2016-02-10 00:12:00 +01:00
|
|
|
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
2017-07-16 01:03:42 +02:00
|
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
|
|
// (found in the LICENSE.Apache file in the root directory).
|
2014-12-23 22:24:07 +01:00
|
|
|
//
|
|
|
|
// Copyright (c) 2012 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.
|
|
|
|
|
2015-07-20 20:24:54 +02:00
|
|
|
#ifndef ROCKSDB_LITE
|
|
|
|
|
2014-12-23 22:24:07 +01:00
|
|
|
#include <stdint.h>
|
|
|
|
#include "rocksdb/sst_dump_tool.h"
|
|
|
|
|
|
|
|
#include "rocksdb/filter_policy.h"
|
|
|
|
#include "table/block_based_table_factory.h"
|
|
|
|
#include "table/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
2015-07-18 01:16:11 +02:00
|
|
|
#include "util/file_reader_writer.h"
|
2014-12-23 22:24:07 +01:00
|
|
|
#include "util/testharness.h"
|
|
|
|
#include "util/testutil.h"
|
|
|
|
|
|
|
|
namespace rocksdb {
|
|
|
|
|
|
|
|
const uint32_t optLength = 100;
|
|
|
|
|
|
|
|
namespace {
|
|
|
|
static std::string MakeKey(int i) {
|
|
|
|
char buf[100];
|
|
|
|
snprintf(buf, sizeof(buf), "k_%04d", i);
|
|
|
|
InternalKey key(std::string(buf), 0, ValueType::kTypeValue);
|
|
|
|
return key.Encode().ToString();
|
|
|
|
}
|
|
|
|
|
|
|
|
static std::string MakeValue(int i) {
|
|
|
|
char buf[100];
|
|
|
|
snprintf(buf, sizeof(buf), "v_%04d", i);
|
|
|
|
InternalKey key(std::string(buf), 0, ValueType::kTypeValue);
|
|
|
|
return key.Encode().ToString();
|
|
|
|
}
|
|
|
|
|
2019-01-03 20:11:09 +01:00
|
|
|
void createSST(const Options& opts, const std::string& file_name) {
|
|
|
|
Env* env = opts.env;
|
|
|
|
EnvOptions env_options(opts);
|
2014-12-23 22:24:07 +01:00
|
|
|
ReadOptions read_options;
|
|
|
|
const ImmutableCFOptions imoptions(opts);
|
2018-05-21 23:33:55 +02:00
|
|
|
const MutableCFOptions moptions(opts);
|
2014-12-23 22:24:07 +01:00
|
|
|
rocksdb::InternalKeyComparator ikc(opts.comparator);
|
2018-11-09 20:17:34 +01:00
|
|
|
std::unique_ptr<TableBuilder> tb;
|
2014-12-23 22:24:07 +01:00
|
|
|
|
2019-01-03 20:11:09 +01:00
|
|
|
std::unique_ptr<WritableFile> file;
|
2018-08-09 23:21:35 +02:00
|
|
|
ASSERT_OK(env->NewWritableFile(file_name, &file, env_options));
|
|
|
|
|
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
2015-04-06 19:04:30 +02:00
|
|
|
std::vector<std::unique_ptr<IntTblPropCollectorFactory> >
|
|
|
|
int_tbl_prop_collector_factories;
|
2018-08-09 23:21:35 +02:00
|
|
|
std::unique_ptr<WritableFileWriter> file_writer(
|
2018-08-23 19:04:10 +02:00
|
|
|
new WritableFileWriter(std::move(file), file_name, EnvOptions()));
|
2016-04-07 08:10:32 +02:00
|
|
|
std::string column_family_name;
|
2016-09-18 07:30:43 +02:00
|
|
|
int unknown_level = -1;
|
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
2015-04-06 19:04:30 +02:00
|
|
|
tb.reset(opts.table_factory->NewTableBuilder(
|
2018-05-21 23:33:55 +02:00
|
|
|
TableBuilderOptions(
|
|
|
|
imoptions, moptions, ikc, &int_tbl_prop_collector_factories,
|
|
|
|
CompressionType::kNoCompression, CompressionOptions(),
|
Reduce scope of compression dictionary to single SST (#4952)
Summary:
Our previous approach was to train one compression dictionary per compaction, using the first output SST to train a dictionary, and then applying it on subsequent SSTs in the same compaction. While this was great for minimizing CPU/memory/I/O overhead, it did not achieve good compression ratios in practice. In our most promising potential use case, moderate reductions in a dictionary's scope make a major difference on compression ratio.
