2016-02-10 00:12:00 +01:00
|
|
|
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
2017-07-16 01:03:42 +02:00
|
|
|
// 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).
|
2014-07-26 01:37:32 +02:00
|
|
|
//
|
|
|
|
// 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"
|
2019-09-16 19:31:27 +02:00
|
|
|
#include "file/random_access_file_reader.h"
|
2017-04-06 04:02:00 +02:00
|
|
|
#include "options/cf_options.h"
|
2014-07-26 01:37:32 +02:00
|
|
|
#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"
|
|
|
|
|
2020-02-20 21:07:53 +01:00
|
|
|
namespace ROCKSDB_NAMESPACE {
|
2014-07-26 01:37:32 +02:00
|
|
|
|
|
|
|
class Arena;
|
|
|
|
class TableReader;
|
|
|
|
|
|
|
|
class CuckooTableReader: public TableReader {
|
|
|
|
public:
|
Move rate_limiter, write buffering, most perf context instrumentation and most random kill out of Env
Summary: We want to keep Env a think layer for better portability. Less platform dependent codes should be moved out of Env. In this patch, I create a wrapper of file readers and writers, and put rate limiting, write buffering, as well as most perf context instrumentation and random kill out of Env. It will make it easier to maintain multiple Env in the future.
Test Plan: Run all existing unit tests.
Reviewers: anthony, kradhakrishnan, IslamAbdelRahman, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D42321
2015-07-18 01:16:11 +02:00
|
|
|
CuckooTableReader(const ImmutableCFOptions& ioptions,
|
|
|
|
std::unique_ptr<RandomAccessFileReader>&& file,
|
|
|
|
uint64_t file_size, const Comparator* user_comparator,
|
|
|
|
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_; }
|
|
|
|
|
2018-05-21 23:33:55 +02:00
|
|
|
Status Get(const ReadOptions& readOptions, const Slice& key,
|
|
|
|
GetContext* get_context, const SliceTransform* prefix_extractor,
|
|
|
|
bool skip_filters = false) override;
|
|
|
|
|
2019-06-19 23:07:36 +02:00
|
|
|
// Returns a new iterator over table contents
|
|
|
|
// compaction_readahead_size: its value will only be used if for_compaction =
|
|
|
|
// true
|
2018-05-21 23:33:55 +02:00
|
|
|
InternalIterator* NewIterator(const ReadOptions&,
|
|
|
|
const SliceTransform* prefix_extractor,
|
2019-06-20 23:28:22 +02:00
|
|
|
Arena* arena, bool skip_filters,
|
2019-09-20 21:00:55 +02:00
|
|
|
TableReaderCaller caller,
|
Properly report IO errors when IndexType::kBinarySearchWithFirstKey is used (#6621)
Summary:
Context: Index type `kBinarySearchWithFirstKey` added the ability for sst file iterator to sometimes report a key from index without reading the corresponding data block. This is useful when sst blocks are cut at some meaningful boundaries (e.g. one block per key prefix), and many seeks land between blocks (e.g. for each prefix, the ranges of keys in different sst files are nearly disjoint, so a typical seek needs to read a data block from only one file even if all files have the prefix). But this added a new error condition, which rocksdb code was really not equipped to deal with: `InternalIterator::value()` may fail with an IO error or Status::Incomplete, but it's just a method returning a Slice, with no way to report error instead. Before this PR, this type of error wasn't handled at all (an empty slice was returned), and kBinarySearchWithFirstKey implementation was considered a prototype.
Now that we (LogDevice) have experimented with kBinarySearchWithFirstKey for a while and confirmed that it's really useful, this PR is adding the missing error handling.
