rocksdb/db/flush_job.cc

485 lines
18 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.
#include "db/flush_job.h"
#include <cinttypes>
#include <algorithm>
#include <vector>
#include "db/builder.h"
#include "db/db_iter.h"
#include "db/dbformat.h"
#include "db/event_helpers.h"
#include "db/log_reader.h"
#include "db/log_writer.h"
#include "db/memtable.h"
#include "db/memtable_list.h"
#include "db/merge_context.h"
#include "db/range_tombstone_fragmenter.h"
#include "db/version_set.h"
#include "file/file_util.h"
#include "file/filename.h"
#include "logging/event_logger.h"
#include "logging/log_buffer.h"
#include "logging/logging.h"
#include "monitoring/iostats_context_imp.h"
#include "monitoring/perf_context_imp.h"
#include "monitoring/thread_status_util.h"
#include "port/port.h"
#include "rocksdb/db.h"
#include "rocksdb/env.h"
#include "rocksdb/statistics.h"
#include "rocksdb/status.h"
#include "rocksdb/table.h"
#include "table/block_based/block.h"
#include "table/block_based/block_based_table_factory.h"
#include "table/merging_iterator.h"
#include "table/table_builder.h"
#include "table/two_level_iterator.h"
#include "test_util/sync_point.h"
#include "util/coding.h"
#include "util/mutexlock.h"
#include "util/stop_watch.h"
namespace ROCKSDB_NAMESPACE {
const char* GetFlushReasonString (FlushReason flush_reason) {
switch (flush_reason) {
FlushReason improvement Summary: Right now flush reason "SuperVersion Change" covers a few different scenarios which is a bit vague. For example, the following db_bench job should trigger "Write Buffer Full" > $ TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=fillrandom -write_buffer_size=1048576 -target_file_size_base=1048576 -max_bytes_for_level_base=4194304 $ grep 'flush_reason' /dev/shm/dbbench/LOG ... 2018/03/06-17:30:42.543638 7f2773b99700 EVENT_LOG_v1 {"time_micros": 1520386242543634, "job": 192, "event": "flush_started", "num_memtables": 1, "num_entries": 7006, "num_deletes": 0, "memory_usage": 1018024, "flush_reason": "SuperVersion Change"} 2018/03/06-17:30:42.569541 7f2773b99700 EVENT_LOG_v1 {"time_micros": 1520386242569536, "job": 193, "event": "flush_started", "num_memtables": 1, "num_entries": 7006, "num_deletes": 0, "memory_usage": 1018104, "flush_reason": "SuperVersion Change"} 2018/03/06-17:30:42.596396 7f2773b99700 EVENT_LOG_v1 {"time_micros": 1520386242596392, "job": 194, "event": "flush_started", "num_memtables": 1, "num_entries": 7008, "num_deletes": 0, "memory_usage": 1018048, "flush_reason": "SuperVersion Change"} 2018/03/06-17:30:42.622444 7f2773b99700 EVENT_LOG_v1 {"time_micros": 1520386242622440, "job": 195, "event": "flush_started", "num_memtables": 1, "num_entries": 7006, "num_deletes": 0, "memory_usage": 1018104, "flush_reason": "SuperVersion Change"} With the fix: > 2018/03/19-14:40:02.341451 7f11dc257700 EVENT_LOG_v1 {"time_micros": 1521495602341444, "job": 98, "event": "flush_started", "num_memtables": 1, "num_entries": 7009, "num_deletes": 0, "memory_usage": 1018008, "flush_reason": "Write Buffer Full"} 2018/03/19-14:40:02.379655 7f11dc257700 EVENT_LOG_v1 {"time_micros": 1521495602379642, "job": 100, "event": "flush_started", "num_memtables": 1, "num_entries": 7006, "num_deletes": 0, "memory_usage": 1018016, "flush_reason": "Write Buffer Full"} 2018/03/19-14:40:02.418479 7f11dc257700 EVENT_LOG_v1 {"time_micros": 1521495602418474, "job": 101, "event": "flush_started", "num_memtables": 1, "num_entries": 7009, "num_deletes": 0, "memory_usage": 1018104, "flush_reason": "Write Buffer Full"} 2018/03/19-14:40:02.455084 7f11dc257700 EVENT_LOG_v1 {"time_micros": 1521495602455079, "job": 102, "event": "flush_started", "num_memtables": 1, "num_entries": 7009, "num_deletes": 0, "memory_usage": 1018048, "flush_reason": "Write Buffer Full"} 2018/03/19-14:40:02.492293 7f11dc257700 EVENT_LOG_v1 {"time_micros": 1521495602492288, "job": 104, "event": "flush_started", "num_memtables": 1, "num_entries": 7007, "num_deletes": 0, "memory_usage": 1018056, "flush_reason": "Write Buffer Full"} 2018/03/19-14:40:02.528720 7f11dc257700 EVENT_LOG_v1 {"time_micros": 1521495602528715, "job": 105, "event": "flush_started", "num_memtables": 1, "num_entries": 7006, "num_deletes": 0, "memory_usage": 1018104, "flush_reason": "Write Buffer Full"} 2018/03/19-14:40:02.566255 7f11dc257700 EVENT_LOG_v1 {"time_micros": 1521495602566238, "job": 107, "event": "flush_started", "num_memtables": 1, "num_entries": 7009, "num_deletes": 0, "memory_usage": 1018112, "flush_reason": "Write Buffer Full"} Closes https://github.com/facebook/rocksdb/pull/3627 Differential Revision: D7328772 Pulled By: miasantreble fbshipit-source-id: 67c94065fbdd36930f09930aad0aaa6d2c152bb8
2018-03-23 02:34:04 +01:00
case FlushReason::kOthers:
return "Other Reasons";
case FlushReason::kGetLiveFiles:
return "Get Live Files";
case FlushReason::kShutDown:
return "Shut down";
case FlushReason::kExternalFileIngestion:
