rocksdb/options/options_helper.cc

1443 lines
58 KiB
C++
Raw Normal View History

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#include "options/options_helper.h"
#include <atomic>
#include <cassert>
#include <cctype>
#include <cstdlib>
Implement XXH3 block checksum type (#9069) Summary: XXH3 - latest hash function that is extremely fast on large data, easily faster than crc32c on most any x86_64 hardware. In integrating this hash function, I have handled the compression type byte in a non-standard way to avoid using the streaming API (extra data movement and active code size because of hash function complexity). This approach got a thumbs-up from Yann Collet. Existing functionality change: * reject bad ChecksumType in options with InvalidArgument This change split off from https://github.com/facebook/rocksdb/issues/9058 because context-aware checksum is likely to be handled through different configuration than ChecksumType. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9069 Test Plan: tests updated, and substantially expanded. Unit tests now check that we don't accidentally change the values generated by the checksum algorithms ("schema test") and that we properly handle invalid/unrecognized checksum types in options or in file footer. DBTestBase::ChangeOptions (etc.) updated from two to one configuration changing from default CRC32c ChecksumType. The point of this test code is to detect possible interactions among features, and the likelihood of some bad interaction being detected by including configurations other than XXH3 and CRC32c--and then not detected by stress/crash test--is extremely low. Stress/crash test also updated (manual run long enough to see it accepts new checksum type). db_bench also updated for microbenchmarking checksums. ### Performance microbenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) ./db_bench -benchmarks=crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3 crc32c : 0.200 micros/op 5005220 ops/sec; 19551.6 MB/s (4096 per op) xxhash : 0.807 micros/op 1238408 ops/sec; 4837.5 MB/s (4096 per op) xxhash64 : 0.421 micros/op 2376514 ops/sec; 9283.3 MB/s (4096 per op) xxh3 : 0.171 micros/op 5858391 ops/sec; 22884.3 MB/s (4096 per op) crc32c : 0.206 micros/op 4859566 ops/sec; 18982.7 MB/s (4096 per op) xxhash : 0.793 micros/op 1260850 ops/sec; 4925.2 MB/s (4096 per op) xxhash64 : 0.410 micros/op 2439182 ops/sec; 9528.1 MB/s (4096 per op) xxh3 : 0.161 micros/op 6202872 ops/sec; 24230.0 MB/s (4096 per op) crc32c : 0.203 micros/op 4924686 ops/sec; 19237.1 MB/s (4096 per op) xxhash : 0.839 micros/op 1192388 ops/sec; 4657.8 MB/s (4096 per op) xxhash64 : 0.424 micros/op 2357391 ops/sec; 9208.6 MB/s (4096 per op) xxh3 : 0.162 micros/op 6182678 ops/sec; 24151.1 MB/s (4096 per op) As you can see, especially once warmed up, xxh3 is fastest. ### Performance macrobenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) Test for I in `seq 1 50`; do for CHK in 0 1 2 3 4; do TEST_TMPDIR=/dev/shm/rocksdb$CHK ./db_bench -benchmarks=fillseq -memtablerep=vector -allow_concurrent_memtable_write=false -num=30000000 -checksum_type=$CHK 2>&1 | grep 'micros/op' | tee -a results-$CHK & done; wait; done Results (ops/sec) for FILE in results*; do echo -n "$FILE "; awk '{ s += $5; c++; } END { print 1.0 * s / c; }' < $FILE; done results-0 252118 # kNoChecksum results-1 251588 # kCRC32c results-2 251863 # kxxHash results-3 252016 # kxxHash64 results-4 252038 # kXXH3 Reviewed By: mrambacher Differential Revision: D31905249 Pulled By: pdillinger fbshipit-source-id: cb9b998ebe2523fc7c400eedf62124a78bf4b4d1
2021-10-29 05:13:47 +00:00
#include <set>
#include <unordered_set>
#include <vector>
#include "options/cf_options.h"
#include "options/db_options.h"
#include "rocksdb/cache.h"
#include "rocksdb/compaction_filter.h"
#include "rocksdb/convenience.h"
#include "rocksdb/filter_policy.h"
#include "rocksdb/flush_block_policy.h"
#include "rocksdb/memtablerep.h"
#include "rocksdb/merge_operator.h"
#include "rocksdb/options.h"
#include "rocksdb/rate_limiter.h"
#include "rocksdb/slice_transform.h"
#include "rocksdb/table.h"
#include "rocksdb/utilities/object_registry.h"
#include "rocksdb/utilities/options_type.h"
#include "util/string_util.h"
namespace ROCKSDB_NAMESPACE {
ConfigOptions::ConfigOptions()
: registry(ObjectRegistry::NewInstance())
{
env = Env::Default();
}
ConfigOptions::ConfigOptions(const DBOptions& db_opts) : env(db_opts.env) {
registry = ObjectRegistry::NewInstance();
}
Status ValidateOptions(const DBOptions& db_opts,
const ColumnFamilyOptions& cf_opts) {
Status s;
auto db_cfg = DBOptionsAsConfigurable(db_opts);
auto cf_cfg = CFOptionsAsConfigurable(cf_opts);
s = db_cfg->ValidateOptions(db_opts, cf_opts);
if (s.ok()) s = cf_cfg->ValidateOptions(db_opts, cf_opts);
return s;
}
DBOptions BuildDBOptions(const ImmutableDBOptions& immutable_db_options,
const MutableDBOptions& mutable_db_options) {
DBOptions options;
options.create_if_missing = immutable_db_options.create_if_missing;
options.create_missing_column_families =
immutable_db_options.create_missing_column_families;
options.error_if_exists = immutable_db_options.error_if_exists;
options.paranoid_checks = immutable_db_options.paranoid_checks;
options.flush_verify_memtable_count =
immutable_db_options.flush_verify_memtable_count;
