|
|
|
// 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).
|
|
|
|
|
|
|
|
#include "cache/compressed_secondary_cache.h"
|
|
|
|
|
Split cache to minimize internal fragmentation (#10287)
Summary:
### **Summary:**
To minimize the internal fragmentation caused by the variable size of the compressed blocks, the original block is split according to the jemalloc bin size in `Insert()` and then merged back in `Lookup()`. Based on the analysis of the results of the following tests, from the overall internal fragmentation perspective, this PR does mitigate the internal fragmentation issue.
_Do more myshadow tests with the latest commit. I finished several myshadow AB Testing and the results are promising. For the config of 4GB primary cache and 3GB secondary cache, Jemalloc resident stats shows consistently ~0.15GB memory saving; the allocated and active stats show similar memory savings. The CPU usage is almost the same before and after this PR._
To evaluate the issue of memory fragmentations and the benefits of this PR, I conducted two sets of local tests as follows.
**T1**
Keys: 16 bytes each (+ 0 bytes user-defined timestamp)
Values: 100 bytes each (50 bytes after compression)
Entries: 90000000
RawSize: 9956.4 MB (estimated)
FileSize: 5664.8 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T1_3 | 4000 | 4000 |
| T1_4 | 2000 | 3000 |
Populate the DB:
./db_bench --benchmarks=fillrandom --num=90000000 -db=/mem_fragmentation/db_bench_1
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=90000000 -use_existing_db -db=/mem_fragmentation/db_bench_1
Run read tests with differnt cache setting:
T1_3:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_3_20220710 -duration=1800 &
T1_4:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_4_20220710 -duration=1800 &
For T1_3 and T1_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T1_3 | T1_3 after mem defrag | T1_4 | T1_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8728 | 8076 | 5518 | 5043 |
| available (MB) | 8753 | 8092 | 5536 | 5051 |
| external fragmentation rate | 0.003 | 0.002 | 0.003 | 0.0016 |
| resident (MB) | 8956 | 8365 | 5655 | 5235 |
**T2**
Keys: 32 bytes each (+ 0 bytes user-defined timestamp)
Values: 256 bytes each (128 bytes after compression)
Entries: 40000000
RawSize: 10986.3 MB (estimated)
FileSize: 6103.5 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T2_3 | 4000 | 4000 |
| T2_4 | 2000 | 3000 |
Create DB (10GB):
./db_bench -benchmarks=fillrandom -use_direct_reads=true -num=40000000 -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=40000000 -use_existing_db -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Run read tests with differnt cache setting:
T2_3:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_3 -duration=1800 &
T2_4:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_4 -duration=1800 &
For T2_3 and T2_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T2_3 | T2_3 after mem defrag | T2_4 | T2_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8425 | 8093 | 5426 | 5149 |
| available (MB) | 8489 | 8138 | 5435 | 5158 |
| external fragmentation rate | 0.008 | 0.0055 | 0.0017 | 0.0017 |
| resident (MB) | 8676 | 8392 | 5541 | 5321 |
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10287
Test Plan: Unit tests.
Reviewed By: anand1976
Differential Revision: D37743362
Pulled By: gitbw95
fbshipit-source-id: 0010c5af08addeacc5ebbc4ffe5be882fb1d38ad
2 years ago
|
|
|
#include <algorithm>
|
|
|
|
#include <cstdint>
|
|
|
|
#include <memory>
|
|
|
|
|
|
|
|
#include "memory/memory_allocator.h"
|
|
|
|
#include "util/compression.h"
|
|
|
|
#include "util/string_util.h"
|
|
|
|
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
|
|
|
|
CompressedSecondaryCache::CompressedSecondaryCache(
|
|
|
|
size_t capacity, int num_shard_bits, bool strict_capacity_limit,
|
|
|
|
double high_pri_pool_ratio, double low_pri_pool_ratio,
|
|
|
|
std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
|
|
|
|
CacheMetadataChargePolicy metadata_charge_policy,
|
|
|
|
CompressionType compression_type, uint32_t compress_format_version)
|
|
|
|
: cache_options_(capacity, num_shard_bits, strict_capacity_limit,
|
|
|
|
high_pri_pool_ratio, memory_allocator, use_adaptive_mutex,
|
|
|
|
metadata_charge_policy, compression_type,
|
|
|
|
compress_format_version, low_pri_pool_ratio) {
|
|
|
|
cache_ =
|
|
|
|
NewLRUCache(capacity, num_shard_bits, strict_capacity_limit,
|
|
|
|
high_pri_pool_ratio, memory_allocator, use_adaptive_mutex,
|
|
|
|
metadata_charge_policy, low_pri_pool_ratio);
|
|
|
|
}
|
|
|
|
|
|
|
|
CompressedSecondaryCache::~CompressedSecondaryCache() { cache_.reset(); }
|
|
|
|
|
|
|
|
std::unique_ptr<SecondaryCacheResultHandle> CompressedSecondaryCache::Lookup(
|
|
|
|
const Slice& key, const Cache::CreateCallback& create_cb, bool /*wait*/,
|
|
|
|
bool& is_in_sec_cache) {
|
|
|
|
std::unique_ptr<SecondaryCacheResultHandle> handle;
|
|
|
|
is_in_sec_cache = false;
|
|
|
|
Cache::Handle* lru_handle = cache_->Lookup(key);
|
|
|
|
if (lru_handle == nullptr) {
|
|
|
|
return handle;
|
|
|
|
}
|
|
|
|
|
Split cache to minimize internal fragmentation (#10287)
Summary:
### **Summary:**
To minimize the internal fragmentation caused by the variable size of the compressed blocks, the original block is split according to the jemalloc bin size in `Insert()` and then merged back in `Lookup()`. Based on the analysis of the results of the following tests, from the overall internal fragmentation perspective, this PR does mitigate the internal fragmentation issue.
_Do more myshadow tests with the latest commit. I finished several myshadow AB Testing and the results are promising. For the config of 4GB primary cache and 3GB secondary cache, Jemalloc resident stats shows consistently ~0.15GB memory saving; the allocated and active stats show similar memory savings. The CPU usage is almost the same before and after this PR._
To evaluate the issue of memory fragmentations and the benefits of this PR, I conducted two sets of local tests as follows.