return "External File Ingestion";
case FlushReason::kManualCompaction:
return "Manual Compaction";
case FlushReason::kWriteBufferManager:
return "Write Buffer Manager";
case FlushReason::kWriteBufferFull:
return "Write Buffer Full";
case FlushReason::kTest:
return "Test";
FlushReason improvement Summary: Right now flush reason "SuperVersion Change" covers a few different scenarios which is a bit vague. For example, the following db_bench job should trigger "Write Buffer Full" > $ TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=fillrandom -write_buffer_size=1048576 -target_file_size_base=1048576 -max_bytes_for_level_base=4194304 $ grep 'flush_reason' /dev/shm/dbbench/LOG ... 2018/03/06-17:30:42.543638 7f2773b99700 EVENT_LOG_v1 {"time_micros": 1520386242543634, "job": 192, "event": "flush_started", "num_memtables": 1, "num_entries": 7006, "num_deletes": 0, "memory_usage": 1018024, "flush_reason": "SuperVersion Change"} 2018/03/06-17:30:42.569541 7f2773b99700 EVENT_LOG_v1 {"time_micros": 1520386242569536, "job": 193, "event": "flush_started", "num_memtables": 1, "num_entries": 7006, "num_deletes": 0, "memory_usage": 1018104, "flush_reason": "SuperVersion Change"} 2018/03/06-17:30:42.596396 7f2773b99700 EVENT_LOG_v1 {"time_micros": 1520386242596392, "job": 194, "event": "flush_started", "num_memtables": 1, "num_entries": 7008, "num_deletes": 0, "memory_usage": 1018048, "flush_reason": "SuperVersion Change"} 2018/03/06-17:30:42.622444 7f2773b99700 EVENT_LOG_v1 {"time_micros": 1520386242622440, "job": 195, "event": "flush_started", "num_memtables": 1, "num_entries": 7006, "num_deletes": 0, "memory_usage": 1018104, "flush_reason": "SuperVersion Change"} With the fix: > 2018/03/19-14:40:02.341451 7f11dc257700 EVENT_LOG_v1 {"time_micros": 1521495602341444, "job": 98, "event": "flush_started", "num_memtables": 1, "num_entries": 7009, "num_deletes": 0, "memory_usage": 1018008, "flush_reason": "Write Buffer Full"} 2018/03/19-14:40:02.379655 7f11dc257700 EVENT_LOG_v1 {"time_micros": 1521495602379642, "job": 100, "event": "flush_started", "num_memtables": 1, "num_entries": 7006, "num_deletes": 0, "memory_usage": 1018016, "flush_reason": "Write Buffer Full"} 2018/03/19-14:40:02.418479 7f11dc257700 EVENT_LOG_v1 {"time_micros": 1521495602418474, "job": 101, "event": "flush_started", "num_memtables": 1, "num_entries": 7009, "num_deletes": 0, "memory_usage": 1018104, "flush_reason": "Write Buffer Full"} 2018/03/19-14:40:02.455084 7f11dc257700 EVENT_LOG_v1 {"time_micros": 1521495602455079, "job": 102, "event": "flush_started", "num_memtables": 1, "num_entries": 7009, "num_deletes": 0, "memory_usage": 1018048, "flush_reason": "Write Buffer Full"} 2018/03/19-14:40:02.492293 7f11dc257700 EVENT_LOG_v1 {"time_micros": 1521495602492288, "job": 104, "event": "flush_started", "num_memtables": 1, "num_entries": 7007, "num_deletes": 0, "memory_usage": 1018056, "flush_reason": "Write Buffer Full"} 2018/03/19-14:40:02.528720 7f11dc257700 EVENT_LOG_v1 {"time_micros": 1521495602528715, "job": 105, "event": "flush_started", "num_memtables": 1, "num_entries": 7006, "num_deletes": 0, "memory_usage": 1018104, "flush_reason": "Write Buffer Full"} 2018/03/19-14:40:02.566255 7f11dc257700 EVENT_LOG_v1 {"time_micros": 1521495602566238, "job": 107, "event": "flush_started", "num_memtables": 1, "num_entries": 7009, "num_deletes": 0, "memory_usage": 1018112, "flush_reason": "Write Buffer Full"} Closes https://github.com/facebook/rocksdb/pull/3627 Differential Revision: D7328772 Pulled By: miasantreble fbshipit-source-id: 67c94065fbdd36930f09930aad0aaa6d2c152bb8
2018-03-23 02:34:04 +01:00
case FlushReason::kDeleteFiles:
return "Delete Files";
case FlushReason::kAutoCompaction:
return "Auto Compaction";
case FlushReason::kManualFlush:
return "Manual Flush";
Auto recovery from out of space errors (#4164) Summary: This commit implements automatic recovery from a Status::NoSpace() error during background operations such as write callback, flush and compaction. The broad design is as follows - 1. Compaction errors are treated as soft errors and don't put the database in read-only mode. A compaction is delayed until enough free disk space is available to accomodate the compaction outputs, which is estimated based on the input size. This means that users can continue to write, and we rely on the WriteController to delay or stop writes if the compaction debt becomes too high due to persistent low disk space condition 2. Errors during write callback and flush are treated as hard errors, i.e the database is put in read-only mode and goes back to read-write only fater certain recovery actions are taken. 