rocksdb/table/sst_file_writer.cc

205 lines
6.3 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.
#include "rocksdb/sst_file_writer.h"
#include <vector>
#include "db/dbformat.h"
#include "rocksdb/table.h"
#include "table/block_based_table_builder.h"
#include "util/file_reader_writer.h"
#include "util/string_util.h"
namespace rocksdb {
const std::string ExternalSstFilePropertyNames::kVersion =
"rocksdb.external_sst_file.version";
// PropertiesCollector used to add properties specific to tables
// generated by SstFileWriter
class SstFileWriter::SstFileWriterPropertiesCollector
: public IntTblPropCollector {
public:
explicit SstFileWriterPropertiesCollector(int32_t version)
: version_(version) {}
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 Status Finish(UserCollectedProperties* properties) override {
std::string version_val;
PutFixed32(&version_val, static_cast<int32_t>(version_));
properties->insert({ExternalSstFilePropertyNames::kVersion, version_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_;
};
class SstFileWriter::SstFileWriterPropertiesCollectorFactory
: public IntTblPropCollectorFactory {
public:
explicit SstFileWriterPropertiesCollectorFactory(int32_t version)
: version_(version) {}
virtual IntTblPropCollector* CreateIntTblPropCollector(
uint32_t column_family_id) override {
return new SstFileWriterPropertiesCollector(version_);
}
virtual const char* Name() const override {
return "SstFileWriterPropertiesCollector";
}
private:
int32_t version_;
};
struct SstFileWriter::Rep {
Rep(const EnvOptions& _env_options, const Options& options,
const Comparator* _user_comparator)
: env_options(_env_options),
ioptions(options),
mutable_cf_options(options, ioptions),
internal_comparator(_user_comparator) {}
std::unique_ptr<WritableFileWriter> file_writer;
std::unique_ptr<TableBuilder> builder;
EnvOptions env_options;
ImmutableCFOptions ioptions;
MutableCFOptions mutable_cf_options;
InternalKeyComparator internal_comparator;
ExternalSstFileInfo file_info;
std::string column_family_name;
Miscellaneous performance improvements Summary: I was investigating performance issues in the SstFileWriter and found all of the following: - The SstFileWriter::Add() function created a local InternalKey every time it was called generating a allocation and free each time. Changed to have an InternalKey member variable that can be reset with the new InternalKey::Set() function. - In SstFileWriter::Add() the smallest_key and largest_key values were assigned the result of a ToString() call, but it is simpler to just assign them directly from the user's key. - The Slice class had no move constructor so each time one was returned from a function a new one had to be allocated, the old data copied to the new, and the old one was freed. I added the move constructor which also required a copy constructor and assignment operator. - The BlockBuilder::CurrentSizeEstimate() function calculates the current estimate size, but was being called 2 or 3 times for each key added. I changed the class to maintain a running estimate (equal to the original calculation) so that the function can return an already calculated value. - The code in BlockBuilder::Add() that calculated the shared bytes between the last key and the new key duplicated what Slice::difference_offset does, so I replaced it with the standard function. - BlockBuilder::Add() had code to copy just the changed portion into the last key value (and asserted that it now matched the new key). It is more efficient just to copy the whole new key over. - Moved this same code up into the 'if (use_delta_encoding_)' since the last key value is only needed when delta encoding is on. - FlushBlockBySizePolicy::BlockAlmostFull calculated a standard deviation value each time it was called, but this information would only change if block_size of block_size_deviation changed, so I created a member variable to hold the value to avoid the calculation each time. - Each PutVarint??() function has a buffer and calls std::string::append(). Two or three calls in a row could share a buffer and a single call to std::string::append(). Some of these will be helpful outside of the SstFileWriter. I'm not 100% the addition of the move constructor is appropriate as I wonder why this wasn't done before - maybe because of compiler compatibility? I tried it on gcc 4.8 and 4.9. Test Plan: The changes should not affect the results so the existing tests should all still work and no new tests were added. The value of the changes was seen by manually testing the SstFileWriter class through MyRocks and adding timing code to identify problem areas. Reviewers: sdong, IslamAbdelRahman Reviewed By: IslamAbdelRahman Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D59607
2016-06-13 18:57:43 +02:00
InternalKey ikey;
};
SstFileWriter::SstFileWriter(const EnvOptions& env_options,
const Options& options,
const Comparator* user_comparator)
: rep_(new Rep(env_options, options, user_comparator)) {}
SstFileWriter::~SstFileWriter() { delete rep_; }
Status SstFileWriter::Open(const std::string& file_path) {
Rep* r = rep_;
Status s;
std::unique_ptr<WritableFile> sst_file;
s = r->ioptions.env->NewWritableFile(file_path, &sst_file, r->env_options);
if (!s.ok()) {
return s;
}
CompressionType compression_type;
if (r->ioptions.bottommost_compression != kDisableCompressionOption) {
compression_type = r->ioptions.bottommost_compression;
