rocksdb/file/random_access_file_reader.h

198 lines
7.2 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 <atomic>
#include <sstream>
#include <string>
#include "env/file_system_tracer.h"
#include "port/port.h"
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
2019-12-13 22:47:08 +00:00
#include "rocksdb/file_system.h"
#include "rocksdb/listener.h"
#include "rocksdb/options.h"
#include "rocksdb/rate_limiter.h"
#include "util/aligned_buffer.h"
namespace ROCKSDB_NAMESPACE {
class Statistics;
class HistogramImpl;
class SystemClock;
using AlignedBuf = std::unique_ptr<char[]>;
// Align the request r according to alignment and return the aligned result.
FSReadRequest Align(const FSReadRequest& r, size_t alignment);
// Try to merge src to dest if they have overlap.
//
// Each request represents an inclusive interval [offset, offset + len].
// If the intervals have overlap, update offset and len to represent the
// merged interval, and return true.
// Otherwise, do nothing and return false.
bool TryMerge(FSReadRequest* dest, const FSReadRequest& src);
// RandomAccessFileReader is a wrapper on top of FSRandomAccessFile. It is
// responsible for:
// - Handling Buffered and Direct reads appropriately.
// - Rate limiting compaction reads.
// - Notifying any interested listeners on the completion of a read.
// - Updating IO stats.
class RandomAccessFileReader {
private:
void NotifyOnFileReadFinish(
uint64_t offset, size_t length,
const FileOperationInfo::StartTimePoint& start_ts,
const FileOperationInfo::FinishTimePoint& finish_ts,
const Status& status) const {
FileOperationInfo info(FileOperationType::kRead, file_name_, start_ts,
finish_ts, status, file_temperature_);
info.offset = offset;
info.length = length;
for (auto& listener : listeners_) {
listener->OnFileReadFinish(info);
}
info.status.PermitUncheckedError();
}
void NotifyOnIOError(const IOStatus& io_status, FileOperationType operation,
const std::string& file_path, size_t length,
uint64_t offset) const {
if (listeners_.empty()) {
return;
}
IOErrorInfo io_error_info(io_status, operation, file_path, length, offset);
for (auto& listener : listeners_) {
listener->OnIOError(io_error_info);
}
io_status.PermitUncheckedError();
}
bool ShouldNotifyListeners() const { return !listeners_.empty(); }
FSRandomAccessFilePtr file_;
std::string file_name_;
SystemClock* clock_;
Statistics* stats_;
uint32_t hist_type_;
HistogramImpl* file_read_hist_;
RateLimiter* rate_limiter_;
std::vector<std::shared_ptr<EventListener>> listeners_;
const Temperature file_temperature_;
const bool is_last_level_;
struct ReadAsyncInfo {
ReadAsyncInfo(std::function<void(FSReadRequest&, void*)> cb, void* cb_arg,
uint64_t start_time)
: cb_(cb),
cb_arg_(cb_arg),
start_time_(start_time),
user_scratch_(nullptr),
user_aligned_buf_(nullptr),
user_offset_(0),
user_len_(0),
is_aligned_(false) {}
std::function<void(FSReadRequest&, void*)> cb_;
void* cb_arg_;
uint64_t start_time_;
FileOperationInfo::StartTimePoint fs_start_ts_;
// Below fields stores the parameters passed by caller in case of direct_io.
