caf0f53a74
Summary: Given that index value is a BlockHandle, which is basically an <offset, size> pair we can apply delta encoding on the values. The first value at each index restart interval encoded the full BlockHandle but the rest encode only the size. Refer to IndexBlockIter::DecodeCurrentValue for the detail of the encoding. This reduces the index size which helps using the block cache more efficiently. The feature is enabled with using format_version 4. The feature comes with a bit of cpu overhead which should be paid back by the higher cache hits due to smaller index block size. Results with sysbench read-only using 4k blocks and using 16 index restart interval: Format 2: 19585 rocksdb read-only range=100 Format 3: 19569 rocksdb read-only range=100 Format 4: 19352 rocksdb read-only range=100 Pull Request resolved: https://github.com/facebook/rocksdb/pull/3983 Differential Revision: D8361343 Pulled By: maysamyabandeh fbshipit-source-id: f882ee082322acac32b0072e2bdbb0b5f854e651
251 lines
9.5 KiB
C++
251 lines
9.5 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).
|
|
|
|
#include "rocksdb/table_properties.h"
|
|
#include "port/port.h"
|
|
#include "rocksdb/env.h"
|
|
#include "rocksdb/iterator.h"
|
|
#include "table/block.h"
|
|
#include "table/internal_iterator.h"
|
|
#include "table/table_properties_internal.h"
|
|
#include "util/string_util.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
const uint32_t TablePropertiesCollectorFactory::Context::kUnknownColumnFamily =
|
|
port::kMaxInt32;
|
|
|
|
namespace {
|
|
void AppendProperty(
|
|
std::string& props,
|
|
const std::string& key,
|
|
const std::string& value,
|
|
const std::string& prop_delim,
|
|
const std::string& kv_delim) {
|
|
props.append(key);
|
|
props.append(kv_delim);
|
|
props.append(value);
|
|
props.append(prop_delim);
|
|
}
|
|
|
|
template <class TValue>
|
|
void AppendProperty(
|
|
std::string& props,
|
|
const std::string& key,
|
|
const TValue& value,
|
|
const std::string& prop_delim,
|
|
const std::string& kv_delim) {
|
|
AppendProperty(
|
|
props, key, ToString(value), prop_delim, kv_delim
|
|
);
|
|
}
|
|
|
|
// Seek to the specified meta block.
|
|
// Return true if it successfully seeks to that block.
|
|
Status SeekToMetaBlock(InternalIterator* meta_iter,
|
|
const std::string& block_name, bool* is_found,
|
|
BlockHandle* block_handle = nullptr) {
|
|
if (block_handle != nullptr) {
|
|
*block_handle = BlockHandle::NullBlockHandle();
|
|
}
|
|
*is_found = true;
|
|
meta_iter->Seek(block_name);
|
|
if (meta_iter->status().ok()) {
|
|
if (meta_iter->Valid() && meta_iter->key() == block_name) {
|
|
*is_found = true;
|
|
if (block_handle) {
|
|
Slice v = meta_iter->value();
|
|
return block_handle->DecodeFrom(&v);
|
|
}
|
|
} else {
|
|
*is_found = false;
|
|
return Status::OK();
|
|
}
|
|
}
|
|
return meta_iter->status();
|
|
}
|
|
}
|
|
|
|
std::string TableProperties::ToString(
|
|
const std::string& prop_delim,
|
|
const std::string& kv_delim) const {
|
|
std::string result;
|
|
result.reserve(1024);
|
|
|
|
// Basic Info
|
|
AppendProperty(result, "# data blocks", num_data_blocks, prop_delim,
|
|
kv_delim);
|
|
AppendProperty(result, "# entries", num_entries, prop_delim, kv_delim);
|
|
AppendProperty(result, "# range deletions", num_range_deletions, prop_delim,
|
|
kv_delim);
|
|
|
|
AppendProperty(result, "raw key size", raw_key_size, prop_delim, kv_delim);
|
|
AppendProperty(result, "raw average key size",