3. Both types of recovery rely on the SstFileManagerImpl to poll for sufficient disk space. We assume that there is a 1-1 mapping between an SFM and the underlying OS storage container. For cases where multiple DBs are hosted on a single storage container, the user is expected to allocate a single SFM instance and use the same one for all the DBs. If no SFM is specified by the user, DBImpl::Open() will allocate one, but this will be one per DB and each DB will recover independently. The recovery implemented by SFM is as follows - a) On the first occurance of an out of space error during compaction, subsequent compactions will be delayed until the disk free space check indicates enough available space. The required space is computed as the sum of input sizes. b) The free space check requirement will be removed once the amount of free space is greater than the size reserved by in progress compactions when the first error occured c) If the out of space error is a hard error, a background thread in SFM will poll for sufficient headroom before triggering the recovery of the database and putting it in write-only mode. The headroom is calculated as the sum of the write_buffer_size of all the DB instances associated with the SFM 4. EventListener callbacks will be called at the start and completion of automatic recovery. Users can disable the auto recov ery in the start callback, and later initiate it manually by calling DB::Resume() Todo: 1. More extensive testing 2. Add disk full condition to db_stress (follow-on PR) Pull Request resolved: https://github.com/facebook/rocksdb/pull/4164 Differential Revision: D9846378 Pulled By: anand1976 fbshipit-source-id: 80ea875dbd7f00205e19c82215ff6e37da10da4a
2018-09-15 22:36:19 +02:00
case FlushReason::kErrorRecovery:
return "Error Recovery";
default:
return "Invalid";
}
}
FlushJob::FlushJob(const std::string& dbname, ColumnFamilyData* cfd,
const ImmutableDBOptions& db_options,
const MutableCFOptions& mutable_cf_options,
const uint64_t* max_memtable_id,
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 23:47:08 +01:00
const FileOptions& file_options, VersionSet* versions,
InstrumentedMutex* db_mutex,
std::atomic<bool>* shutting_down,
std::vector<SequenceNumber> existing_snapshots,
SequenceNumber earliest_write_conflict_snapshot,
SnapshotChecker* snapshot_checker, JobContext* job_context,
LogBuffer* log_buffer, FSDirectory* db_directory,
FSDirectory* output_file_directory,
CompressionType output_compression, Statistics* stats,
EventLogger* event_logger, bool measure_io_stats,
const bool sync_output_directory, const bool write_manifest,
Env::Priority thread_pri, const std::string& db_id,
const std::string& db_session_id)
: dbname_(dbname),
db_id_(db_id),
db_session_id_(db_session_id),
cfd_(cfd),
db_options_(db_options),
mutable_cf_options_(mutable_cf_options),
max_memtable_id_(max_memtable_id),
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 23:47:08 +01:00
file_options_(file_options),
versions_(versions),
db_mutex_(db_mutex),
shutting_down_(shutting_down),
existing_snapshots_(std::move(existing_snapshots)),
earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
snapshot_checker_(snapshot_checker),
job_context_(job_context),
log_buffer_(log_buffer),
db_directory_(db_directory),
output_file_directory_(output_file_directory),
output_compression_(output_compression),
stats_(stats),
event_logger_(event_logger),
measure_io_stats_(measure_io_stats),
sync_output_directory_(sync_output_directory),
write_manifest_(write_manifest),
edit_(nullptr),
base_(nullptr),
pick_memtable_called(false),
thread_pri_(thread_pri) {
Allow GetThreadList() to report operation stage. Summary: Allow GetThreadList() to report operation stage. Test Plan: ./thread_list_test ./db_bench --benchmarks=fillrandom --num=100000 --threads=40 \ --max_background_compactions=10 --max_background_flushes=3 \ --thread_status_per_interval=1000 --key_size=16 --value_size=1000 \ --num_column_families=10 export ROCKSDB_TESTS=ThreadStatus ./db_test Sample output ThreadID ThreadType cfName Operation OP_StartTime ElapsedTime Stage State 140116265861184 Low Pri 140116270055488 Low Pri 140116274249792 High Pri column_family_name_000005 Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116400078912 Low Pri column_family_name_000004 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116358135872 Low Pri column_family_name_000006 Compaction 2015/03/10-14:58:10 1 us CompactionJob::FinishCompactionOutputFile 140116341358656 Low Pri 140116295221312 High Pri default Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116324581440 Low Pri column_family_name_000009 Compaction 2015/03/10-14:58:11 0 us CompactionJob::ProcessKeyValueCompaction 140116278444096 Low Pri 140116299415616 Low Pri column_family_name_000008 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116291027008 High Pri column_family_name_000001 Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116286832704 Low Pri column_family_name_000002 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116282638400 Low Pri Reviewers: rven, igor, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D34683
2015-03-13 18:45:40 +01:00
// Update the thread status to indicate flush.
