in db/db_impl/db_impl_compaction_flush.cc [3006:3500]
Status DBImpl::BackgroundCompaction(bool* made_progress,
JobContext* job_context,
LogBuffer* log_buffer,
PrepickedCompaction* prepicked_compaction,
Env::Priority thread_pri) {
ManualCompactionState* manual_compaction =
prepicked_compaction == nullptr
? nullptr
: prepicked_compaction->manual_compaction_state;
*made_progress = false;
mutex_.AssertHeld();
TEST_SYNC_POINT("DBImpl::BackgroundCompaction:Start");
bool is_manual = (manual_compaction != nullptr);
std::unique_ptr<Compaction> c;
if (prepicked_compaction != nullptr &&
prepicked_compaction->compaction != nullptr) {
c.reset(prepicked_compaction->compaction);
}
bool is_prepicked = is_manual || c;
// (manual_compaction->in_progress == false);
bool trivial_move_disallowed =
is_manual && manual_compaction->disallow_trivial_move;
CompactionJobStats compaction_job_stats;
Status status;
if (!error_handler_.IsBGWorkStopped()) {
if (shutting_down_.load(std::memory_order_acquire)) {
status = Status::ShutdownInProgress();
} else if (is_manual &&
manual_compaction_paused_.load(std::memory_order_acquire) > 0) {
status = Status::Incomplete(Status::SubCode::kManualCompactionPaused);
} else if (is_manual && manual_compaction->canceled &&
manual_compaction->canceled->load(std::memory_order_acquire)) {
status = Status::Incomplete(Status::SubCode::kManualCompactionPaused);
}
} else {
status = error_handler_.GetBGError();
// If we get here, it means a hard error happened after this compaction
// was scheduled by MaybeScheduleFlushOrCompaction(), but before it got
// a chance to execute. Since we didn't pop a cfd from the compaction
// queue, increment unscheduled_compactions_
unscheduled_compactions_++;
}
if (!status.ok()) {
if (is_manual) {
manual_compaction->status = status;
manual_compaction->done = true;
manual_compaction->in_progress = false;
manual_compaction = nullptr;
}
if (c) {
c->ReleaseCompactionFiles(status);
c.reset();
}
return status;
}
if (is_manual) {
// another thread cannot pick up the same work
manual_compaction->in_progress = true;
}
TEST_SYNC_POINT("DBImpl::BackgroundCompaction:InProgress");
std::unique_ptr<TaskLimiterToken> task_token;
// InternalKey manual_end_storage;
// InternalKey* manual_end = &manual_end_storage;
bool sfm_reserved_compact_space = false;
if (is_manual) {
ManualCompactionState* m = manual_compaction;
assert(m->in_progress);
if (!c) {
m->done = true;
m->manual_end = nullptr;
ROCKS_LOG_BUFFER(
log_buffer,
"[%s] Manual compaction from level-%d from %s .. "
"%s; nothing to do\n",
m->cfd->GetName().c_str(), m->input_level,
(m->begin ? m->begin->DebugString(true).c_str() : "(begin)"),
(m->end ? m->end->DebugString(true).c_str() : "(end)"));
} else {
// First check if we have enough room to do the compaction
bool enough_room = EnoughRoomForCompaction(
m->cfd, *(c->inputs()), &sfm_reserved_compact_space, log_buffer);
if (!enough_room) {
// Then don't do the compaction
c->ReleaseCompactionFiles(status);
c.reset();
// m's vars will get set properly at the end of this function,
// as long as status == CompactionTooLarge
status = Status::CompactionTooLarge();
} else {
ROCKS_LOG_BUFFER(
log_buffer,
"[%s] Manual compaction from level-%d to level-%d from %s .. "
"%s; will stop at %s\n",
m->cfd->GetName().c_str(), m->input_level, c->output_level(),
(m->begin ? m->begin->DebugString(true).c_str() : "(begin)"),
(m->end ? m->end->DebugString(true).c_str() : "(end)"),
((m->done || m->manual_end == nullptr)
? "(end)"
: m->manual_end->DebugString(true).c_str()));
}
}
} else if (!is_prepicked && !compaction_queue_.empty()) {
if (HasExclusiveManualCompaction()) {
// Can't compact right now, but try again later
TEST_SYNC_POINT("DBImpl::BackgroundCompaction()::Conflict");
// Stay in the compaction queue.
unscheduled_compactions_++;
return Status::OK();
}
auto cfd = PickCompactionFromQueue(&task_token, log_buffer);
if (cfd == nullptr) {
// Can't find any executable task from the compaction queue.