char* user_scratch_;
AlignedBuf* user_aligned_buf_;
uint64_t user_offset_;
size_t user_len_;
Slice user_result_;
// Used in case of direct_io
AlignedBuffer buf_;
bool is_aligned_;
};
public:
explicit RandomAccessFileReader(
std::unique_ptr<FSRandomAccessFile>&& raf, const std::string& _file_name,
SystemClock* clock = nullptr,
const std::shared_ptr<IOTracer>& io_tracer = nullptr,
Group rocksdb.sst.read.micros stat by IOActivity flush and compaction (#11288) Summary: **Context:** The existing stat rocksdb.sst.read.micros does not reflect each of compaction and flush cases but aggregate them, which is not so helpful for us to understand IO read behavior of each of them. **Summary** - Update `StopWatch` and `RandomAccessFileReader` to record `rocksdb.sst.read.micros` and `rocksdb.file.{flush/compaction}.read.micros` - Fixed the default histogram in `RandomAccessFileReader` - New field `ReadOptions/IOOptions::io_activity`; Pass `ReadOptions` through paths under db open, flush and compaction to where we can prepare `IOOptions` and pass it to `RandomAccessFileReader` - Use `thread_status_util` for assertion in `DbStressFSWrapper` for continuous testing on we are passing correct `io_activity` under db open, flush and compaction Pull Request resolved: https://github.com/facebook/rocksdb/pull/11288 Test Plan: - **Stress test** - **Db bench 1: rocksdb.sst.read.micros COUNT ≈ sum of rocksdb.file.read.flush.micros's and rocksdb.file.read.compaction.micros's.** (without blob) - May not be exactly the same due to `HistogramStat::Add` only guarantees atomic not accuracy across threads. ``` ./db_bench -db=/dev/shm/testdb/ -statistics=true -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -target_file_size_base=655 -disable_auto_compactions=false -compression_type=none -bloom_bits=3 (-use_plain_table=1 -prefix_size=10) ``` ``` // BlockBasedTable rocksdb.sst.read.micros P50 : 2.009374 P95 : 4.968548 P99 : 8.110362 P100 : 43.000000 COUNT : 40456 SUM : 114805 rocksdb.file.read.flush.micros P50 : 1.871841 P95 : 3.872407 P99 : 5.540541 P100 : 43.000000 COUNT : 2250 SUM : 6116 rocksdb.file.read.compaction.micros P50 : 2.023109 P95 : 5.029149 P99 : 8.196910 P100 : 26.000000 COUNT : 38206 SUM : 108689 // PlainTable Does not apply ``` - **Db bench 2: performance** **Read** SETUP: db with 900 files ``` ./db_bench -db=/dev/shm/testdb/ -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=true -target_file_size_base=655 -compression_type=none ```run till convergence ``` ./db_bench -seed=1678564177044286 -use_existing_db=true -db=/dev/shm/testdb -benchmarks=readrandom[-X60] -statistics=true -num=1000000 -disable_auto_compactions=true -compression_type=none -bloom_bits=3 ``` Pre-change `readrandom [AVG 60 runs] : 21568 (± 248) ops/sec` Post-change (no regression, -0.3%) `readrandom [AVG 60 runs] : 21486 (± 236) ops/sec` **Compaction/Flush**run till convergence ``` ./db_bench -db=/dev/shm/testdb2/ -seed=1678564177044286 -benchmarks="fillseq[-X60]" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=false -target_file_size_base=655 -compression_type=none rocksdb.sst.read.micros COUNT : 33820 rocksdb.sst.read.flush.micros COUNT : 1800 rocksdb.sst.read.compaction.micros COUNT : 32020 ``` Pre-change `fillseq [AVG 46 runs] : 1391 (± 214) ops/sec; 0.7 (± 0.1) MB/sec` Post-change (no regression, ~-0.4%) `fillseq [AVG 46 runs] : 1385 (± 216) ops/sec; 0.7 (± 0.1) MB/sec` Reviewed By: ajkr Differential Revision: D44007011 Pulled By: hx235 fbshipit-source-id: a54c89e4846dfc9a135389edf3f3eedfea257132
2023-04-21 16:07:18 +00:00
Statistics* stats = nullptr,
uint32_t hist_type = Histograms::HISTOGRAM_ENUM_MAX,
HistogramImpl* file_read_hist = nullptr,
RateLimiter* rate_limiter = nullptr,
const std::vector<std::shared_ptr<EventListener>>& listeners = {},
Temperature file_temperature = Temperature::kUnknown,
bool is_last_level = false)
: file_(std::move(raf), io_tracer, _file_name),
file_name_(std::move(_file_name)),
clock_(clock),
stats_(stats),
hist_type_(hist_type),
file_read_hist_(file_read_hist),
rate_limiter_(rate_limiter),
listeners_(),
file_temperature_(file_temperature),
is_last_level_(is_last_level) {
std::for_each(listeners.begin(), listeners.end(),
[this](const std::shared_ptr<EventListener>& e) {
if (e->ShouldBeNotifiedOnFileIO()) {
listeners_.emplace_back(e);
}
});
}
static IOStatus Create(const std::shared_ptr<FileSystem>& fs,
const std::string& fname, const FileOptions& file_opts,
std::unique_ptr<RandomAccessFileReader>* reader,
IODebugContext* dbg);
RandomAccessFileReader(const RandomAccessFileReader&) = delete;
RandomAccessFileReader& operator=(const RandomAccessFileReader&) = delete;
// In non-direct IO mode,
// 1. if using mmap, result is stored in a buffer other than scratch;
// 2. if not using mmap, result is stored in the buffer starting from scratch.