Compare the number of input keys and processed keys for compactions (#11571) Summary: ... to improve data integrity validation during compaction. A new option `compaction_verify_record_count` is introduced for this verification and is enabled by default. One exception when the verification is not done is when a compaction filter returns kRemoveAndSkipUntil which can cause CompactionIterator to seek until some key and hence not able to keep track of the number of keys processed. For expected number of input keys, we sum over the number of total keys - number of range tombstones across compaction input files (`CompactionJob::UpdateCompactionStats()`). Table properties are consulted if `FileMetaData` is not initialized for some input file. Since table properties for all input files were also constructed during `DBImpl::NotifyOnCompactionBegin()`, `Compaction::GetTableProperties()` is introduced to reduce duplicated code. For actual number of keys processed, each subcompaction will record its number of keys processed to `sub_compact->compaction_job_stats.num_input_records` and aggregated when all subcompactions finish (`CompactionJob::AggregateCompactionStats()`). In the case when some subcompaction encountered kRemoveAndSkipUntil from compaction filter and does not have accurate count, it propagates this information through `sub_compact->compaction_job_stats.has_num_input_records`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11571 Test Plan: * Add a new unit test `DBCompactionTest.VerifyRecordCount` for the corruption case. * All other unit tests for non-corrupted case. * Ran crash test for a few hours: `python3 ./tools/db_crashtest.py whitebox --simple` Reviewed By: ajkr Differential Revision: D47131965 Pulled By: cbi42 fbshipit-source-id: cc8e94565dd526c4347e9d3843ecf32f6727af92
2023-07-28 16:47:31 +00:00
options.compaction_verify_record_count =
immutable_db_options.compaction_verify_record_count;
options.track_and_verify_wals_in_manifest =
immutable_db_options.track_and_verify_wals_in_manifest;
options.verify_sst_unique_id_in_manifest =
immutable_db_options.verify_sst_unique_id_in_manifest;
options.env = immutable_db_options.env;
options.rate_limiter = immutable_db_options.rate_limiter;
options.sst_file_manager = immutable_db_options.sst_file_manager;
options.info_log = immutable_db_options.info_log;
options.info_log_level = immutable_db_options.info_log_level;
options.max_open_files = mutable_db_options.max_open_files;
options.max_file_opening_threads =
immutable_db_options.max_file_opening_threads;
options.max_total_wal_size = mutable_db_options.max_total_wal_size;
options.statistics = immutable_db_options.statistics;
options.use_fsync = immutable_db_options.use_fsync;
options.db_paths = immutable_db_options.db_paths;
options.db_log_dir = immutable_db_options.db_log_dir;
options.wal_dir = immutable_db_options.wal_dir;
options.delete_obsolete_files_period_micros =
mutable_db_options.delete_obsolete_files_period_micros;
options.max_background_jobs = mutable_db_options.max_background_jobs;
options.max_background_compactions =
mutable_db_options.max_background_compactions;
options.bytes_per_sync = mutable_db_options.bytes_per_sync;
options.wal_bytes_per_sync = mutable_db_options.wal_bytes_per_sync;
Optionally wait on bytes_per_sync to smooth I/O (#5183) Summary: The existing implementation does not guarantee bytes reach disk every `bytes_per_sync` when writing SST files, or every `wal_bytes_per_sync` when writing WALs. This can cause confusing behavior for users who enable this feature to avoid large syncs during flush and compaction, but then end up hitting them anyways. My understanding of the existing behavior is we used `sync_file_range` with `SYNC_FILE_RANGE_WRITE` to submit ranges for async writeback, such that we could continue processing the next range of bytes while that I/O is happening. I believe we can preserve that benefit while also limiting how far the processing can get ahead of the I/O, which prevents huge syncs from happening when the file finishes. Consider this `sync_file_range` usage: `sync_file_range(fd_, 0, static_cast<off_t>(offset + nbytes), SYNC_FILE_RANGE_WAIT_BEFORE | SYNC_FILE_RANGE_WRITE)`. Expanding the range to start at 0 and adding the `SYNC_FILE_RANGE_WAIT_BEFORE` flag causes any pending writeback (like from a previous call to `sync_file_range`) to finish before it proceeds to submit the latest `nbytes` for writeback. The latest `nbytes` are still written back asynchronously, unless processing exceeds I/O speed, in which case the following `sync_file_range` will need to wait on it. There is a second change in this PR to use `fdatasync` when `sync_file_range` is unavailable (determined statically) or has some known problem with the underlying filesystem (determined dynamically). The above two changes only apply when the user enables a new option, `strict_bytes_per_sync`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5183 Differential Revision: D14953553 Pulled By: siying fbshipit-source-id: 445c3862e019fb7b470f9c7f314fc231b62706e9
2019-04-22 18:48:45 +00:00
options.strict_bytes_per_sync = mutable_db_options.strict_bytes_per_sync;
options.max_subcompactions = mutable_db_options.max_subcompactions;
options.max_background_flushes = mutable_db_options.max_background_flushes;
options.max_log_file_size = immutable_db_options.max_log_file_size;
options.log_file_time_to_roll = immutable_db_options.log_file_time_to_roll;
options.keep_log_file_num = immutable_db_options.keep_log_file_num;
options.recycle_log_file_num = immutable_db_options.recycle_log_file_num;
options.max_manifest_file_size = immutable_db_options.max_manifest_file_size;
options.table_cache_numshardbits =
immutable_db_options.table_cache_numshardbits;
options.WAL_ttl_seconds = immutable_db_options.WAL_ttl_seconds;
