|
|
|
// 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 <string>
|
|
|
|
#include <vector>
|
|
|
|
|
|
|
|
#include "db/dbformat.h"
|
|
|
|
#include "options/db_options.h"
|
|
|
|
#include "rocksdb/options.h"
|
|
|
|
#include "util/compression.h"
|
|
|
|
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
|
|
|
|
// ImmutableCFOptions is a data struct used by RocksDB internal. It contains a
|
|
|
|
// subset of Options that should not be changed during the entire lifetime
|
|
|
|
// of DB. Raw pointers defined in this struct do not have ownership to the data
|
|
|
|
// they point to. Options contains std::shared_ptr to these data.
|
|
|
|
struct ImmutableCFOptions {
|
|
|
|
public:
|
|
|
|
static const char* kName() { return "ImmutableCFOptions"; }
|
|
|
|
explicit ImmutableCFOptions();
|
|
|
|
explicit ImmutableCFOptions(const ColumnFamilyOptions& cf_options);
|
|
|
|
|
|
|
|
CompactionStyle compaction_style;
|
|
|
|
|
|
|
|
CompactionPri compaction_pri;
|
|
|
|
|
|
|
|
const Comparator* user_comparator;
|
|
|
|
InternalKeyComparator internal_comparator; // Only in Immutable
|
|
|
|
|
|
|
|
std::shared_ptr<MergeOperator> merge_operator;
|
|
|
|
|
|
|
|
const CompactionFilter* compaction_filter;
|
|
|
|
|
|
|
|
std::shared_ptr<CompactionFilterFactory> compaction_filter_factory;
|
|
|
|
|
|
|
|
int min_write_buffer_number_to_merge;
|
|
|
|
|
|
|
|
int max_write_buffer_number_to_maintain;
|
|
|
|
|
Refactor trimming logic for immutable memtables (#5022)
Summary:
MyRocks currently sets `max_write_buffer_number_to_maintain` in order to maintain enough history for transaction conflict checking. The effectiveness of this approach depends on the size of memtables. When memtables are small, it may not keep enough history; when memtables are large, this may consume too much memory.
We are proposing a new way to configure memtable list history: by limiting the memory usage of immutable memtables. The new option is `max_write_buffer_size_to_maintain` and it will take precedence over the old `max_write_buffer_number_to_maintain` if they are both set to non-zero values. The new option accounts for the total memory usage of flushed immutable memtables and mutable memtable. When the total usage exceeds the limit, RocksDB may start dropping immutable memtables (which is also called trimming history), starting from the oldest one.
The semantics of the old option actually works both as an upper bound and lower bound. History trimming will start if number of immutable memtables exceeds the limit, but it will never go below (limit-1) due to history trimming.
In order the mimic the behavior with the new option, history trimming will stop if dropping the next immutable memtable causes the total memory usage go below the size limit. For example, assuming the size limit is set to 64MB, and there are 3 immutable memtables with sizes of 20, 30, 30. Although the total memory usage is 80MB > 64MB, dropping the oldest memtable will reduce the memory usage to 60MB < 64MB, so in this case no memtable will be dropped.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5022
Differential Revision: D14394062
Pulled By: miasantreble
fbshipit-source-id: 60457a509c6af89d0993f988c9b5c2aa9e45f5c5
5 years ago
|
|
|
int64_t max_write_buffer_size_to_maintain;
|
|
|
|
|
|
|
|
bool inplace_update_support;
|
|
|
|
|
|
|
|
UpdateStatus (*inplace_callback)(char* existing_value,
|
|
|
|
uint32_t* existing_value_size,
|
|
|
|
Slice delta_value,
|
|
|
|
std::string* merged_value);
|
|
|
|
|
|
|
|
std::shared_ptr<MemTableRepFactory> memtable_factory;
|
|
|
|
|
|
|
|
std::shared_ptr<TableFactory> table_factory;
|
|
|
|
|
|
|
|
Options::TablePropertiesCollectorFactories
|
|
|
|
table_properties_collector_factories;
|
|
|
|
|
|
|
|
// This options is required by PlainTableReader. May need to move it
|
|
|
|
// to PlainTableOptions just like bloom_bits_per_key
|
|
|
|
uint32_t bloom_locality;
|
|
|
|
|
|
|
|
bool level_compaction_dynamic_level_bytes;
|
|
|
|
|
Align compaction output file boundaries to the next level ones (#10655)
Summary:
Try to align the compaction output file boundaries to the next level ones
(grandparent level), to reduce the level compaction write-amplification.
In level compaction, there are "wasted" data at the beginning and end of the
output level files. Align the file boundary can avoid such "wasted" compaction.
With this PR, it tries to align the non-bottommost level file boundaries to its
next level ones. It may cut file when the file size is large enough (at least
50% of target_file_size) and not too large (2x target_file_size).
db_bench shows about 12.56% compaction reduction:
```
TEST_TMPDIR=/data/dbbench2 ./db_bench --benchmarks=fillrandom,readrandom -max_background_jobs=12 -num=400000000 -target_file_size_base=33554432
# baseline:
Flush(GB): cumulative 25.882, interval 7.216
Cumulative compaction: 285.90 GB write, 162.36 MB/s write, 269.68 GB read, 153.15 MB/s read, 2926.7 seconds
# with this change:
Flush(GB): cumulative 25.882, interval 7.753
Cumulative compaction: 249.97 GB write, 141.96 MB/s write, 233.74 GB read, 132.74 MB/s read, 2534.9 seconds
```
The compaction simulator shows a similar result (14% with 100G random data).
As a side effect, with this PR, the SST file size can exceed the
target_file_size, but is capped at 2x target_file_size. And there will be
smaller files. Here are file size statistics when loading 100GB with the target
file size 32MB:
```
baseline this_PR
count 1.656000e+03 1.705000e+03
mean 3.116062e+07 3.028076e+07
std 7.145242e+06 8.046139e+06
```
The feature is enabled by default, to revert to the old behavior disable it
with `AdvancedColumnFamilyOptions.level_compaction_dynamic_file_size = false`
Also includes https://github.com/facebook/rocksdb/issues/1963 to cut file before skippable grandparent file. Which is for
use case like user adding 2 or more non-overlapping data range at the same
time, it can reduce the overlapping of 2 datasets in the lower levels.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10655
Reviewed By: cbi42
Differential Revision: D39552321
Pulled By: jay-zhuang
fbshipit-source-id: 640d15f159ab0cd973f2426cfc3af266fc8bdde2
2 years ago
|
|
|
bool level_compaction_dynamic_file_size;
|
|
|
|
|
|
|
|
int num_levels;
|
|
|
|
|
|
|
|
bool optimize_filters_for_hits;
|
|
|
|
|
|
|
|
bool force_consistency_checks;
|
|
|
|
|
|
|
|
uint64_t preclude_last_level_data_seconds;
|
|
|
|
|
|
|
|
uint64_t preserve_internal_time_seconds;
|
|
|
|
|
|
|
|
std::shared_ptr<const SliceTransform>
|
|
|
|
memtable_insert_with_hint_prefix_extractor;
|
|
|
|
|
|
|
|
std::vector<DbPath> cf_paths;
|
Concurrent task limiter for compaction thread control (#4332)
Summary:
The PR is targeting to resolve the issue of:
https://github.com/facebook/rocksdb/issues/3972#issue-330771918
We have a rocksdb created with leveled-compaction with multiple column families (CFs), some of CFs are using HDD to store big and less frequently accessed data and others are using SSD.