ReportStartedFlush();
Allow GetThreadList() to report operation stage. Summary: Allow GetThreadList() to report operation stage. Test Plan: ./thread_list_test ./db_bench --benchmarks=fillrandom --num=100000 --threads=40 \ --max_background_compactions=10 --max_background_flushes=3 \ --thread_status_per_interval=1000 --key_size=16 --value_size=1000 \ --num_column_families=10 export ROCKSDB_TESTS=ThreadStatus ./db_test Sample output ThreadID ThreadType cfName Operation OP_StartTime ElapsedTime Stage State 140116265861184 Low Pri 140116270055488 Low Pri 140116274249792 High Pri column_family_name_000005 Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116400078912 Low Pri column_family_name_000004 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116358135872 Low Pri column_family_name_000006 Compaction 2015/03/10-14:58:10 1 us CompactionJob::FinishCompactionOutputFile 140116341358656 Low Pri 140116295221312 High Pri default Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116324581440 Low Pri column_family_name_000009 Compaction 2015/03/10-14:58:11 0 us CompactionJob::ProcessKeyValueCompaction 140116278444096 Low Pri 140116299415616 Low Pri column_family_name_000008 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116291027008 High Pri column_family_name_000001 Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116286832704 Low Pri column_family_name_000002 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116282638400 Low Pri Reviewers: rven, igor, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D34683
2015-03-13 18:45:40 +01:00
TEST_SYNC_POINT("FlushJob::FlushJob()");
}
FlushJob::~FlushJob() {
ThreadStatusUtil::ResetThreadStatus();
}
void FlushJob::ReportStartedFlush() {
ThreadStatusUtil::SetColumnFamily(cfd_, cfd_->ioptions()->env,
db_options_.enable_thread_tracking);
ThreadStatusUtil::SetThreadOperation(ThreadStatus::OP_FLUSH);
ThreadStatusUtil::SetThreadOperationProperty(
ThreadStatus::COMPACTION_JOB_ID,
job_context_->job_id);
IOSTATS_RESET(bytes_written);
}
void FlushJob::ReportFlushInputSize(const autovector<MemTable*>& mems) {
uint64_t input_size = 0;
for (auto* mem : mems) {
input_size += mem->ApproximateMemoryUsage();
}
ThreadStatusUtil::IncreaseThreadOperationProperty(
ThreadStatus::FLUSH_BYTES_MEMTABLES,
input_size);
}
void FlushJob::RecordFlushIOStats() {
RecordTick(stats_, FLUSH_WRITE_BYTES, IOSTATS(bytes_written));
ThreadStatusUtil::IncreaseThreadOperationProperty(
ThreadStatus::FLUSH_BYTES_WRITTEN, IOSTATS(bytes_written));
IOSTATS_RESET(bytes_written);
}
void FlushJob::PickMemTable() {
db_mutex_->AssertHeld();
assert(!pick_memtable_called);
pick_memtable_called = true;
// Save the contents of the earliest memtable as a new Table
cfd_->imm()->PickMemtablesToFlush(max_memtable_id_, &mems_);
if (mems_.empty()) {
return;
}
ReportFlushInputSize(mems_);
// entries mems are (implicitly) sorted in ascending order by their created
// time. We will use the first memtable's `edit` to keep the meta info for
// this flush.
MemTable* m = mems_[0];
edit_ = m->GetEdits();
edit_->SetPrevLogNumber(0);
// SetLogNumber(log_num) indicates logs with number smaller than log_num
// will no longer be picked up for recovery.
edit_->SetLogNumber(mems_.back()->GetNextLogNumber());
edit_->SetColumnFamily(cfd_->GetID());
// path 0 for level 0 file.
meta_.fd = FileDescriptor(versions_->NewFileNumber(), 0, 0);
base_ = cfd_->current();
base_->Ref(); // it is likely that we do not need this reference
}
Skip deleted WALs during recovery Summary: This patch record min log number to keep to the manifest while flushing SST files to ignore them and any WAL older than them during recovery. This is to avoid scenarios when we have a gap between the WAL files are fed to the recovery procedure. The gap could happen by for example out-of-order WAL deletion. Such gap could cause problems in 2PC recovery where the prepared and commit entry are placed into two separate WAL and gap in the WALs could result into not processing the WAL with the commit entry and hence breaking the 2PC recovery logic. Before the commit, for 2PC case, we determined which log number to keep in FindObsoleteFiles(). We looked at the earliest logs with outstanding prepare entries, or prepare entries whose respective commit or abort are in memtable. With the commit, the same calculation is done while we apply the SST flush. Just before installing the flush file, we precompute the earliest log file to keep after the flush finishes using the same logic (but skipping the memtables just flushed), record this information to the manifest entry for this new flushed SST file. This pre-computed value is also remembered in memory, and will later be used to determine whether a log file can be deleted. This value is unlikely to change until next flush because the commit entry will stay in memtable. (In WritePrepared, we could have removed the older log files as soon as all prepared entries are committed. It's not yet done anyway. Even if we do it, the only thing we loss with this new approach is earlier log deletion between two flushes, which does not guarantee to happen anyway because the obsolete file clean-up function is only executed after flush or compaction) This min log number to keep is stored in the manifest using the safely-ignore customized field of AddFile entry, in order to guarantee that the DB generated using newer release can be opened by previous releases no older than 4.2. Closes https://github.com/facebook/rocksdb/pull/3765 Differential Revision: D7747618 Pulled By: siying fbshipit-source-id: d00c92105b4f83852e9754a1b70d6b64cb590729
2018-05-04 00:35:11 +02:00
Status FlushJob::Run(LogsWithPrepTracker* prep_tracker,
FileMetaData* file_meta) {
TEST_SYNC_POINT("FlushJob::Start");
db_mutex_->AssertHeld();
assert(pick_memtable_called);
Allow GetThreadList() to report operation stage. Summary: Allow GetThreadList() to report operation stage. Test Plan: ./thread_list_test ./db_bench --benchmarks=fillrandom --num=100000 --threads=40 \ --max_background_compactions=10 --max_background_flushes=3 \ --thread_status_per_interval=1000 --key_size=16 --value_size=1000 \ --num_column_families=10 export ROCKSDB_TESTS=ThreadStatus ./db_test Sample output ThreadID ThreadType cfName Operation OP_StartTime ElapsedTime Stage State 140116265861184 Low Pri 140116270055488 Low Pri 140116274249792 High Pri column_family_name_000005 Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116400078912 Low Pri column_family_name_000004 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116358135872 Low Pri column_family_name_000006 Compaction 2015/03/10-14:58:10 1 us CompactionJob::FinishCompactionOutputFile 140116341358656 Low Pri 140116295221312 High Pri default Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116324581440 Low Pri column_family_name_000009 Compaction 2015/03/10-14:58:11 0 us CompactionJob::ProcessKeyValueCompaction 140116278444096 Low Pri 140116299415616 Low Pri column_family_name_000008 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116291027008 High Pri column_family_name_000001 Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116286832704 Low Pri column_family_name_000002 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116282638400 Low Pri Reviewers: rven, igor, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D34683
2015-03-13 18:45:40 +01:00
AutoThreadOperationStageUpdater stage_run(
ThreadStatus::STAGE_FLUSH_RUN);
if (mems_.empty()) {
ROCKS_LOG_BUFFER(log_buffer_, "[%s] Nothing in memtable to flush",
cfd_->GetName().c_str());
return Status::OK();
}
// I/O measurement variables
PerfLevel prev_perf_level = PerfLevel::kEnableTime;
uint64_t prev_write_nanos = 0;
uint64_t prev_fsync_nanos = 0;
uint64_t prev_range_sync_nanos = 0;
uint64_t prev_prepare_write_nanos = 0;
uint64_t prev_cpu_write_nanos = 0;
uint64_t prev_cpu_read_nanos = 0;
if (measure_io_stats_) {
prev_perf_level = GetPerfLevel();
SetPerfLevel(PerfLevel::kEnableTime);
prev_write_nanos = IOSTATS(write_nanos);
prev_fsync_nanos = IOSTATS(fsync_nanos);
prev_range_sync_nanos = IOSTATS(range_sync_nanos);
prev_prepare_write_nanos = IOSTATS(prepare_write_nanos);
prev_cpu_write_nanos = IOSTATS(cpu_write_nanos);
prev_cpu_read_nanos = IOSTATS(cpu_read_nanos);
}
// This will release and re-acquire the mutex.