// All tasks have been throttled by compaction thread limiter.
++unscheduled_compactions_;
return Status::Busy();
}
// We unreference here because the following code will take a Ref() on
// this cfd if it is going to use it (Compaction class holds a
// reference).
// This will all happen under a mutex so we don't have to be afraid of
// somebody else deleting it.
if (cfd->UnrefAndTryDelete()) {
// This was the last reference of the column family, so no need to
// compact.
return Status::OK();
}
// Pick up latest mutable CF Options and use it throughout the
// compaction job
// Compaction makes a copy of the latest MutableCFOptions. It should be used
// throughout the compaction procedure to make sure consistency. It will
// eventually be installed into SuperVersion
auto* mutable_cf_options = cfd->GetLatestMutableCFOptions();
if (!mutable_cf_options->disable_auto_compactions && !cfd->IsDropped()) {
// NOTE: try to avoid unnecessary copy of MutableCFOptions if
// compaction is not necessary. Need to make sure mutex is held
// until we make a copy in the following code
TEST_SYNC_POINT("DBImpl::BackgroundCompaction():BeforePickCompaction");
c.reset(cfd->PickCompaction(*mutable_cf_options, mutable_db_options_,
log_buffer));
TEST_SYNC_POINT("DBImpl::BackgroundCompaction():AfterPickCompaction");
if (c != nullptr) {
bool enough_room = EnoughRoomForCompaction(
cfd, *(c->inputs()), &sfm_reserved_compact_space, log_buffer);
if (!enough_room) {
// Then don't do the compaction
c->ReleaseCompactionFiles(status);
c->column_family_data()
->current()
->storage_info()
->ComputeCompactionScore(*(c->immutable_options()),
*(c->mutable_cf_options()));
AddToCompactionQueue(cfd);
++unscheduled_compactions_;
c.reset();
// Don't need to sleep here, because BackgroundCallCompaction
// will sleep if !s.ok()
status = Status::CompactionTooLarge();
} else {
// update statistics
size_t num_files = 0;
for (auto& each_level : *c->inputs()) {
num_files += each_level.files.size();
}
RecordInHistogram(stats_, NUM_FILES_IN_SINGLE_COMPACTION, num_files);
// There are three things that can change compaction score:
// 1) When flush or compaction finish. This case is covered by
// InstallSuperVersionAndScheduleWork
// 2) When MutableCFOptions changes. This case is also covered by
// InstallSuperVersionAndScheduleWork, because this is when the new
// options take effect.
// 3) When we Pick a new compaction, we "remove" those files being
// compacted from the calculation, which then influences compaction
// score. Here we check if we need the new compaction even without the
// files that are currently being compacted. If we need another
// compaction, we might be able to execute it in parallel, so we add
// it to the queue and schedule a new thread.
if (cfd->NeedsCompaction()) {
// Yes, we need more compactions!