When there are continuously write traffics going on to all CFs, the compaction thread pool is mostly occupied by those slow HDD compactions, which blocks fully utilize SSD bandwidth.
Since atomic write and transaction is needed across CFs, so splitting it to multiple rocksdb instance is not an option for us.
With the compaction thread control, we got 30%+ HDD write throughput gain, and also a lot smooth SSD write since less write stall happening.
ConcurrentTaskLimiter can be shared with multi-CFs across rocksdb instances, so the feature does not only work for multi-CFs scenarios, but also for multi-rocksdbs scenarios, who need disk IO resource control per tenant.
The usage is straight forward:
e.g.:
//
// Enable compaction thread limiter thru ColumnFamilyOptions
//
std::shared_ptr<ConcurrentTaskLimiter> ctl(NewConcurrentTaskLimiter("foo_limiter", 4));
Options options;
ColumnFamilyOptions cf_opt(options);
cf_opt.compaction_thread_limiter = ctl;
...
//
// Compaction thread limiter can be tuned or disabled on-the-fly
//
ctl->SetMaxOutstandingTask(12); // enlarge to 12 tasks
...
ctl->ResetMaxOutstandingTask(); // disable (bypass) thread limiter
ctl->SetMaxOutstandingTask(-1); // Same as above
...
ctl->SetMaxOutstandingTask(0); // full throttle (0 task)
//
// Sharing compaction thread limiter among CFs (to resolve multiple storage perf issue)
//
std::shared_ptr<ConcurrentTaskLimiter> ctl_ssd(NewConcurrentTaskLimiter("ssd_limiter", 8));
std::shared_ptr<ConcurrentTaskLimiter> ctl_hdd(NewConcurrentTaskLimiter("hdd_limiter", 4));
Options options;
ColumnFamilyOptions cf_opt_ssd1(options);
ColumnFamilyOptions cf_opt_ssd2(options);
ColumnFamilyOptions cf_opt_hdd1(options);
ColumnFamilyOptions cf_opt_hdd2(options);
ColumnFamilyOptions cf_opt_hdd3(options);
// SSD CFs
cf_opt_ssd1.compaction_thread_limiter = ctl_ssd;
cf_opt_ssd2.compaction_thread_limiter = ctl_ssd;
// HDD CFs
cf_opt_hdd1.compaction_thread_limiter = ctl_hdd;
cf_opt_hdd2.compaction_thread_limiter = ctl_hdd;
cf_opt_hdd3.compaction_thread_limiter = ctl_hdd;
...
//
// The limiter is disabled by default (or set to nullptr explicitly)
//
Options options;
ColumnFamilyOptions cf_opt(options);
cf_opt.compaction_thread_limiter = nullptr;
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4332
Differential Revision: D13226590
Pulled By: siying
fbshipit-source-id: 14307aec55b8bd59c8223d04aa6db3c03d1b0c1d
6 years ago
|
|
|
|
|
|
|
std::shared_ptr<ConcurrentTaskLimiter> compaction_thread_limiter;
|
|
|
|
|
|
|
|
std::shared_ptr<SstPartitionerFactory> sst_partitioner_factory;
|
|
|
|
|
|
|
|
std::shared_ptr<Cache> blob_cache;
|
|
|
|
|
|
|
|
bool persist_user_defined_timestamps;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct ImmutableOptions : public ImmutableDBOptions, public ImmutableCFOptions {
|
|
|
|
explicit ImmutableOptions();
|
|
|
|
explicit ImmutableOptions(const Options& options);
|
|
|
|
|
|
|
|
ImmutableOptions(const DBOptions& db_options,
|
|
|
|
const ColumnFamilyOptions& cf_options);
|
|
|
|
|
|
|
|
ImmutableOptions(const ImmutableDBOptions& db_options,
|
|
|
|
const ImmutableCFOptions& cf_options);
|
|
|
|
|
|
|
|
ImmutableOptions(const DBOptions& db_options,
|
|
|
|
const ImmutableCFOptions& cf_options);
|
|
|
|
|
|
|
|
ImmutableOptions(const ImmutableDBOptions& db_options,
|
|
|
|
const ColumnFamilyOptions& cf_options);
|
|
|
|
};
|
|
|
|
|
|
|
|
struct MutableCFOptions {
|
|
|
|
static const char* kName() { return "MutableCFOptions"; }
|
|
|
|
explicit MutableCFOptions(const ColumnFamilyOptions& options)
|
Add options.compaction_measure_io_stats to print write I/O stats in compactions
Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:
2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}
Add two more counters in iostats_context.
Also add a parameter of db_bench.
Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44115
9 years ago
|
|
|
: write_buffer_size(options.write_buffer_size),
|
|
|
|
max_write_buffer_number(options.max_write_buffer_number),
|
|
|
|
arena_block_size(options.arena_block_size),
|
|
|
|
memtable_prefix_bloom_size_ratio(
|
|
|
|
options.memtable_prefix_bloom_size_ratio),
|
|
|
|
memtable_whole_key_filtering(options.memtable_whole_key_filtering),
|
|
|
|
memtable_huge_page_size(options.memtable_huge_page_size),
|
Add options.compaction_measure_io_stats to print write I/O stats in compactions
Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:
2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}
Add two more counters in iostats_context.
Also add a parameter of db_bench.
Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44115
9 years ago
|
|
|
max_successive_merges(options.max_successive_merges),
|
|
|
|
inplace_update_num_locks(options.inplace_update_num_locks),
|
|
|
|
prefix_extractor(options.prefix_extractor),
|
|
|
|
experimental_mempurge_threshold(
|
|
|
|
options.experimental_mempurge_threshold),
|
Add options.compaction_measure_io_stats to print write I/O stats in compactions
Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:
2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}
Add two more counters in iostats_context.
Also add a parameter of db_bench.
Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44115
9 years ago
|
|
|
disable_auto_compactions(options.disable_auto_compactions),
|
|
|
|
soft_pending_compaction_bytes_limit(
|
|
|
|
options.soft_pending_compaction_bytes_limit),
|
|
|
|
hard_pending_compaction_bytes_limit(
|
|
|
|
options.hard_pending_compaction_bytes_limit),
|
Add options.compaction_measure_io_stats to print write I/O stats in compactions
Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:
2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}
Add two more counters in iostats_context.
Also add a parameter of db_bench.
Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44115
9 years ago
|
|
|
level0_file_num_compaction_trigger(
|
|
|
|
options.level0_file_num_compaction_trigger),
|
|
|
|
level0_slowdown_writes_trigger(options.level0_slowdown_writes_trigger),
|
|
|
|
level0_stop_writes_trigger(options.level0_stop_writes_trigger),
|
|
|
|
max_compaction_bytes(options.max_compaction_bytes),
|
Ignore max_compaction_bytes for compaction input that are within output key-range (#10835)
Summary:
When picking compaction input files, we sometimes stop picking a file that is fully included in the output key-range due to hitting max_compaction_bytes. Including these input files can potentially reduce WA at the expense of larger compactions. Larger compaction should be fine as files from input level are usually 10X smaller than files from output level. This PR adds a mutable CF option `ignore_max_compaction_bytes_for_input` that is enabled by default. We can remove this option once we are sure it is safe.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10835
Test Plan:
- CI, a unit test on max_compaction_bytes fails before turning this flag off.
- Benchmark does not show much difference in WA: `./db_bench --benchmarks=fillrandom,waitforcompaction,stats,levelstats -max_background_jobs=12 -num=2000000000 -target_file_size_base=33554432 --write_buffer_size=33554432`
```
main:
** Compaction Stats [default] **
Level Files Size Score Read(GB) Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) CompMergeCPU(sec) Comp(cnt) Avg(sec) KeyIn KeyDrop Rblob(GB) Wblob(GB)
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
L0 3/0 91.59 MB 0.8 70.9 0.0 70.9 200.8 129.9 0.0 1.5 25.2 71.2 2886.55 2463.45 9725 0.297 1093M 254K 0.0 0.0
L1 9/0 248.03 MB 1.0 392.0 129.8 262.2 391.7 129.5 0.0 3.0 69.0 68.9 5821.71 5536.90 804 7.241 6029M 5814K 0.0 0.0
L2 87/0 2.50 GB 1.0 537.0 128.5 408.5 533.8 125.2 0.7 4.2 69.5 69.1 7912.24 7323.70 4417 1.791 8299M 36M 0.0 0.0
L3 836/0 24.99 GB 1.0 616.9 118.3 498.7 594.5 95.8 5.2 5.0 66.9 64.5 9442.38 8490.28 4204 2.246 9749M 306M 0.0 0.0
L4 2355/0 62.95 GB 0.3 67.3 37.1 30.2 54.2 24.0 38.9 1.5 72.2 58.2 954.37 821.18 917 1.041 1076M 173M 0.0 0.0
Sum 3290/0 90.77 GB 0.0 1684.2 413.7 1270.5 1775.0 504.5 44.9 13.7 63.8 67.3 27017.25 24635.52 20067 1.346 26G 522M 0.0 0.0
Cumulative compaction: 1774.96 GB write, 154.29 MB/s write, 1684.19 GB read, 146.40 MB/s read, 27017.3 seconds
This PR:
** Compaction Stats [default] **
Level Files Size Score Read(GB) Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) CompMergeCPU(sec) Comp(cnt) Avg(sec) KeyIn KeyDrop Rblob(GB) Wblob(GB)
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
L0 3/0 45.71 MB 0.8 72.9 0.0 72.9 202.8 129.9 0.0 1.6 25.4 70.7 2938.16 2510.36 9741 0.302 1124M 265K 0.0 0.0
L1 8/0 234.54 MB 0.9 384.5 129.8 254.7 384.2 129.6 0.0 3.0 69.0 68.9 5708.08 5424.43 791 7.216 5913M 5753K 0.0 0.0
L2 84/0 2.47 GB 1.0 543.1 128.6 414.5 539.9 125.4 0.7 4.2 69.6 69.2 7989.31 7403.13 4418 1.808 8393M 36M 0.0 0.0
L3 839/0 24.96 GB 1.0 615.6 118.4 497.2 593.2 96.0 5.1 5.0 66.6 64.1 9471.23 8489.31 4193 2.259 9726M 306M 0.0 0.0
L4 2360/0 63.04 GB 0.3 67.6 37.3 30.3 54.4 24.1 38.9 1.5 71.5 57.6 967.30 827.99 907 1.066 1080M 173M 0.0 0.0
Sum 3294/0 90.75 GB 0.0 1683.8 414.2 1269.6 1774.5 504.9 44.8 13.7 63.7 67.1 27074.08 24655.22 20050 1.350 26G 522M 0.0 0.0
Cumulative compaction: 1774.52 GB write, 157.09 MB/s write, 1683.77 GB read, 149.06 MB/s read, 27074.1 seconds
```
Reviewed By: ajkr
Differential Revision: D40518319
Pulled By: cbi42
fbshipit-source-id: f4ea614bc0ebefe007ffaf05bb9aec9a8ca25b60
2 years ago
|
|
|
ignore_max_compaction_bytes_for_input(
|
|
|
|
options.ignore_max_compaction_bytes_for_input),
|
Add options.compaction_measure_io_stats to print write I/O stats in compactions
Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:
2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}
Add two more counters in iostats_context.
Also add a parameter of db_bench.
Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44115
9 years ago
|
|
|
target_file_size_base(options.target_file_size_base),
|
|
|
|
target_file_size_multiplier(options.target_file_size_multiplier),
|
|
|
|
max_bytes_for_level_base(options.max_bytes_for_level_base),
|
|
|
|
max_bytes_for_level_multiplier(options.max_bytes_for_level_multiplier),
|
|
|
|
ttl(options.ttl),
|
Periodic Compactions (#5166)
Summary:
Introducing Periodic Compactions.
This feature allows all the files in a CF to be periodically compacted. It could help in catching any corruptions that could creep into the DB proactively as every file is constantly getting re-compacted. And also, of course, it helps to cleanup data older than certain threshold.
- Introduced a new option `periodic_compaction_time` to control how long a file can live without being compacted in a CF.
- This works across all levels.
- The files are put in the same level after going through the compaction. (Related files in the same level are picked up as `ExpandInputstoCleanCut` is used).
- Compaction filters, if any, are invoked as usual.
- A new table property, `file_creation_time`, is introduced to implement this feature. This property is set to the time at which the SST file was created (and that time is given by the underlying Env/OS).
