rocksdb/cache/cache.cc

194 lines
7.0 KiB
C++
Raw Normal View History

// 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.
#include "rocksdb/cache.h"
#include "cache/lru_cache.h"
#include "rocksdb/secondary_cache.h"
#include "rocksdb/utilities/customizable_util.h"
#include "rocksdb/utilities/options_type.h"
#include "util/string_util.h"
namespace ROCKSDB_NAMESPACE {
const Cache::CacheItemHelper kNoopCacheItemHelper{};
static std::unordered_map<std::string, OptionTypeInfo>
lru_cache_options_type_info = {
{"capacity",
{offsetof(struct LRUCacheOptions, capacity), OptionType::kSizeT,
OptionVerificationType::kNormal, OptionTypeFlags::kMutable}},
{"num_shard_bits",
{offsetof(struct LRUCacheOptions, num_shard_bits), OptionType::kInt,
OptionVerificationType::kNormal, OptionTypeFlags::kMutable}},
{"strict_capacity_limit",
{offsetof(struct LRUCacheOptions, strict_capacity_limit),
OptionType::kBoolean, OptionVerificationType::kNormal,
OptionTypeFlags::kMutable}},
{"high_pri_pool_ratio",
{offsetof(struct LRUCacheOptions, high_pri_pool_ratio),
OptionType::kDouble, OptionVerificationType::kNormal,
OptionTypeFlags::kMutable}},
{"low_pri_pool_ratio",
{offsetof(struct LRUCacheOptions, low_pri_pool_ratio),
OptionType::kDouble, OptionVerificationType::kNormal,
OptionTypeFlags::kMutable}},
};
static std::unordered_map<std::string, OptionTypeInfo>
comp_sec_cache_options_type_info = {
{"capacity",
{offsetof(struct CompressedSecondaryCacheOptions, capacity),
OptionType::kSizeT, OptionVerificationType::kNormal,
OptionTypeFlags::kMutable}},
{"num_shard_bits",
{offsetof(struct CompressedSecondaryCacheOptions, num_shard_bits),
OptionType::kInt, OptionVerificationType::kNormal,
OptionTypeFlags::kMutable}},
{"compression_type",
{offsetof(struct CompressedSecondaryCacheOptions, compression_type),
OptionType::kCompressionType, OptionVerificationType::kNormal,
OptionTypeFlags::kMutable}},
{"compress_format_version",
{offsetof(struct CompressedSecondaryCacheOptions,
compress_format_version),
OptionType::kUInt32T, OptionVerificationType::kNormal,
OptionTypeFlags::kMutable}},
{"enable_custom_split_merge",
{offsetof(struct CompressedSecondaryCacheOptions,
enable_custom_split_merge),
OptionType::kBoolean, OptionVerificationType::kNormal,
OptionTypeFlags::kMutable}},
};
Support compressed and local flash secondary cache stacking (#11812) Summary: This PR implements support for a three tier cache - primary block cache, compressed secondary cache, and a nvm (local flash) secondary cache. This allows more effective utilization of the nvm cache, and minimizes the number of reads from local flash by caching compressed blocks in the compressed secondary cache. The basic design is as follows - 1. A new secondary cache implementation, ```TieredSecondaryCache```, is introduced. It keeps the compressed and nvm secondary caches and manages the movement of blocks between them and the primary block cache. To setup a three tier cache, we allocate a ```CacheWithSecondaryAdapter```, with a ```TieredSecondaryCache``` instance as the secondary cache. 2. The table reader passes both the uncompressed and compressed block to ```FullTypedCacheInterface::InsertFull```, allowing the block cache to optionally store the compressed block. 3. When there's a miss, the block object is constructed and inserted in the primary cache, and the compressed block is inserted into the nvm cache by calling ```InsertSaved```. This avoids the overhead of recompressing the block, as well as avoiding putting more memory pressure on the compressed secondary cache. 4. When there's a hit in the nvm cache, we attempt to insert the block in the compressed secondary cache and the primary cache, subject to the admission policy of those caches (i.e admit on second access). Blocks/items evicted from any tier are simply discarded. We can easily implement additional admission policies if desired. Todo (In a subsequent PR): 1. Add to db_bench and run benchmarks 2. Add to db_stress Pull Request resolved: https://github.com/facebook/rocksdb/pull/11812 Reviewed By: pdillinger Differential Revision: D49461842 Pulled By: anand1976 fbshipit-source-id: b40ac1330ef7cd8c12efa0a3ca75128e602e3a0b
2023-09-22 03:30:53 +00:00
namespace {
static void NoopDelete(Cache::ObjectPtr /*obj*/,
MemoryAllocator* /*allocator*/) {
assert(false);
}
static size_t SliceSize(Cache::ObjectPtr obj) {
return static_cast<Slice*>(obj)->size();
}
static Status SliceSaveTo(Cache::ObjectPtr from_obj, size_t from_offset,
size_t length, char* out) {
