in db/flush_job.cc [798:1026]
Status FlushJob::WriteLevel0Table() {
AutoThreadOperationStageUpdater stage_updater(
ThreadStatus::STAGE_FLUSH_WRITE_L0);
db_mutex_->AssertHeld();
const uint64_t start_micros = clock_->NowMicros();
const uint64_t start_cpu_micros = clock_->CPUMicros();
Status s;
std::vector<BlobFileAddition> blob_file_additions;
{
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;
// Used for testing:
uint64_t mems_size = mems_.size();
(void)mems_size; // avoids unused variable error when
// TEST_SYNC_POINT_CALLBACK not used.
TEST_SYNC_POINT_CALLBACK("FlushJob::WriteLevel0Table:num_memtables",
&mems_size);
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.data(),
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 = clock_->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());
}
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.
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;
uint64_t num_input_entries = 0;
uint64_t memtable_payload_bytes = 0;
uint64_t memtable_garbage_bytes = 0;
IOStatus io_s;
const std::string* const full_history_ts_low =
(full_history_ts_low_.empty()) ? nullptr : &full_history_ts_low_;
TableBuilderOptions tboptions(
*cfd_->ioptions(), mutable_cf_options_, cfd_->internal_comparator(),
cfd_->int_tbl_prop_collector_factories(), output_compression_,
mutable_cf_options_.compression_opts, cfd_->GetID(), cfd_->GetName(),
0 /* level */, false /* is_bottommost */,
TableFileCreationReason::kFlush, creation_time, oldest_key_time,
current_time, db_id_, db_session_id_, 0 /* target_file_size */,
meta_.fd.GetNumber());
s = BuildTable(
dbname_, versions_, db_options_, tboptions, file_options_,
cfd_->table_cache(), iter.get(), std::move(range_del_iters), &meta_,
&blob_file_additions, existing_snapshots_,
earliest_write_conflict_snapshot_, snapshot_checker_,
mutable_cf_options_.paranoid_file_checks, cfd_->internal_stats(),
&io_s, io_tracer_, BlobFileCreationReason::kFlush, event_logger_,
job_context_->job_id, Env::IO_HIGH, &table_properties_, write_hint,
full_history_ts_low, blob_callback_, &num_input_entries,
&memtable_payload_bytes, &memtable_garbage_bytes);
// TODO: Cleanup io_status in BuildTable and table builders
assert(!s.ok() || io_s.ok());
io_s.PermitUncheckedError();
if (num_input_entries != total_num_entries && s.ok()) {
std::string msg = "Expected " + ToString(total_num_entries) +
" entries in memtables, but read " +
ToString(num_input_entries);
ROCKS_LOG_WARN(db_options_.info_log, "[%s] [JOB %d] Level-0 flush %s",
cfd_->GetName().c_str(), job_context_->job_id,
msg.c_str());
if (db_options_.flush_verify_memtable_count) {
s = Status::Corruption(msg);
}
}
if (tboptions.reason == TableFileCreationReason::kFlush) {
TEST_SYNC_POINT("DBImpl::FlushJob:Flush");
RecordTick(stats_, MEMTABLE_PAYLOAD_BYTES_AT_FLUSH,
memtable_payload_bytes);
RecordTick(stats_, MEMTABLE_GARBAGE_BYTES_AT_FLUSH,
memtable_garbage_bytes);
}
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_->FsyncWithDirOptions(
IOOptions(), nullptr,
DirFsyncOptions(DirFsyncOptions::FsyncReason::kNewFileSynced));
}
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.
const bool has_output = meta_.fd.GetFileSize() > 0;
if (s.ok() && has_output) {
TEST_SYNC_POINT("DBImpl::FlushJob:SSTFileCreated");
// 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_.temperature,
meta_.oldest_blob_file_number, meta_.oldest_ancester_time,
meta_.file_creation_time, meta_.file_checksum,
meta_.file_checksum_func_name, meta_.min_timestamp,
meta_.max_timestamp);
edit_->SetBlobFileAdditions(std::move(blob_file_additions));
}
#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);
const uint64_t micros = clock_->NowMicros() - start_micros;
const uint64_t cpu_micros = clock_->CPUMicros() - start_cpu_micros;
stats.micros = micros;
stats.cpu_micros = cpu_micros;
ROCKS_LOG_INFO(db_options_.info_log,
"[%s] [JOB %d] Flush lasted %" PRIu64
" microseconds, and %" PRIu64 " cpu microseconds.\n",
cfd_->GetName().c_str(), job_context_->job_id, micros,
cpu_micros);
if (has_output) {
stats.bytes_written = meta_.fd.GetFileSize();
stats.num_output_files = 1;
}
const auto& blobs = edit_->GetBlobFileAdditions();
for (const auto& blob : blobs) {
stats.bytes_written_blob += blob.GetTotalBlobBytes();
}
stats.num_output_files_blob = static_cast<int>(blobs.size());
RecordTimeToHistogram(stats_, FLUSH_TIME, stats.micros);
cfd_->internal_stats()->AddCompactionStats(0 /* level */, thread_pri_, stats);
cfd_->internal_stats()->AddCFStats(
InternalStats::BYTES_FLUSHED,
stats.bytes_written + stats.bytes_written_blob);
RecordFlushIOStats();
return s;
}