|
|
num_entries != 0 ? 1.0 * raw_key_size / num_entries : 0.0,
|
|
prop_delim, kv_delim);
|
|
AppendProperty(result, "raw value size", raw_value_size, prop_delim,
|
|
kv_delim);
|
|
AppendProperty(result, "raw average value size",
|
|
num_entries != 0 ? 1.0 * raw_value_size / num_entries : 0.0,
|
|
prop_delim, kv_delim);
|
|
|
|
AppendProperty(result, "data block size", data_size, prop_delim, kv_delim);
|
|
char index_block_size_str[80];
|
|
snprintf(index_block_size_str, sizeof(index_block_size_str),
|
|
"index block size (user-key? %d, delta-value? %d)",
|
|
static_cast<int>(index_key_is_user_key),
|
|
static_cast<int>(index_value_is_delta_encoded));
|
|
AppendProperty(result, index_block_size_str, index_size, prop_delim,
|
|
kv_delim);
|
|
if (index_partitions != 0) {
|
|
AppendProperty(result, "# index partitions", index_partitions, prop_delim,
|
|
kv_delim);
|
|
AppendProperty(result, "top-level index size", top_level_index_size, prop_delim,
|
|
kv_delim);
|
|
}
|
|
AppendProperty(result, "filter block size", filter_size, prop_delim,
|
|
kv_delim);
|
|
AppendProperty(result, "(estimated) table size",
|
|
data_size + index_size + filter_size, prop_delim, kv_delim);
|
|
|
|
AppendProperty(
|
|
result, "filter policy name",
|
|
filter_policy_name.empty() ? std::string("N/A") : filter_policy_name,
|
|
prop_delim, kv_delim);
|
|
|
|
AppendProperty(result, "prefix extractor name",
|
|
prefix_extractor_name.empty() ? std::string("N/A")
|
|
: prefix_extractor_name,
|
|
prop_delim, kv_delim);
|
|
|
|
AppendProperty(result, "column family ID",
|
|
column_family_id == rocksdb::TablePropertiesCollectorFactory::
|
|
Context::kUnknownColumnFamily
|
|
? std::string("N/A")
|
|
: rocksdb::ToString(column_family_id),
|
|
prop_delim, kv_delim);
|
|
AppendProperty(
|
|
result, "column family name",
|
|
column_family_name.empty() ? std::string("N/A") : column_family_name,
|
|
prop_delim, kv_delim);
|
|
|
|
AppendProperty(result, "comparator name",
|
|
comparator_name.empty() ? std::string("N/A") : comparator_name,
|
|
prop_delim, kv_delim);
|
|
|
|
AppendProperty(
|
|
result, "merge operator name",
|
|
merge_operator_name.empty() ? std::string("N/A") : merge_operator_name,
|
|
prop_delim, kv_delim);
|
|
|
|
AppendProperty(result, "property collectors names",
|
|
property_collectors_names.empty() ? std::string("N/A")
|
|
: property_collectors_names,
|
|
prop_delim, kv_delim);
|
|
|
|
AppendProperty(
|
|
result, "SST file compression algo",
|
|
compression_name.empty() ? std::string("N/A") : compression_name,
|
|
prop_delim, kv_delim);
|
|
|
|
AppendProperty(result, "creation time", creation_time, prop_delim, kv_delim);
|
|
|
|
AppendProperty(result, "time stamp of earliest key", oldest_key_time,
|
|
prop_delim, kv_delim);
|
|
|
|
return result;
|
|
}
|
|
|
|
void TableProperties::Add(const TableProperties& tp) {
|
|
data_size += tp.data_size;
|
|
index_size += tp.index_size;
|
|
index_partitions += tp.index_partitions;
|
|
top_level_index_size += tp.top_level_index_size;
|
|
index_key_is_user_key += tp.index_key_is_user_key;
|
|
index_value_is_delta_encoded += tp.index_value_is_delta_encoded;
|
|
filter_size += tp.filter_size;
|
|
raw_key_size += tp.raw_key_size;
|
|
raw_value_size += tp.raw_value_size;
|
|
num_data_blocks += tp.num_data_blocks;
|
|
num_entries += tp.num_entries;
|
|
num_range_deletions += tp.num_range_deletions;
|
|
}
|
|
|
|
const std::string TablePropertiesNames::kDataSize =
|
|
"rocksdb.data.size";