So, this PR changes compression dictionary to be scoped per-SST. It accepts the tradeoff during table building to use more memory and CPU. Important changes include:
- The `BlockBasedTableBuilder` has a new state when dictionary compression is in-use: `kBuffered`. In that state it accumulates uncompressed data in-memory whenever `Add` is called.
- After accumulating target file size bytes or calling `BlockBasedTableBuilder::Finish`, a `BlockBasedTableBuilder` moves to the `kUnbuffered` state. The transition (`EnterUnbuffered()`) involves sampling the buffered data, training a dictionary, and compressing/writing out all buffered data. In the `kUnbuffered` state, a `BlockBasedTableBuilder` behaves the same as before -- blocks are compressed/written out as soon as they fill up.
- Samples are now whole uncompressed data blocks, except the final sample may be a partial data block so we don't breach the user's configured `max_dict_bytes` or `zstd_max_train_bytes`. The dictionary trainer is supposed to work better when we pass it real units of compression. Previously we were passing 64-byte KV samples which was not realistic.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4952
Differential Revision: D13967980
Pulled By: ajkr
fbshipit-source-id: 82bea6f7537e1529c7a1a4cdee84585f5949300f
2019-02-12 04:42:25 +01:00
|
|
|
false /* skip_filters */, column_family_name, unknown_level),
|
2015-10-09 01:57:35 +02:00
|
|
|
TablePropertiesCollectorFactory::Context::kUnknownColumnFamily,
|
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
2015-07-18 01:16:11 +02:00
|
|
|
file_writer.get()));
|
2014-12-23 22:24:07 +01:00
|
|
|
|
|
|
|
// Populate slightly more than 1K keys
|
|
|
|
uint32_t num_keys = 1024;
|
|
|
|
for (uint32_t i = 0; i < num_keys; i++) {
|
|
|
|
tb->Add(MakeKey(i), MakeValue(i));
|
|
|
|
}
|
|
|
|
tb->Finish();
|
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
2015-07-18 01:16:11 +02:00
|
|
|
file_writer->Close();
|
2014-12-23 22:24:07 +01:00
|
|
|
}
|
|
|
|
|
2019-01-03 20:11:09 +01:00
|
|
|
void cleanup(const Options& opts, const std::string& file_name) {
|
|
|
|
Env* env = opts.env;
|
2014-12-23 22:24:07 +01:00
|
|
|
env->DeleteFile(file_name);
|
|
|
|
std::string outfile_name = file_name.substr(0, file_name.length() - 4);
|
|
|
|
outfile_name.append("_dump.txt");
|
|
|
|
env->DeleteFile(outfile_name);
|
|
|
|
}
|
|
|
|
} // namespace
|
|
|
|
|
|
|
|
// Test for sst dump tool "raw" mode
|
2015-03-17 22:08:00 +01:00
|
|
|
class SSTDumpToolTest : public testing::Test {
|
2018-08-09 23:21:35 +02:00
|
|
|
std::string testDir_;
|
2018-08-23 19:04:10 +02:00
|
|
|
|
|
|
|
public:
|
|
|
|
SSTDumpToolTest() { testDir_ = test::TmpDir(); }
|
2014-12-23 22:24:07 +01:00
|
|
|
|
2019-02-14 22:52:47 +01:00
|
|
|
~SSTDumpToolTest() override {}
|
2018-08-09 23:21:35 +02:00
|
|
|
|
|
|
|
std::string MakeFilePath(const std::string& file_name) const {
|
|
|
|
std::string path(testDir_);
|
|
|
|
path.append("/").append(file_name);
|
|
|
|
return path;
|
|
|
|
}
|
|
|
|
|
2018-08-23 19:04:10 +02:00
|
|
|
template <std::size_t N>
|
2018-08-09 23:21:35 +02:00
|
|
|
void PopulateCommandArgs(const std::string& file_path, const char* command,