options.WAL_size_limit_MB = immutable_db_options.WAL_size_limit_MB;
options.manifest_preallocation_size =
immutable_db_options.manifest_preallocation_size;
options.allow_mmap_reads = immutable_db_options.allow_mmap_reads;
options.allow_mmap_writes = immutable_db_options.allow_mmap_writes;
options.use_direct_reads = immutable_db_options.use_direct_reads;
options.use_direct_io_for_flush_and_compaction =
immutable_db_options.use_direct_io_for_flush_and_compaction;
options.allow_fallocate = immutable_db_options.allow_fallocate;
options.is_fd_close_on_exec = immutable_db_options.is_fd_close_on_exec;
options.stats_dump_period_sec = mutable_db_options.stats_dump_period_sec;
options.stats_persist_period_sec =
mutable_db_options.stats_persist_period_sec;
options.persist_stats_to_disk = immutable_db_options.persist_stats_to_disk;
options.stats_history_buffer_size =
mutable_db_options.stats_history_buffer_size;
options.advise_random_on_open = immutable_db_options.advise_random_on_open;
options.db_write_buffer_size = immutable_db_options.db_write_buffer_size;
options.write_buffer_manager = immutable_db_options.write_buffer_manager;
options.access_hint_on_compaction_start =
immutable_db_options.access_hint_on_compaction_start;
options.compaction_readahead_size =
mutable_db_options.compaction_readahead_size;
options.random_access_max_buffer_size =
immutable_db_options.random_access_max_buffer_size;
options.writable_file_max_buffer_size =
mutable_db_options.writable_file_max_buffer_size;
options.use_adaptive_mutex = immutable_db_options.use_adaptive_mutex;
options.listeners = immutable_db_options.listeners;
options.enable_thread_tracking = immutable_db_options.enable_thread_tracking;
options.delayed_write_rate = mutable_db_options.delayed_write_rate;
options.enable_pipelined_write = immutable_db_options.enable_pipelined_write;
Unordered Writes (#5218) Summary: Performing unordered writes in rocksdb when unordered_write option is set to true. When enabled the writes to memtable are done without joining any write thread. This offers much higher write throughput since the upcoming writes would not have to wait for the slowest memtable write to finish. The tradeoff is that the writes visible to a snapshot might change over time. If the application cannot tolerate that, it should implement its own mechanisms to work around that. Using TransactionDB with WRITE_PREPARED write policy is one way to achieve that. Doing so increases the max throughput by 2.2x without however compromising the snapshot guarantees. The patch is prepared based on an original by siying Existing unit tests are extended to include unordered_write option. Benchmark Results: ``` TEST_TMPDIR=/dev/shm/ ./db_bench_unordered --benchmarks=fillrandom --threads=32 --num=10000000 -max_write_buffer_number=16 --max_background_jobs=64 --batch_size=8 --writes=3000000 -level0_file_num_compaction_trigger=99999 --level0_slowdown_writes_trigger=99999 --level0_stop_writes_trigger=99999 -enable_pipelined_write=false -disable_auto_compactions --unordered_write=1 ``` With WAL - Vanilla RocksDB: 78.6 MB/s - WRITER_PREPARED with unordered_write: 177.8 MB/s (2.2x) - unordered_write: 368.9 MB/s (4.7x with relaxed snapshot guarantees) Without WAL - Vanilla RocksDB: 111.3 MB/s - WRITER_PREPARED with unordered_write: 259.3 MB/s MB/s (2.3x) - unordered_write: 645.6 MB/s (5.8x with relaxed snapshot guarantees) - WRITER_PREPARED with unordered_write disable concurrency control: 185.3 MB/s MB/s (2.35x) Limitations: - The feature is not yet extended to `max_successive_merges` > 0. The feature is also incompatible with `enable_pipelined_write` = true as well as with `allow_concurrent_memtable_write` = false. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5218 Differential Revision: D15219029 Pulled By: maysamyabandeh fbshipit-source-id: 38f2abc4af8780148c6128acdba2b3227bc81759
2019-05-14 00:43:47 +00:00
options.unordered_write = immutable_db_options.unordered_write;
options.allow_concurrent_memtable_write =
immutable_db_options.allow_concurrent_memtable_write;
options.enable_write_thread_adaptive_yield =
immutable_db_options.enable_write_thread_adaptive_yield;
options.max_write_batch_group_size_bytes =
immutable_db_options.max_write_batch_group_size_bytes;
options.write_thread_max_yield_usec =
immutable_db_options.write_thread_max_yield_usec;
options.write_thread_slow_yield_usec =
immutable_db_options.write_thread_slow_yield_usec;
options.skip_stats_update_on_db_open =
immutable_db_options.skip_stats_update_on_db_open;
options.skip_checking_sst_file_sizes_on_db_open =
immutable_db_options.skip_checking_sst_file_sizes_on_db_open;
options.wal_recovery_mode = immutable_db_options.wal_recovery_mode;
options.allow_2pc = immutable_db_options.allow_2pc;
options.row_cache = immutable_db_options.row_cache;
options.wal_filter = immutable_db_options.wal_filter;
options.fail_if_options_file_error =
immutable_db_options.fail_if_options_file_error;
options.dump_malloc_stats = immutable_db_options.dump_malloc_stats;
options.avoid_flush_during_recovery =
immutable_db_options.avoid_flush_during_recovery;
options.avoid_flush_during_shutdown =
mutable_db_options.avoid_flush_during_shutdown;
options.allow_ingest_behind = immutable_db_options.allow_ingest_behind;
options.two_write_queues = immutable_db_options.two_write_queues;
options.manual_wal_flush = immutable_db_options.manual_wal_flush;
options.wal_compression = immutable_db_options.wal_compression;
options.atomic_flush = immutable_db_options.atomic_flush;
options.avoid_unnecessary_blocking_io =
immutable_db_options.avoid_unnecessary_blocking_io;
