You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/table/block_builder.cc

129 lines
4.5 KiB

// 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.
//
// BlockBuilder generates blocks where keys are prefix-compressed:
//
// When we store a key, we drop the prefix shared with the previous
// string. This helps reduce the space requirement significantly.
// Furthermore, once every K keys, we do not apply the prefix
// compression and store the entire key. We call this a "restart
// point". The tail end of the block stores the offsets of all of the
// restart points, and can be used to do a binary search when looking
// for a particular key. Values are stored as-is (without compression)
// immediately following the corresponding key.
//
// An entry for a particular key-value pair has the form:
// shared_bytes: varint32
// unshared_bytes: varint32
// value_length: varint32
// key_delta: char[unshared_bytes]
// value: char[value_length]
// shared_bytes == 0 for restart points.
//
// The trailer of the block has the form:
// restarts: uint32[num_restarts]
// num_restarts: uint32
// restarts[i] contains the offset within the block of the ith restart point.
#include "table/block_builder.h"
#include <algorithm>
#include <assert.h>
#include "rocksdb/comparator.h"
#include "db/dbformat.h"
#include "util/coding.h"
namespace rocksdb {
Introduce ReadOptions::pin_data (support zero copy for keys) Summary: This patch update the Iterator API to introduce new functions that allow users to keep the Slices returned by key() valid as long as the Iterator is not deleted ReadOptions::pin_data : If true keep loaded blocks in memory as long as the iterator is not deleted Iterator::IsKeyPinned() : If true, this mean that the Slice returned by key() is valid as long as the iterator is not deleted Also add a new option BlockBasedTableOptions::use_delta_encoding to allow users to disable delta_encoding if needed. Benchmark results (using https://phabricator.fb.com/P20083553) ``` // $ du -h /home/tec/local/normal.4K.Snappy/db10077 // 6.1G /home/tec/local/normal.4K.Snappy/db10077 // $ du -h /home/tec/local/zero.8K.LZ4/db10077 // 6.4G /home/tec/local/zero.8K.LZ4/db10077 // Benchmarks for shard db10077 // _build/opt/rocks/benchmark/rocks_copy_benchmark \ // --normal_db_path="/home/tec/local/normal.4K.Snappy/db10077" \ // --zero_db_path="/home/tec/local/zero.8K.LZ4/db10077" // First run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 1.73s 576.97m // BM_StringPiece 103.74% 1.67s 598.55m // ============================================================================ // Match rate : 1000000 / 1000000 // Second run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 611.99ms 1.63 // BM_StringPiece 203.76% 300.35ms 3.33 // ============================================================================ // Match rate : 1000000 / 1000000 ``` Test Plan: Unit tests Reviewers: sdong, igor, anthony, yhchiang, rven Reviewed By: rven Subscribers: dhruba, lovro, adsharma Differential Revision: https://reviews.facebook.net/D48999
9 years ago
BlockBuilder::BlockBuilder(int block_restart_interval, bool use_delta_encoding)
: block_restart_interval_(block_restart_interval),
Introduce ReadOptions::pin_data (support zero copy for keys) Summary: This patch update the Iterator API to introduce new functions that allow users to keep the Slices returned by key() valid as long as the Iterator is not deleted ReadOptions::pin_data : If true keep loaded blocks in memory as long as the iterator is not deleted Iterator::IsKeyPinned() : If true, this mean that the Slice returned by key() is valid as long as the iterator is not deleted Also add a new option BlockBasedTableOptions::use_delta_encoding to allow users to disable delta_encoding if needed. Benchmark results (using https://phabricator.fb.com/P20083553) ``` // $ du -h /home/tec/local/normal.4K.Snappy/db10077 // 6.1G /home/tec/local/normal.4K.Snappy/db10077 // $ du -h /home/tec/local/zero.8K.LZ4/db10077 // 6.4G /home/tec/local/zero.8K.LZ4/db10077 // Benchmarks for shard db10077 // _build/opt/rocks/benchmark/rocks_copy_benchmark \ // --normal_db_path="/home/tec/local/normal.4K.Snappy/db10077" \ // --zero_db_path="/home/tec/local/zero.8K.LZ4/db10077" // First run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 1.73s 576.97m // BM_StringPiece 103.74% 1.67s 598.55m // ============================================================================ // Match rate : 1000000 / 1000000 // Second run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 611.99ms 1.63 // BM_StringPiece 203.76% 300.35ms 3.33 // ============================================================================ // Match rate : 1000000 / 1000000 ``` Test Plan: Unit tests Reviewers: sdong, igor, anthony, yhchiang, rven Reviewed By: rven Subscribers: dhruba, lovro, adsharma Differential Revision: https://reviews.facebook.net/D48999
9 years ago
use_delta_encoding_(use_delta_encoding),
restarts_(),
counter_(0),
finished_(false) {
assert(block_restart_interval_ >= 1);
restarts_.push_back(0); // First restart point is at offset 0
}
void BlockBuilder::Reset() {
buffer_.clear();
restarts_.clear();
restarts_.push_back(0); // First restart point is at offset 0
counter_ = 0;
finished_ = false;
last_key_.clear();
}
size_t BlockBuilder::CurrentSizeEstimate() const {
return (buffer_.size() + // Raw data buffer
restarts_.size() * sizeof(uint32_t) + // Restart array
sizeof(uint32_t)); // Restart array length
}
size_t BlockBuilder::EstimateSizeAfterKV(const Slice& key, const Slice& value)
const {
size_t estimate = CurrentSizeEstimate();
estimate += key.size() + value.size();
if (counter_ >= block_restart_interval_) {
estimate += sizeof(uint32_t); // a new restart entry.