Status s = WriteLevel0Table();
if (s.ok() && cfd_->IsDropped()) {
s = Status::ColumnFamilyDropped("Column family dropped during compaction");
}
if ((s.ok() || s.IsColumnFamilyDropped()) &&
shutting_down_->load(std::memory_order_acquire)) {
s = Status::ShutdownInProgress("Database shutdown");
}
if (!s.ok()) {
cfd_->imm()->RollbackMemtableFlush(mems_, meta_.fd.GetNumber());
} else if (write_manifest_) {
LogAndApply() should fail if the column family has been dropped Summary: This patch finally fixes the ColumnFamilyTest.ReadDroppedColumnFamily test. The test has been failing very sporadically and it was hard to repro. However, I managed to write a new tests that reproes the failure deterministically. Here's what happens: 1. We start the flush for the column family 2. We check if the column family was dropped here: https://github.com/facebook/rocksdb/blob/a3fc49bfddcdb1ff29409aacd06c04df56c7a1d7/db/flush_job.cc#L149 3. This check goes through, ends up in InstallMemtableFlushResults() and it goes into LogAndApply() 4. At about this time, we start dropping the column family. Dropping the column family process gets to LogAndApply() at about the same time as LogAndApply() from flush process 5. Drop column family goes through LogAndApply() first, marking the column family as dropped. 6. Flush process gets woken up and gets a chance to write to the MANIFEST. However, this is where it gets stuck: https://github.com/facebook/rocksdb/blob/a3fc49bfddcdb1ff29409aacd06c04df56c7a1d7/db/version_set.cc#L1975 7. We see that the column family was dropped, so there is no need to write to the MANIFEST. We return OK. 8. Flush gets OK back from LogAndApply() and it deletes the memtable, thinking that the data is now safely persisted to sst file. The fix is pretty simple. Instead of OK, we return ShutdownInProgress. This is not really true, but we have been using this status code to also mean "this operation was canceled because the column family has been dropped". The fix is only one LOC. All other code is related to tests. I added a new test that reproes the failure. I also moved SleepingBackgroundTask to util/testutil.h (because I needed it in column_family_test for my new test). There's plenty of other places where we reimplement SleepingBackgroundTask, but I'll address that in a separate commit. Test Plan: 1. new test 2. make check 3. Make sure the ColumnFamilyTest.ReadDroppedColumnFamily doesn't fail on Travis: https://travis-ci.org/facebook/rocksdb/jobs/79952386 Reviewers: yhchiang, anthony, IslamAbdelRahman, kradhakrishnan, rven, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D46773
2015-09-15 20:28:44 +02:00
TEST_SYNC_POINT("FlushJob::InstallResults");
// Replace immutable memtable with the generated Table
IOStatus tmp_io_s;
s = cfd_->imm()->TryInstallMemtableFlushResults(
Skip deleted WALs during recovery Summary: This patch record min log number to keep to the manifest while flushing SST files to ignore them and any WAL older than them during recovery. This is to avoid scenarios when we have a gap between the WAL files are fed to the recovery procedure. The gap could happen by for example out-of-order WAL deletion. Such gap could cause problems in 2PC recovery where the prepared and commit entry are placed into two separate WAL and gap in the WALs could result into not processing the WAL with the commit entry and hence breaking the 2PC recovery logic. Before the commit, for 2PC case, we determined which log number to keep in FindObsoleteFiles(). We looked at the earliest logs with outstanding prepare entries, or prepare entries whose respective commit or abort are in memtable. With the commit, the same calculation is done while we apply the SST flush. Just before installing the flush file, we precompute the earliest log file to keep after the flush finishes using the same logic (but skipping the memtables just flushed), record this information to the manifest entry for this new flushed SST file. This pre-computed value is also remembered in memory, and will later be used to determine whether a log file can be deleted. This value is unlikely to change until next flush because the commit entry will stay in memtable. (In WritePrepared, we could have removed the older log files as soon as all prepared entries are committed. It's not yet done anyway. Even if we do it, the only thing we loss with this new approach is earlier log deletion between two flushes, which does not guarantee to happen anyway because the obsolete file clean-up function is only executed after flush or compaction) This min log number to keep is stored in the manifest using the safely-ignore customized field of AddFile entry, in order to guarantee that the DB generated using newer release can be opened by previous releases no older than 4.2. Closes https://github.com/facebook/rocksdb/pull/3765 Differential Revision: D7747618 Pulled By: siying fbshipit-source-id: d00c92105b4f83852e9754a1b70d6b64cb590729
2018-05-04 00:35:11 +02:00
cfd_, mutable_cf_options_, mems_, prep_tracker, versions_, db_mutex_,
meta_.fd.GetNumber(), &job_context_->memtables_to_free, db_directory_,
log_buffer_, &committed_flush_jobs_info_, &tmp_io_s);
if (!tmp_io_s.ok()) {
io_status_ = tmp_io_s;
}
}
if (s.ok() && file_meta != nullptr) {
*file_meta = meta_;
}
RecordFlushIOStats();
// When measure_io_stats_ is true, the default 512 bytes is not enough.