const Slice& slice = *static_cast<Slice*>(from_obj);
std::memcpy(out, slice.data() + from_offset, length);
return Status::OK();
}
static Status NoopCreate(const Slice& /*data*/, CompressionType /*type*/,
CacheTier /*source*/, Cache::CreateContext* /*ctx*/,
MemoryAllocator* /*allocator*/,
Cache::ObjectPtr* /*out_obj*/,
size_t* /*out_charge*/) {
assert(false);
return Status::NotSupported();
}
static Cache::CacheItemHelper kBasicCacheItemHelper(CacheEntryRole::kMisc,
&NoopDelete);
} // namespace
const Cache::CacheItemHelper kSliceCacheItemHelper{
CacheEntryRole::kMisc, &NoopDelete, &SliceSize,
&SliceSaveTo, &NoopCreate, &kBasicCacheItemHelper,
};
Status SecondaryCache::CreateFromString(
const ConfigOptions& config_options, const std::string& value,
std::shared_ptr<SecondaryCache>* result) {
if (value.find("compressed_secondary_cache://") == 0) {
std::string args = value;
args.erase(0, std::strlen("compressed_secondary_cache://"));
Status status;
std::shared_ptr<SecondaryCache> sec_cache;
CompressedSecondaryCacheOptions sec_cache_opts;
status = OptionTypeInfo::ParseStruct(config_options, "",
&comp_sec_cache_options_type_info, "",
args, &sec_cache_opts);
if (status.ok()) {
sec_cache = NewCompressedSecondaryCache(sec_cache_opts);
}
if (status.ok()) {
result->swap(sec_cache);
}
return status;
} else {
return LoadSharedObject<SecondaryCache>(config_options, value, result);
}
}
Status Cache::CreateFromString(const ConfigOptions& config_options,
const std::string& value,
std::shared_ptr<Cache>* result) {
Status status;
std::shared_ptr<Cache> cache;
if (value.find('=') == std::string::npos) {
cache = NewLRUCache(ParseSizeT(value));
} else {
LRUCacheOptions cache_opts;
status = OptionTypeInfo::ParseStruct(config_options, "",
&lru_cache_options_type_info, "",
value, &cache_opts);
if (status.ok()) {
cache = NewLRUCache(cache_opts);
}
}
if (status.ok()) {
result->swap(cache);
}
return status;
}
HyperClockCache support for SecondaryCache, with refactoring (#11301) Summary: Internally refactors SecondaryCache integration out of LRUCache specifically and into a wrapper/adapter class that works with various Cache implementations. Notably, this relies on separating the notion of async lookup handles from other cache handles, so that HyperClockCache doesn't have to deal with the problem of allocating handles from the hash table for lookups that might fail anyway, and might be on the same key without support for coalescing. (LRUCache's hash table can incorporate previously allocated handles thanks to its pointer indirection.) Specifically, I'm worried about the case in which hundreds of threads try to access the same block and probing in the hash table degrades to linear search on the pile of entries with the same key. This change is a big step in the direction of supporting stacked SecondaryCaches, but there are obstacles to completing that. Especially, there is no SecondaryCache hook for evictions to pass from one to the next. It has been proposed that evictions be transmitted simply as the persisted data (as in SaveToCallback), but given the current structure provided by the CacheItemHelpers, that would require an extra copy of the block data, because there's intentionally no way to ask for a contiguous Slice of the data (to allow for flexibility in storage). `AsyncLookupHandle` and the re-worked `WaitAll()` should be essentially prepared for stacked SecondaryCaches, but several "TODO with stacked secondaries" issues remain in various places. It could be argued that the stacking instead be done as a SecondaryCache adapter that wraps two (or more) SecondaryCaches, but at least with the current API that would require an extra heap allocation on SecondaryCache Lookup for a wrapper SecondaryCacheResultHandle that can transfer a Lookup between secondaries. We could also consider trying to unify the Cache and SecondaryCache APIs, though that might be difficult if `AsyncLookupHandle` is kept a fixed struct. ## cache.h (public API) Moves `secondary_cache` option from LRUCacheOptions to ShardedCacheOptions so that it is applicable to HyperClockCache. ## advanced_cache.h (advanced public API) * Add `Cache::CreateStandalone()` so that the SecondaryCache support wrapper can use it. * Add `SetEvictionCallback()` / `eviction_callback_` so that the SecondaryCache support wrapper can use it. Only a single callback is supported for efficiency. If there is ever a need for more than one, hopefully that can be handled with a broadcast callback wrapper. These are