This feature can be enabled on its own, or in conjunction with `ttl`. It is possible to set a different time threshold for the bottom level when used in conjunction with ttl. Since `ttl` works only on 0 to last but one levels, you could set `ttl` to, say, 1 day, and `periodic_compaction_time` to, say, 7 days. Since `ttl < periodic_compaction_time` all files in last but one levels keep getting picked up based on ttl, and almost never based on periodic_compaction_time. The files in the bottom level get picked up for compaction based on `periodic_compaction_time`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5166
Differential Revision: D14884441
Pulled By: sagar0
fbshipit-source-id: 408426cbacb409c06386a98632dcf90bfa1bda47
6 years ago
|
|
|
periodic_compaction_seconds(options.periodic_compaction_seconds),
|
Add options.compaction_measure_io_stats to print write I/O stats in compactions
Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:
2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}
Add two more counters in iostats_context.
Also add a parameter of db_bench.
Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44115
9 years ago
|
|
|
max_bytes_for_level_multiplier_additional(
|
|
|
|
options.max_bytes_for_level_multiplier_additional),
|
|
|
|
compaction_options_fifo(options.compaction_options_fifo),
|
|
|
|
compaction_options_universal(options.compaction_options_universal),
|
|
|
|
enable_blob_files(options.enable_blob_files),
|
|
|
|
min_blob_size(options.min_blob_size),
|
|
|
|
blob_file_size(options.blob_file_size),
|
|
|
|
blob_compression_type(options.blob_compression_type),
|
|
|
|
enable_blob_garbage_collection(options.enable_blob_garbage_collection),
|
|
|
|
blob_garbage_collection_age_cutoff(
|
|
|
|
options.blob_garbage_collection_age_cutoff),
|
Make it possible to force the garbage collection of the oldest blob files (#8994)
Summary:
The current BlobDB garbage collection logic works by relocating the valid
blobs from the oldest blob files as they are encountered during compaction,
and cleaning up blob files once they contain nothing but garbage. However,
with sufficiently skewed workloads, it is theoretically possible to end up in a
situation when few or no compactions get scheduled for the SST files that contain
references to the oldest blob files, which can lead to increased space amp due
to the lack of GC.
In order to efficiently handle such workloads, the patch adds a new BlobDB
configuration option called `blob_garbage_collection_force_threshold`,
which signals to BlobDB to schedule targeted compactions for the SST files
that keep alive the oldest batch of blob files if the overall ratio of garbage in
the given blob files meets the threshold *and* all the given blob files are
eligible for GC based on `blob_garbage_collection_age_cutoff`. (For example,
if the new option is set to 0.9, targeted compactions will get scheduled if the
sum of garbage bytes meets or exceeds 90% of the sum of total bytes in the
oldest blob files, assuming all affected blob files are below the age-based cutoff.)
The net result of these targeted compactions is that the valid blobs in the oldest
blob files are relocated and the oldest blob files themselves cleaned up (since
*all* SST files that rely on them get compacted away).
These targeted compactions are similar to periodic compactions in the sense
that they force certain SST files that otherwise would not get picked up to undergo
compaction and also in the sense that instead of merging files from multiple levels,
they target a single file. (Note: such compactions might still include neighboring files
from the same level due to the need of having a "clean cut" boundary but they never
include any files from any other level.)
This functionality is currently only supported with the leveled compaction style
and is inactive by default (since the default value is set to 1.0, i.e. 100%).
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8994
Test Plan: Ran `make check` and tested using `db_bench` and the stress/crash tests.
Reviewed By: riversand963
Differential Revision: D31489850
Pulled By: ltamasi
fbshipit-source-id: 44057d511726a0e2a03c5d9313d7511b3f0c4eab
3 years ago
|
|
|
blob_garbage_collection_force_threshold(
|
|
|
|
options.blob_garbage_collection_force_threshold),
|
|
|
|
blob_compaction_readahead_size(options.blob_compaction_readahead_size),
|
|
|
|
blob_file_starting_level(options.blob_file_starting_level),
|
|
|
|
prepopulate_blob_cache(options.prepopulate_blob_cache),
|
Add options.compaction_measure_io_stats to print write I/O stats in compactions
Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:
2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}
Add two more counters in iostats_context.
Also add a parameter of db_bench.
Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44115
9 years ago
|
|
|
max_sequential_skip_in_iterations(
|
|
|
|
options.max_sequential_skip_in_iterations),
|
|
|
|
check_flush_compaction_key_order(
|
|
|
|
options.check_flush_compaction_key_order),
|
Add options.compaction_measure_io_stats to print write I/O stats in compactions
Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:
2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}
Add two more counters in iostats_context.
Also add a parameter of db_bench.
Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44115
9 years ago
|
|
|
paranoid_file_checks(options.paranoid_file_checks),
|
|
|
|
report_bg_io_stats(options.report_bg_io_stats),
|
|
|
|
compression(options.compression),
|
|
|
|
bottommost_compression(options.bottommost_compression),
|
|
|
|
compression_opts(options.compression_opts),
|
|
|
|
bottommost_compression_opts(options.bottommost_compression_opts),
|
|
|
|
last_level_temperature(options.last_level_temperature ==
|
|
|
|
Temperature::kUnknown
|
|
|
|
? options.bottommost_temperature
|
|
|
|
: options.last_level_temperature),
|
|
|
|
memtable_protection_bytes_per_key(
|
|
|
|
options.memtable_protection_bytes_per_key),
|
|
|
|
block_protection_bytes_per_key(options.block_protection_bytes_per_key),
|
|
|
|
sample_for_compression(
|
|
|
|
options.sample_for_compression), // TODO: is 0 fine here?
|
|
|
|
compression_per_level(options.compression_per_level) {
|
|
|
|
RefreshDerivedOptions(options.num_levels, options.compaction_style);
|
|
|
|
}
|
|
|
|
|
|
|
|
MutableCFOptions()
|
Add options.compaction_measure_io_stats to print write I/O stats in compactions
Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:
2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}
Add two more counters in iostats_context.
Also add a parameter of db_bench.
Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44115
9 years ago
|
|
|
: write_buffer_size(0),
|
|
|
|
max_write_buffer_number(0),
|
|
|
|
arena_block_size(0),
|
|
|
|
memtable_prefix_bloom_size_ratio(0),
|
|
|
|
memtable_whole_key_filtering(false),
|
|
|
|
memtable_huge_page_size(0),
|
Add options.compaction_measure_io_stats to print write I/O stats in compactions
Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:
2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}
Add two more counters in iostats_context.
Also add a parameter of db_bench.
Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44115
9 years ago
|
|
|
max_successive_merges(0),
|
|
|
|
inplace_update_num_locks(0),
|
|
|
|
prefix_extractor(nullptr),
|
|
|
|
experimental_mempurge_threshold(0.0),
|
Add options.compaction_measure_io_stats to print write I/O stats in compactions
Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:
2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}
Add two more counters in iostats_context.
