|
|
|
// Copyright (c) 2013, 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>
|
Simplify querying of merge results
Summary:
While working on supporting mixing merge operators with
single deletes ( https://reviews.facebook.net/D43179 ),
I realized that returning and dealing with merge results
can be made simpler. Submitting this as a separate diff
because it is not directly related to single deletes.
Before, callers of merge helper had to retrieve the merge
result in one of two ways depending on whether the merge
was successful or not (success = result of merge was single
kTypeValue). For successful merges, the caller could query
the resulting key/value pair and for unsuccessful merges,
the result could be retrieved in the form of two deques of
keys and values. However, with single deletes, a successful merge
does not return a single key/value pair (if merge
operands are merged with a single delete, we have to generate
a value and keep the original single delete around to make
sure that we are not accidentially producing a key overwrite).
In addition, the two existing call sites of the merge
helper were taking the same actions independently from whether
the merge was successful or not, so this patch simplifies that.
Test Plan: make clean all check
Reviewers: rven, sdong, yhchiang, anthony, igor
Reviewed By: igor
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D43353
9 years ago
|
|
|
#include <deque>
|
A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.
Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties
Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.
Reviewers: yhchiang, igor.sugak, rven, igor
Reviewed By: rven, igor
Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D35373
10 years ago
|
|
|
#include <vector>
|
Simplify querying of merge results
Summary:
While working on supporting mixing merge operators with
single deletes ( https://reviews.facebook.net/D43179 ),
I realized that returning and dealing with merge results
can be made simpler. Submitting this as a separate diff
because it is not directly related to single deletes.
Before, callers of merge helper had to retrieve the merge
result in one of two ways depending on whether the merge
was successful or not (success = result of merge was single
kTypeValue). For successful merges, the caller could query
the resulting key/value pair and for unsuccessful merges,
the result could be retrieved in the form of two deques of
keys and values. However, with single deletes, a successful merge
does not return a single key/value pair (if merge
operands are merged with a single delete, we have to generate
a value and keep the original single delete around to make
sure that we are not accidentially producing a key overwrite).
In addition, the two existing call sites of the merge
helper were taking the same actions independently from whether
the merge was successful or not, so this patch simplifies that.
Test Plan: make clean all check
Reviewers: rven, sdong, yhchiang, anthony, igor
Reviewed By: igor
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D43353
9 years ago
|
|
|
|
|
|
|
#include "db/compaction_iterator.h"
|
|
|
|
#include "db/dbformat.h"
|
|
|
|
#include "db/filename.h"
|
Measure file read latency histogram per level
Summary: In internal stats, remember read latency histogram, if statistics is enabled. It can be retrieved from DB::GetProperty() with "rocksdb.dbstats" property, if it is enabled.
Test Plan: Manually run db_bench and prints out "rocksdb.dbstats" by hand and make sure it prints out as expected
Reviewers: igor, IslamAbdelRahman, rven, kradhakrishnan, anthony, yhchiang
Reviewed By: yhchiang
Subscribers: MarkCallaghan, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44193
9 years ago
|
|
|
#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"
|
Move rate_limiter, write buffering, most perf context instrumentation and most random kill out of Env
Summary: We want to keep Env a think layer for better portability. Less platform dependent codes should be moved out of Env. In this patch, I create a wrapper of file readers and writers, and put rate limiting, write buffering, as well as most perf context instrumentation and random kill out of Env. It will make it easier to maintain multiple Env in the future.
Test Plan: Run all existing unit tests.
Reviewers: anthony, kradhakrishnan, IslamAbdelRahman, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D42321
9 years ago
|
|
|
#include "util/file_reader_writer.h"
|
|
|
|
#include "util/iostats_context_imp.h"
|
|
|
|
#include "util/stop_watch.h"
|
Simplify querying of merge results
Summary:
While working on supporting mixing merge operators with
single deletes ( https://reviews.facebook.net/D43179 ),
I realized that returning and dealing with merge results
can be made simpler. Submitting this as a separate diff
because it is not directly related to single deletes.