//
// In direct IO mode, an aligned buffer is allocated internally.
// 1. If aligned_buf is null, then results are copied to the buffer
// starting from scratch;
// 2. Otherwise, scratch is not used and can be null, the aligned_buf owns
// the internally allocated buffer on return, and the result refers to a
// region in aligned_buf.
IOStatus Read(const IOOptions& opts, uint64_t offset, size_t n, Slice* result,
Group rocksdb.sst.read.micros stat by different user read IOActivity + misc (#11444) 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: https://github.com/google/benchmark/commit/604f6fd3f4b34a84ec4eb4db81d842fa4db829cd - 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
2023-08-09 00:26:50 +00:00
char* scratch, AlignedBuf* aligned_buf) const;
// REQUIRES:
// num_reqs > 0, reqs do not overlap, and offsets in reqs are increasing.
// In non-direct IO mode, aligned_buf should be null;
// In direct IO mode, aligned_buf stores the aligned buffer allocated inside
// MultiRead, the result Slices in reqs refer to aligned_buf.
IOStatus MultiRead(const IOOptions& opts, FSReadRequest* reqs,
Group rocksdb.sst.read.micros stat by different user read IOActivity + misc (#11444) 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: https://github.com/google/benchmark/commit/604f6fd3f4b34a84ec4eb4db81d842fa4db829cd - 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
2023-08-09 00:26:50 +00:00
size_t num_reqs, AlignedBuf* aligned_buf) const;
Group rocksdb.sst.read.micros stat by different user read IOActivity + misc (#11444) 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: https://github.com/google/benchmark/commit/604f6fd3f4b34a84ec4eb4db81d842fa4db829cd - 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
2023-08-09 00:26:50 +00:00
IOStatus Prefetch(const IOOptions& opts, uint64_t offset, size_t n) const {
Set Read rate limiter priority dynamically and pass it to FS (#9996) Summary: ### Context: Background compactions and flush generate large reads and writes, and can be long running, especially for universal compaction. In some cases, this can impact foreground reads and writes by users. ### Solution User, Flush, and Compaction reads share some code path. For this task, we update the rate_limiter_priority in ReadOptions for code paths (e.g. FindTable (mainly in BlockBasedTable::Open()) and various iterators), and eventually update the rate_limiter_priority in IOOptions for FSRandomAccessFile. **This PR is for the Read path.** The **Read:** dynamic priority for different state are listed as follows: | State | Normal | Delayed | Stalled | | ----- | ------ | ------- | ------- | | Flush (verification read in BuildTable()) | IO_USER | IO_USER | IO_USER | | Compaction | IO_LOW | IO_USER | IO_USER | | User | User provided | User provided | User provided | We will respect the read_options that the user provided and will not set it. The only sst read for Flush is the verification read in BuildTable(). It claims to be "regard as user read". **Details** 1. Set read_options.rate_limiter_priority dynamically: - User: Do not update the read_options. Use the read_options that the user provided. - Compaction: Update read_options in CompactionJob::ProcessKeyValueCompaction(). - Flush: Update read_options in BuildTable(). 2. Pass the rate limiter priority to FSRandomAccessFile functions: - After calling the FindTable(), read_options is passed through GetTableReader(table_cache.cc), BlockBasedTableFactory::NewTableReader(block_based_table_factory.cc), and BlockBasedTable::Open(). The Open() needs some updates for the ReadOptions variable and the updates are also needed for the called functions, including PrefetchTail(), PrepareIOOptions(), ReadFooterFromFile(), ReadMetaIndexblock(), ReadPropertiesBlock(), PrefetchIndexAndFilterBlocks(), and ReadRangeDelBlock(). - In RandomAccessFileReader, the functions to be updated include Read(), MultiRead(), ReadAsync(), and Prefetch(). - Update the downstream functions of NewIndexIterator(), NewDataBlockIterator(), and BlockBasedTableIterator(). ### Test Plans Add unit tests. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9996 Reviewed By: anand1976 Differential Revision: D36452483 Pulled By: gitbw95 fbshipit-source-id: 60978204a4f849bb9261cb78d9bc1cb56d6008cf