|
2018-08-23 19:04:10 +02:00
|
|
|
char* (&usage)[N]) const {
|
2018-08-10 04:37:47 +02:00
|
|
|
for (int i = 0; i < static_cast<int>(N); ++i) {
|
2018-08-09 23:21:35 +02:00
|
|
|
usage[i] = new char[optLength];
|
|
|
|
}
|
|
|
|
snprintf(usage[0], optLength, "./sst_dump");
|
|
|
|
snprintf(usage[1], optLength, "%s", command);
|
|
|
|
snprintf(usage[2], optLength, "--file=%s", file_path.c_str());
|
|
|
|
}
|
2014-12-23 22:24:07 +01:00
|
|
|
};
|
|
|
|
|
2015-03-17 22:08:00 +01:00
|
|
|
TEST_F(SSTDumpToolTest, EmptyFilter) {
|
2019-01-03 20:11:09 +01:00
|
|
|
Options opts;
|
2018-08-09 23:21:35 +02:00
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
2019-01-03 20:11:09 +01:00
|
|
|
createSST(opts, file_path);
|
2014-12-23 22:24:07 +01:00
|
|
|
|
|
|
|
char* usage[3];
|
2018-08-09 23:21:35 +02:00
|
|
|
PopulateCommandArgs(file_path, "--command=raw", usage);
|
2014-12-23 22:24:07 +01:00
|
|
|
|
|
|
|
rocksdb::SSTDumpTool tool;
|
2019-01-03 20:11:09 +01:00
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
2014-12-23 22:24:07 +01:00
|
|
|
|
2019-01-03 20:11:09 +01:00
|
|
|
cleanup(opts, file_path);
|
2014-12-23 22:24:07 +01:00
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-03-17 22:08:00 +01:00
|
|
|
TEST_F(SSTDumpToolTest, FilterBlock) {
|
2019-01-03 20:11:09 +01:00
|
|
|
Options opts;
|
|
|
|
BlockBasedTableOptions table_opts;
|
|
|
|
table_opts.filter_policy.reset(rocksdb::NewBloomFilterPolicy(10, true));
|
|
|
|
opts.table_factory.reset(new BlockBasedTableFactory(table_opts));
|
2018-08-09 23:21:35 +02:00
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
2019-01-03 20:11:09 +01:00
|
|
|
createSST(opts, file_path);
|
2014-12-23 22:24:07 +01:00
|
|
|
|
|
|
|
char* usage[3];
|
2018-08-09 23:21:35 +02:00
|
|
|
PopulateCommandArgs(file_path, "--command=raw", usage);
|
2014-12-23 22:24:07 +01:00
|
|
|
|
|
|
|
rocksdb::SSTDumpTool tool;
|
2019-01-03 20:11:09 +01:00
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
2014-12-23 22:24:07 +01:00
|
|
|
|
2019-01-03 20:11:09 +01:00
|
|
|
cleanup(opts, file_path);
|
2014-12-23 22:24:07 +01:00
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-03-17 22:08:00 +01:00
|
|
|
TEST_F(SSTDumpToolTest, FullFilterBlock) {
|
2019-01-03 20:11:09 +01:00
|
|
|
Options opts;
|
|
|
|
BlockBasedTableOptions table_opts;
|
|
|
|
table_opts.filter_policy.reset(rocksdb::NewBloomFilterPolicy(10, false));
|
|
|
|
opts.table_factory.reset(new BlockBasedTableFactory(table_opts));
|
2018-08-09 23:21:35 +02:00
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
2019-01-03 20:11:09 +01:00
|
|
|
createSST(opts, file_path);
|
2014-12-23 22:24:07 +01:00
|
|
|
|
|
|
|
char* usage[3];
|
2018-08-09 23:21:35 +02:00
|
|
|
PopulateCommandArgs(file_path, "--command=raw", usage);
|
2014-12-23 22:24:07 +01:00
|
|
|
|
|
|
|
rocksdb::SSTDumpTool tool;
|
2019-01-03 20:11:09 +01:00
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
2014-12-23 22:24:07 +01:00
|
|
|
|
2019-01-03 20:11:09 +01:00
|
|
|
cleanup(opts, file_path);
|
2014-12-23 22:24:07 +01:00
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
2015-02-26 01:34:26 +01:00
|
|
|