auto stream = event_logger_->LogToBuffer(log_buffer_, 1024);
stream << "job" << job_context_->job_id << "event"
<< "flush_finished";
stream << "output_compression"
<< CompressionTypeToString(output_compression_);
stream << "lsm_state";
stream.StartArray();
auto vstorage = cfd_->current()->storage_info();
for (int level = 0; level < vstorage->num_levels(); ++level) {
stream << vstorage->NumLevelFiles(level);
}
stream.EndArray();
stream << "immutable_memtables" << cfd_->imm()->NumNotFlushed();
if (measure_io_stats_) {
if (prev_perf_level != PerfLevel::kEnableTime) {
SetPerfLevel(prev_perf_level);
}
stream << "file_write_nanos" << (IOSTATS(write_nanos) - prev_write_nanos);
stream << "file_range_sync_nanos"
<< (IOSTATS(range_sync_nanos) - prev_range_sync_nanos);
stream << "file_fsync_nanos" << (IOSTATS(fsync_nanos) - prev_fsync_nanos);
stream << "file_prepare_write_nanos"
<< (IOSTATS(prepare_write_nanos) - prev_prepare_write_nanos);
stream << "file_cpu_write_nanos"
<< (IOSTATS(cpu_write_nanos) - prev_cpu_write_nanos);
stream << "file_cpu_read_nanos"
<< (IOSTATS(cpu_read_nanos) - prev_cpu_read_nanos);
}
return s;
}
void FlushJob::Cancel() {
db_mutex_->AssertHeld();
assert(base_ != nullptr);
base_->Unref();
}
Status FlushJob::WriteLevel0Table() {
Allow GetThreadList() to report operation stage. Summary: Allow GetThreadList() to report operation stage. Test Plan: ./thread_list_test ./db_bench --benchmarks=fillrandom --num=100000 --threads=40 \ --max_background_compactions=10 --max_background_flushes=3 \ --thread_status_per_interval=1000 --key_size=16 --value_size=1000 \ --num_column_families=10 export ROCKSDB_TESTS=ThreadStatus ./db_test Sample output ThreadID ThreadType cfName Operation OP_StartTime ElapsedTime Stage State 140116265861184 Low Pri 140116270055488 Low Pri 140116274249792 High Pri column_family_name_000005 Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116400078912 Low Pri column_family_name_000004 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116358135872 Low Pri column_family_name_000006 Compaction 2015/03/10-14:58:10 1 us CompactionJob::FinishCompactionOutputFile 140116341358656 Low Pri 140116295221312 High Pri default Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116324581440 Low Pri column_family_name_000009 Compaction 2015/03/10-14:58:11 0 us CompactionJob::ProcessKeyValueCompaction 140116278444096 Low Pri 140116299415616 Low Pri column_family_name_000008 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116291027008 High Pri column_family_name_000001 Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116286832704 Low Pri column_family_name_000002 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116282638400 Low Pri Reviewers: rven, igor, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D34683
2015-03-13 18:45:40 +01:00
AutoThreadOperationStageUpdater stage_updater(
ThreadStatus::STAGE_FLUSH_WRITE_L0);
db_mutex_->AssertHeld();
const uint64_t start_micros = db_options_.env->NowMicros();
const uint64_t start_cpu_micros = db_options_.env->NowCPUNanos() / 1000;
Status s;
{
auto write_hint = cfd_->CalculateSSTWriteHint(0);
db_mutex_->Unlock();
if (log_buffer_) {
log_buffer_->FlushBufferToLog();
}
// memtables and range_del_iters store internal iterators over each data
// memtable and its associated range deletion memtable, respectively, at
// corresponding indexes.
std::vector<InternalIterator*> memtables;
std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
range_del_iters;
ReadOptions ro;
ro.total_order_seek = true;
Arena arena;
uint64_t total_num_entries = 0, total_num_deletes = 0;
uint64_t total_data_size = 0;
size_t total_memory_usage = 0;
for (MemTable* m : mems_) {
ROCKS_LOG_INFO(
db_options_.info_log,
"[%s] [JOB %d] Flushing memtable with next log file: %" PRIu64 "\n",
cfd_->GetName().c_str(), job_context_->job_id, m->GetNextLogNumber());
memtables.push_back(m->NewIterator(ro, &arena));
auto* range_del_iter =
m->NewRangeTombstoneIterator(ro, kMaxSequenceNumber);
if (range_del_iter != nullptr) {
range_del_iters.emplace_back(range_del_iter);
}
total_num_entries += m->num_entries();
total_num_deletes += m->num_deletes();
total_data_size += m->get_data_size();
total_memory_usage += m->ApproximateMemoryUsage();
}
event_logger_->Log() << "job" << job_context_->job_id << "event"
<< "flush_started"
<< "num_memtables" << mems_.size() << "num_entries"
<< total_num_entries << "num_deletes"
<< total_num_deletes << "total_data_size"
<< total_data_size << "memory_usage"
<< total_memory_usage << "flush_reason"
<< GetFlushReasonString(cfd_->GetFlushReason());
{
ScopedArenaIterator iter(
NewMergingIterator(&cfd_->internal_comparator(), &memtables[0],
static_cast<int>(memtables.size()), &arena));
ROCKS_LOG_INFO(db_options_.info_log,
"[%s] [JOB %d] Level-0 flush table #%" PRIu64 ": started",
cfd_->GetName().c_str(), job_context_->job_id,
meta_.fd.GetNumber());
TEST_SYNC_POINT_CALLBACK("FlushJob::WriteLevel0Table:output_compression",
&output_compression_);
int64_t _current_time = 0;
auto status = db_options_.env->GetCurrentTime(&_current_time);
// Safe to proceed even if GetCurrentTime fails. So, log and proceed.