It's a pretty inconvenient situation implementation-wise. The error needs to be reported from InternalIterator when trying to access value. But there are ~700 call sites of `InternalIterator::value()`, most of which either can't hit the error condition (because the iterator is reading from memtable or from index or something) or wouldn't benefit from the deferred loading of the value (e.g. compaction iterator that reads all values anyway). Adding error handling to all these call sites would needlessly bloat the code. So instead I made the deferred value loading optional: only the call sites that may use deferred loading have to call the new method `PrepareValue()` before calling `value()`. The feature is enabled with a new bool argument `allow_unprepared_value` to a bunch of methods that create iterators (it wouldn't make sense to put it in ReadOptions because it's completely internal to iterators, with virtually no user-visible effect). Lmk if you have better ideas.
Note that the deferred value loading only happens for *internal* iterators. The user-visible iterator (DBIter) always prepares the value before returning from Seek/Next/etc. We could go further and add an API to defer that value loading too, but that's most likely not useful for LogDevice, so it doesn't seem worth the complexity for now.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6621
Test Plan: make -j5 check . Will also deploy to some logdevice test clusters and look at stats.
Reviewed By: siying
Differential Revision: D20786930
Pulled By: al13n321
fbshipit-source-id: 6da77d918bad3780522e918f17f4d5513d3e99ee
2020-04-16 02:37:23 +02:00
|
|
|
size_t compaction_readahead_size = 0,
|
|
|
|
bool allow_unprepared_value = false) 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
|
2019-06-11 00:30:05 +02:00
|
|
|
uint64_t ApproximateOffsetOf(const Slice& /*key*/,
|
2019-06-20 23:28:22 +02:00
|
|
|
TableReaderCaller /*caller*/) override {
|
2019-06-11 00:30:05 +02:00
|
|
|
return 0;
|
|
|
|
}
|
2019-08-16 23:16:49 +02:00
|
|
|
|
|
|
|
uint64_t ApproximateSize(const Slice& /*start*/, const Slice& /*end*/,
|
|
|
|
TableReaderCaller /*caller*/) override {
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2014-08-06 01:35:02 +02:00
|
|
|
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);
|
Move rate_limiter, write buffering, most perf context instrumentation and most random kill out of Env
Summary: We want to keep Env a think layer for better portability. Less platform dependent codes should be moved out of Env. In this patch, I create a wrapper of file readers and writers, and put rate limiting, write buffering, as well as most perf context instrumentation and random kill out of Env. It will make it easier to maintain multiple Env in the future.
Test Plan: Run all existing unit tests.
Reviewers: anthony, kradhakrishnan, IslamAbdelRahman, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D42321
2015-07-18 01:16:11 +02:00
|
|
|
std::unique_ptr<RandomAccessFileReader> file_;
|
2014-07-26 01:37:32 +02:00
|
|
|
Slice file_data_;
|
|
|
|
bool is_last_level_;
|
CuckooTable: add one option to allow identity function for the first hash function
Summary:
MurmurHash becomes expensive when we do millions Get() a second in one
thread. Add this option to allow the first hash function to use identity
function as hash function. It results in QPS increase from 3.7M/s to
~4.3M/s. I did not observe improvement for end to end RocksDB
performance. This may be caused by other bottlenecks that I will address
in a separate diff.
Test Plan:
```
[ljin@dev1964 rocksdb] ./cuckoo_table_reader_test --enable_perf --file_dir=/dev/shm --write --identity_as_first_hash=0
==== Test CuckooReaderTest.WhenKeyExists
==== Test CuckooReaderTest.WhenKeyExistsWithUint64Comparator
==== Test CuckooReaderTest.CheckIterator
==== Test CuckooReaderTest.CheckIteratorUint64
==== Test CuckooReaderTest.WhenKeyNotFound
==== Test CuckooReaderTest.TestReadPerformance
With 125829120 items, utilization is 93.75%, number of hash functions: 2.
Time taken per op is 0.272us (3.7 Mqps) with batch size of 0, # of found keys 125829120
With 125829120 items, utilization is 93.75%, number of hash functions: 2.
Time taken per op is 0.138us (7.2 Mqps) with batch size of 10, # of found keys 125829120
With 125829120 items, utilization is 93.75%, number of hash functions: 2.