Also add a parameter of db_bench.
Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44115
9 years ago
|
|
|
disable_auto_compactions(false),
|
|
|
|
soft_pending_compaction_bytes_limit(0),
|
|
|
|
hard_pending_compaction_bytes_limit(0),
|
Add options.compaction_measure_io_stats to print write I/O stats in compactions
Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:
2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}
Add two more counters in iostats_context.
Also add a parameter of db_bench.
Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44115
9 years ago
|
|
|
level0_file_num_compaction_trigger(0),
|
|
|
|
level0_slowdown_writes_trigger(0),
|
|
|
|
level0_stop_writes_trigger(0),
|
|
|
|
max_compaction_bytes(0),
|
Ignore max_compaction_bytes for compaction input that are within output key-range (#10835)
Summary:
When picking compaction input files, we sometimes stop picking a file that is fully included in the output key-range due to hitting max_compaction_bytes. Including these input files can potentially reduce WA at the expense of larger compactions. Larger compaction should be fine as files from input level are usually 10X smaller than files from output level. This PR adds a mutable CF option `ignore_max_compaction_bytes_for_input` that is enabled by default. We can remove this option once we are sure it is safe.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10835
Test Plan:
- CI, a unit test on max_compaction_bytes fails before turning this flag off.
- Benchmark does not show much difference in WA: `./db_bench --benchmarks=fillrandom,waitforcompaction,stats,levelstats -max_background_jobs=12 -num=2000000000 -target_file_size_base=33554432 --write_buffer_size=33554432`
```
main:
** Compaction Stats [default] **
Level Files Size Score Read(GB) Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) CompMergeCPU(sec) Comp(cnt) Avg(sec) KeyIn KeyDrop Rblob(GB) Wblob(GB)
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
L0 3/0 91.59 MB 0.8 70.9 0.0 70.9 200.8 129.9 0.0 1.5 25.2 71.2 2886.55 2463.45 9725 0.297 1093M 254K 0.0 0.0
L1 9/0 248.03 MB 1.0 392.0 129.8 262.2 391.7 129.5 0.0 3.0 69.0 68.9 5821.71 5536.90 804 7.241 6029M 5814K 0.0 0.0
L2 87/0 2.50 GB 1.0 537.0 128.5 408.5 533.8 125.2 0.7 4.2 69.5 69.1 7912.24 7323.70 4417 1.791 8299M 36M 0.0 0.0
L3 836/0 24.99 GB 1.0 616.9 118.3 498.7 594.5 95.8 5.2 5.0 66.9 64.5 9442.38 8490.28 4204 2.246 9749M 306M 0.0 0.0
L4 2355/0 62.95 GB 0.3 67.3 37.1 30.2 54.2 24.0 38.9 1.5 72.2 58.2 954.37 821.18 917 1.041 1076M 173M 0.0 0.0
Sum 3290/0 90.77 GB 0.0 1684.2 413.7 1270.5 1775.0 504.5 44.9 13.7 63.8 67.3 27017.25 24635.52 20067 1.346 26G 522M 0.0 0.0
Cumulative compaction: 1774.96 GB write, 154.29 MB/s write, 1684.19 GB read, 146.40 MB/s read, 27017.3 seconds
This PR:
** Compaction Stats [default] **
Level Files Size Score Read(GB) Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) CompMergeCPU(sec) Comp(cnt) Avg(sec) KeyIn KeyDrop Rblob(GB) Wblob(GB)
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
L0 3/0 45.71 MB 0.8 72.9 0.0 72.9 202.8 129.9 0.0 1.6 25.4 70.7 2938.16 2510.36 9741 0.302 1124M 265K 0.0 0.0
L1 8/0 234.54 MB 0.9 384.5 129.8 254.7 384.2 129.6 0.0 3.0 69.0 68.9 5708.08 5424.43 791 7.216 5913M 5753K 0.0 0.0
L2 84/0 2.47 GB 1.0 543.1 128.6 414.5 539.9 125.4 0.7 4.2 69.6 69.2 7989.31 7403.13 4418 1.808 8393M 36M 0.0 0.0
L3 839/0 24.96 GB 1.0 615.6 118.4 497.2 593.2 96.0 5.1 5.0 66.6 64.1 9471.23 8489.31 4193 2.259 9726M 306M 0.0 0.0
L4 2360/0 63.04 GB 0.3 67.6 37.3 30.3 54.4 24.1 38.9 1.5 71.5 57.6 967.30 827.99 907 1.066 1080M 173M 0.0 0.0
Sum 3294/0 90.75 GB 0.0 1683.8 414.2 1269.6 1774.5 504.9 44.8 13.7 63.7 67.1 27074.08 24655.22 20050 1.350 26G 522M 0.0 0.0
Cumulative compaction: 1774.52 GB write, 157.09 MB/s write, 1683.77 GB read, 149.06 MB/s read, 27074.1 seconds
```
Reviewed By: ajkr
Differential Revision: D40518319
Pulled By: cbi42
fbshipit-source-id: f4ea614bc0ebefe007ffaf05bb9aec9a8ca25b60
2 years ago
|
|
|
ignore_max_compaction_bytes_for_input(true),
|
Add options.compaction_measure_io_stats to print write I/O stats in compactions
Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:
2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}
Add two more counters in iostats_context.
Also add a parameter of db_bench.
Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44115
9 years ago
|
|
|
target_file_size_base(0),
|
|
|
|
target_file_size_multiplier(0),
|
|
|
|
max_bytes_for_level_base(0),
|
|
|
|
max_bytes_for_level_multiplier(0),
|
|
|
|
ttl(0),
|
Periodic Compactions (#5166)
Summary:
Introducing Periodic Compactions.
This feature allows all the files in a CF to be periodically compacted. It could help in catching any corruptions that could creep into the DB proactively as every file is constantly getting re-compacted. And also, of course, it helps to cleanup data older than certain threshold.
- Introduced a new option `periodic_compaction_time` to control how long a file can live without being compacted in a CF.
- This works across all levels.
- The files are put in the same level after going through the compaction. (Related files in the same level are picked up as `ExpandInputstoCleanCut` is used).
- Compaction filters, if any, are invoked as usual.
- A new table property, `file_creation_time`, is introduced to implement this feature. This property is set to the time at which the SST file was created (and that time is given by the underlying Env/OS).