if (!status.ok()) {
ROCKS_LOG_WARN(
db_options_.info_log,
"Failed to get current time to populate creation_time property. "
"Status: %s",
status.ToString().c_str());
}
FIFO Compaction with TTL Summary: Introducing FIFO compactions with TTL. FIFO compaction is based on size only which makes it tricky to enable in production as use cases can have organic growth. A user requested an option to drop files based on the time of their creation instead of the total size. To address that request: - Added a new TTL option to FIFO compaction options. - Updated FIFO compaction score to take TTL into consideration. - Added a new table property, creation_time, to keep track of when the SST file is created. - Creation_time is set as below: - On Flush: Set to the time of flush. - On Compaction: Set to the max creation_time of all the files involved in the compaction. - On Repair and Recovery: Set to the time of repair/recovery. - Old files created prior to this code change will have a creation_time of 0. - FIFO compaction with TTL is enabled when ttl > 0. All files older than ttl will be deleted during compaction. i.e. `if (file.creation_time < (current_time - ttl)) then delete(file)`. This will enable cases where you might want to delete all files older than, say, 1 day. - FIFO compaction will fall back to the prior way of deleting files based on size if: - the creation_time of all files involved in compaction is 0. - the total size (of all SST files combined) does not drop below `compaction_options_fifo.max_table_files_size` even if the files older than ttl are deleted. This feature is not supported if max_open_files != -1 or with table formats other than Block-based. **Test Plan:** Added tests. **Benchmark results:** Base: FIFO with max size: 100MB :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 readwhilewriting : 1.924 micros/op 519858 ops/sec; 13.6 MB/s (1176277 of 5000000 found) ``` With TTL (a low one for testing) :: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=readwhilewriting --num=5000000 --threads=16 --compaction_style=2 --fifo_compaction_max_table_files_size_mb=100 --fifo_compaction_ttl=20 readwhilewriting : 1.902 micros/op 525817 ops/sec; 13.7 MB/s (1185057 of 5000000 found) ``` Example Log lines: ``` 2017/06/26-15:17:24.609249 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609177) [db/compaction_picker.cc:1471] [default] FIFO compaction: picking file 40 with creation time 1498515423 for deletion 2017/06/26-15:17:24.609255 7fd5a45ff700 (Original Log Time 2017/06/26-15:17:24.609234) [db/db_impl_compaction_flush.cc:1541] [default] Deleted 1 files ... 2017/06/26-15:17:25.553185 7fd5a61a5800 [DEBUG] [db/db_impl_files.cc:309] [JOB 0] Delete /dev/shm/dbbench/000040.sst type=2 #40 -- OK 2017/06/26-15:17:25.553205 7fd5a61a5800 EVENT_LOG_v1 {"time_micros": 1498515445553199, "job": 0, "event": "table_file_deletion", "file_number": 40} ``` SST Files remaining in the dbbench dir, after db_bench execution completed: ``` svemuri@dev15905 ~/rocksdb (fifo-compaction) $ ls -l /dev/shm//dbbench/*.sst -rw-r--r--. 1 svemuri users 30749887 Jun 26 15:17 /dev/shm//dbbench/000042.sst -rw-r--r--. 1 svemuri users 30768779 Jun 26 15:17 /dev/shm//dbbench/000044.sst -rw-r--r--. 1 svemuri users 30757481 Jun 26 15:17 /dev/shm//dbbench/000046.sst ``` Closes https://github.com/facebook/rocksdb/pull/2480 Differential Revision: D5305116 Pulled By: sagar0 fbshipit-source-id: 3e5cfcf5dd07ed2211b5b37492eb235b45139174
2017-06-28 02:02:20 +02:00
const uint64_t current_time = static_cast<uint64_t>(_current_time);
uint64_t oldest_key_time =
mems_.front()->ApproximateOldestKeyTime();
// It's not clear whether oldest_key_time is always available. In case
// it is not available, use current_time.