} else if (!r->ioptions.compression_per_level.empty()) {
// Use the compression of the last level if we have per level compression
compression_type = *(r->ioptions.compression_per_level.rbegin());
} else {
compression_type = r->mutable_cf_options.compression;
}
std::vector<std::unique_ptr<IntTblPropCollectorFactory>>
int_tbl_prop_collector_factories;
int_tbl_prop_collector_factories.emplace_back(
new SstFileWriterPropertiesCollectorFactory(1 /* version */));
TableBuilderOptions table_builder_options(
r->ioptions, r->internal_comparator, &int_tbl_prop_collector_factories,
compression_type, r->ioptions.compression_opts,
nullptr /* compression_dict */, false /* skip_filters */,
r->column_family_name);
r->file_writer.reset(
new WritableFileWriter(std::move(sst_file), r->env_options));
r->builder.reset(r->ioptions.table_factory->NewTableBuilder(
table_builder_options,
TablePropertiesCollectorFactory::Context::kUnknownColumnFamily,
r->file_writer.get()));
r->file_info.file_path = file_path;
r->file_info.file_size = 0;
r->file_info.num_entries = 0;
r->file_info.sequence_number = 0;
r->file_info.version = 1;
return s;
}
Status SstFileWriter::Add(const Slice& user_key, const Slice& value) {
Rep* r = rep_;
if (!r->builder) {
return Status::InvalidArgument("File is not opened");
}
if (r->file_info.num_entries == 0) {
Miscellaneous performance improvements Summary: I was investigating performance issues in the SstFileWriter and found all of the following: - The SstFileWriter::Add() function created a local InternalKey every time it was called generating a allocation and free each time. Changed to have an InternalKey member variable that can be reset with the new InternalKey::Set() function. - In SstFileWriter::Add() the smallest_key and largest_key values were assigned the result of a ToString() call, but it is simpler to just assign them directly from the user's key. - The Slice class had no move constructor so each time one was returned from a function a new one had to be allocated, the old data copied to the new, and the old one was freed. I added the move constructor which also required a copy constructor and assignment operator. - The BlockBuilder::CurrentSizeEstimate() function calculates the current estimate size, but was being called 2 or 3 times for each key added. I changed the class to maintain a running estimate (equal to the original calculation) so that the function can return an already calculated value. - The code in BlockBuilder::Add() that calculated the shared bytes between the last key and the new key duplicated what Slice::difference_offset does, so I replaced it with the standard function. - BlockBuilder::Add() had code to copy just the changed portion into the last key value (and asserted that it now matched the new key). It is more efficient just to copy the whole new key over. - Moved this same code up into the 'if (use_delta_encoding_)' since the last key value is only needed when delta encoding is on. - FlushBlockBySizePolicy::BlockAlmostFull calculated a standard deviation value each time it was called, but this information would only change if block_size of block_size_deviation changed, so I created a member variable to hold the value to avoid the calculation each time. - Each PutVarint??() function has a buffer and calls std::string::append(). Two or three calls in a row could share a buffer and a single call to std::string::append(). Some of these will be helpful outside of the SstFileWriter. I'm not 100% the addition of the move constructor is appropriate as I wonder why this wasn't done before - maybe because of compiler compatibility? I tried it on gcc 4.8 and 4.9. Test Plan: The changes should not affect the results so the existing tests should all still work and no new tests were added. The value of the changes was seen by manually testing the SstFileWriter class through MyRocks and adding timing code to identify problem areas. Reviewers: sdong, IslamAbdelRahman Reviewed By: IslamAbdelRahman Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D59607
2016-06-13 18:57:43 +02:00
r->file_info.smallest_key.assign(user_key.data(), user_key.size());
} else {
if (r->internal_comparator.user_comparator()->Compare(
user_key, r->file_info.largest_key) <= 0) {
// Make sure that keys are added in order
return Status::InvalidArgument("Keys must be added in order");
}
}
// update file info
r->file_info.num_entries++;
Miscellaneous performance improvements Summary: I was investigating performance issues in the SstFileWriter and found all of the following: - The SstFileWriter::Add() function created a local InternalKey every time it was called generating a allocation and free each time. Changed to have an InternalKey member variable that can be reset with the new InternalKey::Set() function. - In SstFileWriter::Add() the smallest_key and largest_key values were assigned the result of a ToString() call, but it is simpler to just assign them directly from the user's key. - The Slice class had no move constructor so each time one was returned from a function a new one had to be allocated, the old data copied to the new, and the old one was freed. I added the move constructor which also required a copy constructor and assignment operator. - The BlockBuilder::CurrentSizeEstimate() function calculates the current estimate size, but was being called 2 or 3 times for each key added. I changed the class to maintain a running estimate (equal to the