This feature can be enabled on its own, or in conjunction with `ttl`. It is possible to set a different time threshold for the bottom level when used in conjunction with ttl. Since `ttl` works only on 0 to last but one levels, you could set `ttl` to, say, 1 day, and `periodic_compaction_time` to, say, 7 days. Since `ttl < periodic_compaction_time` all files in last but one levels keep getting picked up based on ttl, and almost never based on periodic_compaction_time. The files in the bottom level get picked up for compaction based on `periodic_compaction_time`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5166
Differential Revision: D14884441
Pulled By: sagar0
fbshipit-source-id: 408426cbacb409c06386a98632dcf90bfa1bda47
6 years ago
|
|
|
periodic_compaction_seconds(0),
|
|
|
|
compaction_options_fifo(),
|
|
|
|
enable_blob_files(false),
|
|
|
|
min_blob_size(0),
|
|
|
|
blob_file_size(0),
|
|
|
|
blob_compression_type(kNoCompression),
|
|
|
|
enable_blob_garbage_collection(false),
|
|
|
|
blob_garbage_collection_age_cutoff(0.0),
|
Make it possible to force the garbage collection of the oldest blob files (#8994)
Summary:
The current BlobDB garbage collection logic works by relocating the valid
blobs from the oldest blob files as they are encountered during compaction,
and cleaning up blob files once they contain nothing but garbage. However,
with sufficiently skewed workloads, it is theoretically possible to end up in a
situation when few or no compactions get scheduled for the SST files that contain
references to the oldest blob files, which can lead to increased space amp due
to the lack of GC.
In order to efficiently handle such workloads, the patch adds a new BlobDB
configuration option called `blob_garbage_collection_force_threshold`,
which signals to BlobDB to schedule targeted compactions for the SST files
that keep alive the oldest batch of blob files if the overall ratio of garbage in
the given blob files meets the threshold *and* all the given blob files are
eligible for GC based on `blob_garbage_collection_age_cutoff`. (For example,
if the new option is set to 0.9, targeted compactions will get scheduled if the
sum of garbage bytes meets or exceeds 90% of the sum of total bytes in the
oldest blob files, assuming all affected blob files are below the age-based cutoff.)
The net result of these targeted compactions is that the valid blobs in the oldest
blob files are relocated and the oldest blob files themselves cleaned up (since
*all* SST files that rely on them get compacted away).
These targeted compactions are similar to periodic compactions in the sense
that they force certain SST files that otherwise would not get picked up to undergo
compaction and also in the sense that instead of merging files from multiple levels,
they target a single file. (Note: such compactions might still include neighboring files
from the same level due to the need of having a "clean cut" boundary but they never
include any files from any other level.)
This functionality is currently only supported with the leveled compaction style
and is inactive by default (since the default value is set to 1.0, i.e. 100%).
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8994
Test Plan: Ran `make check` and tested using `db_bench` and the stress/crash tests.
Reviewed By: riversand963
Differential Revision: D31489850
Pulled By: ltamasi
fbshipit-source-id: 44057d511726a0e2a03c5d9313d7511b3f0c4eab
3 years ago
|
|
|
blob_garbage_collection_force_threshold(0.0),
|
|
|
|
blob_compaction_readahead_size(0),
|
|
|
|
blob_file_starting_level(0),
|
|
|
|
prepopulate_blob_cache(PrepopulateBlobCache::kDisable),
|
Add options.compaction_measure_io_stats to print write I/O stats in compactions
Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:
2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}
Add two more counters in iostats_context.
Also add a parameter of db_bench.
Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44115
9 years ago
|
|
|
max_sequential_skip_in_iterations(0),
|
|
|
|
check_flush_compaction_key_order(true),
|
Add options.compaction_measure_io_stats to print write I/O stats in compactions
Summary:
Add options.compaction_measure_io_stats to print out / pass to listener accumulated time spent on write calls. Example outputs in info logs:
2015/08/12-16:27:59.463944 7fd428bff700 (Original Log Time 2015/08/12-16:27:59.463922) EVENT_LOG_v1 {"time_micros": 1439422079463897, "job": 6, "event": "compaction_finished", "output_level": 1, "num_output_files": 4, "total_output_size": 6900525, "num_input_records": 111483, "num_output_records": 106877, "file_write_nanos": 15663206, "file_range_sync_nanos": 649588, "file_fsync_nanos": 349614797, "file_prepare_write_nanos": 1505812, "lsm_state": [2, 4, 0, 0, 0, 0, 0]}
Add two more counters in iostats_context.
Also add a parameter of db_bench.
Test Plan: Add a unit test. Also manually verify LOG outputs in db_bench
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D44115
9 years ago
|
|
|
paranoid_file_checks(false),
|
|
|
|
report_bg_io_stats(false),
|
|
|
|
compression(Snappy_Supported() ? kSnappyCompression : kNoCompression),
|
|
|
|
bottommost_compression(kDisableCompressionOption),
|
|
|
|
last_level_temperature(Temperature::kUnknown),
|
|
|
|
memtable_protection_bytes_per_key(0),
|
|
|
|
block_protection_bytes_per_key(0),
|
|
|
|
sample_for_compression(0) {}
|
|
|
|
|
|
|
|
explicit MutableCFOptions(const Options& options);
|
|
|
|
|
|
|
|
// Must be called after any change to MutableCFOptions
|
|
|
|
void RefreshDerivedOptions(int num_levels, CompactionStyle compaction_style);
|
|
|
|
|
|
|
|
void RefreshDerivedOptions(const ImmutableCFOptions& ioptions) {
|
|
|
|
RefreshDerivedOptions(ioptions.num_levels, ioptions.compaction_style);
|
|
|
|
}
|
|
|
|
|
|
|
|
int MaxBytesMultiplerAdditional(int level) const {
|
|
|
|
if (level >=
|
|
|
|
static_cast<int>(max_bytes_for_level_multiplier_additional.size())) {
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return max_bytes_for_level_multiplier_additional[level];
|
|
|
|
}
|
|
|
|
|
|
|
|
void Dump(Logger* log) const;
|
|
|
|
|
|
|
|
// Memtable related options
|
|
|
|
size_t write_buffer_size;
|
|
|
|
int max_write_buffer_number;
|
|
|
|
size_t arena_block_size;
|
|
|
|
double memtable_prefix_bloom_size_ratio;
|
|
|
|
bool memtable_whole_key_filtering;
|
|
|
|
size_t memtable_huge_page_size;
|
|
|
|
size_t max_successive_merges;
|
|
|
|
size_t inplace_update_num_locks;
|
|
|
|
std::shared_ptr<const SliceTransform> prefix_extractor;
|
|
|
|
// [experimental]
|
|
|
|
// Used to activate or deactive the Mempurge feature (memtable garbage
|
|
|
|
// collection). (deactivated by default). At every flush, the total useful
|
|
|
|
// payload (total entries minus garbage entries) is estimated as a ratio
|
|
|
|
// [useful payload bytes]/[size of a memtable (in bytes)]. This ratio is then
|
|
|
|
// compared to this `threshold` value:
|
|
|
|
// - if ratio<threshold: the flush is replaced by a mempurge operation
|
|
|
|
// - else: a regular flush operation takes place.