**T1**
Keys: 16 bytes each (+ 0 bytes user-defined timestamp)
Values: 100 bytes each (50 bytes after compression)
Entries: 90000000
RawSize: 9956.4 MB (estimated)
FileSize: 5664.8 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T1_3 | 4000 | 4000 |
| T1_4 | 2000 | 3000 |
Populate the DB:
./db_bench --benchmarks=fillrandom --num=90000000 -db=/mem_fragmentation/db_bench_1
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=90000000 -use_existing_db -db=/mem_fragmentation/db_bench_1
Run read tests with differnt cache setting:
T1_3:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_3_20220710 -duration=1800 &
T1_4:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_4_20220710 -duration=1800 &
For T1_3 and T1_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T1_3 | T1_3 after mem defrag | T1_4 | T1_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8728 | 8076 | 5518 | 5043 |
| available (MB) | 8753 | 8092 | 5536 | 5051 |
| external fragmentation rate | 0.003 | 0.002 | 0.003 | 0.0016 |
| resident (MB) | 8956 | 8365 | 5655 | 5235 |
**T2**
Keys: 32 bytes each (+ 0 bytes user-defined timestamp)
Values: 256 bytes each (128 bytes after compression)
Entries: 40000000
RawSize: 10986.3 MB (estimated)
FileSize: 6103.5 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T2_3 | 4000 | 4000 |
| T2_4 | 2000 | 3000 |
Create DB (10GB):
./db_bench -benchmarks=fillrandom -use_direct_reads=true -num=40000000 -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=40000000 -use_existing_db -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Run read tests with differnt cache setting:
T2_3:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_3 -duration=1800 &
T2_4:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_4 -duration=1800 &
For T2_3 and T2_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T2_3 | T2_3 after mem defrag | T2_4 | T2_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8425 | 8093 | 5426 | 5149 |
| available (MB) | 8489 | 8138 | 5435 | 5158 |
| external fragmentation rate | 0.008 | 0.0055 | 0.0017 | 0.0017 |
| resident (MB) | 8676 | 8392 | 5541 | 5321 |
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10287
Test Plan: Unit tests.
Reviewed By: anand1976
Differential Revision: D37743362
Pulled By: gitbw95
fbshipit-source-id: 0010c5af08addeacc5ebbc4ffe5be882fb1d38ad
2 years ago
|
|
|
CacheValueChunk* handle_value =
|
|
|
|
reinterpret_cast<CacheValueChunk*>(cache_->Value(lru_handle));
|
|
|
|
size_t handle_value_charge{0};
|
|
|
|
CacheAllocationPtr merged_value =
|
|
|
|
MergeChunksIntoValue(handle_value, handle_value_charge);
|
|
|
|
|
Split cache to minimize internal fragmentation (#10287)
Summary:
### **Summary:**
To minimize the internal fragmentation caused by the variable size of the compressed blocks, the original block is split according to the jemalloc bin size in `Insert()` and then merged back in `Lookup()`. Based on the analysis of the results of the following tests, from the overall internal fragmentation perspective, this PR does mitigate the internal fragmentation issue.
_Do more myshadow tests with the latest commit. I finished several myshadow AB Testing and the results are promising. For the config of 4GB primary cache and 3GB secondary cache, Jemalloc resident stats shows consistently ~0.15GB memory saving; the allocated and active stats show similar memory savings. The CPU usage is almost the same before and after this PR._
To evaluate the issue of memory fragmentations and the benefits of this PR, I conducted two sets of local tests as follows.
**T1**
Keys: 16 bytes each (+ 0 bytes user-defined timestamp)
Values: 100 bytes each (50 bytes after compression)
Entries: 90000000
RawSize: 9956.4 MB (estimated)
FileSize: 5664.8 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T1_3 | 4000 | 4000 |
| T1_4 | 2000 | 3000 |
Populate the DB:
./db_bench --benchmarks=fillrandom --num=90000000 -db=/mem_fragmentation/db_bench_1
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=90000000 -use_existing_db -db=/mem_fragmentation/db_bench_1
Run read tests with differnt cache setting:
T1_3:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_3_20220710 -duration=1800 &
T1_4:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_4_20220710 -duration=1800 &
For T1_3 and T1_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T1_3 | T1_3 after mem defrag | T1_4 | T1_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8728 | 8076 | 5518 | 5043 |
| available (MB) | 8753 | 8092 | 5536 | 5051 |
| external fragmentation rate | 0.003 | 0.002 | 0.003 | 0.0016 |
| resident (MB) | 8956 | 8365 | 5655 | 5235 |
**T2**
Keys: 32 bytes each (+ 0 bytes user-defined timestamp)
Values: 256 bytes each (128 bytes after compression)
Entries: 40000000
RawSize: 10986.3 MB (estimated)
FileSize: 6103.5 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T2_3 | 4000 | 4000 |
| T2_4 | 2000 | 3000 |
Create DB (10GB):
./db_bench -benchmarks=fillrandom -use_direct_reads=true -num=40000000 -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=40000000 -use_existing_db -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Run read tests with differnt cache setting:
T2_3:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_3 -duration=1800 &
T2_4:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_4 -duration=1800 &
For T2_3 and T2_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T2_3 | T2_3 after mem defrag | T2_4 | T2_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8425 | 8093 | 5426 | 5149 |
| available (MB) | 8489 | 8138 | 5435 | 5158 |
| external fragmentation rate | 0.008 | 0.0055 | 0.0017 | 0.0017 |
| resident (MB) | 8676 | 8392 | 5541 | 5321 |
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10287
Test Plan: Unit tests.
Reviewed By: anand1976
Differential Revision: D37743362
Pulled By: gitbw95
fbshipit-source-id: 0010c5af08addeacc5ebbc4ffe5be882fb1d38ad
2 years ago
|
|
|
Status s;
|
|
|
|
void* value{nullptr};
|
|
|
|
size_t charge{0};
|
|
|
|
if (cache_options_.compression_type == kNoCompression) {
|
Split cache to minimize internal fragmentation (#10287)
Summary:
### **Summary:**
To minimize the internal fragmentation caused by the variable size of the compressed blocks, the original block is split according to the jemalloc bin size in `Insert()` and then merged back in `Lookup()`. Based on the analysis of the results of the following tests, from the overall internal fragmentation perspective, this PR does mitigate the internal fragmentation issue.
