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
206
207
208
209
210
211
212
213
214
215
|
// 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 <atomic>
#include <memory>
#include <utility>
#include "memory/allocator.h"
#include "memory/arena.h"
#include "port/lang.h"
#include "port/likely.h"
#include "util/core_local.h"
#include "util/mutexlock.h"
#include "util/thread_local.h"
// Only generate field unused warning for padding array, or build under
// GCC 4.8.1 will fail.
#ifdef __clang__
#define ROCKSDB_FIELD_UNUSED __attribute__((__unused__))
#else
#define ROCKSDB_FIELD_UNUSED
#endif // __clang__
namespace ROCKSDB_NAMESPACE {
class Logger;
// ConcurrentArena wraps an Arena. It makes it thread safe using a fast
// inlined spinlock, and adds small per-core allocation caches to avoid
// contention for small allocations. To avoid any memory waste from the
// per-core shards, they are kept small, they are lazily instantiated
// only if ConcurrentArena actually notices concurrent use, and they
// adjust their size so that there is no fragmentation waste when the
// shard blocks are allocated from the underlying main arena.
class ConcurrentArena : public Allocator {
public:
// block_size and huge_page_size are the same as for Arena (and are
// in fact just passed to the constructor of arena_. The core-local
// shards compute their shard_block_size as a fraction of block_size
// that varies according to the hardware concurrency level.
explicit ConcurrentArena(size_t block_size = Arena::kMinBlockSize,
AllocTracker* tracker = nullptr,
size_t huge_page_size = 0);
char* Allocate(size_t bytes) override {
return AllocateImpl(bytes, false /*force_arena*/,
[this, bytes]() { return arena_.Allocate(bytes); });
}
char* AllocateAligned(size_t bytes, size_t huge_page_size = 0,
Logger* logger = nullptr) override {
size_t rounded_up = ((bytes - 1) | (sizeof(void*) - 1)) + 1;
assert(rounded_up >= bytes && rounded_up < bytes + sizeof(void*) &&
(rounded_up % sizeof(void*)) == 0);
return AllocateImpl(rounded_up, huge_page_size != 0 /*force_arena*/,
[this, rounded_up, huge_page_size, logger]() {
return arena_.AllocateAligned(rounded_up,
huge_page_size, logger);
});
}
size_t ApproximateMemoryUsage() const {
std::unique_lock<SpinMutex> lock(arena_mutex_, std::defer_lock);
lock.lock();
return arena_.ApproximateMemoryUsage() - ShardAllocatedAndUnused();
}
size_t MemoryAllocatedBytes() const {
return memory_allocated_bytes_.load(std::memory_order_relaxed);
}
size_t AllocatedAndUnused() const {
return arena_allocated_and_unused_.load(std::memory_order_relaxed) +
ShardAllocatedAndUnused();
}
size_t IrregularBlockNum() const {
return irregular_block_num_.load(std::memory_order_relaxed);
}
size_t BlockSize() const override { return arena_.BlockSize(); }
private:
struct Shard {
char padding[40] ROCKSDB_FIELD_UNUSED;
mutable SpinMutex mutex;
char* free_begin_;
std::atomic<size_t> allocated_and_unused_;
Shard() : free_begin_(nullptr), allocated_and_unused_(0) {}
};
static thread_local size_t tls_cpuid;
char padding0[56] ROCKSDB_FIELD_UNUSED;
size_t shard_block_size_;
CoreLocalArray<Shard> shards_;
Arena arena_;
mutable SpinMutex arena_mutex_;
std::atomic<size_t> arena_allocated_and_unused_;
std::atomic<size_t> memory_allocated_bytes_;
std::atomic<size_t> irregular_block_num_;
char padding1[56] ROCKSDB_FIELD_UNUSED;
Shard* Repick();
size_t ShardAllocatedAndUnused() const {
size_t total = 0;
for (size_t i = 0; i < shards_.Size(); ++i) {
total += shards_.AccessAtCore(i)->allocated_and_unused_.load(
std::memory_order_relaxed);
}
return total;
}
template <typename Func>
char* AllocateImpl(size_t bytes, bool force_arena, const Func& func) {
size_t cpu;
// Go directly to the arena if the allocation is too large, or if
// we've never needed to Repick() and the arena mutex is available
// with no waiting. This keeps the fragmentation penalty of
// concurrency zero unless it might actually confer an advantage.
std::unique_lock<SpinMutex> arena_lock(arena_mutex_, std::defer_lock);
if (bytes > shard_block_size_ / 4 || force_arena ||
((cpu = tls_cpuid) == 0 &&
!shards_.AccessAtCore(0)->allocated_and_unused_.load(
std::memory_order_relaxed) &&
arena_lock.try_lock())) {
if (!arena_lock.owns_lock()) {
arena_lock.lock();
}
auto rv = func();
Fixup();
return rv;
}
// pick a shard from which to allocate
Shard* s = shards_.AccessAtCore(cpu & (shards_.Size() - 1));
if (!s->mutex.try_lock()) {
s = Repick();
s->mutex.lock();
}
std::unique_lock<SpinMutex> lock(s->mutex, std::adopt_lock);
size_t avail = s->allocated_and_unused_.load(std::memory_order_relaxed);
if (avail < bytes) {
// reload
std::lock_guard<SpinMutex> reload_lock(arena_mutex_);
// If the arena's current block is within a factor of 2 of the right
// size, we adjust our request to avoid arena waste.
auto exact = arena_allocated_and_unused_.load(std::memory_order_relaxed);
assert(exact == arena_.AllocatedAndUnused());
if (exact >= bytes && arena_.IsInInlineBlock()) {
// If we haven't exhausted arena's inline block yet, allocate from arena
// directly. This ensures that we'll do the first few small allocations
// without allocating any blocks.
// In particular this prevents empty memtables from using
// disproportionately large amount of memory: a memtable allocates on
// the order of 1 KB of memory when created; we wouldn't want to
// allocate a full arena block (typically a few megabytes) for that,
// especially if there are thousands of empty memtables.
auto rv = func();
Fixup();
return rv;
}
avail = exact >= shard_block_size_ / 2 && exact < shard_block_size_ * 2
? exact
: shard_block_size_;
s->free_begin_ = arena_.AllocateAligned(avail);
Fixup();
}
s->allocated_and_unused_.store(avail - bytes, std::memory_order_relaxed);
char* rv;
if ((bytes % sizeof(void*)) == 0) {
// aligned allocation from the beginning
rv = s->free_begin_;
s->free_begin_ += bytes;
} else {
// unaligned from the end
rv = s->free_begin_ + avail - bytes;
}
return rv;
}
void Fixup() {
arena_allocated_and_unused_.store(arena_.AllocatedAndUnused(),
std::memory_order_relaxed);
memory_allocated_bytes_.store(arena_.MemoryAllocatedBytes(),
std::memory_order_relaxed);
irregular_block_num_.store(arena_.IrregularBlockNum(),
std::memory_order_relaxed);
}
ConcurrentArena(const ConcurrentArena&) = delete;
ConcurrentArena& operator=(const ConcurrentArena&) = delete;
};
} // namespace ROCKSDB_NAMESPACE
|