Before, callers of merge helper had to retrieve the merge
result in one of two ways depending on whether the merge
was successful or not (success = result of merge was single
kTypeValue). For successful merges, the caller could query
the resulting key/value pair and for unsuccessful merges,
the result could be retrieved in the form of two deques of
keys and values. However, with single deletes, a successful merge
does not return a single key/value pair (if merge
operands are merged with a single delete, we have to generate
a value and keep the original single delete around to make
sure that we are not accidentially producing a key overwrite).
In addition, the two existing call sites of the merge
helper were taking the same actions independently from whether
the merge was successful or not, so this patch simplifies that.
Test Plan: make clean all check
Reviewers: rven, sdong, yhchiang, anthony, igor
Reviewed By: igor
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D43353
9 years ago
|
|
|
#include "util/thread_status_util.h"
|
|
|
|
|
|
|
|
namespace rocksdb {
|
|
|
|
|
|
|
|
class TableFactory;
|
|
|
|
|
A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.
Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties
Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.
Reviewers: yhchiang, igor.sugak, rven, igor
Reviewed By: rven, igor
Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D35373
10 years ago
|
|
|
TableBuilder* NewTableBuilder(
|
|
|
|
const ImmutableCFOptions& ioptions,
|
|
|
|
const InternalKeyComparator& internal_comparator,
|
|
|
|
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
|
|
|
|
int_tbl_prop_collector_factories,
|
Move rate_limiter, write buffering, most perf context instrumentation and most random kill out of Env
Summary: We want to keep Env a think layer for better portability. Less platform dependent codes should be moved out of Env. In this patch, I create a wrapper of file readers and writers, and put rate limiting, write buffering, as well as most perf context instrumentation and random kill out of Env. It will make it easier to maintain multiple Env in the future.
Test Plan: Run all existing unit tests.
Reviewers: anthony, kradhakrishnan, IslamAbdelRahman, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D42321
9 years ago
|
|
|
WritableFileWriter* file, const CompressionType compression_type,
|
A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.
Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties
Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.
Reviewers: yhchiang, igor.sugak, rven, igor
Reviewed By: rven, igor
Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D35373
10 years ago
|
|
|
const CompressionOptions& compression_opts, const bool skip_filters) {
|
|
|
|
return ioptions.table_factory->NewTableBuilder(
|
|
|
|
TableBuilderOptions(ioptions, internal_comparator,
|
|
|
|
int_tbl_prop_collector_factories, compression_type,
|
|
|
|
compression_opts, skip_filters),
|
|
|
|
file);
|
|
|
|
}
|
|
|
|
|
A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.
Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties
Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.
Reviewers: yhchiang, igor.sugak, rven, igor
Reviewed By: rven, igor
Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D35373
10 years ago
|
|
|
Status BuildTable(
|
|
|
|
const std::string& dbname, Env* env, const ImmutableCFOptions& ioptions,
|
|
|
|
const EnvOptions& env_options, TableCache* table_cache, Iterator* iter,
|
|
|
|
FileMetaData* meta, const InternalKeyComparator& internal_comparator,
|
|
|
|
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
|
|
|
|
int_tbl_prop_collector_factories,
|
|
|
|
std::vector<SequenceNumber> snapshots, const CompressionType compression,
|
|
|
|
const CompressionOptions& compression_opts, bool paranoid_file_checks,
|
Measure file read latency histogram per level
Summary: In internal stats, remember read latency histogram, if statistics is enabled. It can be retrieved from DB::GetProperty() with "rocksdb.dbstats" property, if it is enabled.
Test Plan: Manually run db_bench and prints out "rocksdb.dbstats" by hand and make sure it prints out as expected
Reviewers: igor, IslamAbdelRahman, rven, kradhakrishnan, anthony, yhchiang
Reviewed By: yhchiang
Subscribers: MarkCallaghan, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44193
9 years ago
|
|
|
InternalStats* internal_stats, const Env::IOPriority io_priority,
|
|
|
|
TableProperties* table_properties) {
|
|
|
|
// 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());
|
|
|
|
if (iter->Valid()) {
|
Move rate_limiter, write buffering, most perf context instrumentation and most random kill out of Env
Summary: We want to keep Env a think layer for better portability. Less platform dependent codes should be moved out of Env. In this patch, I create a wrapper of file readers and writers, and put rate limiting, write buffering, as well as most perf context instrumentation and random kill out of Env. It will make it easier to maintain multiple Env in the future.