_Do more myshadow tests with the latest commit. I finished several myshadow AB Testing and the results are promising. For the config of 4GB primary cache and 3GB secondary cache, Jemalloc resident stats shows consistently ~0.15GB memory saving; the allocated and active stats show similar memory savings. The CPU usage is almost the same before and after this PR._
To evaluate the issue of memory fragmentations and the benefits of this PR, I conducted two sets of local tests as follows.
**T1**
Keys: 16 bytes each (+ 0 bytes user-defined timestamp)
Values: 100 bytes each (50 bytes after compression)
Entries: 90000000
RawSize: 9956.4 MB (estimated)
FileSize: 5664.8 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T1_3 | 4000 | 4000 |
| T1_4 | 2000 | 3000 |
Populate the DB:
./db_bench --benchmarks=fillrandom --num=90000000 -db=/mem_fragmentation/db_bench_1
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=90000000 -use_existing_db -db=/mem_fragmentation/db_bench_1
Run read tests with differnt cache setting:
T1_3:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_3_20220710 -duration=1800 &
T1_4:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_4_20220710 -duration=1800 &
For T1_3 and T1_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T1_3 | T1_3 after mem defrag | T1_4 | T1_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8728 | 8076 | 5518 | 5043 |
| available (MB) | 8753 | 8092 | 5536 | 5051 |
| external fragmentation rate | 0.003 | 0.002 | 0.003 | 0.0016 |
| resident (MB) | 8956 | 8365 | 5655 | 5235 |
**T2**
Keys: 32 bytes each (+ 0 bytes user-defined timestamp)
Values: 256 bytes each (128 bytes after compression)
Entries: 40000000
RawSize: 10986.3 MB (estimated)
FileSize: 6103.5 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T2_3 | 4000 | 4000 |
| T2_4 | 2000 | 3000 |
Create DB (10GB):
./db_bench -benchmarks=fillrandom -use_direct_reads=true -num=40000000 -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=40000000 -use_existing_db -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Run read tests with differnt cache setting:
T2_3:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_3 -duration=1800 &
T2_4:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_4 -duration=1800 &
For T2_3 and T2_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T2_3 | T2_3 after mem defrag | T2_4 | T2_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8425 | 8093 | 5426 | 5149 |
| available (MB) | 8489 | 8138 | 5435 | 5158 |
| external fragmentation rate | 0.008 | 0.0055 | 0.0017 | 0.0017 |
| resident (MB) | 8676 | 8392 | 5541 | 5321 |
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10287
Test Plan: Unit tests.
Reviewed By: anand1976
Differential Revision: D37743362
Pulled By: gitbw95
fbshipit-source-id: 0010c5af08addeacc5ebbc4ffe5be882fb1d38ad
2 years ago
|
|
|
s = create_cb(merged_value.get(), handle_value_charge, &value, &charge);
|
|
|
|
} else {
|
|
|
|
UncompressionContext uncompression_context(cache_options_.compression_type);
|
|
|
|
UncompressionInfo uncompression_info(uncompression_context,
|
|
|
|
UncompressionDict::GetEmptyDict(),
|
|
|
|
cache_options_.compression_type);
|
|
|
|
|
Split cache to minimize internal fragmentation (#10287)
Summary:
### **Summary:**
To minimize the internal fragmentation caused by the variable size of the compressed blocks, the original block is split according to the jemalloc bin size in `Insert()` and then merged back in `Lookup()`. Based on the analysis of the results of the following tests, from the overall internal fragmentation perspective, this PR does mitigate the internal fragmentation issue.
_Do more myshadow tests with the latest commit. I finished several myshadow AB Testing and the results are promising. For the config of 4GB primary cache and 3GB secondary cache, Jemalloc resident stats shows consistently ~0.15GB memory saving; the allocated and active stats show similar memory savings. The CPU usage is almost the same before and after this PR._
To evaluate the issue of memory fragmentations and the benefits of this PR, I conducted two sets of local tests as follows.
**T1**
Keys: 16 bytes each (+ 0 bytes user-defined timestamp)
Values: 100 bytes each (50 bytes after compression)
Entries: 90000000
RawSize: 9956.4 MB (estimated)
FileSize: 5664.8 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T1_3 | 4000 | 4000 |
| T1_4 | 2000 | 3000 |
Populate the DB:
./db_bench --benchmarks=fillrandom --num=90000000 -db=/mem_fragmentation/db_bench_1
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=90000000 -use_existing_db -db=/mem_fragmentation/db_bench_1
Run read tests with differnt cache setting:
T1_3:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_3_20220710 -duration=1800 &
T1_4:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_4_20220710 -duration=1800 &
For T1_3 and T1_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T1_3 | T1_3 after mem defrag | T1_4 | T1_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8728 | 8076 | 5518 | 5043 |
| available (MB) | 8753 | 8092 | 5536 | 5051 |
| external fragmentation rate | 0.003 | 0.002 | 0.003 | 0.0016 |
| resident (MB) | 8956 | 8365 | 5655 | 5235 |
**T2**
Keys: 32 bytes each (+ 0 bytes user-defined timestamp)
Values: 256 bytes each (128 bytes after compression)
Entries: 40000000
RawSize: 10986.3 MB (estimated)
FileSize: 6103.5 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T2_3 | 4000 | 4000 |
| T2_4 | 2000 | 3000 |
Create DB (10GB):
./db_bench -benchmarks=fillrandom -use_direct_reads=true -num=40000000 -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=40000000 -use_existing_db -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Run read tests with differnt cache setting:
T2_3:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_3 -duration=1800 &
T2_4:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_4 -duration=1800 &
For T2_3 and T2_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T2_3 | T2_3 after mem defrag | T2_4 | T2_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8425 | 8093 | 5426 | 5149 |
| available (MB) | 8489 | 8138 | 5435 | 5158 |
| external fragmentation rate | 0.008 | 0.0055 | 0.0017 | 0.0017 |
| resident (MB) | 8676 | 8392 | 5541 | 5321 |
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10287
Test Plan: Unit tests.