|
|
const std::string TablePropertiesNames::kIndexSize =
|
|
"rocksdb.index.size";
|
|
const std::string TablePropertiesNames::kIndexPartitions =
|
|
"rocksdb.index.partitions";
|
|
const std::string TablePropertiesNames::kTopLevelIndexSize =
|
|
"rocksdb.top-level.index.size";
|
|
const std::string TablePropertiesNames::kIndexKeyIsUserKey =
|
|
"rocksdb.index.key.is.user.key";
|
|
const std::string TablePropertiesNames::kIndexValueIsDeltaEncoded =
|
|
"rocksdb.index.value.is.delta.encoded";
|
|
const std::string TablePropertiesNames::kFilterSize =
|
|
"rocksdb.filter.size";
|
|
const std::string TablePropertiesNames::kRawKeySize =
|
|
"rocksdb.raw.key.size";
|
|
const std::string TablePropertiesNames::kRawValueSize =
|
|
"rocksdb.raw.value.size";
|
|
const std::string TablePropertiesNames::kNumDataBlocks =
|
|
"rocksdb.num.data.blocks";
|
|
const std::string TablePropertiesNames::kNumEntries =
|
|
"rocksdb.num.entries";
|
|
const std::string TablePropertiesNames::kNumRangeDeletions =
|
|
"rocksdb.num.range-deletions";
|
|
const std::string TablePropertiesNames::kFilterPolicy =
|
|
"rocksdb.filter.policy";
|
|
const std::string TablePropertiesNames::kFormatVersion =
|
|
"rocksdb.format.version";
|
|
const std::string TablePropertiesNames::kFixedKeyLen =
|
|
"rocksdb.fixed.key.length";
|
|
const std::string TablePropertiesNames::kColumnFamilyId =
|
|
"rocksdb.column.family.id";
|
|
const std::string TablePropertiesNames::kColumnFamilyName =
|
|
"rocksdb.column.family.name";
|
|
const std::string TablePropertiesNames::kComparator = "rocksdb.comparator";
|
|
const std::string TablePropertiesNames::kMergeOperator =
|
|
"rocksdb.merge.operator";
|
|
const std::string TablePropertiesNames::kPrefixExtractorName =
|
|
"rocksdb.prefix.extractor.name";
|
|
const std::string TablePropertiesNames::kPropertyCollectors =
|
|
"rocksdb.property.collectors";
|
|
const std::string TablePropertiesNames::kCompression = "rocksdb.compression";
|
|
const std::string TablePropertiesNames::kCreationTime = "rocksdb.creation.time";
|
|
const std::string TablePropertiesNames::kOldestKeyTime =
|
|
"rocksdb.oldest.key.time";
|
|
|
|
extern const std::string kPropertiesBlock = "rocksdb.properties";
|
|
// Old property block name for backward compatibility
|
|
extern const std::string kPropertiesBlockOldName = "rocksdb.stats";
|
|
extern const std::string kCompressionDictBlock = "rocksdb.compression_dict";
|
|
extern const std::string kRangeDelBlock = "rocksdb.range_del";
|
|
|
|
// Seek to the properties block.
|
|
// Return true if it successfully seeks to the properties block.
|
|
Status SeekToPropertiesBlock(InternalIterator* meta_iter, bool* is_found) {
|
|
Status status = SeekToMetaBlock(meta_iter, kPropertiesBlock, is_found);
|
|
if (!*is_found && status.ok()) {
|
|
status = SeekToMetaBlock(meta_iter, kPropertiesBlockOldName, is_found);
|
|
}
|
|
return status;
|
|
}
|
|
|
|
// Seek to the compression dictionary block.
|
|
// Return true if it successfully seeks to that block.
|
|
Status SeekToCompressionDictBlock(InternalIterator* meta_iter, bool* is_found,
|
|
BlockHandle* block_handle) {
|
|
return SeekToMetaBlock(meta_iter, kCompressionDictBlock, is_found, block_handle);
|
|
}
|
|
|
|
Status SeekToRangeDelBlock(InternalIterator* meta_iter, bool* is_found,
|
|
BlockHandle* block_handle = nullptr) {
|
|
return SeekToMetaBlock(meta_iter, kRangeDelBlock, is_found, block_handle);
|
|
}
|
|
|
|
} // namespace rocksdb
|