Time taken per op is 0.142us (7.1 Mqps) with batch size of 25, # of found keys 125829120
With 125829120 items, utilization is 93.75%, number of hash functions: 2.
Time taken per op is 0.142us (7.0 Mqps) with batch size of 50, # of found keys 125829120
With 125829120 items, utilization is 93.75%, number of hash functions: 2.
Time taken per op is 0.144us (6.9 Mqps) with batch size of 100, # of found keys 125829120
With 104857600 items, utilization is 78.12%, number of hash functions: 2.
Time taken per op is 0.201us (5.0 Mqps) with batch size of 0, # of found keys 104857600
With 104857600 items, utilization is 78.12%, number of hash functions: 2.
Time taken per op is 0.121us (8.3 Mqps) with batch size of 10, # of found keys 104857600
With 104857600 items, utilization is 78.12%, number of hash functions: 2.
Time taken per op is 0.123us (8.1 Mqps) with batch size of 25, # of found keys 104857600
With 104857600 items, utilization is 78.12%, number of hash functions: 2.
Time taken per op is 0.121us (8.3 Mqps) with batch size of 50, # of found keys 104857600
With 104857600 items, utilization is 78.12%, number of hash functions: 2.
Time taken per op is 0.112us (8.9 Mqps) with batch size of 100, # of found keys 104857600
With 83886080 items, utilization is 62.50%, number of hash functions: 2.
Time taken per op is 0.251us (4.0 Mqps) with batch size of 0, # of found keys 83886080
With 83886080 items, utilization is 62.50%, number of hash functions: 2.
Time taken per op is 0.107us (9.4 Mqps) with batch size of 10, # of found keys 83886080
With 83886080 items, utilization is 62.50%, number of hash functions: 2.
Time taken per op is 0.099us (10.1 Mqps) with batch size of 25, # of found keys 83886080
With 83886080 items, utilization is 62.50%, number of hash functions: 2.
Time taken per op is 0.100us (10.0 Mqps) with batch size of 50, # of found keys 83886080
With 83886080 items, utilization is 62.50%, number of hash functions: 2.
Time taken per op is 0.116us (8.6 Mqps) with batch size of 100, # of found keys 83886080
With 73400320 items, utilization is 54.69%, number of hash functions: 2.
Time taken per op is 0.189us (5.3 Mqps) with batch size of 0, # of found keys 73400320
With 73400320 items, utilization is 54.69%, number of hash functions: 2.
Time taken per op is 0.095us (10.5 Mqps) with batch size of 10, # of found keys 73400320
With 73400320 items, utilization is 54.69%, number of hash functions: 2.
Time taken per op is 0.096us (10.4 Mqps) with batch size of 25, # of found keys 73400320
With 73400320 items, utilization is 54.69%, number of hash functions: 2.
Time taken per op is 0.098us (10.2 Mqps) with batch size of 50, # of found keys 73400320
With 73400320 items, utilization is 54.69%, number of hash functions: 2.
Time taken per op is 0.105us (9.5 Mqps) with batch size of 100, # of found keys 73400320
[ljin@dev1964 rocksdb] ./cuckoo_table_reader_test --enable_perf --file_dir=/dev/shm --write --identity_as_first_hash=1
==== Test CuckooReaderTest.WhenKeyExists
==== Test CuckooReaderTest.WhenKeyExistsWithUint64Comparator
==== Test CuckooReaderTest.CheckIterator
==== Test CuckooReaderTest.CheckIteratorUint64
==== Test CuckooReaderTest.WhenKeyNotFound
==== Test CuckooReaderTest.TestReadPerformance
With 125829120 items, utilization is 93.75%, number of hash functions: 2.
Time taken per op is 0.230us (4.3 Mqps) with batch size of 0, # of found keys 125829120
With 125829120 items, utilization is 93.75%, number of hash functions: 2.
Time taken per op is 0.086us (11.7 Mqps) with batch size of 10, # of found keys 125829120
With 125829120 items, utilization is 93.75%, number of hash functions: 2.