options.log_readahead_size = immutable_db_options.log_readahead_size;
options.file_checksum_gen_factory =
immutable_db_options.file_checksum_gen_factory;
options.best_efforts_recovery = immutable_db_options.best_efforts_recovery;
options.max_bgerror_resume_count =
immutable_db_options.max_bgerror_resume_count;
options.bgerror_resume_retry_interval =
immutable_db_options.bgerror_resume_retry_interval;
options.db_host_id = immutable_db_options.db_host_id;
options.allow_data_in_errors = immutable_db_options.allow_data_in_errors;
options.checksum_handoff_file_types =
immutable_db_options.checksum_handoff_file_types;
options.lowest_used_cache_tier = immutable_db_options.lowest_used_cache_tier;
options.enforce_single_del_contracts =
immutable_db_options.enforce_single_del_contracts;
options.daily_offpeak_time_utc = mutable_db_options.daily_offpeak_time_utc;
return options;
}
ColumnFamilyOptions BuildColumnFamilyOptions(
const ColumnFamilyOptions& options,
const MutableCFOptions& mutable_cf_options) {
ColumnFamilyOptions cf_opts(options);
UpdateColumnFamilyOptions(mutable_cf_options, &cf_opts);
// TODO(yhchiang): find some way to handle the following derived options
// * max_file_size
return cf_opts;
}
void UpdateColumnFamilyOptions(const MutableCFOptions& moptions,
ColumnFamilyOptions* cf_opts) {
// Memtable related options
cf_opts->write_buffer_size = moptions.write_buffer_size;
cf_opts->max_write_buffer_number = moptions.max_write_buffer_number;
cf_opts->arena_block_size = moptions.arena_block_size;
cf_opts->memtable_prefix_bloom_size_ratio =
moptions.memtable_prefix_bloom_size_ratio;
cf_opts->memtable_whole_key_filtering = moptions.memtable_whole_key_filtering;
cf_opts->memtable_huge_page_size = moptions.memtable_huge_page_size;
cf_opts->max_successive_merges = moptions.max_successive_merges;
cf_opts->inplace_update_num_locks = moptions.inplace_update_num_locks;
cf_opts->prefix_extractor = moptions.prefix_extractor;
Dynamically changeable `MemPurge` option (#10011) Summary: **Summary** Make the mempurge option flag a Mutable Column Family option flag. Therefore, the mempurge feature can be dynamically toggled. **Motivation** RocksDB users prefer having the ability to switch features on and off without having to close and reopen the DB. This is particularly important if the feature causes issues and needs to be turned off. Dynamically changing a DB option flag does not seem currently possible. Moreover, with this new change, the MemPurge feature can be toggled on or off independently between column families, which we see as a major improvement. **Content of this PR** This PR includes removal of the `experimental_mempurge_threshold` flag as a DB option flag, and its re-introduction as a `MutableCFOption` flag. I updated the code to handle dynamic changes of the flag (in particular inside the `FlushJob` file). Additionally, this PR includes a new test to demonstrate the capacity of the code to toggle the MemPurge feature on and off, as well as the addition in the `db_stress` module of 2 different mempurge threshold values (0.0 and 1.0) that can be randomly changed with the `set_option_one_in` flag. This is useful to stress test the dynamic changes. **Benchmarking** I will add numbers to prove that there is no performance impact within the next 12 hours. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10011 Reviewed By: pdillinger Differential Revision: D36462357 Pulled By: bjlemaire fbshipit-source-id: 5e3d63bdadf085c0572ecc2349e7dd9729ce1802
2022-06-23 16:42:18 +00:00
cf_opts->experimental_mempurge_threshold =
moptions.experimental_mempurge_threshold;
Add memtable per key-value checksum (#10281) Summary: Append per key-value checksum to internal key. These checksums are verified on read paths including Get, Iterator and during Flush. Get and Iterator will return `Corruption` status if there is a checksum verification failure. Flush will make DB become read-only upon memtable entry checksum verification failure. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10281 Test Plan: - Added new unit test cases: `make check` - Benchmark on memtable insert ``` TEST_TMPDIR=/dev/shm/memtable_write ./db_bench -benchmarks=fillseq -disable_wal=true -max_write_buffer_number=100 -num=10000000 -min_write_buffer_number_to_merge=100 # avg over 10 runs Baseline: 1166936 ops/sec memtable 2 bytes kv checksum : 1.11674e+06 ops/sec (-4%) memtable 2 bytes kv checksum + write batch 8 bytes kv checksum: 1.08579e+06 ops/sec (-6.95%) write batch 8 bytes kv checksum: 1.17979e+06 ops/sec (+1.1%) ``` - Benchmark on only memtable read: ops/sec dropped 31% for `readseq` due to time spend on verifying checksum. ops/sec for `readrandom` dropped ~6.8%. ``` # Readseq sudo TEST_TMPDIR=/dev/shm/memtable_read ./db_bench -benchmarks=fillseq,readseq"[-X20]" -disable_wal=true -max_write_buffer_number=100 -num=10000000 -min_write_buffer_number_to_merge=100 readseq [AVG 20 runs] : 7432840 (± 212005) ops/sec; 822.3 (± 23.5) MB/sec readseq [MEDIAN 20 runs] : 7573878 ops/sec; 837.9 MB/sec With -memtable_protection_bytes_per_key=2: readseq [AVG 20 runs] : 5134607 (± 119596) ops/sec; 568.0 (± 13.2) MB/sec readseq [MEDIAN 20 runs] : 5232946 ops/sec; 578.9 MB/sec # Readrandom sudo TEST_TMPDIR=/dev/shm/memtable_read ./db_bench -benchmarks=fillrandom,readrandom"[-X10]" -disable_wal=true -max_write_buffer_number=100 -num=1000000 -min_write_buffer_number_to_merge=100 readrandom [AVG 10 runs] : 140236 (± 3938) ops/sec; 9.8 (± 0.3) MB/sec readrandom [MEDIAN 10 runs] : 140545 ops/sec; 9.8 MB/sec With -memtable_protection_bytes_per_key=2: readrandom [AVG 10 runs] : 130632 (± 2738) ops/sec; 9.1 (± 0.2) MB/sec readrandom [MEDIAN 10 runs] : 130341 ops/sec; 9.1 MB/sec ``` - Stress test: `python3 -u tools/db_crashtest.py whitebox --duration=1800` Reviewed By: ajkr Differential Revision: D37607896 Pulled By: cbi42 fbshipit-source-id: fdaefb475629d2471780d4a5f5bf81b44ee56113
