mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-30 04:41:49 +00:00
3f62215210
Summary: Since a RangeDelAggregator is created for each read request, these heap-allocating member variables were consuming significant CPU (~3% total) which slowed down request throughput. The map and pinning manager are only necessary when range deletions exist, so we can defer their initialization until the first range deletion is encountered. Currently lazy initialization is done for reads only since reads pass us a single snapshot, which is easier to store on the stack for later insertion into the map than the vector passed to us by flush or compaction. Note the Arena member variable is still expensive, I will figure out what to do with it in a subsequent diff. It cannot be lazily initialized because we currently use this arena even to allocate empty iterators, which is necessary even when no range deletions exist. Closes https://github.com/facebook/rocksdb/pull/1539 Differential Revision: D4203488 Pulled By: ajkr fbshipit-source-id: 3b36279
197 lines
6.7 KiB
C++
197 lines
6.7 KiB
C++
// 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.
|
|
|
|
|
|
#include "db/db_impl_readonly.h"
|
|
|
|
#include "db/compacted_db_impl.h"
|
|
#include "db/db_impl.h"
|
|
#include "db/db_iter.h"
|
|
#include "db/merge_context.h"
|
|
#include "db/range_del_aggregator.h"
|
|
#include "util/perf_context_imp.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
#ifndef ROCKSDB_LITE
|
|
|
|
DBImplReadOnly::DBImplReadOnly(const DBOptions& db_options,
|
|
const std::string& dbname)
|
|
: DBImpl(db_options, dbname) {
|
|
Log(INFO_LEVEL, immutable_db_options_.info_log,
|
|
"Opening the db in read only mode");
|
|
LogFlush(immutable_db_options_.info_log);
|
|
}
|
|
|
|
DBImplReadOnly::~DBImplReadOnly() {
|
|
}
|
|
|
|
// Implementations of the DB interface
|
|
Status DBImplReadOnly::Get(const ReadOptions& read_options,
|
|
ColumnFamilyHandle* column_family, const Slice& key,
|
|
std::string* value) {
|
|
Status s;
|
|
SequenceNumber snapshot = versions_->LastSequence();
|
|
auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
|
|
auto cfd = cfh->cfd();
|
|
SuperVersion* super_version = cfd->GetSuperVersion();
|
|
MergeContext merge_context;
|
|
RangeDelAggregator range_del_agg(cfd->internal_comparator(), snapshot);
|
|
LookupKey lkey(key, snapshot);
|
|
if (super_version->mem->Get(lkey, value, &s, &merge_context, &range_del_agg,
|
|
read_options)) {
|
|
} else {
|
|
PERF_TIMER_GUARD(get_from_output_files_time);
|
|
super_version->current->Get(read_options, lkey, value, &s, &merge_context,
|
|
&range_del_agg);
|
|
}
|
|
return s;
|
|
}
|
|
|
|
Iterator* DBImplReadOnly::NewIterator(const ReadOptions& read_options,
|
|
ColumnFamilyHandle* column_family) {
|
|
auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
|
|
auto cfd = cfh->cfd();
|
|
SuperVersion* super_version = cfd->GetSuperVersion()->Ref();
|
|
SequenceNumber latest_snapshot = versions_->LastSequence();
|
|
auto db_iter = NewArenaWrappedDbIterator(
|
|
env_, *cfd->ioptions(), cfd->user_comparator(),
|
|
(read_options.snapshot != nullptr
|
|
? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
|
|
->number_
|
|
: latest_snapshot),
|
|
super_version->mutable_cf_options.max_sequential_skip_in_iterations,
|
|
super_version->version_number);
|
|
auto internal_iter =
|
|
NewInternalIterator(read_options, cfd, super_version, db_iter->GetArena(),
|
|
db_iter->GetRangeDelAggregator());
|
|
db_iter->SetIterUnderDBIter(internal_iter);
|
|
return db_iter;
|
|
}
|
|
|
|
Status DBImplReadOnly::NewIterators(
|
|
const ReadOptions& read_options,
|
|
const std::vector<ColumnFamilyHandle*>& column_families,
|
|
std::vector<Iterator*>* iterators) {
|
|
if (iterators == nullptr) {
|
|
