rocksdb/table/block_based_table_factory.cc
Sameet Agarwal e7c434c364 Add columnfamily option optimize_filters_for_hits to optimize for key hits only
Summary:
    Summary:
    Added a new option to ColumnFamllyOptions  - optimize_filters_for_hits. This option can be used in the case where most
    accesses to the store are key hits and we dont need to optimize performance for key misses.
    This is useful when you have a very large database and most of your lookups succeed.  The option allows the store to
     not store and use filters in the last level (the largest level which contains data). These filters can take a large amount of
     space for large databases (in memory and on-disk). For the last level, these filters are only useful for key misses and not
     for key hits. If we are not optimizing for key misses, we can choose to not store these filters for that level.

    This option is only provided for BlockBasedTable. We skip the filters when we are compacting

Test Plan:
1. Modified db_test toalso run tests with an additonal option (skip_filters_on_last_level)
 2. Added another unit test to db_test which specifically tests that filters are being skipped

Reviewers: rven, igor, sdong

Reviewed By: sdong

Subscribers: lgalanis, yoshinorim, MarkCallaghan, rven, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D33717
2015-02-26 16:25:56 -08:00

171 lines
6.6 KiB
C++

// 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 "table/block_based_table_factory.h"
#include <memory>
#include <string>
#include <stdint.h>
#include "port/port.h"
#include "rocksdb/flush_block_policy.h"
#include "rocksdb/cache.h"
#include "table/block_based_table_builder.h"
#include "table/block_based_table_reader.h"
#include "table/format.h"
namespace rocksdb {
BlockBasedTableFactory::BlockBasedTableFactory(
const BlockBasedTableOptions& table_options)
: table_options_(table_options) {
if (table_options_.flush_block_policy_factory == nullptr) {
table_options_.flush_block_policy_factory.reset(
new FlushBlockBySizePolicyFactory());
}
if (table_options_.no_block_cache) {
table_options_.block_cache.reset();
} else if (table_options_.block_cache == nullptr) {
table_options_.block_cache = NewLRUCache(8 << 20);
}
if (table_options_.block_size_deviation < 0 ||
table_options_.block_size_deviation > 100) {
table_options_.block_size_deviation = 0;
}
}
Status BlockBasedTableFactory::NewTableReader(
const ImmutableCFOptions& ioptions, const EnvOptions& soptions,
const InternalKeyComparator& internal_comparator,
unique_ptr<RandomAccessFile>&& file, uint64_t file_size,
unique_ptr<TableReader>* table_reader, const bool prefetch_enabled) const {
return BlockBasedTable::Open(ioptions, soptions, table_options_,
internal_comparator, std::move(file), file_size,
table_reader, prefetch_enabled);
}
TableBuilder* BlockBasedTableFactory::NewTableBuilder(
const ImmutableCFOptions& ioptions,
const InternalKeyComparator& internal_comparator, WritableFile* file,
const CompressionType compression_type,
const CompressionOptions& compression_opts, const bool skip_filters) const {
auto table_builder = new BlockBasedTableBuilder(
ioptions, table_options_, internal_comparator, file, compression_type,
compression_opts, skip_filters);
return table_builder;
}
Status BlockBasedTableFactory::SanitizeOptions(
const DBOptions& db_opts,
const ColumnFamilyOptions& cf_opts) const {
if (table_options_.index_type == BlockBasedTableOptions::kHashSearch &&
cf_opts.prefix_extractor == nullptr) {
return Status::InvalidArgument("Hash index is specified for block-based "
"table, but prefix_extractor is not given");
}
if (table_options_.cache_index_and_filter_blocks &&
table_options_.no_block_cache) {
return Status::InvalidArgument("Enable cache_index_and_filter_blocks, "
", but block cache is disabled");
}
if (!BlockBasedTableSupportedVersion(table_options_.format_version)) {
return Status::InvalidArgument(
"Unsupported BlockBasedTable format_version. Please check "
"include/rocksdb/table.h for more info");
}
return Status::OK();
}
std::string BlockBasedTableFactory::GetPrintableTableOptions() const {
std::string ret;
ret.reserve(20000);
const int kBufferSize = 200;
char buffer[kBufferSize];
snprintf(buffer, kBufferSize, " flush_block_policy_factory: %s (%p)\n",
table_options_.flush_block_policy_factory->Name(),
table_options_.flush_block_policy_factory.get());
ret.append(buffer);
snprintf(buffer, kBufferSize, " cache_index_and_filter_blocks: %d\n",
table_options_.cache_index_and_filter_blocks);
ret.append(buffer);
snprintf(buffer, kBufferSize, " index_type: %d\n",
table_options_.index_type);
ret.append(buffer);
snprintf(buffer, kBufferSize, " hash_index_allow_collision: %d\n",
table_options_.hash_index_allow_collision);
ret.append(buffer);
snprintf(buffer, kBufferSize, " checksum: %d\n",
table_options_.checksum);
ret.append(buffer);
snprintf(buffer, kBufferSize, " no_block_cache: %d\n",
table_options_.no_block_cache);
ret.append(buffer);
snprintf(buffer, kBufferSize, " block_cache: %p\n",
table_options_.block_cache.get());
ret.append(buffer);
if (table_options_.block_cache) {
snprintf(buffer, kBufferSize, " block_cache_size: %zd\n",
table_options_.block_cache->GetCapacity());
ret.append(buffer);
}
snprintf(buffer, kBufferSize, " block_cache_compressed: %p\n",
table_options_.block_cache_compressed.get());
ret.append(buffer);
if (table_options_.block_cache_compressed) {
snprintf(buffer, kBufferSize, " block_cache_compressed_size: %zd\n",
table_options_.block_cache_compressed->GetCapacity());
ret.append(buffer);
}
snprintf(buffer, kBufferSize, " block_size: %zd\n",
table_options_.block_size);
ret.append(buffer);
snprintf(buffer, kBufferSize, " block_size_deviation: %d\n",
table_options_.block_size_deviation);
ret.append(buffer);
snprintf(buffer, kBufferSize, " block_restart_interval: %d\n",
table_options_.block_restart_interval);
ret.append(buffer);
snprintf(buffer, kBufferSize, " filter_policy: %s\n",
table_options_.filter_policy == nullptr ?
"nullptr" : table_options_.filter_policy->Name());
ret.append(buffer);
snprintf(buffer, kBufferSize, " whole_key_filtering: %d\n",
table_options_.whole_key_filtering);
snprintf(buffer, kBufferSize, " format_version: %d\n",
table_options_.format_version);
ret.append(buffer);
return ret;
}
const BlockBasedTableOptions& BlockBasedTableFactory::GetTableOptions() const {
return table_options_;
}
TableFactory* NewBlockBasedTableFactory(
const BlockBasedTableOptions& table_options) {
return new BlockBasedTableFactory(table_options);
}
const std::string BlockBasedTablePropertyNames::kIndexType =
"rocksdb.block.based.table.index.type";
const std::string BlockBasedTablePropertyNames::kWholeKeyFiltering =
"rocksdb.block.based.table.whole.key.filtering";
const std::string BlockBasedTablePropertyNames::kPrefixFiltering =
"rocksdb.block.based.table.prefix.filtering";
const std::string kHashIndexPrefixesBlock = "rocksdb.hashindex.prefixes";
const std::string kHashIndexPrefixesMetadataBlock =
"rocksdb.hashindex.metadata";
const std::string kPropTrue = "1";
const std::string kPropFalse = "0";
} // namespace rocksdb