Test Plan: Run all existing unit tests.
Reviewers: anthony, kradhakrishnan, IslamAbdelRahman, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D42321
9 years ago
|
|
|
TableBuilder* builder;
|
|
|
|
unique_ptr<WritableFileWriter> file_writer;
|
|
|
|
{
|
|
|
|
unique_ptr<WritableFile> file;
|
|
|
|
s = env->NewWritableFile(fname, &file, env_options);
|
|
|
|
if (!s.ok()) {
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
file->SetIOPriority(io_priority);
|
|
|
|
|
Move rate_limiter, write buffering, most perf context instrumentation and most random kill out of Env
Summary: We want to keep Env a think layer for better portability. Less platform dependent codes should be moved out of Env. In this patch, I create a wrapper of file readers and writers, and put rate limiting, write buffering, as well as most perf context instrumentation and random kill out of Env. It will make it easier to maintain multiple Env in the future.
Test Plan: Run all existing unit tests.
Reviewers: anthony, kradhakrishnan, IslamAbdelRahman, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D42321
9 years ago
|
|
|
file_writer.reset(new WritableFileWriter(std::move(file), env_options));
|
|
|
|
|
|
|
|
builder = NewTableBuilder(
|
|
|
|
ioptions, internal_comparator, int_tbl_prop_collector_factories,
|
|
|
|
file_writer.get(), compression, compression_opts);
|
|
|
|
}
|
|
|
|
|
|
|
|
MergeHelper merge(internal_comparator.user_comparator(),
|
|
|
|
ioptions.merge_operator, ioptions.info_log,
|
|
|
|
ioptions.min_partial_merge_operands,
|
|
|
|
true /* internal key corruption is not ok */);
|
|
|
|
|
|
|
|
CompactionIterator c_iter(iter, internal_comparator.user_comparator(),
|
|
|
|
&merge, kMaxSequenceNumber, &snapshots, 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::IncreaseThreadOperationProperty(
|
|
|
|
ThreadStatus::FLUSH_BYTES_WRITTEN, IOSTATS(bytes_written));
|
|
|
|
IOSTATS_RESET(bytes_written);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// Finish and check for builder errors
|
|
|
|
s = c_iter.status();
|
|
|
|
if (s.ok()) {
|
|
|
|
s = builder->Finish();
|
|
|
|
} else {
|
|
|
|
builder->Abandon();
|
|
|
|
}
|
Add more table properties to EventLogger
Summary:
Example output:
{"time_micros": 1431463794310521, "job": 353, "event": "table_file_creation", "file_number": 387, "file_size": 86937, "table_info": {"data_size": "81801", "index_size": "9751", "filter_size": "0", "raw_key_size": "23448", "raw_average_key_size": "24.000000", "raw_value_size": "990571", "raw_average_value_size": "1013.890481", "num_data_blocks": "245", "num_entries": "977", "filter_policy_name": "", "kDeletedKeys": "0"}}
Also fixed a bug where BuildTable() in recovery was passing Env::IOHigh argument into paranoid_checks_file parameter.
Test Plan: make check + check out the output in the log
Reviewers: sdong, rven, yhchiang
Reviewed By: yhchiang
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D38343
10 years ago
|
|
|
if (s.ok()) {
|
|
|
|
meta->fd.file_size = builder->FileSize();
|
|
|
|
meta->marked_for_compaction = builder->NeedCompact();
|
Add more table properties to EventLogger
Summary:
Example output:
{"time_micros": 1431463794310521, "job": 353, "event": "table_file_creation", "file_number": 387, "file_size": 86937, "table_info": {"data_size": "81801", "index_size": "9751", "filter_size": "0", "raw_key_size": "23448", "raw_average_key_size": "24.000000", "raw_value_size": "990571", "raw_average_value_size": "1013.890481", "num_data_blocks": "245", "num_entries": "977", "filter_policy_name": "", "kDeletedKeys": "0"}}
Also fixed a bug where BuildTable() in recovery was passing Env::IOHigh argument into paranoid_checks_file parameter.