|
2015-03-17 22:08:00 +01:00
|
|
|
TEST_F(SSTDumpToolTest, GetProperties) {
|
2019-01-03 20:11:09 +01:00
|
|
|
Options opts;
|
|
|
|
BlockBasedTableOptions table_opts;
|
|
|
|
table_opts.filter_policy.reset(rocksdb::NewBloomFilterPolicy(10, false));
|
|
|
|
opts.table_factory.reset(new BlockBasedTableFactory(table_opts));
|
2018-08-09 23:21:35 +02:00
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
2019-01-03 20:11:09 +01:00
|
|
|
createSST(opts, file_path);
|
2015-02-26 01:34:26 +01:00
|
|
|
|
|
|
|
char* usage[3];
|
2018-08-09 23:21:35 +02:00
|
|
|
PopulateCommandArgs(file_path, "--show_properties", usage);
|
2015-02-26 01:34:26 +01:00
|
|
|
|
|
|
|
rocksdb::SSTDumpTool tool;
|
2019-01-03 20:11:09 +01:00
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
2015-02-26 01:34:26 +01:00
|
|
|
|
2019-01-03 20:11:09 +01:00
|
|
|
cleanup(opts, file_path);
|
2015-02-26 01:34:26 +01:00
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
2015-07-24 02:05:33 +02:00
|
|
|
|
|
|
|
TEST_F(SSTDumpToolTest, CompressedSizes) {
|
2019-01-03 20:11:09 +01:00
|
|
|
Options opts;
|
|
|
|
BlockBasedTableOptions table_opts;
|
|
|
|
table_opts.filter_policy.reset(rocksdb::NewBloomFilterPolicy(10, false));
|
|
|
|
opts.table_factory.reset(new BlockBasedTableFactory(table_opts));
|
2018-08-09 23:21:35 +02:00
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
2019-01-03 20:11:09 +01:00
|
|
|
createSST(opts, file_path);
|
2015-07-24 02:05:33 +02:00
|
|
|
|
|
|
|
char* usage[3];
|
2018-08-09 23:21:35 +02:00
|
|
|
PopulateCommandArgs(file_path, "--command=recompress", usage);
|
2015-07-24 02:05:33 +02:00
|
|
|
|
|
|
|
rocksdb::SSTDumpTool tool;
|
2019-01-03 20:11:09 +01:00
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
2015-07-24 02:05:33 +02:00
|
|
|
|
2019-01-03 20:11:09 +01:00
|
|
|
cleanup(opts, file_path);
|
2015-07-24 02:05:33 +02:00
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
2019-01-03 20:11:09 +01:00
|
|
|
|
|
|
|
TEST_F(SSTDumpToolTest, MemEnv) {
|
|
|
|
std::unique_ptr<Env> env(NewMemEnv(Env::Default()));
|
|
|
|
Options opts;
|
|
|
|
opts.env = env.get();
|
|
|
|
std::string file_path = MakeFilePath("rocksdb_sst_test.sst");
|
|
|
|
createSST(opts, file_path);
|
|
|
|
|
|
|
|
char* usage[3];
|
|
|
|
PopulateCommandArgs(file_path, "--command=verify_checksum", usage);
|
|
|
|
|
|
|
|
rocksdb::SSTDumpTool tool;
|
|
|
|
ASSERT_TRUE(!tool.Run(3, usage, opts));
|
|
|
|
|
|
|
|
cleanup(opts, file_path);
|
|
|
|
for (int i = 0; i < 3; i++) {
|
|
|
|
delete[] usage[i];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-12-23 22:24:07 +01:00
|
|
|
} // namespace rocksdb
|
|
|
|
|
2015-03-17 22:08:00 +01:00
|
|
|
int main(int argc, char** argv) {
|
|
|
|
::testing::InitGoogleTest(&argc, argv);
|
|
|
|
return RUN_ALL_TESTS();
|
|
|
|
}
|
2015-07-20 20:24:54 +02:00
|
|
|
|
|
|
|
#else
|
|
|
|
#include <stdio.h>
|
|
|
|
|
2018-04-16 02:19:57 +02:00
|
|
|
int main(int /*argc*/, char** /*argv*/) {
|
2015-07-20 20:24:54 +02:00
|
|
|
fprintf(stderr, "SKIPPED as SSTDumpTool is not supported in ROCKSDB_LITE\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif // !ROCKSDB_LITE return RUN_ALL_TESTS();
|