Reviewed By: anand1976
Differential Revision: D37743362
Pulled By: gitbw95
fbshipit-source-id: 0010c5af08addeacc5ebbc4ffe5be882fb1d38ad
2 years ago
|
|
|
size_t uncompressed_size{0};
|
|
|
|
CacheAllocationPtr uncompressed;
|
Split cache to minimize internal fragmentation (#10287)
Summary:
### **Summary:**
To minimize the internal fragmentation caused by the variable size of the compressed blocks, the original block is split according to the jemalloc bin size in `Insert()` and then merged back in `Lookup()`. Based on the analysis of the results of the following tests, from the overall internal fragmentation perspective, this PR does mitigate the internal fragmentation issue.
_Do more myshadow tests with the latest commit. I finished several myshadow AB Testing and the results are promising. For the config of 4GB primary cache and 3GB secondary cache, Jemalloc resident stats shows consistently ~0.15GB memory saving; the allocated and active stats show similar memory savings. The CPU usage is almost the same before and after this PR._
To evaluate the issue of memory fragmentations and the benefits of this PR, I conducted two sets of local tests as follows.
**T1**
Keys: 16 bytes each (+ 0 bytes user-defined timestamp)
Values: 100 bytes each (50 bytes after compression)
Entries: 90000000
RawSize: 9956.4 MB (estimated)
FileSize: 5664.8 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T1_3 | 4000 | 4000 |
| T1_4 | 2000 | 3000 |
Populate the DB:
./db_bench --benchmarks=fillrandom --num=90000000 -db=/mem_fragmentation/db_bench_1
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=90000000 -use_existing_db -db=/mem_fragmentation/db_bench_1
Run read tests with differnt cache setting:
T1_3:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_3_20220710 -duration=1800 &
T1_4:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_4_20220710 -duration=1800 &
For T1_3 and T1_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T1_3 | T1_3 after mem defrag | T1_4 | T1_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8728 | 8076 | 5518 | 5043 |
| available (MB) | 8753 | 8092 | 5536 | 5051 |
| external fragmentation rate | 0.003 | 0.002 | 0.003 | 0.0016 |
| resident (MB) | 8956 | 8365 | 5655 | 5235 |
**T2**
Keys: 32 bytes each (+ 0 bytes user-defined timestamp)
Values: 256 bytes each (128 bytes after compression)
Entries: 40000000
RawSize: 10986.3 MB (estimated)
FileSize: 6103.5 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T2_3 | 4000 | 4000 |
| T2_4 | 2000 | 3000 |
Create DB (10GB):
./db_bench -benchmarks=fillrandom -use_direct_reads=true -num=40000000 -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=40000000 -use_existing_db -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Run read tests with differnt cache setting:
T2_3:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_3 -duration=1800 &
T2_4:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_4 -duration=1800 &
For T2_3 and T2_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T2_3 | T2_3 after mem defrag | T2_4 | T2_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8425 | 8093 | 5426 | 5149 |
| available (MB) | 8489 | 8138 | 5435 | 5158 |
| external fragmentation rate | 0.008 | 0.0055 | 0.0017 | 0.0017 |
| resident (MB) | 8676 | 8392 | 5541 | 5321 |
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10287
Test Plan: Unit tests.
Reviewed By: anand1976
Differential Revision: D37743362
Pulled By: gitbw95
fbshipit-source-id: 0010c5af08addeacc5ebbc4ffe5be882fb1d38ad
2 years ago
|
|
|
uncompressed = UncompressData(uncompression_info, (char*)merged_value.get(),
|
|
|
|
handle_value_charge, &uncompressed_size,
|
|
|
|
cache_options_.compress_format_version,
|
|
|
|
cache_options_.memory_allocator.get());
|
|
|
|
|
|
|
|
if (!uncompressed) {
|
|
|
|
cache_->Release(lru_handle, /* erase_if_last_ref */ true);
|
|
|
|
return handle;
|
|
|
|
}
|
|
|
|
s = create_cb(uncompressed.get(), uncompressed_size, &value, &charge);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!s.ok()) {
|
|
|
|
cache_->Release(lru_handle, /* erase_if_last_ref */ true);
|
|
|
|
return handle;
|
|
|
|
}
|
|
|
|
|
|
|
|
cache_->Release(lru_handle, /* erase_if_last_ref */ true);
|
|
|
|
handle.reset(new CompressedSecondaryCacheResultHandle(value, charge));
|
|
|
|
|
|
|
|
return handle;
|
|
|
|
}
|
|
|
|
|
|
|
|
Status CompressedSecondaryCache::Insert(const Slice& key, void* value,
|
|
|
|
const Cache::CacheItemHelper* helper) {
|
|
|
|
size_t size = (*helper->size_cb)(value);
|
|
|
|
CacheAllocationPtr ptr =
|
|
|
|
AllocateBlock(size, cache_options_.memory_allocator.get());
|
|
|
|
|
|
|
|
Status s = (*helper->saveto_cb)(value, 0, size, ptr.get());
|
|
|
|
if (!s.ok()) {
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
Slice val(ptr.get(), size);
|
|
|
|
|
|
|
|
std::string compressed_val;
|
|
|
|
if (cache_options_.compression_type != kNoCompression) {
|
|
|
|
CompressionOptions compression_opts;
|
|
|
|
CompressionContext compression_context(cache_options_.compression_type);
|
Split cache to minimize internal fragmentation (#10287)
Summary:
### **Summary:**
To minimize the internal fragmentation caused by the variable size of the compressed blocks, the original block is split according to the jemalloc bin size in `Insert()` and then merged back in `Lookup()`. Based on the analysis of the results of the following tests, from the overall internal fragmentation perspective, this PR does mitigate the internal fragmentation issue.
_Do more myshadow tests with the latest commit. I finished several myshadow AB Testing and the results are promising. For the config of 4GB primary cache and 3GB secondary cache, Jemalloc resident stats shows consistently ~0.15GB memory saving; the allocated and active stats show similar memory savings. The CPU usage is almost the same before and after this PR._
To evaluate the issue of memory fragmentations and the benefits of this PR, I conducted two sets of local tests as follows.
