rocksdb/cache/compressed_secondary_cache.h
anand76 fcc358baf2 Integrate CacheReservationManager with compressed secondary cache (#11449)
Summary:
This draft PR implements charging of reserved memory, for write buffers, table readers, and other purposes, proportionally to the block cache and the compressed secondary cache. The basic flow of memory reservation is maintained - clients use ```CacheReservationManager``` to request reservations, and ```CacheReservationManager``` inserts placeholder entries, i.e null value and non-zero charge, into the block cache. The ```CacheWithSecondaryAdapter``` wrapper uses its own instance of ```CacheReservationManager``` to keep track of reservations charged to the secondary cache, while the placeholder entries are inserted into the primary block cache. The design is as follows.

When ```CacheWithSecondaryAdapter``` is constructed with the ```distribute_cache_res``` parameter set to true, it manages the entire memory budget across the primary and secondary cache. The secondary cache is assumed to be in memory, such as the ```CompressedSecondaryCache```. When a placeholder entry is inserted by a CacheReservationManager instance to reserve memory, the ```CacheWithSecondaryAdapter```ensures that the reservation is distributed proportionally across the primary/secondary caches.

The primary block cache is initially sized to the sum of the primary cache budget + the secondary cache budget, as follows -
  |---------    Primary Cache Configured Capacity  -----------|
  |---Secondary Cache Budget----|----Primary Cache Budget-----|

A ```ConcurrentCacheReservationManager``` member in the ```CacheWithSecondaryAdapter```, ```pri_cache_res_```, is used to help with tracking the distribution of memory reservations. Initially, it accounts for the entire secondary cache budget as a reservation against the primary cache. This shrinks the usable capacity of the primary cache to the budget that the user originally desired.

  |--Reservation for Sec Cache--|-Pri Cache Usable Capacity---|

When a reservation placeholder is inserted into the adapter, it is inserted directly into the primary cache. This means the entire charge of the placeholder is counted against the primary cache. To compensate and count a portion of it against the secondary cache, the secondary cache ```Deflate()``` method is called to shrink it. Since the ```Deflate()``` causes the secondary actual usage to shrink, it is reflected here by releasing an equal amount from the ```pri_cache_res_``` reservation.

For example, if the pri/sec ratio is 50/50, this would be the state after placeholder insertion -

  |-Reservation for Sec Cache-|-Pri Cache Usable Capacity-|-R-|

Likewise, when the user inserted placeholder is released, the secondary cache ```Inflate()``` method is called to grow it, and the ```pri_cache_res_``` reservation is increased by an equal amount.

Other alternatives -
1. Another way of implementing this would have been to simply split the user reservation in ```CacheWithSecondaryAdapter``` into primary and secondary components. However, this would require allocating a structure to track the associated secondary cache reservation, which adds some complexity and overhead.
2. Yet another option is to implement the splitting directly in ```CacheReservationManager```. However, there are multiple instances of ```CacheReservationManager``` in a DB instance, making it complicated to keep track of them.

The PR contains the following changes -
1. A new cache allocator, ```NewTieredVolatileCache()```, is defined for allocating a tiered primary block cache and compressed secondary cache. This internally allocates an instance of ```CacheWithSecondaryAdapter```.
3. New interfaces, ```Deflate()``` and ```Inflate()```, are added to the ```SecondaryCache``` interface. The default implementaion returns ```NotSupported``` with overrides in ```CompressedSecondaryCache```.
4. The ```CompressedSecondaryCache``` uses a ```ConcurrentCacheReservationManager``` instance to manage reservations done using ```Inflate()/Deflate()```.
5. The ```CacheWithSecondaryAdapter``` optionally distributes memory reservations across the primary and secondary caches. The primary cache is sized to the total memory budget (primary + secondary), and the capacity allocated to secondary cache is "reserved" against the primary cache. For any subsequent reservations, the primary cache pre-reserved capacity is adjusted.

Benchmarks -
Baseline
```
time ~/rocksdb_anand76/db_bench --db=/dev/shm/comp_cache_res/base --use_existing_db=true --benchmarks="readseq,readwhilewriting" --key_size=32 --value_size=1024 --num=20000000 --threads=32 --bloom_bits=10 --cache_size=30000000000 --use_compressed_secondary_cache=true --compressed_secondary_cache_size=5000000000 --duration=300 --cost_write_buffer_to_cache=true
```
```
readseq      :       3.301 micros/op 9694317 ops/sec 66.018 seconds 640000000 operations; 9763.0 MB/s
readwhilewriting :      22.921 micros/op 1396058 ops/sec 300.021 seconds 418846968 operations; 1405.9 MB/s (13068999 of 13068999 found)

real    6m31.052s
user    152m5.660s
sys     26m18.738s
```
With TieredVolatileCache
```
time ~/rocksdb_anand76/db_bench --db=/dev/shm/comp_cache_res/base --use_existing_db=true --benchmarks="readseq,readwhilewriting" --key_size=32 --value_size=1024 --num=20000000 --threads=32 --bloom_bits=10 --cache_size=30000000000 --use_compressed_secondary_cache=true --compressed_secondary_cache_size=5000000000 --duration=300 --cost_write_buffer_to_cache=true --use_tiered_volatile_cache=true
```
```
readseq      :       4.064 micros/op 7873915 ops/sec 81.281 seconds 640000000 operations; 7929.7 MB/s
readwhilewriting :      20.944 micros/op 1527827 ops/sec 300.020 seconds 458378968 operations; 1538.6 MB/s (14296999 of 14296999 found)

real    6m42.743s
user    157m58.972s
sys     33m16.671
```
```
readseq      :       3.484 micros/op 9184967 ops/sec 69.679 seconds 640000000 operations; 9250.0 MB/s
readwhilewriting :      21.261 micros/op 1505035 ops/sec 300.024 seconds 451545968 operations; 1515.7 MB/s (14101999 of 14101999 found)

real    6m31.469s
user    155m16.570s
sys     27m47.834s
```