Test Plan: make check + check out the output in the log
Reviewers: sdong, rven, yhchiang
Reviewed By: yhchiang
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D38343
10 years ago
|
|
|
assert(meta->fd.GetFileSize() > 0);
|
|
|
|
if (table_properties) {
|
|
|
|
*table_properties = builder->GetTableProperties();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
delete builder;
|
|
|
|
|
|
|
|
// Finish and check for file errors
|
|
|
|
if (s.ok() && !ioptions.disable_data_sync) {
|
Move rate_limiter, write buffering, most perf context instrumentation and most random kill out of Env
Summary: We want to keep Env a think layer for better portability. Less platform dependent codes should be moved out of Env. In this patch, I create a wrapper of file readers and writers, and put rate limiting, write buffering, as well as most perf context instrumentation and random kill out of Env. It will make it easier to maintain multiple Env in the future.
Test Plan: Run all existing unit tests.
Reviewers: anthony, kradhakrishnan, IslamAbdelRahman, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D42321
9 years ago
|
|
|
StopWatch sw(env, ioptions.statistics, TABLE_SYNC_MICROS);
|
|
|
|
file_writer->Sync(ioptions.use_fsync);
|
|
|
|
}
|
|
|
|
if (s.ok()) {
|
Move rate_limiter, write buffering, most perf context instrumentation and most random kill out of Env
Summary: We want to keep Env a think layer for better portability. Less platform dependent codes should be moved out of Env. In this patch, I create a wrapper of file readers and writers, and put rate limiting, write buffering, as well as most perf context instrumentation and random kill out of Env. It will make it easier to maintain multiple Env in the future.
Test Plan: Run all existing unit tests.
Reviewers: anthony, kradhakrishnan, IslamAbdelRahman, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D42321
9 years ago
|
|
|
s = file_writer->Close();
|
|
|
|
}
|
|
|
|
|
|
|
|
if (s.ok()) {
|
|
|
|
// Verify that the table is usable
|
Measure file read latency histogram per level
Summary: In internal stats, remember read latency histogram, if statistics is enabled. It can be retrieved from DB::GetProperty() with "rocksdb.dbstats" property, if it is enabled.
Test Plan: Manually run db_bench and prints out "rocksdb.dbstats" by hand and make sure it prints out as expected
Reviewers: igor, IslamAbdelRahman, rven, kradhakrishnan, anthony, yhchiang
Reviewed By: yhchiang
Subscribers: MarkCallaghan, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44193
9 years ago
|
|
|
Iterator* it = table_cache->NewIterator(
|
|
|
|
ReadOptions(), env_options, internal_comparator, meta->fd, nullptr,
|
|
|
|
(internal_stats == nullptr) ? nullptr
|
|
|
|
: internal_stats->GetFileReadHist(0),
|
|
|
|
false);
|
|
|
|
s = it->status();
|
|
|
|
if (s.ok() && paranoid_file_checks) {
|
|
|
|
for (it->SeekToFirst(); it->Valid(); it->Next()) {}
|
|
|
|
s = it->status();
|
|
|
|
}
|
|
|
|
|
|
|
|
delete it;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// Check for input iterator errors
|
|
|
|
if (!iter->status().ok()) {
|
|
|
|
s = iter->status();
|
|
|
|
}
|
|
|
|
|
|
|
|
if (s.ok() && meta->fd.GetFileSize() > 0) {
|
|
|
|
// Keep it
|
|
|
|
} else {
|
|
|
|
env->DeleteFile(fname);
|
|
|
|
}
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
|
|
|
} // namespace rocksdb
|