AddToCompactionQueue(cfd);
++unscheduled_compactions_;
MaybeScheduleFlushOrCompaction();
}
}
}
}
}
IOStatus io_s;
if (!c) {
// Nothing to do
ROCKS_LOG_BUFFER(log_buffer, "Compaction nothing to do");
} else if (c->deletion_compaction()) {
// TODO(icanadi) Do we want to honor snapshots here? i.e. not delete old
// file if there is alive snapshot pointing to it
TEST_SYNC_POINT_CALLBACK("DBImpl::BackgroundCompaction:BeforeCompaction",
c->column_family_data());
assert(c->num_input_files(1) == 0);
assert(c->level() == 0);
assert(c->column_family_data()->ioptions()->compaction_style ==
kCompactionStyleFIFO);
compaction_job_stats.num_input_files = c->num_input_files(0);
NotifyOnCompactionBegin(c->column_family_data(), c.get(), status,
compaction_job_stats, job_context->job_id);
for (const auto& f : *c->inputs(0)) {
c->edit()->DeleteFile(c->level(), f->fd.GetNumber());
}
status = versions_->LogAndApply(c->column_family_data(),
*c->mutable_cf_options(), c->edit(),
&mutex_, directories_.GetDbDir());
io_s = versions_->io_status();
InstallSuperVersionAndScheduleWork(c->column_family_data(),
&job_context->superversion_contexts[0],
*c->mutable_cf_options());
ROCKS_LOG_BUFFER(log_buffer, "[%s] Deleted %d files\n",
c->column_family_data()->GetName().c_str(),
c->num_input_files(0));
*made_progress = true;
TEST_SYNC_POINT_CALLBACK("DBImpl::BackgroundCompaction:AfterCompaction",
c->column_family_data());
} else if (!trivial_move_disallowed && c->IsTrivialMove()) {
TEST_SYNC_POINT("DBImpl::BackgroundCompaction:TrivialMove");
TEST_SYNC_POINT_CALLBACK("DBImpl::BackgroundCompaction:BeforeCompaction",
c->column_family_data());
// Instrument for event update
// TODO(yhchiang): add op details for showing trivial-move.
ThreadStatusUtil::SetColumnFamily(
c->column_family_data(), c->column_family_data()->ioptions()->env,
immutable_db_options_.enable_thread_tracking);
ThreadStatusUtil::SetThreadOperation(ThreadStatus::OP_COMPACTION);
compaction_job_stats.num_input_files = c->num_input_files(0);
NotifyOnCompactionBegin(c->column_family_data(), c.get(), status,
compaction_job_stats, job_context->job_id);
// Move files to next level
int32_t moved_files = 0;
int64_t moved_bytes = 0;
for (unsigned int l = 0; l < c->num_input_levels(); l++) {
if (c->level(l) == c->output_level()) {
continue;
}
for (size_t i = 0; i < c->num_input_files(l); i++) {
FileMetaData* f = c->input(l, i);
c->edit()->DeleteFile(c->level(l), f->fd.GetNumber());
c->edit()->AddFile(
c->output_level(), f->fd.GetNumber(), f->fd.GetPathId(),
f->fd.GetFileSize(), f->smallest, f->largest, f->fd.smallest_seqno,
f->fd.largest_seqno, f->marked_for_compaction, f->temperature,
f->oldest_blob_file_number, f->oldest_ancester_time,
f->file_creation_time, f->file_checksum, f->file_checksum_func_name,
f->min_timestamp, f->max_timestamp);
ROCKS_LOG_BUFFER(
log_buffer,
"[%s] Moving #%" PRIu64 " to level-%d %" PRIu64 " bytes\n",
c->column_family_data()->GetName().c_str(), f->fd.GetNumber(),
c->output_level(), f->fd.GetFileSize());
++moved_files;
moved_bytes += f->fd.GetFileSize();
}
}
status = versions_->LogAndApply(c->column_family_data(),
*c->mutable_cf_options(), c->edit(),
&mutex_, directories_.GetDbDir());
io_s = versions_->io_status();
// Use latest MutableCFOptions
InstallSuperVersionAndScheduleWork(c->column_family_data(),
&job_context->superversion_contexts[0],
*c->mutable_cf_options());
VersionStorageInfo::LevelSummaryStorage tmp;
c->column_family_data()->internal_stats()->IncBytesMoved(c->output_level(),
moved_bytes);
{
event_logger_.LogToBuffer(log_buffer)
<< "job" << job_context->job_id << "event"
<< "trivial_move"
<< "destination_level" << c->output_level() << "files" << moved_files
<< "total_files_size" << moved_bytes;
}
ROCKS_LOG_BUFFER(
log_buffer,
"[%s] Moved #%d files to level-%d %" PRIu64 " bytes %s: %s\n",
c->column_family_data()->GetName().c_str(), moved_files,
c->output_level(), moved_bytes, status.ToString().c_str(),
c->column_family_data()->current()->storage_info()->LevelSummary(&tmp));
*made_progress = true;
// Clear Instrument
ThreadStatusUtil::ResetThreadStatus();
TEST_SYNC_POINT_CALLBACK("DBImpl::BackgroundCompaction:AfterCompaction",
c->column_family_data());
} else if (!is_prepicked && c->output_level() > 0 &&
c->output_level() ==
c->column_family_data()
->current()
->storage_info()
->MaxOutputLevel(
immutable_db_options_.allow_ingest_behind) &&
env_->GetBackgroundThreads(Env::Priority::BOTTOM) > 0) {
// Forward compactions involving last level to the bottom pool if it exists,
// such that compactions unlikely to contribute to write stalls can be
// delayed or deprioritized.