|
|
|
|
// Threshold values:
|
|
|
|
// 0.0: mempurge deactivated (default).
|
|
|
|
// 1.0: recommended threshold value.
|
|
|
|
// >1.0 : aggressive mempurge.
|
|
|
|
// 0 < threshold < 1.0: mempurge triggered only for very low useful payload
|
|
|
|
// ratios.
|
|
|
|
// [experimental]
|
|
|
|
double experimental_mempurge_threshold;
|
|
|
|
|
|
|
|
// Compaction related options
|
|
|
|
bool disable_auto_compactions;
|
|
|
|
uint64_t soft_pending_compaction_bytes_limit;
|
|
|
|
uint64_t hard_pending_compaction_bytes_limit;
|
|
|
|
int level0_file_num_compaction_trigger;
|
|
|
|
int level0_slowdown_writes_trigger;
|
|
|
|
int level0_stop_writes_trigger;
|
|
|
|
uint64_t max_compaction_bytes;
|
Ignore max_compaction_bytes for compaction input that are within output key-range (#10835)
Summary:
When picking compaction input files, we sometimes stop picking a file that is fully included in the output key-range due to hitting max_compaction_bytes. Including these input files can potentially reduce WA at the expense of larger compactions. Larger compaction should be fine as files from input level are usually 10X smaller than files from output level. This PR adds a mutable CF option `ignore_max_compaction_bytes_for_input` that is enabled by default. We can remove this option once we are sure it is safe.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10835
Test Plan:
- CI, a unit test on max_compaction_bytes fails before turning this flag off.
- Benchmark does not show much difference in WA: `./db_bench --benchmarks=fillrandom,waitforcompaction,stats,levelstats -max_background_jobs=12 -num=2000000000 -target_file_size_base=33554432 --write_buffer_size=33554432`
```
main:
** Compaction Stats [default] **
Level Files Size Score Read(GB) Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) CompMergeCPU(sec) Comp(cnt) Avg(sec) KeyIn KeyDrop Rblob(GB) Wblob(GB)
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
L0 3/0 91.59 MB 0.8 70.9 0.0 70.9 200.8 129.9 0.0 1.5 25.2 71.2 2886.55 2463.45 9725 0.297 1093M 254K 0.0 0.0
L1 9/0 248.03 MB 1.0 392.0 129.8 262.2 391.7 129.5 0.0 3.0 69.0 68.9 5821.71 5536.90 804 7.241 6029M 5814K 0.0 0.0
L2 87/0 2.50 GB 1.0 537.0 128.5 408.5 533.8 125.2 0.7 4.2 69.5 69.1 7912.24 7323.70 4417 1.791 8299M 36M 0.0 0.0
L3 836/0 24.99 GB 1.0 616.9 118.3 498.7 594.5 95.8 5.2 5.0 66.9 64.5 9442.38 8490.28 4204 2.246 9749M 306M 0.0 0.0
L4 2355/0 62.95 GB 0.3 67.3 37.1 30.2 54.2 24.0 38.9 1.5 72.2 58.2 954.37 821.18 917 1.041 1076M 173M 0.0 0.0
Sum 3290/0 90.77 GB 0.0 1684.2 413.7 1270.5 1775.0 504.5 44.9 13.7 63.8 67.3 27017.25 24635.52 20067 1.346 26G 522M 0.0 0.0
Cumulative compaction: 1774.96 GB write, 154.29 MB/s write, 1684.19 GB read, 146.40 MB/s read, 27017.3 seconds
This PR:
** Compaction Stats [default] **
Level Files Size Score Read(GB) Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) CompMergeCPU(sec) Comp(cnt) Avg(sec) KeyIn KeyDrop Rblob(GB) Wblob(GB)
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
L0 3/0 45.71 MB 0.8 72.9 0.0 72.9 202.8 129.9 0.0 1.6 25.4 70.7 2938.16 2510.36 9741 0.302 1124M 265K 0.0 0.0
L1 8/0 234.54 MB 0.9 384.5 129.8 254.7 384.2 129.6 0.0 3.0 69.0 68.9 5708.08 5424.43 791 7.216 5913M 5753K 0.0 0.0
L2 84/0 2.47 GB 1.0 543.1 128.6 414.5 539.9 125.4 0.7 4.2 69.6 69.2 7989.31 7403.13 4418 1.808 8393M 36M 0.0 0.0
L3 839/0 24.96 GB 1.0 615.6 118.4 497.2 593.2 96.0 5.1 5.0 66.6 64.1 9471.23 8489.31 4193 2.259 9726M 306M 0.0 0.0
L4 2360/0 63.04 GB 0.3 67.6 37.3 30.3 54.4 24.1 38.9 1.5 71.5 57.6 967.30 827.99 907 1.066 1080M 173M 0.0 0.0
Sum 3294/0 90.75 GB 0.0 1683.8 414.2 1269.6 1774.5 504.9 44.8 13.7 63.7 67.1 27074.08 24655.22 20050 1.350 26G 522M 0.0 0.0
Cumulative compaction: 1774.52 GB write, 157.09 MB/s write, 1683.77 GB read, 149.06 MB/s read, 27074.1 seconds
```
Reviewed By: ajkr
Differential Revision: D40518319
Pulled By: cbi42
fbshipit-source-id: f4ea614bc0ebefe007ffaf05bb9aec9a8ca25b60
2 years ago
|
|
|
bool ignore_max_compaction_bytes_for_input;
|
|
|
|
uint64_t target_file_size_base;
|
|
|
|
int target_file_size_multiplier;
|
|
|
|
uint64_t max_bytes_for_level_base;
|
|
|
|
double max_bytes_for_level_multiplier;
|
|
|
|
uint64_t ttl;
|
Periodic Compactions (#5166)
Summary:
Introducing Periodic Compactions.
This feature allows all the files in a CF to be periodically compacted. It could help in catching any corruptions that could creep into the DB proactively as every file is constantly getting re-compacted. And also, of course, it helps to cleanup data older than certain threshold.
- Introduced a new option `periodic_compaction_time` to control how long a file can live without being compacted in a CF.
- This works across all levels.
- The files are put in the same level after going through the compaction. (Related files in the same level are picked up as `ExpandInputstoCleanCut` is used).
- Compaction filters, if any, are invoked as usual.
- A new table property, `file_creation_time`, is introduced to implement this feature. This property is set to the time at which the SST file was created (and that time is given by the underlying Env/OS).