2022-08-12 20:51:32 +00:00
cf_opts->memtable_protection_bytes_per_key =
moptions.memtable_protection_bytes_per_key;
Block per key-value checksum (#11287) Summary: add option `block_protection_bytes_per_key` and implementation for block per key-value checksum. The main changes are 1. checksum construction and verification in block.cc/h 2. pass the option `block_protection_bytes_per_key` around (mainly for methods defined in table_cache.h) 3. unit tests/crash test updates Tests: * Added unit tests * Crash test: `python3 tools/db_crashtest.py blackbox --simple --block_protection_bytes_per_key=1 --write_buffer_size=1048576` Follow up (maybe as a separate PR): make sure corruption status returned from BlockIters are correctly handled. Performance: Turning on block per KV protection has a non-trivial negative impact on read performance and costs additional memory. For memory, each block includes additional 24 bytes for checksum-related states beside checksum itself. For CPU, I set up a DB of size ~1.2GB with 5M keys (32 bytes key and 200 bytes value) which compacts to ~5 SST files (target file size 256 MB) in L6 without compression. I tested readrandom performance with various block cache size (to mimic various cache hit rates): ``` SETUP make OPTIMIZE_LEVEL="-O3" USE_LTO=1 DEBUG_LEVEL=0 -j32 db_bench ./db_bench -benchmarks=fillseq,compact0,waitforcompaction,compact,waitforcompaction -write_buffer_size=33554432 -level_compaction_dynamic_level_bytes=true -max_background_jobs=8 -target_file_size_base=268435456 --num=5000000 --key_size=32 --value_size=200 --compression_type=none BENCHMARK ./db_bench --use_existing_db -benchmarks=readtocache,readrandom[-X10] --num=5000000 --key_size=32 --disable_auto_compactions --reads=1000000 --block_protection_bytes_per_key=[0|1] --cache_size=$CACHESIZE The readrandom ops/sec looks like the following: Block cache size: 2GB 1.2GB * 0.9 1.2GB * 0.8 1.2GB * 0.5 8MB Main 240805 223604 198176 161653 139040 PR prot_bytes=0 238691 226693 200127 161082 141153 PR prot_bytes=1 214983 193199 178532 137013 108211 prot_bytes=1 vs -10% -15% -10.8% -15% -23% prot_bytes=0 ``` The benchmark has a lot of variance, but there was a 5% to 25% regression in this benchmark with different cache hit rates. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11287 Reviewed By: ajkr Differential Revision: D43970708 Pulled By: cbi42 fbshipit-source-id: ef98d898b71779846fa74212b9ec9e08b7183940
2023-04-25 19:08:23 +00:00
cf_opts->block_protection_bytes_per_key =
moptions.block_protection_bytes_per_key;
Delay bottommost level single file compactions (#11701) Summary: For leveled compaction, RocksDB has a special kind of compaction with reason "kBottommmostFiles" that compacts bottommost level files to clear data held by snapshots (more detail in https://github.com/facebook/rocksdb/issues/3009). Such compactions can happen soon after a relevant snapshot is released. For some use cases, a bottommost file may contain only a small amount of keys that can be cleared, so compacting such a file has a high write amp. In addition, these bottommost files may be compacted in compactions with reason other than "kBottommmostFiles" if we wait for some time (so that enough data is ingested to trigger such a compaction). This PR introduces an option `bottommost_file_compaction_delay` to specify the delay of these bottommost level single file compactions. * The main change is in `VersionStorageInfo::ComputeBottommostFilesMarkedForCompaction()` where we only add a file to `bottommost_files_marked_for_compaction_` if it oldest_snapshot is larger than its non-zero largest_seqno **and** the file is old enough. Note that if a file is not old enough but its largest_seqno is less than oldest_snapshot, we exclude it from the calculation of `bottommost_files_mark_threshold_`. This makes the change simpler, but such a file's eligibility for compaction will only be checked the next time `ComputeBottommostFilesMarkedForCompaction()` is called. This happens when a new Version is created (compaction, flush, SetOptions()...), a new enough snapshot is released (`VersionStorageInfo::UpdateOldestSnapshot()`) or when a compaction is picked and compaction score has to be re-calculated. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11701 Test Plan: * Add two unit tests to test when bottommost_file_compaction_delay > 0. * Ran crash test with the new option. Reviewed By: jaykorean, ajkr Differential Revision: D48331564 Pulled By: cbi42 fbshipit-source-id: c584f3dc5f6354fce3ed65f4c6366dc450b15ba8
2023-08-17 00:45:44 +00:00
cf_opts->bottommost_file_compaction_delay =
moptions.bottommost_file_compaction_delay;
// Compaction related options
cf_opts->disable_auto_compactions = moptions.disable_auto_compactions;
cf_opts->soft_pending_compaction_bytes_limit =
moptions.soft_pending_compaction_bytes_limit;
cf_opts->hard_pending_compaction_bytes_limit =
moptions.hard_pending_compaction_bytes_limit;
cf_opts->level0_file_num_compaction_trigger =
moptions.level0_file_num_compaction_trigger;
cf_opts->level0_slowdown_writes_trigger =
moptions.level0_slowdown_writes_trigger;
cf_opts->level0_stop_writes_trigger = moptions.level0_stop_writes_trigger;
cf_opts->max_compaction_bytes = moptions.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
