3dff28cf9b
Summary: For performance purposes, the lower level routines were changed to use a SystemClock* instead of a std::shared_ptr<SystemClock>. The shared ptr has some performance degradation on certain hardware classes. For most of the system, there is no risk of the pointer being deleted/invalid because the shared_ptr will be stored elsewhere. For example, the ImmutableDBOptions stores the Env which has a std::shared_ptr<SystemClock> in it. The SystemClock* within the ImmutableDBOptions is essentially a "short cut" to gain access to this constant resource. There were a few classes (PeriodicWorkScheduler?) where the "short cut" property did not hold. In those cases, the shared pointer was preserved. Using db_bench readrandom perf_level=3 on my EC2 box, this change performed as well or better than 6.17: 6.17: readrandom : 28.046 micros/op 854902 ops/sec; 61.3 MB/s (355999 of 355999 found) 6.18: readrandom : 32.615 micros/op 735306 ops/sec; 52.7 MB/s (290999 of 290999 found) PR: readrandom : 27.500 micros/op 871909 ops/sec; 62.5 MB/s (367999 of 367999 found) (Note that the times for 6.18 are prior to revert of the SystemClock). Pull Request resolved: https://github.com/facebook/rocksdb/pull/8033 Reviewed By: pdillinger Differential Revision: D27014563 Pulled By: mrambacher fbshipit-source-id: ad0459eba03182e454391b5926bf5cdd45657b67
77 lines
2.4 KiB
C++
77 lines
2.4 KiB
C++
#pragma once
|
|
#include <string>
|
|
#include <unordered_set>
|
|
#include <vector>
|
|
|
|
#include "db/column_family.h"
|
|
#include "db/dbformat.h"
|
|
#include "db/external_sst_file_ingestion_job.h"
|
|
#include "db/snapshot_impl.h"
|
|
#include "options/db_options.h"
|
|
#include "rocksdb/db.h"
|
|
#include "rocksdb/metadata.h"
|
|
#include "rocksdb/sst_file_writer.h"
|
|
#include "util/autovector.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
struct EnvOptions;
|
|
class SystemClock;
|
|
|
|
// Imports a set of sst files as is into a new column family. Logic is similar
|
|
// to ExternalSstFileIngestionJob.
|
|
class ImportColumnFamilyJob {
|
|
public:
|
|
ImportColumnFamilyJob(VersionSet* versions, ColumnFamilyData* cfd,
|
|
const ImmutableDBOptions& db_options,
|
|
const EnvOptions& env_options,
|
|
const ImportColumnFamilyOptions& import_options,
|
|
const std::vector<LiveFileMetaData>& metadata,
|
|
const std::shared_ptr<IOTracer>& io_tracer)
|
|
: clock_(db_options.clock),
|
|
versions_(versions),
|
|
cfd_(cfd),
|
|
db_options_(db_options),
|
|
fs_(db_options_.fs, io_tracer),
|
|
env_options_(env_options),
|
|
import_options_(import_options),
|
|
metadata_(metadata),
|
|
io_tracer_(io_tracer) {}
|
|
|
|
// Prepare the job by copying external files into the DB.
|
|
Status Prepare(uint64_t next_file_number, SuperVersion* sv);
|
|
|
|
// Will execute the import job and prepare edit() to be applied.
|
|
// REQUIRES: Mutex held
|
|
Status Run();
|
|
|
|
// Cleanup after successful/failed job
|
|
void Cleanup(const Status& status);
|
|
|
|
VersionEdit* edit() { return &edit_; }
|
|
|
|
const autovector<IngestedFileInfo>& files_to_import() const {
|
|
return files_to_import_;
|
|
}
|
|
|
|
private:
|
|
// Open the external file and populate `file_to_import` with all the
|
|
// external information we need to import this file.
|
|
Status GetIngestedFileInfo(const std::string& external_file,
|
|
IngestedFileInfo* file_to_import,
|
|
SuperVersion* sv);
|
|
|
|
SystemClock* clock_;
|
|
VersionSet* versions_;
|
|
ColumnFamilyData* cfd_;
|
|
const ImmutableDBOptions& db_options_;
|
|
const FileSystemPtr fs_;
|
|
const EnvOptions& env_options_;
|
|
autovector<IngestedFileInfo> files_to_import_;
|
|
VersionEdit edit_;
|
|
const ImportColumnFamilyOptions& import_options_;
|
|
std::vector<LiveFileMetaData> metadata_;
|
|
const std::shared_ptr<IOTracer> io_tracer_;
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|