This feature can be enabled on its own, or in conjunction with `ttl`. It is possible to set a different time threshold for the bottom level when used in conjunction with ttl. Since `ttl` works only on 0 to last but one levels, you could set `ttl` to, say, 1 day, and `periodic_compaction_time` to, say, 7 days. Since `ttl < periodic_compaction_time` all files in last but one levels keep getting picked up based on ttl, and almost never based on periodic_compaction_time. The files in the bottom level get picked up for compaction based on `periodic_compaction_time`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5166
Differential Revision: D14884441
Pulled By: sagar0
fbshipit-source-id: 408426cbacb409c06386a98632dcf90bfa1bda47
6 years ago
|
|
|
uint64_t periodic_compaction_seconds;
|
|
|
|
std::vector<int> max_bytes_for_level_multiplier_additional;
|
|
|
|
CompactionOptionsFIFO compaction_options_fifo;
|
|
|
|
CompactionOptionsUniversal compaction_options_universal;
|
|
|
|
|
|
|
|
// Blob file related options
|
|
|
|
bool enable_blob_files;
|
|
|
|
uint64_t min_blob_size;
|
|
|
|
uint64_t blob_file_size;
|
|
|
|
CompressionType blob_compression_type;
|
|
|
|
bool enable_blob_garbage_collection;
|
|
|
|
double blob_garbage_collection_age_cutoff;
|
Make it possible to force the garbage collection of the oldest blob files (#8994)
Summary:
The current BlobDB garbage collection logic works by relocating the valid
blobs from the oldest blob files as they are encountered during compaction,
and cleaning up blob files once they contain nothing but garbage. However,
with sufficiently skewed workloads, it is theoretically possible to end up in a
situation when few or no compactions get scheduled for the SST files that contain
references to the oldest blob files, which can lead to increased space amp due
to the lack of GC.
In order to efficiently handle such workloads, the patch adds a new BlobDB
configuration option called `blob_garbage_collection_force_threshold`,
which signals to BlobDB to schedule targeted compactions for the SST files
that keep alive the oldest batch of blob files if the overall ratio of garbage in
the given blob files meets the threshold *and* all the given blob files are
eligible for GC based on `blob_garbage_collection_age_cutoff`. (For example,
if the new option is set to 0.9, targeted compactions will get scheduled if the
sum of garbage bytes meets or exceeds 90% of the sum of total bytes in the
oldest blob files, assuming all affected blob files are below the age-based cutoff.)
The net result of these targeted compactions is that the valid blobs in the oldest
blob files are relocated and the oldest blob files themselves cleaned up (since
*all* SST files that rely on them get compacted away).
These targeted compactions are similar to periodic compactions in the sense
that they force certain SST files that otherwise would not get picked up to undergo
compaction and also in the sense that instead of merging files from multiple levels,
they target a single file. (Note: such compactions might still include neighboring files
from the same level due to the need of having a "clean cut" boundary but they never
include any files from any other level.)
This functionality is currently only supported with the leveled compaction style
and is inactive by default (since the default value is set to 1.0, i.e. 100%).
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8994
Test Plan: Ran `make check` and tested using `db_bench` and the stress/crash tests.
Reviewed By: riversand963
Differential Revision: D31489850
Pulled By: ltamasi
fbshipit-source-id: 44057d511726a0e2a03c5d9313d7511b3f0c4eab
3 years ago
|
|
|
double blob_garbage_collection_force_threshold;
|
|
|
|
uint64_t blob_compaction_readahead_size;
|
|
|
|
int blob_file_starting_level;
|
|
|
|
PrepopulateBlobCache prepopulate_blob_cache;
|
|
|
|
|
|
|
|
// Misc options
|
|
|
|
uint64_t max_sequential_skip_in_iterations;
|
|
|
|
bool check_flush_compaction_key_order;
|
|
|
|
bool paranoid_file_checks;
|
|
|
|
bool report_bg_io_stats;
|
|
|
|
CompressionType compression;
|
|
|
|
CompressionType bottommost_compression;
|
|
|
|
CompressionOptions compression_opts;
|
|
|
|
CompressionOptions bottommost_compression_opts;
|
|
|
|
Temperature last_level_temperature;
|
|
|
|
uint32_t memtable_protection_bytes_per_key;
|
|
|
|
uint8_t block_protection_bytes_per_key;
|
|
|
|
|
|
|
|
uint64_t sample_for_compression;
|
|
|
|
std::vector<CompressionType> compression_per_level;
|
|
|
|
|
|
|
|
// Derived options
|
|
|
|
// Per-level target file size.
|
|
|
|
std::vector<uint64_t> max_file_size;
|
|
|
|
};
|
|
|
|
|
|
|
|
uint64_t MultiplyCheckOverflow(uint64_t op1, double op2);
|
options.level_compaction_dynamic_level_bytes to allow RocksDB to pick size bases of levels dynamically.
Summary:
When having fixed max_bytes_for_level_base, the ratio of size of largest level and the second one can range from 0 to the multiplier. This makes LSM tree frequently irregular and unpredictable. It can also cause poor space amplification in some cases.
In this improvement (proposed by Igor Kabiljo), we introduce a parameter option.level_compaction_use_dynamic_max_bytes. When turning it on, RocksDB is free to pick a level base in the range of (options.max_bytes_for_level_base/options.max_bytes_for_level_multiplier, options.max_bytes_for_level_base] so that real level ratios are close to options.max_bytes_for_level_multiplier.
Test Plan: New unit tests and pass tests suites including valgrind.
Reviewers: MarkCallaghan, rven, yhchiang, igor, ikabiljo
Reviewed By: ikabiljo
Subscribers: yoshinorim, ikabiljo, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D31437
10 years ago
|
|
|
|
|
|
|
// Get the max file size in a given level.
|
|
|
|
uint64_t MaxFileSizeForLevel(const MutableCFOptions& cf_options,
|
|
|
|
int level, CompactionStyle compaction_style, int base_level = 1,
|
|
|
|
bool level_compaction_dynamic_level_bytes = false);
|
|
|
|
|
|
|
|
// Get the max size of an L0 file for which we will pin its meta-blocks when
|
|
|
|
// `pin_l0_filter_and_index_blocks_in_cache` is set.
|
|
|
|
size_t MaxFileSizeForL0MetaPin(const MutableCFOptions& cf_options);
|
|
|
|
|
|
|
|
Status GetStringFromMutableCFOptions(const ConfigOptions& config_options,
|
|
|
|
const MutableCFOptions& mutable_opts,
|
|
|
|
std::string* opt_string);
|
|
|
|
|
|
|
|
Status GetMutableOptionsFromStrings(
|
|
|
|
const MutableCFOptions& base_options,
|
|
|
|
const std::unordered_map<std::string, std::string>& options_map,
|
|
|
|
Logger* info_log, MutableCFOptions* new_options);
|
|
|
|
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|