2022-10-21 17:22:41 +00:00
cf_opts->ignore_max_compaction_bytes_for_input =
moptions.ignore_max_compaction_bytes_for_input;
cf_opts->target_file_size_base = moptions.target_file_size_base;
cf_opts->target_file_size_multiplier = moptions.target_file_size_multiplier;
cf_opts->max_bytes_for_level_base = moptions.max_bytes_for_level_base;
cf_opts->max_bytes_for_level_multiplier =
moptions.max_bytes_for_level_multiplier;
cf_opts->ttl = moptions.ttl;
cf_opts->periodic_compaction_seconds = moptions.periodic_compaction_seconds;
cf_opts->max_bytes_for_level_multiplier_additional.clear();
for (auto value : moptions.max_bytes_for_level_multiplier_additional) {
cf_opts->max_bytes_for_level_multiplier_additional.emplace_back(value);
}
cf_opts->compaction_options_fifo = moptions.compaction_options_fifo;
cf_opts->compaction_options_universal = moptions.compaction_options_universal;
// Blob file related options
cf_opts->enable_blob_files = moptions.enable_blob_files;
cf_opts->min_blob_size = moptions.min_blob_size;
cf_opts->blob_file_size = moptions.blob_file_size;
cf_opts->blob_compression_type = moptions.blob_compression_type;
cf_opts->enable_blob_garbage_collection =
moptions.enable_blob_garbage_collection;
cf_opts->blob_garbage_collection_age_cutoff =
moptions.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
2021-10-12 01:00:44 +00:00
cf_opts->blob_garbage_collection_force_threshold =
moptions.blob_garbage_collection_force_threshold;
cf_opts->blob_compaction_readahead_size =
moptions.blob_compaction_readahead_size;
Make it possible to enable blob files starting from a certain LSM tree level (#10077) Summary: Currently, if blob files are enabled (i.e. `enable_blob_files` is true), large values are extracted both during flush/recovery (when SST files are written into level 0 of the LSM tree) and during compaction into any LSM tree level. For certain use cases that have a mix of short-lived and long-lived values, it might make sense to support extracting large values only during compactions whose output level is greater than or equal to a specified LSM tree level (e.g. compactions into L1/L2/... or above). This could reduce the space amplification caused by large values that are turned into garbage shortly after being written at the price of some write amplification incurred by long-lived values whose extraction to blob files is delayed. In order to achieve this, we would like to do the following: - Add a new configuration option `blob_file_starting_level` (default: 0) to `AdvancedColumnFamilyOptions` (and `MutableCFOptions` and extend the related logic) - Instantiate `BlobFileBuilder` in `BuildTable` (used during flush and recovery, where the LSM tree level is L0) and `CompactionJob` iff `enable_blob_files` is set and the LSM tree level is `>= blob_file_starting_level` - Add unit tests for the new functionality, and add the new option to our stress tests (`db_stress` and `db_crashtest.py` ) - Add the new option to our benchmarking tool `db_bench` and the BlobDB benchmark script `run_blob_bench.sh` - Add the new option to the `ldb` tool (see https://github.com/facebook/rocksdb/wiki/Administration-and-Data-Access-Tool) - Ideally extend the C and Java bindings with the new option - Update the BlobDB wiki to document the new option. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10077 Reviewed By: ltamasi Differential Revision: D36884156 Pulled By: gangliao fbshipit-source-id: 942bab025f04633edca8564ed64791cb5e31627d
2022-06-03 03:04:33 +00:00
cf_opts->blob_file_starting_level = moptions.blob_file_starting_level;
cf_opts->prepopulate_blob_cache = moptions.prepopulate_blob_cache;
// Misc options
cf_opts->max_sequential_skip_in_iterations =
moptions.max_sequential_skip_in_iterations;
cf_opts->check_flush_compaction_key_order =
moptions.check_flush_compaction_key_order;
cf_opts->paranoid_file_checks = moptions.paranoid_file_checks;
cf_opts->report_bg_io_stats = moptions.report_bg_io_stats;
cf_opts->compression = moptions.compression;
cf_opts->compression_opts = moptions.compression_opts;
cf_opts->bottommost_compression = moptions.bottommost_compression;
cf_opts->bottommost_compression_opts = moptions.bottommost_compression_opts;
cf_opts->sample_for_compression = moptions.sample_for_compression;
cf_opts->compression_per_level = moptions.compression_per_level;
cf_opts->last_level_temperature = moptions.last_level_temperature;
cf_opts->bottommost_temperature = moptions.last_level_temperature;
cf_opts->memtable_max_range_deletions = moptions.memtable_max_range_deletions;
}
void UpdateColumnFamilyOptions(const ImmutableCFOptions& ioptions,
ColumnFamilyOptions* cf_opts) {
cf_opts->compaction_style = ioptions.compaction_style;
cf_opts->compaction_pri = ioptions.compaction_pri;
cf_opts->comparator = ioptions.user_comparator;
cf_opts->merge_operator = ioptions.merge_operator;
cf_opts->compaction_filter = ioptions.compaction_filter;
cf_opts->compaction_filter_factory = ioptions.compaction_filter_factory;
cf_opts->min_write_buffer_number_to_merge =
ioptions.min_write_buffer_number_to_merge;
cf_opts->max_write_buffer_number_to_maintain =
ioptions.max_write_buffer_number_to_maintain;
cf_opts->max_write_buffer_size_to_maintain =
ioptions.max_write_buffer_size_to_maintain;
cf_opts->inplace_update_support = ioptions.inplace_update_support;
cf_opts->inplace_callback = ioptions.inplace_callback;
cf_opts->memtable_factory = ioptions.memtable_factory;
cf_opts->table_factory = ioptions.table_factory;
cf_opts->table_properties_collector_factories =