TEST_SYNC_POINT("DBImpl::BackgroundCompaction:ForwardToBottomPriPool");
CompactionArg* ca = new CompactionArg;
ca->db = this;
ca->compaction_pri_ = Env::Priority::BOTTOM;
ca->prepicked_compaction = new PrepickedCompaction;
ca->prepicked_compaction->compaction = c.release();
ca->prepicked_compaction->manual_compaction_state = nullptr;
// Transfer requested token, so it doesn't need to do it again.
ca->prepicked_compaction->task_token = std::move(task_token);
++bg_bottom_compaction_scheduled_;
env_->Schedule(&DBImpl::BGWorkBottomCompaction, ca, Env::Priority::BOTTOM,
this, &DBImpl::UnscheduleCompactionCallback);
} else {
TEST_SYNC_POINT_CALLBACK("DBImpl::BackgroundCompaction:BeforeCompaction",
c->column_family_data());
int output_level __attribute__((__unused__));
output_level = c->output_level();
TEST_SYNC_POINT_CALLBACK("DBImpl::BackgroundCompaction:NonTrivial",
&output_level);
std::vector<SequenceNumber> snapshot_seqs;
SequenceNumber earliest_write_conflict_snapshot;
SnapshotChecker* snapshot_checker;
GetSnapshotContext(job_context, &snapshot_seqs,
&earliest_write_conflict_snapshot, &snapshot_checker);
assert(is_snapshot_supported_ || snapshots_.empty());
CompactionJob compaction_job(
job_context->job_id, c.get(), immutable_db_options_,
mutable_db_options_, file_options_for_compaction_, versions_.get(),
&shutting_down_, preserve_deletes_seqnum_.load(), log_buffer,
directories_.GetDbDir(),
GetDataDir(c->column_family_data(), c->output_path_id()),
GetDataDir(c->column_family_data(), 0), stats_, &mutex_,
&error_handler_, snapshot_seqs, earliest_write_conflict_snapshot,
snapshot_checker, table_cache_, &event_logger_,
c->mutable_cf_options()->paranoid_file_checks,
c->mutable_cf_options()->report_bg_io_stats, dbname_,
&compaction_job_stats, thread_pri, io_tracer_,
is_manual ? &manual_compaction_paused_ : nullptr,
is_manual ? manual_compaction->canceled : nullptr, db_id_,
db_session_id_, c->column_family_data()->GetFullHistoryTsLow(),
c->trim_ts(), &blob_callback_);
compaction_job.Prepare();
NotifyOnCompactionBegin(c->column_family_data(), c.get(), status,
compaction_job_stats, job_context->job_id);
mutex_.Unlock();
TEST_SYNC_POINT_CALLBACK(
"DBImpl::BackgroundCompaction:NonTrivial:BeforeRun", nullptr);
// Should handle erorr?