**T1**
Keys: 16 bytes each (+ 0 bytes user-defined timestamp)
Values: 100 bytes each (50 bytes after compression)
Entries: 90000000
RawSize: 9956.4 MB (estimated)
FileSize: 5664.8 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T1_3 | 4000 | 4000 |
| T1_4 | 2000 | 3000 |
Populate the DB:
./db_bench --benchmarks=fillrandom --num=90000000 -db=/mem_fragmentation/db_bench_1
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=90000000 -use_existing_db -db=/mem_fragmentation/db_bench_1
Run read tests with differnt cache setting:
T1_3:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_3_20220710 -duration=1800 &
T1_4:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_4_20220710 -duration=1800 &
For T1_3 and T1_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T1_3 | T1_3 after mem defrag | T1_4 | T1_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8728 | 8076 | 5518 | 5043 |
| available (MB) | 8753 | 8092 | 5536 | 5051 |
| external fragmentation rate | 0.003 | 0.002 | 0.003 | 0.0016 |
| resident (MB) | 8956 | 8365 | 5655 | 5235 |
**T2**
Keys: 32 bytes each (+ 0 bytes user-defined timestamp)
Values: 256 bytes each (128 bytes after compression)
Entries: 40000000
RawSize: 10986.3 MB (estimated)
FileSize: 6103.5 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T2_3 | 4000 | 4000 |
| T2_4 | 2000 | 3000 |
Create DB (10GB):
./db_bench -benchmarks=fillrandom -use_direct_reads=true -num=40000000 -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=40000000 -use_existing_db -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Run read tests with differnt cache setting:
T2_3:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_3 -duration=1800 &
T2_4:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_4 -duration=1800 &
For T2_3 and T2_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T2_3 | T2_3 after mem defrag | T2_4 | T2_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8425 | 8093 | 5426 | 5149 |
| available (MB) | 8489 | 8138 | 5435 | 5158 |
| external fragmentation rate | 0.008 | 0.0055 | 0.0017 | 0.0017 |
| resident (MB) | 8676 | 8392 | 5541 | 5321 |
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10287
Test Plan: Unit tests.
Reviewed By: anand1976
Differential Revision: D37743362
Pulled By: gitbw95
fbshipit-source-id: 0010c5af08addeacc5ebbc4ffe5be882fb1d38ad
2 years ago
|
|
|
uint64_t sample_for_compression{0};
|
|
|
|
CompressionInfo compression_info(
|
|
|
|
compression_opts, compression_context, CompressionDict::GetEmptyDict(),
|
|
|
|
cache_options_.compression_type, sample_for_compression);
|
|
|
|
|
|
|
|
bool success =
|
|
|
|
CompressData(val, compression_info,
|
|
|
|
cache_options_.compress_format_version, &compressed_val);
|
|
|
|
|
|
|
|
if (!success) {
|
|
|
|
return Status::Corruption("Error compressing value.");
|
|
|
|
}
|
|
|
|
|
|
|
|
val = Slice(compressed_val);
|
|
|
|
}
|
|
|
|
|
Split cache to minimize internal fragmentation (#10287)
Summary:
### **Summary:**
To minimize the internal fragmentation caused by the variable size of the compressed blocks, the original block is split according to the jemalloc bin size in `Insert()` and then merged back in `Lookup()`. Based on the analysis of the results of the following tests, from the overall internal fragmentation perspective, this PR does mitigate the internal fragmentation issue.
_Do more myshadow tests with the latest commit. I finished several myshadow AB Testing and the results are promising. For the config of 4GB primary cache and 3GB secondary cache, Jemalloc resident stats shows consistently ~0.15GB memory saving; the allocated and active stats show similar memory savings. The CPU usage is almost the same before and after this PR._
To evaluate the issue of memory fragmentations and the benefits of this PR, I conducted two sets of local tests as follows.
**T1**
Keys: 16 bytes each (+ 0 bytes user-defined timestamp)
Values: 100 bytes each (50 bytes after compression)
Entries: 90000000
RawSize: 9956.4 MB (estimated)
FileSize: 5664.8 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T1_3 | 4000 | 4000 |
| T1_4 | 2000 | 3000 |
Populate the DB:
./db_bench --benchmarks=fillrandom --num=90000000 -db=/mem_fragmentation/db_bench_1
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=90000000 -use_existing_db -db=/mem_fragmentation/db_bench_1
Run read tests with differnt cache setting:
T1_3:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_3_20220710 -duration=1800 &
T1_4:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_4_20220710 -duration=1800 &
For T1_3 and T1_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T1_3 | T1_3 after mem defrag | T1_4 | T1_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8728 | 8076 | 5518 | 5043 |
| available (MB) | 8753 | 8092 | 5536 | 5051 |
| external fragmentation rate | 0.003 | 0.002 | 0.003 | 0.0016 |
| resident (MB) | 8956 | 8365 | 5655 | 5235 |
**T2**
Keys: 32 bytes each (+ 0 bytes user-defined timestamp)
Values: 256 bytes each (128 bytes after compression)
Entries: 40000000
RawSize: 10986.3 MB (estimated)
FileSize: 6103.5 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T2_3 | 4000 | 4000 |
| T2_4 | 2000 | 3000 |
Create DB (10GB):
./db_bench -benchmarks=fillrandom -use_direct_reads=true -num=40000000 -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=40000000 -use_existing_db -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Run read tests with differnt cache setting:
T2_3:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_3 -duration=1800 &
T2_4:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_4 -duration=1800 &
For T2_3 and T2_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T2_3 | T2_3 after mem defrag | T2_4 | T2_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8425 | 8093 | 5426 | 5149 |
| available (MB) | 8489 | 8138 | 5435 | 5158 |
| external fragmentation rate | 0.008 | 0.0055 | 0.0017 | 0.0017 |
| resident (MB) | 8676 | 8392 | 5541 | 5321 |
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10287
Test Plan: Unit tests.