ioptions.table_properties_collector_factories;
cf_opts->bloom_locality = ioptions.bloom_locality;
cf_opts->level_compaction_dynamic_level_bytes =
ioptions.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
2022-09-30 02:43:55 +00:00
cf_opts->level_compaction_dynamic_file_size =
ioptions.level_compaction_dynamic_file_size;
cf_opts->num_levels = ioptions.num_levels;
cf_opts->optimize_filters_for_hits = ioptions.optimize_filters_for_hits;
cf_opts->force_consistency_checks = ioptions.force_consistency_checks;
cf_opts->memtable_insert_with_hint_prefix_extractor =
ioptions.memtable_insert_with_hint_prefix_extractor;
cf_opts->cf_paths = ioptions.cf_paths;
cf_opts->compaction_thread_limiter = ioptions.compaction_thread_limiter;
cf_opts->sst_partitioner_factory = ioptions.sst_partitioner_factory;
cf_opts->blob_cache = ioptions.blob_cache;
cf_opts->preclude_last_level_data_seconds =
ioptions.preclude_last_level_data_seconds;
cf_opts->preserve_internal_time_seconds =
ioptions.preserve_internal_time_seconds;
cf_opts->persist_user_defined_timestamps =
ioptions.persist_user_defined_timestamps;
cf_opts->default_temperature = ioptions.default_temperature;
// TODO(yhchiang): find some way to handle the following derived options
// * max_file_size
}
std::map<CompactionStyle, std::string>
OptionsHelper::compaction_style_to_string = {
{kCompactionStyleLevel, "kCompactionStyleLevel"},
{kCompactionStyleUniversal, "kCompactionStyleUniversal"},
{kCompactionStyleFIFO, "kCompactionStyleFIFO"},
{kCompactionStyleNone, "kCompactionStyleNone"}};
std::map<CompactionPri, std::string> OptionsHelper::compaction_pri_to_string = {
{kByCompensatedSize, "kByCompensatedSize"},
{kOldestLargestSeqFirst, "kOldestLargestSeqFirst"},
{kOldestSmallestSeqFirst, "kOldestSmallestSeqFirst"},
Add basic kRoundRobin compaction policy (#10107) Summary: Add `kRoundRobin` as a compaction priority. The implementation is as follows. - Define a cursor as the smallest Internal key in the successor of the selected file. Add `vector<InternalKey> compact_cursor_` into `VersionStorageInfo` where each element (`InternalKey`) in `compact_cursor_` represents a cursor. In round-robin compaction policy, we just need to select the first file (assuming files are sorted) and also has the smallest InternalKey larger than/equal to the cursor. After a file is chosen, we create a new `Fsize` vector which puts the selected file is placed at the first position in `temp`, the next cursor is then updated as the smallest InternalKey in successor of the selected file (the above logic is implemented in `SortFileByRoundRobin`). - After a compaction succeeds, typically `InstallCompactionResults()`, we choose the next cursor for the input level and save it to `edit`. When calling `LogAndApply`, we save the next cursor with its level into some local variable and finally apply the change to `vstorage` in `SaveTo` function. - Cursors are persist pair by pair (<level, InternalKey>) in `EncodeTo` so that they can be reconstructed when reopening. An empty cursor will not be encoded to MANIFEST Pull Request resolved: https://github.com/facebook/rocksdb/pull/10107 Test Plan: add unit test (`CompactionPriRoundRobin`) in `compaction_picker_test`, add `kRoundRobin` priority in `CompactionPriTest` from `db_compaction_test`, and add `PersistRoundRobinCompactCursor` in `db_compaction_test` Reviewed By: ajkr Differential Revision: D37316037 Pulled By: littlepig2013 fbshipit-source-id: 9f481748190ace416079139044e00df2968fb1ee
2022-06-21 18:56:53 +00:00
{kMinOverlappingRatio, "kMinOverlappingRatio"},
{kRoundRobin, "kRoundRobin"}};
std::map<CompactionStopStyle, std::string>
OptionsHelper::compaction_stop_style_to_string = {
{kCompactionStopStyleSimilarSize, "kCompactionStopStyleSimilarSize"},
{kCompactionStopStyleTotalSize, "kCompactionStopStyleTotalSize"}};
New backup meta schema, with file temperatures (#9660) Summary: The primary goal of this change is to add support for backing up and restoring (applying on restore) file temperature metadata, without committing to either the DB manifest or the FS reported "current" temperatures being exclusive "source of truth". To achieve this goal, we need to add temperature information to backup metadata, which requires updated backup meta schema. Fortunately I prepared for this in https://github.com/facebook/rocksdb/issues/8069, which began forward compatibility in version 6.19.0 for this kind of schema update. (Previously, backup meta schema was not extensible! Making this schema update public will allow some other "nice to have" features like taking backups with hard links, and avoiding crc32c checksum computation when another checksum is already available.) While schema version 2 is newly public, the default schema version is still 1. Until we change the default, users will need to set to 2 to enable features like temperature data backup+restore. New metadata like temperature information will be ignored with a warning in versions before this change and since 6.19.0. The metadata is considered ignorable because a functioning DB can be restored without it. Some detail: * Some renaming because "future schema" is now just public schema 2. * Initialize some atomics in TestFs (linter reported) * Add temperature hint support to SstFileDumper (used by BackupEngine) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9660 Test Plan: related unit test majorly updated for the new functionality, including some shared testing support for tracking temperatures in a FS. Some other tests and testing hooks into production code also updated for making the backup meta schema change public. Reviewed By: ajkr Differential Revision: D34686968 Pulled By: pdillinger fbshipit-source-id: 3ac1fa3e67ee97ca8a5103d79cc87d872c1d862a
