reads = num_file_reads_;
}
void DecreaseReadAheadIfEligible(uint64_t offset, size_t size,
size_t value = DEAFULT_DECREMENT) {
// Decrease the readahead_size if
// - its enabled internally by RocksDB (implicit_auto_readahead_) and,
// - readahead_size is greater than 0 and,
// - this block would have called prefetch API if not found in cache for
// which conditions are:
// - few/no bytes are in buffer and,
// - block is sequential with the previous read and,
// - num_file_reads_ + 1 (including this read) >
// kMinNumFileReadsToStartAutoReadahead
if (implicit_auto_readahead_ && readahead_size_ > 0) {
if ((offset + size > buffer_offset_ + buffer_.CurrentSize()) &&
IsBlockSequential(offset) &&
(num_file_reads_ + 1 > kMinNumFileReadsToStartAutoReadahead)) {
Fix bug in rocksdb internal automatic prefetching (#9234) Summary: After introducing adaptive_readahead, the original flow got broken. Readahead size was set to 0 because of which rocksdb wasn't be able to do automatic prefetching which it enables after seeing sequential reads. This PR fixes it. ---------------------------------------------------------------------------------------------------- Before this patch: b_bench -use_existing_db=true -db=/tmp/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_size=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 Initializing RocksDB Options from the specified file Initializing RocksDB Options from command-line flags RocksDB: version 6.27 Date: Tue Nov 30 11:56:50 2021 CPU: 24 * Intel Core Processor (Broadwell) CPUCache: 16384 KB Keys: 32 bytes each (+ 0 bytes user-defined timestamp) Values: 512 bytes each (256 bytes after compression) Entries: 5000000 Prefix: 0 bytes Keys per prefix: 0 RawSize: 2594.0 MB (estimated) FileSize: 1373.3 MB (estimated) Write rate: 0 bytes/second Read rate: 0 ops/second Compression: Snappy Compression sampling rate: 0 Memtablerep: SkipListFactory Perf Level: 1 WARNING: Assertions are enabled; benchmarks unnecessarily slow ------------------------------------------------ DB path: [/tmp/prefix_scan] seekrandom : 5356367.174 micros/op 0 ops/sec; 29.4 MB/s (23 of 23 found) ---------------------------------------------------------------------------------------------------- After the patch: ./db_bench -use_existing_db=true -db=/tmp/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_size=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 Initializing RocksDB Options from the specified file Initializing RocksDB Options from command-line flags RocksDB: version 6.27 Date: Tue Nov 30 14:38:33 2021 CPU: 24 * Intel Core Processor (Broadwell) CPUCache: 16384 KB Keys: 32 bytes each (+ 0 bytes user-defined timestamp) Values: 512 bytes each (256 bytes after compression) Entries: 5000000 Prefix: 0 bytes Keys per prefix: 0 RawSize: 2594.0 MB (estimated) FileSize: 1373.3 MB (estimated) Write rate: 0 bytes/second Read rate: 0 ops/second Compression: Snappy Compression sampling rate: 0 Memtablerep: SkipListFactory Perf Level: 1 WARNING: Assertions are enabled; benchmarks unnecessarily slow ------------------------------------------------ DB path: [/tmp/prefix_scan] seekrandom : 456504.277 micros/op 2 ops/sec; 359.8 MB/s (264 of 264 found) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9234 Test Plan: Ran ./db_bench -db=/data/mysql/rocksdb/prefix_scan -benchmarks="fillseq" -key_size=32 -value_size=512 -num=5000000 -use_d irect_io_for_flush_and_compaction=true -target_file_size_base=16777216 and then ./db_bench -use_existing_db=true -db=/data/mysql/rocksdb/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_siz e=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 and compared the results. Reviewed By: anand1976 Differential Revision: D32743965 Pulled By: akankshamahajan15 fbshipit-source-id: b950fba68c91963b7deb5c20acdf471bc60251f5
2021-12-01 06:52:14 +00:00
size_t initial_auto_readahead_size = kInitAutoReadaheadSize;
readahead_size_ =