Reviewed By: anand1976
Differential Revision: D37743362
Pulled By: gitbw95
fbshipit-source-id: 0010c5af08addeacc5ebbc4ffe5be882fb1d38ad
2 years ago
|
|
|
size_t charge{0};
|
|
|
|
CacheValueChunk* value_chunks_head =
|
|
|
|
SplitValueIntoChunks(val, cache_options_.compression_type, charge);
|
|
|
|
return cache_->Insert(key, value_chunks_head, charge, DeletionCallback);
|
|
|
|
}
|
|
|
|
|
|
|
|
void CompressedSecondaryCache::Erase(const Slice& key) { cache_->Erase(key); }
|
|
|
|
|
|
|
|
std::string CompressedSecondaryCache::GetPrintableOptions() const {
|
|
|
|
std::string ret;
|
|
|
|
ret.reserve(20000);
|
Split cache to minimize internal fragmentation (#10287)
Summary:
### **Summary:**
To minimize the internal fragmentation caused by the variable size of the compressed blocks, the original block is split according to the jemalloc bin size in `Insert()` and then merged back in `Lookup()`. Based on the analysis of the results of the following tests, from the overall internal fragmentation perspective, this PR does mitigate the internal fragmentation issue.
_Do more myshadow tests with the latest commit. I finished several myshadow AB Testing and the results are promising. For the config of 4GB primary cache and 3GB secondary cache, Jemalloc resident stats shows consistently ~0.15GB memory saving; the allocated and active stats show similar memory savings. The CPU usage is almost the same before and after this PR._
To evaluate the issue of memory fragmentations and the benefits of this PR, I conducted two sets of local tests as follows.
**T1**
Keys: 16 bytes each (+ 0 bytes user-defined timestamp)
Values: 100 bytes each (50 bytes after compression)
Entries: 90000000
RawSize: 9956.4 MB (estimated)
FileSize: 5664.8 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T1_3 | 4000 | 4000 |
| T1_4 | 2000 | 3000 |
Populate the DB:
./db_bench --benchmarks=fillrandom --num=90000000 -db=/mem_fragmentation/db_bench_1
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=90000000 -use_existing_db -db=/mem_fragmentation/db_bench_1
Run read tests with differnt cache setting:
T1_3:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_3_20220710 -duration=1800 &
T1_4:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_4_20220710 -duration=1800 &
For T1_3 and T1_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T1_3 | T1_3 after mem defrag | T1_4 | T1_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8728 | 8076 | 5518 | 5043 |
| available (MB) | 8753 | 8092 | 5536 | 5051 |
| external fragmentation rate | 0.003 | 0.002 | 0.003 | 0.0016 |
| resident (MB) | 8956 | 8365 | 5655 | 5235 |
**T2**
Keys: 32 bytes each (+ 0 bytes user-defined timestamp)
Values: 256 bytes each (128 bytes after compression)
Entries: 40000000
RawSize: 10986.3 MB (estimated)
FileSize: 6103.5 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T2_3 | 4000 | 4000 |
| T2_4 | 2000 | 3000 |
Create DB (10GB):
./db_bench -benchmarks=fillrandom -use_direct_reads=true -num=40000000 -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=40000000 -use_existing_db -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Run read tests with differnt cache setting:
T2_3:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_3 -duration=1800 &
T2_4:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_4 -duration=1800 &
For T2_3 and T2_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T2_3 | T2_3 after mem defrag | T2_4 | T2_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8425 | 8093 | 5426 | 5149 |
| available (MB) | 8489 | 8138 | 5435 | 5158 |
| external fragmentation rate | 0.008 | 0.0055 | 0.0017 | 0.0017 |
| resident (MB) | 8676 | 8392 | 5541 | 5321 |
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10287
Test Plan: Unit tests.
Reviewed By: anand1976
Differential Revision: D37743362
Pulled By: gitbw95
fbshipit-source-id: 0010c5af08addeacc5ebbc4ffe5be882fb1d38ad
2 years ago
|
|
|
const int kBufferSize{200};
|
|
|
|
char buffer[kBufferSize];
|
|
|
|
ret.append(cache_->GetPrintableOptions());
|
|
|
|
snprintf(buffer, kBufferSize, " compression_type : %s\n",
|
|
|
|
CompressionTypeToString(cache_options_.compression_type).c_str());
|
|
|
|
ret.append(buffer);
|
|
|
|
snprintf(buffer, kBufferSize, " compress_format_version : %d\n",
|
|
|
|
cache_options_.compress_format_version);
|
|
|
|
ret.append(buffer);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
Split cache to minimize internal fragmentation (#10287)
Summary:
### **Summary:**
To minimize the internal fragmentation caused by the variable size of the compressed blocks, the original block is split according to the jemalloc bin size in `Insert()` and then merged back in `Lookup()`. Based on the analysis of the results of the following tests, from the overall internal fragmentation perspective, this PR does mitigate the internal fragmentation issue.
_Do more myshadow tests with the latest commit. I finished several myshadow AB Testing and the results are promising. For the config of 4GB primary cache and 3GB secondary cache, Jemalloc resident stats shows consistently ~0.15GB memory saving; the allocated and active stats show similar memory savings. The CPU usage is almost the same before and after this PR._
To evaluate the issue of memory fragmentations and the benefits of this PR, I conducted two sets of local tests as follows.
**T1**
Keys: 16 bytes each (+ 0 bytes user-defined timestamp)
Values: 100 bytes each (50 bytes after compression)
Entries: 90000000
RawSize: 9956.4 MB (estimated)
FileSize: 5664.8 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T1_3 | 4000 | 4000 |
| T1_4 | 2000 | 3000 |
Populate the DB:
./db_bench --benchmarks=fillrandom --num=90000000 -db=/mem_fragmentation/db_bench_1
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=90000000 -use_existing_db -db=/mem_fragmentation/db_bench_1
Run read tests with differnt cache setting:
T1_3:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_3_20220710 -duration=1800 &
T1_4:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_4_20220710 -duration=1800 &
For T1_3 and T1_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T1_3 | T1_3 after mem defrag | T1_4 | T1_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8728 | 8076 | 5518 | 5043 |
| available (MB) | 8753 | 8092 | 5536 | 5051 |
| external fragmentation rate | 0.003 | 0.002 | 0.003 | 0.0016 |
| resident (MB) | 8956 | 8365 | 5655 | 5235 |
**T2**
Keys: 32 bytes each (+ 0 bytes user-defined timestamp)
Values: 256 bytes each (128 bytes after compression)
Entries: 40000000
RawSize: 10986.3 MB (estimated)
FileSize: 6103.5 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T2_3 | 4000 | 4000 |
| T2_4 | 2000 | 3000 |
Create DB (10GB):
./db_bench -benchmarks=fillrandom -use_direct_reads=true -num=40000000 -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=40000000 -use_existing_db -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Run read tests with differnt cache setting:
T2_3:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_3 -duration=1800 &
T2_4:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_4 -duration=1800 &
For T2_3 and T2_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T2_3 | T2_3 after mem defrag | T2_4 | T2_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8425 | 8093 | 5426 | 5149 |
| available (MB) | 8489 | 8138 | 5435 | 5158 |
| external fragmentation rate | 0.008 | 0.0055 | 0.0017 | 0.0017 |
| resident (MB) | 8676 | 8392 | 5541 | 5321 |
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10287
Test Plan: Unit tests.
