rocksdb/table/sst_file_writer_collectors.h
Shobhit Dayal b45b1cde3e Feature for sampling and reporting compressibility (#4842)
Summary:
This is a feature to sample data-block compressibility and and report them as stats. 1 in N (tunable) blocks is sampled for compressibility using two algorithms:
1. lz4 or snappy for fast compression
2. zstd or zlib for slow but higher compression.

The stats are reported to the caller as raw-bytes and compressed-bytes. The block continues to be compressed for storage using the specified CompressionType.

The db_bench_tool how has a command line option for specifying the sampling rate. It's default value is 0 (no sampling). To test the overhead for a certain value, users can compare the performance of db_bench_tool, varying the sampling rate. It is unlikely to have a noticeable impact for high values like 20.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4842

Differential Revision: D13629011

Pulled By: shobhitdayal

fbshipit-source-id: 14ca668bcab6499b2a1734edf848eb62a4f4fafa
2019-03-18 12:15:34 -07:00

93 lines
3.0 KiB
C++

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// 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).
#pragma once
#include <string>
#include "rocksdb/types.h"
#include "util/string_util.h"
namespace rocksdb {
// Table Properties that are specific to tables created by SstFileWriter.
struct ExternalSstFilePropertyNames {
// value of this property is a fixed uint32 number.
static const std::string kVersion;
// value of this property is a fixed uint64 number.
static const std::string kGlobalSeqno;
};
// PropertiesCollector used to add properties specific to tables
// generated by SstFileWriter
class SstFileWriterPropertiesCollector : public IntTblPropCollector {
public:
explicit SstFileWriterPropertiesCollector(int32_t version,
SequenceNumber global_seqno)
: version_(version), global_seqno_(global_seqno) {}
virtual Status InternalAdd(const Slice& /*key*/, const Slice& /*value*/,
uint64_t /*file_size*/) override {
// Intentionally left blank. Have no interest in collecting stats for
// individual key/value pairs.
return Status::OK();
}
virtual void BlockAdd(uint64_t /* blockRawBytes */,
uint64_t /* blockCompressedBytesFast */,
uint64_t /* blockCompressedBytesSlow */) override {
// Intentionally left blank. No interest in collecting stats for
// blocks.
return;
}
virtual Status Finish(UserCollectedProperties* properties) override {
// File version
std::string version_val;
PutFixed32(&version_val, static_cast<uint32_t>(version_));
properties->insert({ExternalSstFilePropertyNames::kVersion, version_val});
// Global Sequence number
std::string seqno_val;
PutFixed64(&seqno_val, static_cast<uint64_t>(global_seqno_));
properties->insert({ExternalSstFilePropertyNames::kGlobalSeqno, seqno_val});
return Status::OK();
}
virtual const char* Name() const override {
return "SstFileWriterPropertiesCollector";
}
virtual UserCollectedProperties GetReadableProperties() const override {
return {{ExternalSstFilePropertyNames::kVersion, ToString(version_)}};
}
private:
int32_t version_;
SequenceNumber global_seqno_;
};
class SstFileWriterPropertiesCollectorFactory
: public IntTblPropCollectorFactory {
public:
explicit SstFileWriterPropertiesCollectorFactory(int32_t version,
SequenceNumber global_seqno)
: version_(version), global_seqno_(global_seqno) {}
virtual IntTblPropCollector* CreateIntTblPropCollector(
uint32_t /*column_family_id*/) override {
return new SstFileWriterPropertiesCollector(version_, global_seqno_);
}
virtual const char* Name() const override {
return "SstFileWriterPropertiesCollector";
}
private:
int32_t version_;
SequenceNumber global_seqno_;
};
} // namespace rocksdb