ToDo -
1. Add to db_stress

Pull Request resolved: https://github.com/facebook/rocksdb/pull/11449

Reviewed By: pdillinger

Differential Revision: D46197388

Pulled By: anand1976

fbshipit-source-id: 42d16f0254df683db4929db20d06ff26030e90df
2023-05-30 14:05:48 -07:00

141 lines
5 KiB
C++

// 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).
#pragma once
#include <array>
#include <cstddef>
#include <memory>
#include "cache/cache_reservation_manager.h"
#include "cache/lru_cache.h"
#include "memory/memory_allocator_impl.h"
#include "rocksdb/secondary_cache.h"
#include "rocksdb/slice.h"
#include "rocksdb/status.h"
#include "util/compression.h"
#include "util/mutexlock.h"
namespace ROCKSDB_NAMESPACE {
class CompressedSecondaryCacheResultHandle : public SecondaryCacheResultHandle {
public:
CompressedSecondaryCacheResultHandle(Cache::ObjectPtr value, size_t size)
: value_(value), size_(size) {}
~CompressedSecondaryCacheResultHandle() override = default;
CompressedSecondaryCacheResultHandle(
const CompressedSecondaryCacheResultHandle&) = delete;
CompressedSecondaryCacheResultHandle& operator=(
const CompressedSecondaryCacheResultHandle&) = delete;
bool IsReady() override { return true; }
void Wait() override {}
Cache::ObjectPtr Value() override { return value_; }
size_t Size() override { return size_; }
private:
Cache::ObjectPtr value_;
size_t size_;
};
// The CompressedSecondaryCache is a concrete implementation of
// rocksdb::SecondaryCache.
//
// When a block is found from CompressedSecondaryCache::Lookup, we check whether
// there is a dummy block with the same key in the primary cache.
// 1. If the dummy block exits, we erase the block from
// CompressedSecondaryCache and insert it into the primary cache.
// 2. If not, we just insert a dummy block into the primary cache
// (charging the actual size of the block) and don not erase the block from
// CompressedSecondaryCache. A standalone handle is returned to the caller.
//
// When a block is evicted from the primary cache, we check whether
// there is a dummy block with the same key in CompressedSecondaryCache.
// 1. If the dummy block exits, the block is inserted into
// CompressedSecondaryCache.
// 2. If not, we just insert a dummy block (size 0) in CompressedSecondaryCache.
//
// Users can also cast a pointer to CompressedSecondaryCache and call methods on
// it directly, especially custom methods that may be added
// in the future. For example -
// std::unique_ptr<rocksdb::SecondaryCache> cache =
// NewCompressedSecondaryCache(opts);
// static_cast<CompressedSecondaryCache*>(cache.get())->Erase(key);
class CompressedSecondaryCache : public SecondaryCache {
public:
explicit CompressedSecondaryCache(
const CompressedSecondaryCacheOptions& opts);
~CompressedSecondaryCache() override;
const char* Name() const override { return "CompressedSecondaryCache"; }
Status Insert(const Slice& key, Cache::ObjectPtr value,
const Cache::CacheItemHelper* helper) override;
std::unique_ptr<SecondaryCacheResultHandle> Lookup(
const Slice& key, const Cache::CacheItemHelper* helper,
Cache::CreateContext* create_context, bool /*wait*/, bool advise_erase,
bool& kept_in_sec_cache) override;
bool SupportForceErase() const override { return true; }
void Erase(const Slice& key) override;
void WaitAll(std::vector<SecondaryCacheResultHandle*> /*handles*/) override {}
Status SetCapacity(size_t capacity) override;
Status GetCapacity(size_t& capacity) override;
Status Deflate(size_t decrease) override;
Status Inflate(size_t increase) override;
std::string GetPrintableOptions() const override;
size_t TEST_GetUsage() { return cache_->GetUsage(); }
private:
friend class CompressedSecondaryCacheTestBase;
static constexpr std::array<uint16_t, 8> malloc_bin_sizes_{
128, 256, 512, 1024, 2048, 4096, 8192, 16384};
struct CacheValueChunk {
// TODO try "CacheAllocationPtr next;".
CacheValueChunk* next;
size_t size;
// Beginning of the chunk data (MUST BE THE LAST FIELD IN THIS STRUCT!)
char data[1];
void Free() { delete[] reinterpret_cast<char*>(this); }
};
// Split value into chunks to better fit into jemalloc bins. The chunks
// are stored in CacheValueChunk and extra charge is needed for each chunk,
// so the cache charge is recalculated here.
CacheValueChunk* SplitValueIntoChunks(const Slice& value,
CompressionType compression_type,
size_t& charge);
// After merging chunks, the extra charge for each chunk is removed, so
// the charge is recalculated.
CacheAllocationPtr MergeChunksIntoValue(const void* chunks_head,
size_t& charge);
// TODO: clean up to use cleaner interfaces in typed_cache.h
const Cache::CacheItemHelper* GetHelper(bool enable_custom_split_merge) const;
std::shared_ptr<Cache> cache_;
CompressedSecondaryCacheOptions cache_options_;
mutable port::Mutex capacity_mutex_;
std::shared_ptr<ConcurrentCacheReservationManager> cache_res_mgr_;
};
} // namespace ROCKSDB_NAMESPACE