compaction_job.Run().PermitUncheckedError();
TEST_SYNC_POINT("DBImpl::BackgroundCompaction:NonTrivial:AfterRun");
mutex_.Lock();
status = compaction_job.Install(*c->mutable_cf_options());
io_s = compaction_job.io_status();
if (status.ok()) {
InstallSuperVersionAndScheduleWork(c->column_family_data(),
&job_context->superversion_contexts[0],
*c->mutable_cf_options());
}
*made_progress = true;
TEST_SYNC_POINT_CALLBACK("DBImpl::BackgroundCompaction:AfterCompaction",
c->column_family_data());
}
if (status.ok() && !io_s.ok()) {
status = io_s;
} else {
io_s.PermitUncheckedError();
}
if (c != nullptr) {
c->ReleaseCompactionFiles(status);
*made_progress = true;
#ifndef ROCKSDB_LITE
// Need to make sure SstFileManager does its bookkeeping
auto sfm = static_cast<SstFileManagerImpl*>(
immutable_db_options_.sst_file_manager.get());
if (sfm && sfm_reserved_compact_space) {
sfm->OnCompactionCompletion(c.get());
}
#endif // ROCKSDB_LITE
NotifyOnCompactionCompleted(c->column_family_data(), c.get(), status,
compaction_job_stats, job_context->job_id);
}
if (status.ok() || status.IsCompactionTooLarge() ||
status.IsManualCompactionPaused()) {
// Done
} else if (status.IsColumnFamilyDropped() || status.IsShutdownInProgress()) {
// Ignore compaction errors found during shutting down
} else {
ROCKS_LOG_WARN(immutable_db_options_.info_log, "Compaction error: %s",
status.ToString().c_str());
if (!io_s.ok()) {
// Error while writing to MANIFEST.
// In fact, versions_->io_status() can also be the result of renaming
// CURRENT file. With current code, it's just difficult to tell. So just
// be pessimistic and try write to a new MANIFEST.
// TODO: distinguish between MANIFEST write and CURRENT renaming
auto err_reason = versions_->io_status().ok()
? BackgroundErrorReason::kCompaction
: BackgroundErrorReason::kManifestWrite;
error_handler_.SetBGError(io_s, err_reason);
} else {
error_handler_.SetBGError(status, BackgroundErrorReason::kCompaction);
}
if (c != nullptr && !is_manual && !error_handler_.IsBGWorkStopped()) {
// Put this cfd back in the compaction queue so we can retry after some
// time
auto cfd = c->column_family_data();
assert(cfd != nullptr);
// Since this compaction failed, we need to recompute the score so it
// takes the original input files into account
c->column_family_data()
->current()
->storage_info()
->ComputeCompactionScore(*(c->immutable_options()),
*(c->mutable_cf_options()));
if (!cfd->queued_for_compaction()) {
AddToCompactionQueue(cfd);
++unscheduled_compactions_;
}
}
}
// this will unref its input_version and column_family_data
c.reset();
if (is_manual) {
ManualCompactionState* m = manual_compaction;
if (!status.ok()) {
m->status = status;
m->done = true;
}
// For universal compaction:
// Because universal compaction always happens at level 0, so one
// compaction will pick up all overlapped files. No files will be
// filtered out due to size limit and left for a successive compaction.
// So we can safely conclude the current compaction.
//
// Also note that, if we don't stop here, then the current compaction
// writes a new file back to level 0, which will be used in successive
// compaction. Hence the manual compaction will never finish.
//
// Stop the compaction if manual_end points to nullptr -- this means
// that we compacted the whole range. manual_end should always point
// to nullptr in case of universal compaction
if (m->manual_end == nullptr) {
m->done = true;
}
if (!m->done) {
// We only compacted part of the requested range. Update *m
// to the range that is left to be compacted.
// Universal and FIFO compactions should always compact the whole range
assert(m->cfd->ioptions()->compaction_style !=
kCompactionStyleUniversal ||
m->cfd->ioptions()->num_levels > 1);
assert(m->cfd->ioptions()->compaction_style != kCompactionStyleFIFO);
m->tmp_storage = *m->manual_end;
m->begin = &m->tmp_storage;
m->incomplete = true;
}
m->in_progress = false; // not being processed anymore
}
TEST_SYNC_POINT("DBImpl::BackgroundCompaction:Finish");
return status;
}