Fix+clean up handling of mock sleeps (#7101) Summary: We have a number of tests hanging on MacOS and windows due to mishandling of code for mock sleeps. In addition, the code was in terrible shape because the same variable (addon_time_) would sometimes refer to microseconds and sometimes to seconds. One test even assumed it was nanoseconds but was written to pass anyway. This has been cleaned up so that DB tests generally use a SpecialEnv function to mock sleep, for either some number of microseconds or seconds depending on the function called. But to call one of these, the test must first call SetMockSleep (precondition enforced with assertion), which also turns sleeps in RocksDB into mock sleeps. To also removes accounting for actual clock time, call SetTimeElapseOnlySleepOnReopen, which implies SetMockSleep (on DB re-open). This latter setting only works by applying on DB re-open, otherwise havoc can ensue if Env goes back in time with DB open. More specifics: Removed some unused test classes, and updated comments on the general problem. Fixed DBSSTTest.GetTotalSstFilesSize using a sync point callback instead of mock time. For this we have the only modification to production code, inserting a sync point callback in flush_job.cc, which is not a change to production behavior. Removed unnecessary resetting of mock times to 0 in many tests. RocksDB deals in relative time. Any behaviors relying on absolute date/time are likely a bug. (The above test DBSSTTest.GetTotalSstFilesSize was the only one clearly injecting a specific absolute time for actual testing convenience.) Just in case I misunderstood some test, I put this note in each replacement: // NOTE: Presumed unnecessary and removed: resetting mock time in env Strengthened some tests like MergeTestTime, MergeCompactionTimeTest, and FilterCompactionTimeTest in db_test.cc stats_history_test and blob_db_test are each their own beast, rather deeply dependent on MockTimeEnv. Each gets its own variant of a work-around for TimedWait in a mock time environment. (Reduces redundancy and inconsistency in stats_history_test.) Intended follow-up: Remove TimedWait from the public API of InstrumentedCondVar, and only make that accessible through Env by passing in an InstrumentedCondVar and a deadline. Then the Env implementations mocking time can fix this problem without using sync points. (Test infrastructure using sync points interferes with individual tests' control over sync points.) With that change, we can simplify/consolidate the scattered work-arounds. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7101 Test Plan: make check on Linux and MacOS Reviewed By: zhichao-cao Differential Revision: D23032815 Pulled By: pdillinger fbshipit-source-id: 7f33967ada8b83011fb54e8279365c008bd6610b
2020-08-11 21:39:49 +02:00
uint64_t oldest_ancester_time = std::min(current_time, oldest_key_time);
TEST_SYNC_POINT_CALLBACK(
"FlushJob::WriteLevel0Table:oldest_ancester_time",
&oldest_ancester_time);
meta_.oldest_ancester_time = oldest_ancester_time;
meta_.file_creation_time = current_time;
uint64_t creation_time = (cfd_->ioptions()->compaction_style ==
CompactionStyle::kCompactionStyleFIFO)
? current_time
: meta_.oldest_ancester_time;
IOStatus io_s;
s = BuildTable(
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 23:47:08 +01:00
dbname_, db_options_.env, db_options_.fs.get(), *cfd_->ioptions(),
mutable_cf_options_, file_options_, cfd_->table_cache(), iter.get(),
std::move(range_del_iters), &meta_, cfd_->internal_comparator(),
cfd_->int_tbl_prop_collector_factories(), cfd_->GetID(),
cfd_->GetName(), existing_snapshots_,
earliest_write_conflict_snapshot_, snapshot_checker_,
output_compression_, mutable_cf_options_.sample_for_compression,
mutable_cf_options_.compression_opts,
mutable_cf_options_.paranoid_file_checks, cfd_->internal_stats(),
TableFileCreationReason::kFlush, &io_s, event_logger_,
job_context_->job_id, Env::IO_HIGH, &table_properties_, 0 /* level */,
creation_time, oldest_key_time, write_hint, current_time, db_id_,
db_session_id_);
if (!io_s.ok()) {
io_status_ = io_s;
}
LogFlush(db_options_.info_log);
}
ROCKS_LOG_INFO(db_options_.info_log,
"[%s] [JOB %d] Level-0 flush table #%" PRIu64 ": %" PRIu64
" bytes %s"
"%s",
cfd_->GetName().c_str(), job_context_->job_id,
meta_.fd.GetNumber(), meta_.fd.GetFileSize(),
s.ToString().c_str(),
meta_.marked_for_compaction ? " (needs compaction)" : "");
if (s.ok() && output_file_directory_ != nullptr && sync_output_directory_) {
s = output_file_directory_->Fsync(IOOptions(), nullptr);
}
TEST_SYNC_POINT_CALLBACK("FlushJob::WriteLevel0Table", &mems_);
db_mutex_->Lock();
}
base_->Unref();
// Note that if file_size is zero, the file has been deleted and
// should not be added to the manifest.
if (s.ok() && meta_.fd.GetFileSize() > 0) {
// if we have more than 1 background thread, then we cannot
// insert files directly into higher levels because some other
// threads could be concurrently producing compacted files for
// that key range.
// Add file to L0
edit_->AddFile(0 /* level */, meta_.fd.GetNumber(), meta_.fd.GetPathId(),
meta_.fd.GetFileSize(), meta_.smallest, meta_.largest,
meta_.fd.smallest_seqno, meta_.fd.largest_seqno,
meta_.marked_for_compaction, meta_.oldest_blob_file_number,
meta_.oldest_ancester_time, meta_.file_creation_time,
meta_.file_checksum, meta_.file_checksum_func_name);
}
#ifndef ROCKSDB_LITE
// Piggyback FlushJobInfo on the first first flushed memtable.
mems_[0]->SetFlushJobInfo(GetFlushJobInfo());
#endif // !ROCKSDB_LITE
// Note that here we treat flush as level 0 compaction in internal stats
InternalStats::CompactionStats stats(CompactionReason::kFlush, 1);
stats.micros = db_options_.env->NowMicros() - start_micros;
stats.cpu_micros = db_options_.env->NowCPUNanos() / 1000 - start_cpu_micros;
stats.bytes_written = meta_.fd.GetFileSize();
RecordTimeToHistogram(stats_, FLUSH_TIME, stats.micros);
cfd_->internal_stats()->AddCompactionStats(0 /* level */, thread_pri_, stats);
cfd_->internal_stats()->AddCFStats(InternalStats::BYTES_FLUSHED,
meta_.fd.GetFileSize());
RecordFlushIOStats();
return s;
}
#ifndef ROCKSDB_LITE
std::unique_ptr<FlushJobInfo> FlushJob::GetFlushJobInfo() const {
db_mutex_->AssertHeld();
std::unique_ptr<FlushJobInfo> info(new FlushJobInfo{});
info->cf_id = cfd_->GetID();
info->cf_name = cfd_->GetName();
const uint64_t file_number = meta_.fd.GetNumber();
info->file_path =
MakeTableFileName(cfd_->ioptions()->cf_paths[0].path, file_number);
info->file_number = file_number;
info->oldest_blob_file_number = meta_.oldest_blob_file_number;
info->thread_id = db_options_.env->GetThreadID();
info->job_id = job_context_->job_id;
info->smallest_seqno = meta_.fd.smallest_seqno;
info->largest_seqno = meta_.fd.largest_seqno;
info->table_properties = table_properties_;
info->flush_reason = cfd_->GetFlushReason();
return info;
}
#endif // !ROCKSDB_LITE
} // namespace ROCKSDB_NAMESPACE