Time taken per op is 0.088us (11.3 Mqps) with batch size of 25, # of found keys 125829120
With 125829120 items, utilization is 93.75%, number of hash functions: 2.
Time taken per op is 0.083us (12.1 Mqps) with batch size of 50, # of found keys 125829120
With 125829120 items, utilization is 93.75%, number of hash functions: 2.
Time taken per op is 0.083us (12.1 Mqps) with batch size of 100, # of found keys 125829120
With 104857600 items, utilization is 78.12%, number of hash functions: 2.
Time taken per op is 0.159us (6.3 Mqps) with batch size of 0, # of found keys 104857600
With 104857600 items, utilization is 78.12%, number of hash functions: 2.
Time taken per op is 0.078us (12.8 Mqps) with batch size of 10, # of found keys 104857600
With 104857600 items, utilization is 78.12%, number of hash functions: 2.
Time taken per op is 0.080us (12.6 Mqps) with batch size of 25, # of found keys 104857600
With 104857600 items, utilization is 78.12%, number of hash functions: 2.
Time taken per op is 0.080us (12.5 Mqps) with batch size of 50, # of found keys 104857600
With 104857600 items, utilization is 78.12%, number of hash functions: 2.
Time taken per op is 0.082us (12.2 Mqps) with batch size of 100, # of found keys 104857600
With 83886080 items, utilization is 62.50%, number of hash functions: 2.
Time taken per op is 0.154us (6.5 Mqps) with batch size of 0, # of found keys 83886080
With 83886080 items, utilization is 62.50%, number of hash functions: 2.
Time taken per op is 0.077us (13.0 Mqps) with batch size of 10, # of found keys 83886080
With 83886080 items, utilization is 62.50%, number of hash functions: 2.
Time taken per op is 0.077us (12.9 Mqps) with batch size of 25, # of found keys 83886080
With 83886080 items, utilization is 62.50%, number of hash functions: 2.
Time taken per op is 0.078us (12.8 Mqps) with batch size of 50, # of found keys 83886080
With 83886080 items, utilization is 62.50%, number of hash functions: 2.
Time taken per op is 0.079us (12.6 Mqps) with batch size of 100, # of found keys 83886080
With 73400320 items, utilization is 54.69%, number of hash functions: 2.
Time taken per op is 0.218us (4.6 Mqps) with batch size of 0, # of found keys 73400320
With 73400320 items, utilization is 54.69%, number of hash functions: 2.
Time taken per op is 0.083us (12.0 Mqps) with batch size of 10, # of found keys 73400320
With 73400320 items, utilization is 54.69%, number of hash functions: 2.
Time taken per op is 0.085us (11.7 Mqps) with batch size of 25, # of found keys 73400320
With 73400320 items, utilization is 54.69%, number of hash functions: 2.
Time taken per op is 0.086us (11.6 Mqps) with batch size of 50, # of found keys 73400320
With 73400320 items, utilization is 54.69%, number of hash functions: 2.
Time taken per op is 0.078us (12.8 Mqps) with batch size of 100, # of found keys 73400320
```
Reviewers: sdong, igor, yhchiang
Reviewed By: igor
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D23451
2014-09-18 20:00:48 +02:00
|
|
|
bool identity_as_first_hash_;
|
2014-09-25 22:53:27 +02:00
|
|
|
bool use_module_hash_;
|
2014-07-26 01:37:32 +02:00
|
|
|
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_;
|
2014-09-26 01:15:23 +02:00
|
|
|
uint32_t user_key_length_;
|
2014-07-26 01:37:32 +02:00
|
|
|
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_;
|
2014-09-25 22:53:27 +02:00
|
|
|
uint64_t table_size_;
|
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);
|
|
|
|
};
|
|
|
|
|
2020-02-20 21:07:53 +01:00
|
|
|
} // namespace ROCKSDB_NAMESPACE
|
2014-07-26 01:37:32 +02:00
|
|
|
#endif // ROCKSDB_LITE
|