2014-07-26 01:37:32 +02:00
|
|
|
// Copyright (c) 2014, 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.
|
|
|
|
|
|
|
|
#pragma once
|
|
|
|
#ifndef ROCKSDB_LITE
|
|
|
|
#include <string>
|
|
|
|
#include <memory>
|
2014-08-06 01:35:02 +02:00
|
|
|
#include <utility>
|
|
|
|
#include <vector>
|
2014-07-26 01:37:32 +02:00
|
|
|
|
|
|
|
#include "db/dbformat.h"
|
|
|
|
#include "rocksdb/env.h"
|
2014-09-05 01:18:36 +02:00
|
|
|
#include "rocksdb/options.h"
|
2014-07-26 01:37:32 +02:00
|
|
|
#include "table/table_reader.h"
|
|
|
|
|
|
|
|
namespace rocksdb {
|
|
|
|
|
|
|
|
class Arena;
|
|
|
|
class TableReader;
|
|
|
|
|
|
|
|
class CuckooTableReader: public TableReader {
|
|
|
|
public:
|
|
|
|
CuckooTableReader(
|
2014-09-05 01:18:36 +02:00
|
|
|
const ImmutableCFOptions& ioptions,
|
2014-07-26 01:37:32 +02:00
|
|
|
std::unique_ptr<RandomAccessFile>&& file,
|
|
|
|
uint64_t file_size,
|
2014-08-27 19:39:31 +02:00
|
|
|
const Comparator* user_comparator,
|
2014-08-06 05:55:46 +02:00
|
|
|
uint64_t (*get_slice_hash)(const Slice&, uint32_t, uint64_t));
|
2014-07-26 01:37:32 +02:00
|
|
|
~CuckooTableReader() {}
|
|
|
|
|
2014-08-06 01:35:02 +02:00
|
|
|
std::shared_ptr<const TableProperties> GetTableProperties() const override {
|
2014-07-26 01:37:32 +02:00
|
|
|
return table_props_;
|
|
|
|
}
|
|
|
|
|
|
|
|
Status status() const { return status_; }
|
|
|
|
|
|
|
|
Status Get(
|
2014-09-05 01:18:36 +02:00
|
|
|
const ReadOptions& read_options, const Slice& key, void* handle_context,
|
2014-07-26 01:37:32 +02:00
|
|
|
bool (*result_handler)(void* arg, const ParsedInternalKey& k,
|
|
|
|
const Slice& v),
|
2014-08-06 01:35:02 +02:00
|
|
|
void (*mark_key_may_exist_handler)(void* handle_context) = nullptr)
|
|
|
|
override;
|
2014-07-26 01:37:32 +02:00
|
|
|
|
2014-08-06 01:35:02 +02:00
|
|
|
Iterator* NewIterator(const ReadOptions&, Arena* arena = nullptr) override;
|
Implement Prepare method in CuckooTableReader
Summary:
- Implement Prepare method
- Rewrite performance tests in cuckoo_table_reader_test to write new file only if one doesn't already exist.
- Add performance tests for batch lookup along with prefetching.
Test Plan:
./cuckoo_table_reader_test --enable_perf
Results (We get better results if we used int64 comparator instead of string comparator (TBD in future diffs)):
With 100000000 items and hash table ratio 0.500000, number of hash functions used: 2.
Time taken per op is 0.208us (4.8 Mqps) with batch size of 0
With 100000000 items and hash table ratio 0.500000, number of hash functions used: 2.
Time taken per op is 0.182us (5.5 Mqps) with batch size of 10
With 100000000 items and hash table ratio 0.500000, number of hash functions used: 2.
Time taken per op is 0.161us (6.2 Mqps) with batch size of 25
With 100000000 items and hash table ratio 0.500000, number of hash functions used: 2.
Time taken per op is 0.161us (6.2 Mqps) with batch size of 50
With 100000000 items and hash table ratio 0.500000, number of hash functions used: 2.
Time taken per op is 0.163us (6.1 Mqps) with batch size of 100
With 100000000 items and hash table ratio 0.600000, number of hash functions used: 3.
Time taken per op is 0.252us (4.0 Mqps) with batch size of 0
With 100000000 items and hash table ratio 0.600000, number of hash functions used: 3.
Time taken per op is 0.192us (5.2 Mqps) with batch size of 10
With 100000000 items and hash table ratio 0.600000, number of hash functions used: 3.
Time taken per op is 0.195us (5.1 Mqps) with batch size of 25
With 100000000 items and hash table ratio 0.600000, number of hash functions used: 3.
Time taken per op is 0.191us (5.2 Mqps) with batch size of 50
With 100000000 items and hash table ratio 0.600000, number of hash functions used: 3.
Time taken per op is 0.194us (5.1 Mqps) with batch size of 100
With 100000000 items and hash table ratio 0.750000, number of hash functions used: 3.
Time taken per op is 0.228us (4.4 Mqps) with batch size of 0
With 100000000 items and hash table ratio 0.750000, number of hash functions used: 3.
