1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
|
// 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).
//
// 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
#include <type_traits>
#include "block.h"
#include "block_cache.h"
#include "table/block_based/block_based_table_reader.h"
#include "table/block_based/reader_common.h"
// The file contains some member functions of BlockBasedTable that
// cannot be implemented in block_based_table_reader.cc because
// it's called by other files (e.g. block_based_iterator.h) and
// are templates.
namespace ROCKSDB_NAMESPACE {
namespace {
using IterPlaceholderCacheInterface =
PlaceholderCacheInterface<CacheEntryRole::kMisc>;
template <typename TBlockIter>
struct IterTraits {};
template <>
struct IterTraits<DataBlockIter> {
using IterBlocklike = Block_kData;
};
template <>
struct IterTraits<IndexBlockIter> {
using IterBlocklike = Block_kIndex;
};
} // namespace
// Convert an index iterator value (i.e., an encoded BlockHandle)
// into an iterator over the contents of the corresponding block.
// If input_iter is null, new a iterator
// If input_iter is not null, update this iter and return it
template <typename TBlockIter>
TBlockIter* BlockBasedTable::NewDataBlockIterator(
const ReadOptions& ro, const BlockHandle& handle, TBlockIter* input_iter,
BlockType block_type, GetContext* get_context,
BlockCacheLookupContext* lookup_context,
FilePrefetchBuffer* prefetch_buffer, bool for_compaction, bool async_read,
Status& s, bool use_block_cache_for_lookup) const {
using IterBlocklike = typename IterTraits<TBlockIter>::IterBlocklike;
PERF_TIMER_GUARD(new_table_block_iter_nanos);
TBlockIter* iter = input_iter != nullptr ? input_iter : new TBlockIter;
if (!s.ok()) {
iter->Invalidate(s);
return iter;
}
CachableEntry<Block> block;
if (rep_->uncompression_dict_reader && block_type == BlockType::kData) {
CachableEntry<UncompressionDict> uncompression_dict;
// For async scans, don't use the prefetch buffer since an async prefetch
// might already be under way and this would invalidate it. Also, the
// uncompression dict is typically at the end of the file and would
// most likely break the sequentiality of the access pattern.
// Same is with auto_readahead_size. It iterates over index to lookup for
// data blocks. And this could break the the sequentiality of the access
// pattern.
s = rep_->uncompression_dict_reader->GetOrReadUncompressionDictionary(
((ro.async_io || ro.auto_readahead_size) ? nullptr : prefetch_buffer),
ro, get_context, lookup_context, &uncompression_dict);
if (!s.ok()) {
iter->Invalidate(s);
return iter;
}
const UncompressionDict& dict = uncompression_dict.GetValue()
? *uncompression_dict.GetValue()
: UncompressionDict::GetEmptyDict();
s = RetrieveBlock(
prefetch_buffer, ro, handle, dict, &block.As<IterBlocklike>(),
get_context, lookup_context, for_compaction,
/* use_cache */ true, async_read, use_block_cache_for_lookup);
} else {
s = RetrieveBlock(
prefetch_buffer, ro, handle, UncompressionDict::GetEmptyDict(),
&block.As<IterBlocklike>(), get_context, lookup_context, for_compaction,
/* use_cache */ true, async_read, use_block_cache_for_lookup);
}
if (s.IsTryAgain() && async_read) {
return iter;
}
if (!s.ok()) {
assert(block.IsEmpty());
iter->Invalidate(s);
return iter;
}
assert(block.GetValue() != nullptr);
// Block contents are pinned and it is still pinned after the iterator
// is destroyed as long as cleanup functions are moved to another object,
// when:
// 1. block cache handle is set to be released in cleanup function, or
// 2. it's pointing to immortal source. If own_bytes is true then we are
// not reading data from the original source, whether immortal or not.
// Otherwise, the block is pinned iff the source is immortal.
const bool block_contents_pinned =
block.IsCached() ||
(!block.GetValue()->own_bytes() && rep_->immortal_table);
iter = InitBlockIterator<TBlockIter>(rep_, block.GetValue(), block_type, iter,
block_contents_pinned);
if (!block.IsCached()) {
if (!ro.fill_cache) {
IterPlaceholderCacheInterface block_cache{
rep_->table_options.block_cache.get()};
if (block_cache) {
// insert a dummy record to block cache to track the memory usage
Cache::Handle* cache_handle = nullptr;
CacheKey key =
CacheKey::CreateUniqueForCacheLifetime(block_cache.get());
s = block_cache.Insert(key.AsSlice(),
block.GetValue()->ApproximateMemoryUsage(),
&cache_handle);
if (s.ok()) {
assert(cache_handle != nullptr);
iter->RegisterCleanup(&ForceReleaseCachedEntry, block_cache.get(),
cache_handle);
}
}
}
} else {
iter->SetCacheHandle(block.GetCacheHandle());
}
block.TransferTo(iter);
return iter;
}
// Convert an uncompressed data block (i.e CachableEntry<Block>)
// into an iterator over the contents of the corresponding block.
// If input_iter is null, new a iterator
// If input_iter is not null, update this iter and return it
template <typename TBlockIter>
TBlockIter* BlockBasedTable::NewDataBlockIterator(const ReadOptions& ro,
CachableEntry<Block>& block,
TBlockIter* input_iter,
Status s) const {
PERF_TIMER_GUARD(new_table_block_iter_nanos);
TBlockIter* iter = input_iter != nullptr ? input_iter : new TBlockIter;
if (!s.ok()) {
iter->Invalidate(s);
return iter;
}
assert(block.GetValue() != nullptr);
// Block contents are pinned and it is still pinned after the iterator
// is destroyed as long as cleanup functions are moved to another object,
// when:
// 1. block cache handle is set to be released in cleanup function, or
// 2. it's pointing to immortal source. If own_bytes is true then we are
// not reading data from the original source, whether immortal or not.
// Otherwise, the block is pinned iff the source is immortal.
const bool block_contents_pinned =
block.IsCached() ||
(!block.GetValue()->own_bytes() && rep_->immortal_table);
iter = InitBlockIterator<TBlockIter>(rep_, block.GetValue(), BlockType::kData,
iter, block_contents_pinned);
if (!block.IsCached()) {
if (!ro.fill_cache) {
IterPlaceholderCacheInterface block_cache{
rep_->table_options.block_cache.get()};
if (block_cache) {
// insert a dummy record to block cache to track the memory usage
Cache::Handle* cache_handle = nullptr;
CacheKey key =
CacheKey::CreateUniqueForCacheLifetime(block_cache.get());
s = block_cache.Insert(key.AsSlice(),
block.GetValue()->ApproximateMemoryUsage(),
&cache_handle);
if (s.ok()) {
assert(cache_handle != nullptr);
iter->RegisterCleanup(&ForceReleaseCachedEntry, block_cache.get(),
cache_handle);
}
}
}
} else {
iter->SetCacheHandle(block.GetCacheHandle());
}
block.TransferTo(iter);
return iter;
}
} // namespace ROCKSDB_NAMESPACE
|