2022-05-19 02:41:44 +00:00
return file_->Prefetch(offset, n, opts, nullptr);
}
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
2019-12-13 22:47:08 +00:00
FSRandomAccessFile* file() { return file_.get(); }
const std::string& file_name() const { return file_name_; }
bool use_direct_io() const { return file_->use_direct_io(); }
Group rocksdb.sst.read.micros stat by IOActivity flush and compaction (#11288) Summary: **Context:** The existing stat rocksdb.sst.read.micros does not reflect each of compaction and flush cases but aggregate them, which is not so helpful for us to understand IO read behavior of each of them. **Summary** - Update `StopWatch` and `RandomAccessFileReader` to record `rocksdb.sst.read.micros` and `rocksdb.file.{flush/compaction}.read.micros` - Fixed the default histogram in `RandomAccessFileReader` - New field `ReadOptions/IOOptions::io_activity`; Pass `ReadOptions` through paths under db open, flush and compaction to where we can prepare `IOOptions` and pass it to `RandomAccessFileReader` - Use `thread_status_util` for assertion in `DbStressFSWrapper` for continuous testing on we are passing correct `io_activity` under db open, flush and compaction Pull Request resolved: https://github.com/facebook/rocksdb/pull/11288 Test Plan: - **Stress test** - **Db bench 1: rocksdb.sst.read.micros COUNT ≈ sum of rocksdb.file.read.flush.micros's and rocksdb.file.read.compaction.micros's.** (without blob) - May not be exactly the same due to `HistogramStat::Add` only guarantees atomic not accuracy across threads. ``` ./db_bench -db=/dev/shm/testdb/ -statistics=true -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -target_file_size_base=655 -disable_auto_compactions=false -compression_type=none -bloom_bits=3 (-use_plain_table=1 -prefix_size=10) ``` ``` // BlockBasedTable rocksdb.sst.read.micros P50 : 2.009374 P95 : 4.968548 P99 : 8.110362 P100 : 43.000000 COUNT : 40456 SUM : 114805 rocksdb.file.read.flush.micros P50 : 1.871841 P95 : 3.872407 P99 : 5.540541 P100 : 43.000000 COUNT : 2250 SUM : 6116 rocksdb.file.read.compaction.micros P50 : 2.023109 P95 : 5.029149 P99 : 8.196910 P100 : 26.000000 COUNT : 38206 SUM : 108689 // PlainTable Does not apply ``` - **Db bench 2: performance** **Read** SETUP: db with 900 files ``` ./db_bench -db=/dev/shm/testdb/ -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=true -target_file_size_base=655 -compression_type=none ```run till convergence ``` ./db_bench -seed=1678564177044286 -use_existing_db=true -db=/dev/shm/testdb -benchmarks=readrandom[-X60] -statistics=true -num=1000000 -disable_auto_compactions=true -compression_type=none -bloom_bits=3 ``` Pre-change `readrandom [AVG 60 runs] : 21568 (± 248) ops/sec` Post-change (no regression, -0.3%) `readrandom [AVG 60 runs] : 21486 (± 236) ops/sec` **Compaction/Flush**run till convergence ``` ./db_bench -db=/dev/shm/testdb2/ -seed=1678564177044286 -benchmarks="fillseq[-X60]" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=false -target_file_size_base=655 -compression_type=none rocksdb.sst.read.micros COUNT : 33820 rocksdb.sst.read.flush.micros COUNT : 1800 rocksdb.sst.read.compaction.micros COUNT : 32020 ``` Pre-change `fillseq [AVG 46 runs] : 1391 (± 214) ops/sec; 0.7 (± 0.1) MB/sec` Post-change (no regression, ~-0.4%) `fillseq [AVG 46 runs] : 1385 (± 216) ops/sec; 0.7 (± 0.1) MB/sec` Reviewed By: ajkr Differential Revision: D44007011 Pulled By: hx235 fbshipit-source-id: a54c89e4846dfc9a135389edf3f3eedfea257132
2023-04-21 16:07:18 +00:00
IOStatus PrepareIOOptions(const ReadOptions& ro, IOOptions& opts) const;