Time taken per op is 0.185us (5.4 Mqps) with batch size of 10
With 100000000 items and hash table ratio 0.750000, number of hash functions used: 3.
Time taken per op is 0.186us (5.4 Mqps) with batch size of 25
With 100000000 items and hash table ratio 0.750000, number of hash functions used: 3.
Time taken per op is 0.189us (5.3 Mqps) with batch size of 50
With 100000000 items and hash table ratio 0.750000, number of hash functions used: 3.
Time taken per op is 0.188us (5.3 Mqps) with batch size of 100
With 100000000 items and hash table ratio 0.900000, number of hash functions used: 3.
Time taken per op is 0.325us (3.1 Mqps) with batch size of 0
With 100000000 items and hash table ratio 0.900000, number of hash functions used: 3.
Time taken per op is 0.196us (5.1 Mqps) with batch size of 10
With 100000000 items and hash table ratio 0.900000, number of hash functions used: 3.
Time taken per op is 0.199us (5.0 Mqps) with batch size of 25
With 100000000 items and hash table ratio 0.900000, number of hash functions used: 3.
Time taken per op is 0.196us (5.1 Mqps) with batch size of 50
With 100000000 items and hash table ratio 0.900000, number of hash functions used: 3.
Time taken per op is 0.209us (4.8 Mqps) with batch size of 100
Reviewers: sdong, yhchiang, igor, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D22167
2014-08-21 03:35:35 +02:00
|
|
|
void Prepare(const Slice& target) override;
|
2014-07-26 01:37:32 +02:00
|
|
|
|
2014-08-05 20:27:34 +02:00
|
|
|
// Report an approximation of how much memory has been used.
|
|
|
|
size_t ApproximateMemoryUsage() const override;
|
|
|
|
|
2014-07-26 01:37:32 +02:00
|
|
|
// Following methods are not implemented for Cuckoo Table Reader
|
2014-08-06 01:35:02 +02:00
|
|
|
uint64_t ApproximateOffsetOf(const Slice& key) override { return 0; }
|
|
|
|
void SetupForCompaction() override {}
|
2014-07-26 01:37:32 +02:00
|
|
|
// End of methods not implemented.
|
|
|
|
|
|
|
|
private:
|
2014-08-06 01:35:02 +02:00
|
|
|
friend class CuckooTableIterator;
|
|
|
|
void LoadAllKeys(std::vector<std::pair<Slice, uint32_t>>* key_to_bucket_id);
|
2014-07-26 01:37:32 +02:00
|
|
|
std::unique_ptr<RandomAccessFile> file_;
|
|
|
|
Slice file_data_;
|
|
|
|
bool is_last_level_;
|
|
|
|
std::shared_ptr<const TableProperties> table_props_;
|
|
|
|
Status status_;
|
2014-08-28 19:42:23 +02:00
|
|
|
uint32_t num_hash_func_;
|
2014-07-26 01:37:32 +02:00
|
|
|
std::string unused_key_;
|
|
|
|
uint32_t key_length_;
|
|
|
|
uint32_t value_length_;
|
|
|
|
uint32_t bucket_length_;
|
2014-08-28 19:42:23 +02:00
|
|
|
uint32_t cuckoo_block_size_;
|
|
|
|
uint32_t cuckoo_block_bytes_minus_one_;
|
Improve Cuckoo Table Reader performance. Inlined hash function and number of buckets a power of two.
Summary:
Use inlined hash functions instead of function pointer. Make number of buckets a power of two and use bitwise and instead of mod.
After these changes, we get almost 50% improvement in performance.
Results:
With 120000000 items, utilization is 89.41%, number of hash functions: 2.
Time taken per op is 0.231us (4.3 Mqps) with batch size of 0
Time taken per op is 0.229us (4.4 Mqps) with batch size of 0
Time taken per op is 0.185us (5.4 Mqps) with batch size of 0
With 120000000 items, utilization is 89.41%, number of hash functions: 2.
Time taken per op is 0.108us (9.3 Mqps) with batch size of 10
Time taken per op is 0.100us (10.0 Mqps) with batch size of 10
Time taken per op is 0.103us (9.7 Mqps) with batch size of 10
With 120000000 items, utilization is 89.41%, number of hash functions: 2.
Time taken per op is 0.101us (9.9 Mqps) with batch size of 25
Time taken per op is 0.098us (10.2 Mqps) with batch size of 25
Time taken per op is 0.097us (10.3 Mqps) with batch size of 25
With 120000000 items, utilization is 89.41%, number of hash functions: 2.
Time taken per op is 0.100us (10.0 Mqps) with batch size of 50
Time taken per op is 0.097us (10.3 Mqps) with batch size of 50
Time taken per op is 0.097us (10.3 Mqps) with batch size of 50
With 120000000 items, utilization is 89.41%, number of hash functions: 2.
Time taken per op is 0.102us (9.8 Mqps) with batch size of 100
Time taken per op is 0.098us (10.2 Mqps) with batch size of 100
Time taken per op is 0.115us (8.7 Mqps) with batch size of 100
With 100000000 items, utilization is 74.51%, number of hash functions: 2.