Reviewed By: anand1976
Differential Revision: D37743362
Pulled By: gitbw95
fbshipit-source-id: 0010c5af08addeacc5ebbc4ffe5be882fb1d38ad
2 years ago
|
|
|
CompressedSecondaryCache::CacheValueChunk*
|
|
|
|
CompressedSecondaryCache::SplitValueIntoChunks(
|
|
|
|
const Slice& value, const CompressionType compression_type,
|
|
|
|
size_t& charge) {
|
|
|
|
assert(!value.empty());
|
|
|
|
const char* src_ptr = value.data();
|
|
|
|
size_t src_size{value.size()};
|
|
|
|
|
|
|
|
CacheValueChunk dummy_head = CacheValueChunk();
|
|
|
|
CacheValueChunk* current_chunk = &dummy_head;
|
|
|
|
// Do not split when value size is large or there is no compression.
|
|
|
|
size_t predicted_chunk_size{0};
|
|
|
|
size_t actual_chunk_size{0};
|
|
|
|
size_t tmp_size{0};
|
|
|
|
while (src_size > 0) {
|
|
|
|
predicted_chunk_size = sizeof(CacheValueChunk) - 1 + src_size;
|
|
|
|
auto upper =
|
|
|
|
std::upper_bound(malloc_bin_sizes_.begin(), malloc_bin_sizes_.end(),
|
|
|
|
predicted_chunk_size);
|
|
|
|
// Do not split when value size is too small, too large, close to a bin
|
|
|
|
// size, or there is no compression.
|
|
|
|
if (upper == malloc_bin_sizes_.begin() ||
|
|
|
|
upper == malloc_bin_sizes_.end() ||
|
|
|
|
*upper - predicted_chunk_size < malloc_bin_sizes_.front() ||
|
|
|
|
compression_type == kNoCompression) {
|
|
|
|
tmp_size = predicted_chunk_size;
|
|
|
|
} else {
|
|
|
|
tmp_size = *(--upper);
|
|
|
|
}
|
|
|
|
|
|
|
|
CacheValueChunk* new_chunk =
|
|
|
|
reinterpret_cast<CacheValueChunk*>(new char[tmp_size]);
|
|
|
|
current_chunk->next = new_chunk;
|
Split cache to minimize internal fragmentation (#10287)
Summary:
### **Summary:**
To minimize the internal fragmentation caused by the variable size of the compressed blocks, the original block is split according to the jemalloc bin size in `Insert()` and then merged back in `Lookup()`. Based on the analysis of the results of the following tests, from the overall internal fragmentation perspective, this PR does mitigate the internal fragmentation issue.
_Do more myshadow tests with the latest commit. I finished several myshadow AB Testing and the results are promising. For the config of 4GB primary cache and 3GB secondary cache, Jemalloc resident stats shows consistently ~0.15GB memory saving; the allocated and active stats show similar memory savings. The CPU usage is almost the same before and after this PR._
To evaluate the issue of memory fragmentations and the benefits of this PR, I conducted two sets of local tests as follows.
**T1**
Keys: 16 bytes each (+ 0 bytes user-defined timestamp)
Values: 100 bytes each (50 bytes after compression)
Entries: 90000000
RawSize: 9956.4 MB (estimated)
FileSize: 5664.8 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T1_3 | 4000 | 4000 |
| T1_4 | 2000 | 3000 |
Populate the DB:
./db_bench --benchmarks=fillrandom --num=90000000 -db=/mem_fragmentation/db_bench_1
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=90000000 -use_existing_db -db=/mem_fragmentation/db_bench_1
Run read tests with differnt cache setting:
T1_3:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_3_20220710 -duration=1800 &
T1_4:
MALLOC_CONF="prof:true,prof_stats:true" ../rocksdb/db_bench --benchmarks=seekrandom --threads=16 --num=90000000 -use_existing_db --benchmark_write_rate_limit=52000000 -use_direct_reads --cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -db=/mem_fragmentation/db_bench_1 --print_malloc_stats=true > ~/temp/mem_frag/20220710/jemalloc_stats_json_T1_4_20220710 -duration=1800 &
For T1_3 and T1_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T1_3 | T1_3 after mem defrag | T1_4 | T1_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8728 | 8076 | 5518 | 5043 |
| available (MB) | 8753 | 8092 | 5536 | 5051 |
| external fragmentation rate | 0.003 | 0.002 | 0.003 | 0.0016 |
| resident (MB) | 8956 | 8365 | 5655 | 5235 |
**T2**
Keys: 32 bytes each (+ 0 bytes user-defined timestamp)
Values: 256 bytes each (128 bytes after compression)
Entries: 40000000
RawSize: 10986.3 MB (estimated)
FileSize: 6103.5 MB (estimated)
| Test Name | Primary Cache Size (MB) | Compressed Secondary Cache Size (MB) |
| - | - | - |
| T2_3 | 4000 | 4000 |
| T2_4 | 2000 | 3000 |
Create DB (10GB):
./db_bench -benchmarks=fillrandom -use_direct_reads=true -num=40000000 -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Overwrite it to a stable state:
./db_bench --benchmarks=overwrite --num=40000000 -use_existing_db -key_size=32 -value_size=256 -db=/mem_fragmentation/db_bench_2
Run read tests with differnt cache setting:
T2_3:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=4000000000 -compressed_secondary_cache_size=4000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_3 -duration=1800 &
T2_4:
MALLOC_CONF="prof:true,prof_stats:true" ./db_bench --benchmarks="mixgraph" -use_direct_io_for_flush_and_compaction=true -use_direct_reads=true -cache_size=2000000000 -compressed_secondary_cache_size=3000000000 -use_compressed_secondary_cache -keyrange_dist_a=14.18 -keyrange_dist_b=-2.917 -keyrange_dist_c=0.0164 -keyrange_dist_d=-0.08082 -keyrange_num=30 -value_k=0.2615 -value_sigma=25.45 -iter_k=2.517 -iter_sigma=14.236 -mix_get_ratio=0.85 -mix_put_ratio=0.14 -mix_seek_ratio=0.01 -sine_mix_rate_interval_milliseconds=5000 -sine_a=1000 -sine_b=0.000073 -sine_d=400000 -reads=80000000 -num=40000000 -key_size=32 -value_size=256 -use_existing_db=true -db=/mem_fragmentation/db_bench_2 --print_malloc_stats=true > ~/temp/mem_frag/jemalloc_stats_T2_4 -duration=1800 &
For T2_3 and T2_4, I also conducted the tests before and after this PR. The following table show the important jemalloc stats.
