rocksdb/db/builder.cc

205 lines
7.5 KiB
C++
Raw Normal View History

// 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.
//
// 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/builder.h"
#include <algorithm>
#include <deque>
#include <vector>
#include "db/compaction_iterator.h"
#include "db/dbformat.h"
#include "db/event_helpers.h"
#include "db/filename.h"
#include "db/internal_stats.h"
#include "db/merge_helper.h"
#include "db/table_cache.h"
#include "db/version_edit.h"
#include "rocksdb/db.h"
#include "rocksdb/env.h"
#include "rocksdb/iterator.h"
#include "rocksdb/options.h"
#include "rocksdb/table.h"
#include "table/block_based_table_builder.h"
#include "table/internal_iterator.h"
#include "util/file_reader_writer.h"
#include "util/iostats_context_imp.h"
#include "util/stop_watch.h"
#include "util/thread_status_util.h"
namespace rocksdb {
class TableFactory;
TableBuilder* NewTableBuilder(
const ImmutableCFOptions& ioptions,
const InternalKeyComparator& internal_comparator,
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
int_tbl_prop_collector_factories,
uint32_t column_family_id, const std::string& column_family_name,
WritableFileWriter* file, const CompressionType compression_type,
const CompressionOptions& compression_opts,
int level,
const std::string* compression_dict, const bool skip_filters) {
assert((column_family_id ==
TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
column_family_name.empty());
return ioptions.table_factory->NewTableBuilder(
TableBuilderOptions(ioptions, internal_comparator,
int_tbl_prop_collector_factories, compression_type,
compression_opts, compression_dict, skip_filters,
column_family_name, level),
column_family_id, file);
}
Status BuildTable(
const std::string& dbname, Env* env, const ImmutableCFOptions& ioptions,
const MutableCFOptions& mutable_cf_options, const EnvOptions& env_options,
TableCache* table_cache, InternalIterator* iter, FileMetaData* meta,
const InternalKeyComparator& internal_comparator,
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
int_tbl_prop_collector_factories,
uint32_t column_family_id, const std::string& column_family_name,
std::vector<SequenceNumber> snapshots,
SequenceNumber earliest_write_conflict_snapshot,
const CompressionType compression,
const CompressionOptions& compression_opts, bool paranoid_file_checks,
InternalStats* internal_stats, TableFileCreationReason reason,
EventLogger* event_logger, int job_id, const Env::IOPriority io_priority,
TableProperties* table_properties, int level) {
assert((column_family_id ==
TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
column_family_name.empty());
// Reports the IOStats for flush for every following bytes.
const size_t kReportFlushIOStatsEvery = 1048576;
Status s;
meta->fd.file_size = 0;
iter->SeekToFirst();
std::string fname = TableFileName(ioptions.db_paths, meta->fd.GetNumber(),
meta->fd.GetPathId());
#ifndef ROCKSDB_LITE
EventHelpers::NotifyTableFileCreationStarted(
ioptions.listeners, dbname, column_family_name, fname, job_id, reason);
#endif // !ROCKSDB_LITE
TableProperties tp;
if (iter->Valid()) {
TableBuilder* builder;
unique_ptr<WritableFileWriter> file_writer;
{
unique_ptr<WritableFile> file;
s = NewWritableFile(env, fname, &file, env_options);
if (!s.ok()) {
EventHelpers::LogAndNotifyTableFileCreationFinished(
event_logger, ioptions.listeners, dbname, column_family_name, fname,
job_id, meta->fd, tp, reason, s);
return s;
}
file->SetIOPriority(io_priority);
file_writer.reset(new WritableFileWriter(std::move(file), env_options));
builder = NewTableBuilder(
ioptions, internal_comparator, int_tbl_prop_collector_factories,
column_family_id, column_family_name, file_writer.get(), compression,
compression_opts, level);
}
MergeHelper merge(env, internal_comparator.user_comparator(),
ioptions.merge_operator, nullptr, ioptions.info_log,
mutable_cf_options.min_partial_merge_operands,
true /* internal key corruption is not ok */,
snapshots.empty() ? 0 : snapshots.back());
CompactionIterator c_iter(iter, internal_comparator.user_comparator(),
&merge, kMaxSequenceNumber, &snapshots,
earliest_write_conflict_snapshot, env,
true /* internal key corruption is not ok */);
c_iter.SeekToFirst();
for (; c_iter.Valid(); c_iter.Next()) {
const Slice& key = c_iter.key();
const Slice& value = c_iter.value();
builder->Add(key, value);
meta->UpdateBoundaries(key, c_iter.ikey().sequence);
// TODO(noetzli): Update stats after flush, too.
if (io_priority == Env::IO_HIGH &&
IOSTATS(bytes_written) >= kReportFlushIOStatsEvery) {
ThreadStatusUtil::SetThreadOperationProperty(
ThreadStatus::FLUSH_BYTES_WRITTEN, IOSTATS(bytes_written));
}
}
// Finish and check for builder errors
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 20:42:56 +02:00
bool empty = builder->NumEntries() == 0;
s = c_iter.status();
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 20:42:56 +02:00
if (!s.ok() || empty) {
builder->Abandon();
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 20:42:56 +02:00
} else {
s = builder->Finish();
}
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 20:42:56 +02:00
if (s.ok() && !empty) {
uint64_t file_size = builder->FileSize();
meta->fd.file_size = file_size;
meta->marked_for_compaction = builder->NeedCompact();
assert(meta->fd.GetFileSize() > 0);
tp = builder->GetTableProperties();
if (table_properties) {
*table_properties = tp;
}
}
delete builder;
// Finish and check for file errors
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 20:42:56 +02:00
if (s.ok() && !empty && !ioptions.disable_data_sync) {
StopWatch sw(env, ioptions.statistics, TABLE_SYNC_MICROS);
file_writer->Sync(ioptions.use_fsync);
}
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 20:42:56 +02:00
if (s.ok() && !empty) {
s = file_writer->Close();
}
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 20:42:56 +02:00
if (s.ok() && !empty) {
// Verify that the table is usable
std::unique_ptr<InternalIterator> it(table_cache->NewIterator(
ReadOptions(), env_options, internal_comparator, meta->fd, nullptr,
(internal_stats == nullptr) ? nullptr
: internal_stats->GetFileReadHist(0),
false /* for_compaction */, nullptr /* arena */,
false /* skip_filter */, level));
s = it->status();
if (s.ok() && paranoid_file_checks) {
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 20:42:56 +02:00
for (it->SeekToFirst(); it->Valid(); it->Next()) {
}
s = it->status();
}
}
}
// Check for input iterator errors
if (!iter->status().ok()) {
s = iter->status();
}
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 20:42:56 +02:00
if (!s.ok() || meta->fd.GetFileSize() == 0) {
env->DeleteFile(fname);
}
// Output to event logger and fire events.
EventHelpers::LogAndNotifyTableFileCreationFinished(
event_logger, ioptions.listeners, dbname, column_family_name, fname,
job_id, meta->fd, tp, reason, s);
return s;
}
} // namespace rocksdb