return Status::InvalidArgument("iterators not allowed to be nullptr");
|
|
}
|
|
iterators->clear();
|
|
iterators->reserve(column_families.size());
|
|
SequenceNumber latest_snapshot = versions_->LastSequence();
|
|
|
|
for (auto cfh : column_families) {
|
|
auto* cfd = reinterpret_cast<ColumnFamilyHandleImpl*>(cfh)->cfd();
|
|
auto* sv = cfd->GetSuperVersion()->Ref();
|
|
auto* db_iter = NewArenaWrappedDbIterator(
|
|
env_, *cfd->ioptions(), cfd->user_comparator(),
|
|
(read_options.snapshot != nullptr
|
|
? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
|
|
->number_
|
|
: latest_snapshot),
|
|
sv->mutable_cf_options.max_sequential_skip_in_iterations,
|
|
sv->version_number);
|
|
auto* internal_iter =
|
|
NewInternalIterator(read_options, cfd, sv, db_iter->GetArena(),
|
|
db_iter->GetRangeDelAggregator());
|
|
db_iter->SetIterUnderDBIter(internal_iter);
|
|
iterators->push_back(db_iter);
|
|
}
|
|
|
|
return Status::OK();
|
|
}
|
|
|
|
Status DB::OpenForReadOnly(const Options& options, const std::string& dbname,
|
|
DB** dbptr, bool error_if_log_file_exist) {
|
|
*dbptr = nullptr;
|
|
|
|
// Try to first open DB as fully compacted DB
|
|
Status s;
|
|
s = CompactedDBImpl::Open(options, dbname, dbptr);
|
|
if (s.ok()) {
|
|
return s;
|
|
}
|
|
|
|
DBOptions db_options(options);
|
|
ColumnFamilyOptions cf_options(options);
|
|
std::vector<ColumnFamilyDescriptor> column_families;
|
|
column_families.push_back(
|
|
ColumnFamilyDescriptor(kDefaultColumnFamilyName, cf_options));
|
|
std::vector<ColumnFamilyHandle*> handles;
|
|
|
|
s = DB::OpenForReadOnly(db_options, dbname, column_families, &handles, dbptr);
|
|
if (s.ok()) {
|
|
assert(handles.size() == 1);
|
|
// i can delete the handle since DBImpl is always holding a
|
|
// reference to default column family
|
|
delete handles[0];
|
|
}
|
|
return s;
|
|
}
|
|
|
|
Status DB::OpenForReadOnly(
|
|
const DBOptions& db_options, const std::string& dbname,
|
|
const std::vector<ColumnFamilyDescriptor>& column_families,
|
|
std::vector<ColumnFamilyHandle*>* handles, DB** dbptr,
|
|
bool error_if_log_file_exist) {
|
|
*dbptr = nullptr;
|
|
handles->clear();
|
|
|
|
DBImplReadOnly* impl = new DBImplReadOnly(db_options, dbname);
|
|
impl->mutex_.Lock();
|
|
Status s = impl->Recover(column_families, true /* read only */,
|
|
error_if_log_file_exist);
|
|
if (s.ok()) {
|
|
// set column family handles
|
|
for (auto cf : column_families) {
|
|
auto cfd =
|
|
impl->versions_->GetColumnFamilySet()->GetColumnFamily(cf.name);
|
|
if (cfd == nullptr) {
|
|
s = Status::InvalidArgument("Column family not found: ", cf.name);
|
|
break;
|
|
}
|
|
handles->push_back(new ColumnFamilyHandleImpl(cfd, impl, &impl->mutex_));
|
|
}
|
|
}
|
|
if (s.ok()) {
|
|
for (auto cfd : *impl->versions_->GetColumnFamilySet()) {
|
|
delete cfd->InstallSuperVersion(new SuperVersion(), &impl->mutex_);
|
|
}
|
|
}
|
|
impl->mutex_.Unlock();
|
|
if (s.ok()) {
|
|
*dbptr = impl;
|
|
for (auto* h : *handles) {
|
|
impl->NewThreadStatusCfInfo(
|
|
reinterpret_cast<ColumnFamilyHandleImpl*>(h)->cfd());
|
|
}
|
|
} else {
|
|
for (auto h : *handles) {
|
|
delete h;
|
|
}
|
|
handles->clear();
|
|
delete impl;
|
|
}
|
|
return s;
|
|
}
|
|
|
|
#else // !ROCKSDB_LITE
|
|
|
|
Status DB::OpenForReadOnly(const Options& options, const std::string& dbname,
|
|
DB** dbptr, bool error_if_log_file_exist) {
|
|
return Status::NotSupported("Not supported in ROCKSDB_LITE.");
|
|
}
|
|
|
|
Status DB::OpenForReadOnly(
|
|
const DBOptions& db_options, const std::string& dbname,
|
|
const std::vector<ColumnFamilyDescriptor>& column_families,
|
|
std::vector<ColumnFamilyHandle*>* handles, DB** dbptr,
|
|
bool error_if_log_file_exist) {
|
|
return Status::NotSupported("Not supported in ROCKSDB_LITE.");
|
|
}
|
|
#endif // !ROCKSDB_LITE
|
|
|
|
} // namespace rocksdb
|