You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/db/flush_job.cc

365 lines
13 KiB

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
//
// 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"
#ifndef __STDC_FORMAT_MACROS
#define __STDC_FORMAT_MACROS
#endif
#include <inttypes.h>
#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_list.h"
#include "db/merge_context.h"
#include "db/version_set.h"
#include "monitoring/iostats_context_imp.h"
#include "monitoring/perf_context_imp.h"
#include "monitoring/thread_status_util.h"
#include "port/likely.h"
#include "port/port.h"
#include "db/memtable.h"
#include "rocksdb/db.h"
#include "rocksdb/env.h"
#include "rocksdb/statistics.h"
#include "rocksdb/status.h"
#include "rocksdb/table.h"
#include "table/block.h"
#include "table/block_based_table_factory.h"
#include "table/merging_iterator.h"
#include "table/table_builder.h"
#include "table/two_level_iterator.h"
#include "util/coding.h"
#include "util/event_logger.h"
#include "util/file_util.h"
#include "util/filename.h"
#include "util/log_buffer.h"
#include "util/logging.h"
#include "util/mutexlock.h"
#include "util/stop_watch.h"
#include "util/sync_point.h"
namespace rocksdb {
FlushJob::FlushJob(const std::string& dbname, ColumnFamilyData* cfd,
const ImmutableDBOptions& db_options,
const MutableCFOptions& mutable_cf_options,
const EnvOptions& env_options, VersionSet* versions,
InstrumentedMutex* db_mutex,
std::atomic<bool>* shutting_down,
std::vector<SequenceNumber> existing_snapshots,
SequenceNumber earliest_write_conflict_snapshot,
JobContext* job_context, LogBuffer* log_buffer,
Directory* db_directory, Directory* output_file_directory,
CompressionType output_compression, Statistics* stats,
EventLogger* event_logger, bool measure_io_stats)
: dbname_(dbname),
cfd_(cfd),
db_options_(db_options),
mutable_cf_options_(mutable_cf_options),
env_options_(env_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),
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),
pick_memtable_called(false) {
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
10 years ago
// 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
10 years ago
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(&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
}
Status FlushJob::Run(FileMetaData* file_meta) {
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
10 years ago
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;
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);
}
// This will release and re-acquire the mutex.
Status s = WriteLevel0Table();
if (s.ok() &&
(shutting_down_->load(std::memory_order_acquire) || cfd_->IsDropped())) {
s = Status::ShutdownInProgress(
"Database shutdown or Column family drop during flush");
}
if (!s.ok()) {
cfd_->imm()->RollbackMemtableFlush(mems_, meta_.fd.GetNumber());
} else {
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
9 years ago
TEST_SYNC_POINT("FlushJob::InstallResults");
// Replace immutable memtable with the generated Table
s = cfd_->imm()->InstallMemtableFlushResults(
cfd_, mutable_cf_options_, mems_, versions_, db_mutex_,
meta_.fd.GetNumber(), &job_context_->memtables_to_free, db_directory_,
log_buffer_);
}
if (s.ok() && file_meta != nullptr) {
*file_meta = meta_;
}
RecordFlushIOStats();
auto stream = event_logger_->LogToBuffer(log_buffer_);
stream << "job" << job_context_->job_id << "event"
<< "flush_finished";
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);
}
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
10 years ago
AutoThreadOperationStageUpdater stage_updater(
ThreadStatus::STAGE_FLUSH_WRITE_L0);
db_mutex_->AssertHeld();
const uint64_t start_micros = db_options_.env->NowMicros();
Status s;
{
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<InternalIterator*> range_del_iters;
ReadOptions ro;
ro.total_order_seek = true;
Arena arena;
uint64_t total_num_entries = 0, total_num_deletes = 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);
if (range_del_iter != nullptr) {
range_del_iters.push_back(range_del_iter);
}
total_num_entries += m->num_entries();
total_num_deletes += m->num_deletes();
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 << "memory_usage"
<< total_memory_usage;
{
ScopedArenaIterator iter(
NewMergingIterator(&cfd_->internal_comparator(), &memtables[0],
static_cast<int>(memtables.size()), &arena));
std::unique_ptr<InternalIterator> range_del_iter(NewMergingIterator(
&cfd_->internal_comparator(),
range_del_iters.empty() ? nullptr : &range_del_iters[0],
static_cast<int>(range_del_iters.size())));
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_);
EnvOptions optimized_env_options =
db_options_.env->OptimizeForCompactionTableWrite(env_options_, db_options_);
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
7 years ago
int64_t _current_time;
auto status = db_options_.env->GetCurrentTime(&_current_time);
if (!status.ok()) {
_current_time = 0;
}
const uint64_t current_time = static_cast<uint64_t>(_current_time);
s = BuildTable(
dbname_, db_options_.env, *cfd_->ioptions(), mutable_cf_options_,
optimized_env_options, cfd_->table_cache(), iter.get(),
std::move(range_del_iter), &meta_, cfd_->internal_comparator(),
cfd_->int_tbl_prop_collector_factories(), cfd_->GetID(),
cfd_->GetName(), existing_snapshots_,
earliest_write_conflict_snapshot_, output_compression_,
cfd_->ioptions()->compression_opts,
mutable_cf_options_.paranoid_file_checks, cfd_->internal_stats(),
TableFileCreationReason::kFlush, event_logger_, job_context_->job_id,
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
7 years ago
Env::IO_HIGH, &table_properties_, 0 /* level */, current_time);
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 (output_file_directory_ != nullptr) {
output_file_directory_->Fsync();
}
TEST_SYNC_POINT("FlushJob::WriteLevel0Table");
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_.smallest_seqno, meta_.largest_seqno,
meta_.marked_for_compaction);
}
// Note that here we treat flush as level 0 compaction in internal stats
InternalStats::CompactionStats stats(1);
stats.micros = db_options_.env->NowMicros() - start_micros;
stats.bytes_written = meta_.fd.GetFileSize();
cfd_->internal_stats()->AddCompactionStats(0 /* level */, stats);
cfd_->internal_stats()->AddCFStats(InternalStats::BYTES_FLUSHED,
meta_.fd.GetFileSize());
RecordFlushIOStats();
return s;
}
} // namespace rocksdb