essentially the two "extra" pieces of `Cache` for pulling out specific SecondaryCache support from the `Cache` implementation. I think it's a good trade-off as these are reasonable, limited, and reusable "cut points" into the `Cache` implementations. * Remove async capability from standard `Lookup()` (getting rid of awkward restrictions on pending Handles) and add `AsyncLookupHandle` and `StartAsyncLookup()`. As noted in the comments, the full struct of `AsyncLookupHandle` is exposed so that it can be stack allocated, for efficiency, though more data is being copied around than before, which could impact performance. (Lookup info -> AsyncLookupHandle -> Handle vs. Lookup info -> Handle) I could foresee a future in which a Cache internally saves a pointer to the AsyncLookupHandle, which means it's dangerous to allow it to be copyable or even movable. It also means it's not compatible with std::vector (which I don't like requiring as an API parameter anyway), so `WaitAll()` expects any contiguous array of AsyncLookupHandles. I believe this is best for common case efficiency, while behaving well in other cases also. For example, `WaitAll()` has no effect on default-constructed AsyncLookupHandles, which look like a completed cache miss. ## cacheable_entry.h A couple of functions are obsolete because Cache::Handle can no longer be pending. ## cache.cc Provides default implementations for new or revamped Cache functions, especially appropriate for non-blocking caches. ## secondary_cache_adapter.{h,cc} The full details of the Cache wrapper adding SecondaryCache support. Essentially replicates the SecondaryCache handling that was in LRUCache, but obviously refactored. There is a bit of logic duplication, where Lookup() is essentially a manually optimized version of StartAsyncLookup() and Wait(), but it's roughly a dozen lines of code. ## sharded_cache.h, typed_cache.h, charged_cache.{h,cc}, sim_cache.cc Simply updated for Cache API changes. ## lru_cache.{h,cc} Carefully remove SecondaryCache logic, implement `CreateStandalone` and eviction handler functionality. ## clock_cache.{h,cc} Expose existing `CreateStandalone` functionality, add eviction handler functionality. Light refactoring. ## block_based_table_reader* Mostly re-worked the only usage of async Lookup, which is in BlockBasedTable::MultiGet. Used arrays in place of autovector in some places for efficiency. Simplified some logic by not trying to process some cache results before they're all ready. Created new function `BlockBasedTable::GetCachePriority()` to reduce some pre-existing code duplication (and avoid making it worse). Fixed at least one small bug from the prior confusing mixture of async and sync Lookups. In MaybeReadBlockAndLoadToCache(), called by RetrieveBlock(), called by MultiGet() with wait=false, is_cache_hit for the block_cache_tracer entry would not be set to true if the handle was pending after Lookup and before Wait. ## Intended follow-up work * Figure out if there are any missing stats or block_cache_tracer work in refactored BlockBasedTable::MultiGet * Stacked secondary caches (see above discussion) * See if we can make up for the small MultiGet performance regression. * Study more performance with SecondaryCache * Items evicted from over-full LRUCache in Release were not being demoted to SecondaryCache, and still aren't to minimize unit test churn. Ideally they would be demoted, but it's an exceptional case so not a big deal. * Use CreateStandalone for cache reservations (save unnecessary hash table operations). Not a big deal, but worthy cleanup. * Somehow I got the contract for SecondaryCache::Insert wrong in #10945. (Doesn't take ownership!) That API comment needs to be fixed, but didn't want to mingle that in here. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11301 Test Plan: ## Unit tests Generally updated to include HCC in SecondaryCache tests, though HyperClockCache has some different, less strict behaviors that leads to some tests not really being set up to work with it. Some of the tests remain disabled with it, but I think we have good coverage without them. ## Crash/stress test Updated to use the new combination. ## Performance First, let's check for regression on caches without secondary cache configured. Adding support for the eviction callback is likely to have a tiny effect, but it shouldn't be worrisome. LRUCache could benefit slightly from less logic around SecondaryCache handling. We can test with cache_bench default settings, built