Time taken per op is 0.201us (5.0 Mqps) with batch size of 0
Time taken per op is 0.155us (6.5 Mqps) with batch size of 0
Time taken per op is 0.152us (6.6 Mqps) with batch size of 0
With 100000000 items, utilization is 74.51%, number of hash functions: 2.
Time taken per op is 0.089us (11.3 Mqps) with batch size of 10
Time taken per op is 0.084us (11.9 Mqps) with batch size of 10
Time taken per op is 0.086us (11.6 Mqps) with batch size of 10
With 100000000 items, utilization is 74.51%, number of hash functions: 2.
Time taken per op is 0.087us (11.5 Mqps) with batch size of 25
Time taken per op is 0.085us (11.7 Mqps) with batch size of 25
Time taken per op is 0.093us (10.8 Mqps) with batch size of 25
With 100000000 items, utilization is 74.51%, number of hash functions: 2.
Time taken per op is 0.094us (10.6 Mqps) with batch size of 50
Time taken per op is 0.094us (10.7 Mqps) with batch size of 50
Time taken per op is 0.093us (10.8 Mqps) with batch size of 50
With 100000000 items, utilization is 74.51%, number of hash functions: 2.
Time taken per op is 0.092us (10.9 Mqps) with batch size of 100
Time taken per op is 0.089us (11.2 Mqps) with batch size of 100
Time taken per op is 0.088us (11.3 Mqps) with batch size of 100
With 80000000 items, utilization is 59.60%, number of hash functions: 2.
Time taken per op is 0.154us (6.5 Mqps) with batch size of 0
Time taken per op is 0.168us (6.0 Mqps) with batch size of 0
Time taken per op is 0.190us (5.3 Mqps) with batch size of 0
With 80000000 items, utilization is 59.60%, number of hash functions: 2.
Time taken per op is 0.081us (12.4 Mqps) with batch size of 10
Time taken per op is 0.077us (13.0 Mqps) with batch size of 10
Time taken per op is 0.083us (12.1 Mqps) with batch size of 10
With 80000000 items, utilization is 59.60%, number of hash functions: 2.
Time taken per op is 0.077us (13.0 Mqps) with batch size of 25
Time taken per op is 0.073us (13.7 Mqps) with batch size of 25
Time taken per op is 0.073us (13.7 Mqps) with batch size of 25
With 80000000 items, utilization is 59.60%, number of hash functions: 2.
Time taken per op is 0.076us (13.1 Mqps) with batch size of 50
Time taken per op is 0.072us (13.8 Mqps) with batch size of 50
Time taken per op is 0.072us (13.8 Mqps) with batch size of 50
With 80000000 items, utilization is 59.60%, number of hash functions: 2.
Time taken per op is 0.077us (13.0 Mqps) with batch size of 100
Time taken per op is 0.074us (13.6 Mqps) with batch size of 100
Time taken per op is 0.073us (13.6 Mqps) with batch size of 100
With 70000000 items, utilization is 52.15%, number of hash functions: 2.
Time taken per op is 0.190us (5.3 Mqps) with batch size of 0
Time taken per op is 0.186us (5.4 Mqps) with batch size of 0
Time taken per op is 0.184us (5.4 Mqps) with batch size of 0
With 70000000 items, utilization is 52.15%, number of hash functions: 2.
Time taken per op is 0.079us (12.7 Mqps) with batch size of 10
Time taken per op is 0.070us (14.2 Mqps) with batch size of 10
Time taken per op is 0.072us (14.0 Mqps) with batch size of 10
With 70000000 items, utilization is 52.15%, number of hash functions: 2.
Time taken per op is 0.080us (12.5 Mqps) with batch size of 25
Time taken per op is 0.072us (14.0 Mqps) with batch size of 25
Time taken per op is 0.071us (14.1 Mqps) with batch size of 25
With 70000000 items, utilization is 52.15%, number of hash functions: 2.
Time taken per op is 0.082us (12.1 Mqps) with batch size of 50
Time taken per op is 0.071us (14.1 Mqps) with batch size of 50
Time taken per op is 0.073us (13.6 Mqps) with batch size of 50
With 70000000 items, utilization is 52.15%, number of hash functions: 2.
Time taken per op is 0.080us (12.5 Mqps) with batch size of 100
Time taken per op is 0.077us (13.0 Mqps) with batch size of 100
Time taken per op is 0.078us (12.8 Mqps) with batch size of 100
Test Plan:
make check all
make valgrind_check
make asan_check
Reviewers: sdong, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D22539
2014-08-30 04:06:15 +02:00
|
|
|
uint64_t table_size_minus_one_;
|
2014-08-27 19:39:31 +02:00
|
|
|
const Comparator* ucomp_;
|
2014-08-06 05:55:46 +02:00
|
|
|
uint64_t (*get_slice_hash_)(const Slice& s, uint32_t index,
|
2014-07-26 01:37:32 +02:00
|
|
|
uint64_t max_num_buckets);
|
|
|
|
};
|
|
|
|
|
|
|
|
} // namespace rocksdb
|
|
|
|
#endif // ROCKSDB_LITE
|