}
estimate += sizeof(int32_t); // varint for shared prefix length.
estimate += VarintLength(key.size()); // varint for key length.
estimate += VarintLength(value.size()); // varint for value length.
return estimate;
}
Slice BlockBuilder::Finish() {
// Append restart array
for (size_t i = 0; i < restarts_.size(); i++) {
PutFixed32(&buffer_, restarts_[i]);
}
PutFixed32(&buffer_, static_cast<uint32_t>(restarts_.size()));
finished_ = true;
return Slice(buffer_);
}
void BlockBuilder::Add(const Slice& key, const Slice& value) {
Slice last_key_piece(last_key_);
assert(!finished_);
assert(counter_ <= block_restart_interval_);
Introduce ReadOptions::pin_data (support zero copy for keys) Summary: This patch update the Iterator API to introduce new functions that allow users to keep the Slices returned by key() valid as long as the Iterator is not deleted ReadOptions::pin_data : If true keep loaded blocks in memory as long as the iterator is not deleted Iterator::IsKeyPinned() : If true, this mean that the Slice returned by key() is valid as long as the iterator is not deleted Also add a new option BlockBasedTableOptions::use_delta_encoding to allow users to disable delta_encoding if needed. Benchmark results (using https://phabricator.fb.com/P20083553) ``` // $ du -h /home/tec/local/normal.4K.Snappy/db10077 // 6.1G /home/tec/local/normal.4K.Snappy/db10077 // $ du -h /home/tec/local/zero.8K.LZ4/db10077 // 6.4G /home/tec/local/zero.8K.LZ4/db10077 // Benchmarks for shard db10077 // _build/opt/rocks/benchmark/rocks_copy_benchmark \ // --normal_db_path="/home/tec/local/normal.4K.Snappy/db10077" \ // --zero_db_path="/home/tec/local/zero.8K.LZ4/db10077" // First run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 1.73s 576.97m // BM_StringPiece 103.74% 1.67s 598.55m // ============================================================================ // Match rate : 1000000 / 1000000 // Second run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 611.99ms 1.63 // BM_StringPiece 203.76% 300.35ms 3.33 // ============================================================================ // Match rate : 1000000 / 1000000 ``` Test Plan: Unit tests Reviewers: sdong, igor, anthony, yhchiang, rven Reviewed By: rven Subscribers: dhruba, lovro, adsharma Differential Revision: https://reviews.facebook.net/D48999
9 years ago
size_t shared = 0; // number of bytes shared with prev key
if (counter_ >= block_restart_interval_) {
// Restart compression
restarts_.push_back(static_cast<uint32_t>(buffer_.size()));
counter_ = 0;
} else if (use_delta_encoding_) {
// See how much sharing to do with previous string
const size_t min_length = std::min(last_key_piece.size(), key.size());
while ((shared < min_length) && (last_key_piece[shared] == key[shared])) {
shared++;
}
}
const size_t non_shared = key.size() - shared;
// Add "<shared><non_shared><value_size>" to buffer_
PutVarint32(&buffer_, static_cast<uint32_t>(shared));
PutVarint32(&buffer_, static_cast<uint32_t>(non_shared));
PutVarint32(&buffer_, static_cast<uint32_t>(value.size()));
// Add string delta to buffer_ followed by value
buffer_.append(key.data() + shared, non_shared);
buffer_.append(value.data(), value.size());
// Update state
last_key_.resize(shared);
last_key_.append(key.data() + shared, non_shared);
assert(Slice(last_key_) == key);
counter_++;
}
} // namespace rocksdb