Fix bug in rocksdb internal automatic prefetching (#9234) Summary: After introducing adaptive_readahead, the original flow got broken. Readahead size was set to 0 because of which rocksdb wasn't be able to do automatic prefetching which it enables after seeing sequential reads. This PR fixes it. ---------------------------------------------------------------------------------------------------- Before this patch: b_bench -use_existing_db=true -db=/tmp/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_size=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 Initializing RocksDB Options from the specified file Initializing RocksDB Options from command-line flags RocksDB: version 6.27 Date: Tue Nov 30 11:56:50 2021 CPU: 24 * Intel Core Processor (Broadwell) CPUCache: 16384 KB Keys: 32 bytes each (+ 0 bytes user-defined timestamp) Values: 512 bytes each (256 bytes after compression) Entries: 5000000 Prefix: 0 bytes Keys per prefix: 0 RawSize: 2594.0 MB (estimated) FileSize: 1373.3 MB (estimated) Write rate: 0 bytes/second Read rate: 0 ops/second Compression: Snappy Compression sampling rate: 0 Memtablerep: SkipListFactory Perf Level: 1 WARNING: Assertions are enabled; benchmarks unnecessarily slow ------------------------------------------------ DB path: [/tmp/prefix_scan] seekrandom : 5356367.174 micros/op 0 ops/sec; 29.4 MB/s (23 of 23 found) ---------------------------------------------------------------------------------------------------- After the patch: ./db_bench -use_existing_db=true -db=/tmp/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_size=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 Initializing RocksDB Options from the specified file Initializing RocksDB Options from command-line flags RocksDB: version 6.27 Date: Tue Nov 30 14:38:33 2021 CPU: 24 * Intel Core Processor (Broadwell) CPUCache: 16384 KB Keys: 32 bytes each (+ 0 bytes user-defined timestamp) Values: 512 bytes each (256 bytes after compression) Entries: 5000000 Prefix: 0 bytes Keys per prefix: 0 RawSize: 2594.0 MB (estimated) FileSize: 1373.3 MB (estimated) Write rate: 0 bytes/second Read rate: 0 ops/second Compression: Snappy Compression sampling rate: 0 Memtablerep: SkipListFactory Perf Level: 1 WARNING: Assertions are enabled; benchmarks unnecessarily slow ------------------------------------------------ DB path: [/tmp/prefix_scan] seekrandom : 456504.277 micros/op 2 ops/sec; 359.8 MB/s (264 of 264 found) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9234 Test Plan: Ran ./db_bench -db=/data/mysql/rocksdb/prefix_scan -benchmarks="fillseq" -key_size=32 -value_size=512 -num=5000000 -use_d irect_io_for_flush_and_compaction=true -target_file_size_base=16777216 and then ./db_bench -use_existing_db=true -db=/data/mysql/rocksdb/prefix_scan -benchmarks="seekrandom" -key_size=32 -value_siz e=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1 and compared the results. Reviewed By: anand1976 Differential Revision: D32743965 Pulled By: akankshamahajan15 fbshipit-source-id: b950fba68c91963b7deb5c20acdf471bc60251f5
2021-12-01 06:52:14 +00:00
std::max(initial_auto_readahead_size,
(readahead_size_ >= value ? readahead_size_ - value : 0));
}
}
}
private:
AlignedBuffer buffer_;
uint64_t buffer_offset_;
size_t readahead_size_;
// FilePrefetchBuffer object won't be created from Iterator flow if
// max_readahead_size_ = 0.
size_t max_readahead_size_;
// The minimum `offset` ever passed to TryReadFromCache().
size_t min_offset_read_;
// if false, TryReadFromCache() always return false, and we only take stats
// for track_min_offset_ if track_min_offset_ = true
bool enable_;
// If true, track minimum `offset` ever passed to TryReadFromCache(), which
// can be fetched from min_offset_read().
bool track_min_offset_;
// implicit_auto_readahead is enabled by rocksdb internally after 2
// sequential IOs.
bool implicit_auto_readahead_;
uint64_t prev_offset_;
size_t prev_len_;
int64_t num_file_reads_;
};
} // namespace ROCKSDB_NAMESPACE