original calculation) so that the function can return an already calculated value. - The code in BlockBuilder::Add() that calculated the shared bytes between the last key and the new key duplicated what Slice::difference_offset does, so I replaced it with the standard function. - BlockBuilder::Add() had code to copy just the changed portion into the last key value (and asserted that it now matched the new key). It is more efficient just to copy the whole new key over. - Moved this same code up into the 'if (use_delta_encoding_)' since the last key value is only needed when delta encoding is on. - FlushBlockBySizePolicy::BlockAlmostFull calculated a standard deviation value each time it was called, but this information would only change if block_size of block_size_deviation changed, so I created a member variable to hold the value to avoid the calculation each time. - Each PutVarint??() function has a buffer and calls std::string::append(). Two or three calls in a row could share a buffer and a single call to std::string::append(). Some of these will be helpful outside of the SstFileWriter. I'm not 100% the addition of the move constructor is appropriate as I wonder why this wasn't done before - maybe because of compiler compatibility? I tried it on gcc 4.8 and 4.9. Test Plan: The changes should not affect the results so the existing tests should all still work and no new tests were added. The value of the changes was seen by manually testing the SstFileWriter class through MyRocks and adding timing code to identify problem areas. Reviewers: sdong, IslamAbdelRahman Reviewed By: IslamAbdelRahman Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D59607
2016-06-13 18:57:43 +02:00
r->file_info.largest_key.assign(user_key.data(), user_key.size());
r->file_info.file_size = r->builder->FileSize();
Miscellaneous performance improvements Summary: I was investigating performance issues in the SstFileWriter and found all of the following: - The SstFileWriter::Add() function created a local InternalKey every time it was called generating a allocation and free each time. Changed to have an InternalKey member variable that can be reset with the new InternalKey::Set() function. - In SstFileWriter::Add() the smallest_key and largest_key values were assigned the result of a ToString() call, but it is simpler to just assign them directly from the user's key. - The Slice class had no move constructor so each time one was returned from a function a new one had to be allocated, the old data copied to the new, and the old one was freed. I added the move constructor which also required a copy constructor and assignment operator. - The BlockBuilder::CurrentSizeEstimate() function calculates the current estimate size, but was being called 2 or 3 times for each key added. I changed the class to maintain a running estimate (equal to the original calculation) so that the function can return an already calculated value. - The code in BlockBuilder::Add() that calculated the shared bytes between the last key and the new key duplicated what Slice::difference_offset does, so I replaced it with the standard function. - BlockBuilder::Add() had code to copy just the changed portion into the last key value (and asserted that it now matched the new key). It is more efficient just to copy the whole new key over. - Moved this same code up into the 'if (use_delta_encoding_)' since the last key value is only needed when delta encoding is on. - FlushBlockBySizePolicy::BlockAlmostFull calculated a standard deviation value each time it was called, but this information would only change if block_size of block_size_deviation changed, so I created a member variable to hold the value to avoid the calculation each time. - Each PutVarint??() function has a buffer and calls std::string::append(). Two or three calls in a row could share a buffer and a single call to std::string::append(). Some of these will be helpful outside of the SstFileWriter. I'm not 100% the addition of the move constructor is appropriate as I wonder why this wasn't done before - maybe because of compiler compatibility? I tried it on gcc 4.8 and 4.9. Test Plan: The changes should not affect the results so the existing tests should all still work and no new tests were added. The value of the changes was seen by manually testing the SstFileWriter class through MyRocks and adding timing code to identify problem areas. Reviewers: sdong, IslamAbdelRahman Reviewed By: IslamAbdelRahman Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D59607
2016-06-13 18:57:43 +02:00
r->ikey.Set(user_key, 0 /* Sequence Number */,
ValueType::kTypeValue /* Put */);
r->builder->Add(r->ikey.Encode(), value);
return Status::OK();
}
Status SstFileWriter::Finish(ExternalSstFileInfo* file_info) {
Rep* r = rep_;
if (!r->builder) {
return Status::InvalidArgument("File is not opened");
}
if (r->file_info.num_entries == 0) {
return Status::InvalidArgument("Cannot create sst file with no entries");
}
Status s = r->builder->Finish();
if (s.ok()) {
if (!r->ioptions.disable_data_sync) {
s = r->file_writer->Sync(r->ioptions.use_fsync);
}
if (s.ok()) {
s = r->file_writer->Close();
}
} else {
r->builder->Abandon();
}
if (!s.ok()) {
r->ioptions.env->DeleteFile(r->file_info.file_path);
}
if (s.ok() && file_info != nullptr) {
r->file_info.file_size = r->builder->FileSize();
*file_info = r->file_info;
}
r->builder.reset();
return s;
}
} // namespace rocksdb