with DEBUG_LEVEL=0 and PORTABLE=0. ``` (while :; do base/cache_bench --cache_type=hyper_clock_cache | grep Rough; done) | awk '{ sum += $9; count++; print $0; print "Average: " int(sum / count) }' ``` **Before** this and #11299 (which could also have a small effect), running for about an hour, before & after running concurrently for each cache type: HyperClockCache: 3168662 (average parallel ops/sec) LRUCache: 2940127 **After** this and #11299, running for about an hour: HyperClockCache: 3164862 (average parallel ops/sec) (0.12% slower) LRUCache: 2940928 (0.03% faster) This is an acceptable difference IMHO. Next, let's consider essentially the worst case of new CPU overhead affecting overall performance. MultiGet uses the async lookup interface regardless of whether SecondaryCache or folly are used. We can configure a benchmark where all block cache queries are for data blocks, and all are hits. Create DB and test (before and after tests running simultaneously): ``` TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=fillrandom -num=30000000 -disable_wal=1 -bloom_bits=16 TEST_TMPDIR=/dev/shm base/db_bench -benchmarks=multireadrandom[-X30] -readonly -multiread_batched -batch_size=32 -num=30000000 -bloom_bits=16 -cache_size=6789000000 -duration 20 -threads=16 ``` **Before**: multireadrandom [AVG 30 runs] : 3444202 (± 57049) ops/sec; 240.9 (± 4.0) MB/sec multireadrandom [MEDIAN 30 runs] : 3514443 ops/sec; 245.8 MB/sec **After**: multireadrandom [AVG 30 runs] : 3291022 (± 58851) ops/sec; 230.2 (± 4.1) MB/sec multireadrandom [MEDIAN 30 runs] : 3366179 ops/sec; 235.4 MB/sec So that's roughly a 3% regression, on kind of a *worst case* test of MultiGet CPU. Similar story with HyperClockCache: **Before**: multireadrandom [AVG 30 runs] : 3933777 (± 41840) ops/sec; 275.1 (± 2.9) MB/sec multireadrandom [MEDIAN 30 runs] : 3970667 ops/sec; 277.7 MB/sec **After**: multireadrandom [AVG 30 runs] : 3755338 (± 30391) ops/sec; 262.6 (± 2.1) MB/sec multireadrandom [MEDIAN 30 runs] : 3785696 ops/sec; 264.8 MB/sec Roughly a 4-5% regression. Not ideal, but not the whole story, fortunately. Let's also look at Get() in db_bench: ``` TEST_TMPDIR=/dev/shm ./db_bench -benchmarks=readrandom[-X30] -readonly -num=30000000 -bloom_bits=16 -cache_size=6789000000 -duration 20 -threads=16 ``` **Before**: readrandom [AVG 30 runs] : 2198685 (± 13412) ops/sec; 153.8 (± 0.9) MB/sec readrandom [MEDIAN 30 runs] : 2209498 ops/sec; 154.5 MB/sec **After**: readrandom [AVG 30 runs] : 2292814 (± 43508) ops/sec; 160.3 (± 3.0) MB/sec readrandom [MEDIAN 30 runs] : 2365181 ops/sec; 165.4 MB/sec That's showing roughly a 4% improvement, perhaps because of the secondary cache code that is no longer part of LRUCache. But weirdly, HyperClockCache is also showing 2-3% improvement: **Before**: readrandom [AVG 30 runs] : 2272333 (± 9992) ops/sec; 158.9 (± 0.7) MB/sec readrandom [MEDIAN 30 runs] : 2273239 ops/sec; 159.0 MB/sec **After**: readrandom [AVG 30 runs] : 2332407 (± 11252) ops/sec; 163.1 (± 0.8) MB/sec readrandom [MEDIAN 30 runs] : 2335329 ops/sec; 163.3 MB/sec Reviewed By: ltamasi Differential Revision: D44177044 Pulled By: pdillinger fbshipit-source-id: e808e48ff3fe2f792a79841ba617be98e48689f5
2023-03-18 03:23:49 +00:00
bool Cache::AsyncLookupHandle::IsReady() {
return pending_handle == nullptr || pending_handle->IsReady();
}
bool Cache::AsyncLookupHandle::IsPending() { return pending_handle != nullptr; }
Cache::Handle* Cache::AsyncLookupHandle::Result() {
assert(!IsPending());
return result_handle;
}
void Cache::StartAsyncLookup(AsyncLookupHandle& async_handle) {
async_handle.found_dummy_entry = false; // in case re-used
assert(!async_handle.IsPending());
async_handle.result_handle =
Lookup(async_handle.key, async_handle.helper, async_handle.create_context,
async_handle.priority, async_handle.stats);
}
Cache::Handle* Cache::Wait(AsyncLookupHandle& async_handle) {
WaitAll(&async_handle, 1);
return async_handle.Result();
}
void Cache::WaitAll(AsyncLookupHandle* async_handles, size_t count) {
for (size_t i = 0; i < count; ++i) {
if (async_handles[i].IsPending()) {
// If a pending handle gets here, it should be marked at "to be handled
// by a caller" by that caller erasing the pending_cache on it.
assert(async_handles[i].pending_cache == nullptr);
}
}
}
void Cache::SetEvictionCallback(EvictionCallback&& fn) {
// Overwriting non-empty with non-empty could indicate a bug
assert(!eviction_callback_ || !fn);
eviction_callback_ = std::move(fn);
}
} // namespace ROCKSDB_NAMESPACE