Provide implementation to prefetch data asynchronously in FilePrefetchBuffer (#9674) Summary: In FilePrefetchBuffer if reads are sequential, after prefetching call ReadAsync API to prefetch data asynchronously so that in next prefetching data will be available. Data prefetched asynchronously will be readahead_size/2. It uses two buffers, one for synchronous prefetching and one for asynchronous. In case, the data is overlapping, the data is copied from both buffers to third buffer to make it continuous. This feature is under ReadOptions::async_io and is under experimental. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9674 Test Plan: 1. Add new unit tests 2. Run **db_stress** to make sure nothing crashes. - Normal prefetch without `async_io` ran successfully: ``` export CRASH_TEST_EXT_ARGS=" --async_io=0" make crash_test -j ``` 3. **Run Regressions**. i) Main branch without any change for normal prefetching with async_io disabled: ``` ./db_bench -db=/tmp/prefix_scan_prefetch_main -benchmarks="fillseq" -key_size=32 -value_size=512 -num=5000000 - use_direct_io_for_flush_and_compaction=true -target_file_size_base=16777216 ``` ``` ./db_bench -use_existing_db=true -db=/tmp/prefix_scan_prefetch_main -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 7.0 Date: Thu Mar 17 13:11:34 2022 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 ------------------------------------------------ DB path: [/tmp/prefix_scan_prefetch_main] seekrandom : 483618.390 micros/op 2 ops/sec; 338.9 MB/s (249 of 249 found) ``` ii) normal prefetching after changes with async_io disable: ``` ./db_bench -use_existing_db=true -db=/tmp/prefix_scan_prefetch_withchange -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 7.0 Date: Thu Mar 17 14:11:31 2022 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 ------------------------------------------------ DB path: [/tmp/prefix_scan_prefetch_withchange] seekrandom : 471347.227 micros/op 2 ops/sec; 348.1 MB/s (255 of 255 found) ``` Reviewed By: anand1976 Differential Revision: D34731543 Pulled By: akankshamahajan15 fbshipit-source-id: 8e23aa93453d5fe3c672b9231ad582f60207937f
2022-03-21 14:12:43 +00:00
IOStatus ReadAsync(FSReadRequest& req, const IOOptions& opts,
std::function<void(FSReadRequest&, void*)> cb,
Provide implementation to prefetch data asynchronously in FilePrefetchBuffer (#9674) Summary: In FilePrefetchBuffer if reads are sequential, after prefetching call ReadAsync API to prefetch data asynchronously so that in next prefetching data will be available. Data prefetched asynchronously will be readahead_size/2. It uses two buffers, one for synchronous prefetching and one for asynchronous. In case, the data is overlapping, the data is copied from both buffers to third buffer to make it continuous. This feature is under ReadOptions::async_io and is under experimental. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9674 Test Plan: 1. Add new unit tests 2. Run **db_stress** to make sure nothing crashes. - Normal prefetch without `async_io` ran successfully: ``` export CRASH_TEST_EXT_ARGS=" --async_io=0" make crash_test -j ``` 3. **Run Regressions**. i) Main branch without any change for normal prefetching with async_io disabled: ``` ./db_bench -db=/tmp/prefix_scan_prefetch_main -benchmarks="fillseq" -key_size=32 -value_size=512 -num=5000000 - use_direct_io_for_flush_and_compaction=true -target_file_size_base=16777216 ``` ``` ./db_bench -use_existing_db=true -db=/tmp/prefix_scan_prefetch_main -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 7.0 Date: Thu Mar 17 13:11:34 2022 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 ------------------------------------------------ DB path: [/tmp/prefix_scan_prefetch_main] seekrandom : 483618.390 micros/op 2 ops/sec; 338.9 MB/s (249 of 249 found) ``` ii) normal prefetching after changes with async_io disable: ``` ./db_bench -use_existing_db=true -db=/tmp/prefix_scan_prefetch_withchange -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 7.0 Date: Thu Mar 17 14:11:31 2022 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 ------------------------------------------------ DB path: [/tmp/prefix_scan_prefetch_withchange] seekrandom : 471347.227 micros/op 2 ops/sec; 348.1 MB/s (255 of 255 found) ``` Reviewed By: anand1976 Differential Revision: D34731543 Pulled By: akankshamahajan15 fbshipit-source-id: 8e23aa93453d5fe3c672b9231ad582f60207937f
2022-03-21 14:12:43 +00:00
void* cb_arg, void** io_handle, IOHandleDeleter* del_fn,
AlignedBuf* aligned_buf);
void ReadAsyncCallback(FSReadRequest& req, void* cb_arg);
};
} // namespace ROCKSDB_NAMESPACE