| Test Name | T2_3 | T2_3 after mem defrag | T2_4 | T2_4 after mem defrag |
| - | - | - | - | - |
| allocated (MB) | 8425 | 8093 | 5426 | 5149 |
| available (MB) | 8489 | 8138 | 5435 | 5158 |
| external fragmentation rate | 0.008 | 0.0055 | 0.0017 | 0.0017 |
| resident (MB) | 8676 | 8392 | 5541 | 5321 |
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10287
Test Plan: Unit tests.
Reviewed By: anand1976
Differential Revision: D37743362
Pulled By: gitbw95
fbshipit-source-id: 0010c5af08addeacc5ebbc4ffe5be882fb1d38ad
2 years ago
|
|
|
current_chunk = current_chunk->next;
|
|
|
|
actual_chunk_size = tmp_size - sizeof(CacheValueChunk) + 1;
|
|
|
|
memcpy(current_chunk->data, src_ptr, actual_chunk_size);
|
|
|
|
current_chunk->size = actual_chunk_size;
|
|
|
|
src_ptr += actual_chunk_size;
|
|
|
|
src_size -= actual_chunk_size;
|
|
|
|
charge += tmp_size;
|
|
|
|
}
|
|
|
|
current_chunk->next = nullptr;
|
|
|
|
|
|
|
|
return dummy_head.next;
|
|
|
|
}
|
|
|
|
|
|
|
|
CacheAllocationPtr CompressedSecondaryCache::MergeChunksIntoValue(
|
|
|
|
const void* chunks_head, size_t& charge) {
|
|
|
|
const CacheValueChunk* head =
|
|
|
|
reinterpret_cast<const CacheValueChunk*>(chunks_head);
|
|
|
|
const CacheValueChunk* current_chunk = head;
|
|
|
|
charge = 0;
|
|
|
|
while (current_chunk != nullptr) {
|
|
|
|
charge += current_chunk->size;
|
|
|
|
current_chunk = current_chunk->next;
|
|
|
|
}
|
|
|
|
|
|
|
|
CacheAllocationPtr ptr =
|
|
|
|
AllocateBlock(charge, cache_options_.memory_allocator.get());
|
|
|
|
current_chunk = head;
|
|
|
|
size_t pos{0};
|
|
|
|
while (current_chunk != nullptr) {
|
|
|
|
memcpy(ptr.get() + pos, current_chunk->data, current_chunk->size);
|
|
|
|
pos += current_chunk->size;
|
|
|
|
current_chunk = current_chunk->next;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ptr;
|
|
|
|
}
|
|
|
|
|
|
|
|
void CompressedSecondaryCache::DeletionCallback(const Slice& /*key*/,
|
|
|
|
void* obj) {
|
|
|
|
CacheValueChunk* chunks_head = reinterpret_cast<CacheValueChunk*>(obj);
|
|
|
|
while (chunks_head != nullptr) {
|
|
|
|
CacheValueChunk* tmp_chunk = chunks_head;
|
|
|
|
chunks_head = chunks_head->next;
|
|
|
|
tmp_chunk->Free();
|
|
|
|
}
|
|
|
|
obj = nullptr;
|
|
|
|
}
|
|
|
|
|
|
|
|
std::shared_ptr<SecondaryCache> NewCompressedSecondaryCache(
|
|
|
|
size_t capacity, int num_shard_bits, bool strict_capacity_limit,
|
|
|
|
double high_pri_pool_ratio,
|
|
|
|
std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
|
|
|
|
CacheMetadataChargePolicy metadata_charge_policy,
|
|
|
|
CompressionType compression_type, uint32_t compress_format_version,
|
|
|
|
double low_pri_pool_ratio) {
|
|
|
|
return std::make_shared<CompressedSecondaryCache>(
|
|
|
|
capacity, num_shard_bits, strict_capacity_limit, high_pri_pool_ratio,
|
|
|
|
low_pri_pool_ratio, memory_allocator, use_adaptive_mutex,
|
|
|
|
metadata_charge_policy, compression_type, compress_format_version);
|
|
|
|
}
|
|
|
|
|
|
|
|
std::shared_ptr<SecondaryCache> NewCompressedSecondaryCache(
|
|
|
|
const CompressedSecondaryCacheOptions& opts) {
|
|
|
|
// The secondary_cache is disabled for this LRUCache instance.
|
|
|
|
assert(opts.secondary_cache == nullptr);
|
|
|
|
return NewCompressedSecondaryCache(
|
|
|
|
opts.capacity, opts.num_shard_bits, opts.strict_capacity_limit,
|
|
|
|
opts.high_pri_pool_ratio, opts.memory_allocator, opts.use_adaptive_mutex,
|
|
|
|
opts.metadata_charge_policy, opts.compression_type,
|
|
|
|
opts.compress_format_version, opts.low_pri_pool_ratio);
|
|
|
|
}
|
|
|
|
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|