2022-03-18 18:06:17 +00:00
std::map<Temperature, std::string> OptionsHelper::temperature_to_string = {
{Temperature::kUnknown, "kUnknown"},
{Temperature::kHot, "kHot"},
{Temperature::kWarm, "kWarm"},
{Temperature::kCold, "kCold"}};
std::unordered_map<std::string, ChecksumType>
OptionsHelper::checksum_type_string_map = {{"kNoChecksum", kNoChecksum},
{"kCRC32c", kCRC32c},
{"kxxHash", kxxHash},
Implement XXH3 block checksum type (#9069) Summary: XXH3 - latest hash function that is extremely fast on large data, easily faster than crc32c on most any x86_64 hardware. In integrating this hash function, I have handled the compression type byte in a non-standard way to avoid using the streaming API (extra data movement and active code size because of hash function complexity). This approach got a thumbs-up from Yann Collet. Existing functionality change: * reject bad ChecksumType in options with InvalidArgument This change split off from https://github.com/facebook/rocksdb/issues/9058 because context-aware checksum is likely to be handled through different configuration than ChecksumType. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9069 Test Plan: tests updated, and substantially expanded. Unit tests now check that we don't accidentally change the values generated by the checksum algorithms ("schema test") and that we properly handle invalid/unrecognized checksum types in options or in file footer. DBTestBase::ChangeOptions (etc.) updated from two to one configuration changing from default CRC32c ChecksumType. The point of this test code is to detect possible interactions among features, and the likelihood of some bad interaction being detected by including configurations other than XXH3 and CRC32c--and then not detected by stress/crash test--is extremely low. Stress/crash test also updated (manual run long enough to see it accepts new checksum type). db_bench also updated for microbenchmarking checksums. ### Performance microbenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) ./db_bench -benchmarks=crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3 crc32c : 0.200 micros/op 5005220 ops/sec; 19551.6 MB/s (4096 per op) xxhash : 0.807 micros/op 1238408 ops/sec; 4837.5 MB/s (4096 per op) xxhash64 : 0.421 micros/op 2376514 ops/sec; 9283.3 MB/s (4096 per op) xxh3 : 0.171 micros/op 5858391 ops/sec; 22884.3 MB/s (4096 per op) crc32c : 0.206 micros/op 4859566 ops/sec; 18982.7 MB/s (4096 per op) xxhash : 0.793 micros/op 1260850 ops/sec; 4925.2 MB/s (4096 per op) xxhash64 : 0.410 micros/op 2439182 ops/sec; 9528.1 MB/s (4096 per op) xxh3 : 0.161 micros/op 6202872 ops/sec; 24230.0 MB/s (4096 per op) crc32c : 0.203 micros/op 4924686 ops/sec; 19237.1 MB/s (4096 per op) xxhash : 0.839 micros/op 1192388 ops/sec; 4657.8 MB/s (4096 per op) xxhash64 : 0.424 micros/op 2357391 ops/sec; 9208.6 MB/s (4096 per op) xxh3 : 0.162 micros/op 6182678 ops/sec; 24151.1 MB/s (4096 per op) As you can see, especially once warmed up, xxh3 is fastest. ### Performance macrobenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) Test for I in `seq 1 50`; do for CHK in 0 1 2 3 4; do TEST_TMPDIR=/dev/shm/rocksdb$CHK ./db_bench -benchmarks=fillseq -memtablerep=vector -allow_concurrent_memtable_write=false -num=30000000 -checksum_type=$CHK 2>&1 | grep 'micros/op' | tee -a results-$CHK & done; wait; done Results (ops/sec) for FILE in results*; do echo -n "$FILE "; awk '{ s += $5; c++; } END { print 1.0 * s / c; }' < $FILE; done results-0 252118 # kNoChecksum results-1 251588 # kCRC32c results-2 251863 # kxxHash results-3 252016 # kxxHash64 results-4 252038 # kXXH3 Reviewed By: mrambacher Differential Revision: D31905249 Pulled By: pdillinger fbshipit-source-id: cb9b998ebe2523fc7c400eedf62124a78bf4b4d1
2021-10-29 05:13:47 +00:00
{"kxxHash64", kxxHash64},
{"kXXH3", kXXH3}};
std::unordered_map<std::string, CompressionType>
OptionsHelper::compression_type_string_map = {
{"kNoCompression", kNoCompression},
{"kSnappyCompression", kSnappyCompression},
{"kZlibCompression", kZlibCompression},
{"kBZip2Compression", kBZip2Compression},
{"kLZ4Compression", kLZ4Compression},
{"kLZ4HCCompression", kLZ4HCCompression},
{"kXpressCompression", kXpressCompression},
{"kZSTD", kZSTD},
{"kZSTDNotFinalCompression", kZSTDNotFinalCompression},
{"kDisableCompressionOption", kDisableCompressionOption}};
std::vector<CompressionType> GetSupportedCompressions() {
Implement XXH3 block checksum type (#9069) Summary: XXH3 - latest hash function that is extremely fast on large data, easily faster than crc32c on most any x86_64 hardware. In integrating this hash function, I have handled the compression type byte in a non-standard way to avoid using the streaming API (extra data movement and active code size because of hash function complexity). This approach got a thumbs-up from Yann Collet. Existing functionality change: * reject bad ChecksumType in options with InvalidArgument This change split off from https://github.com/facebook/rocksdb/issues/9058 because context-aware checksum is likely to be handled through different configuration than ChecksumType. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9069 Test Plan: tests updated, and substantially expanded. Unit tests now check that we don't accidentally change the values generated by the checksum algorithms ("schema test") and that we properly handle invalid/unrecognized checksum types in options or in file footer. DBTestBase::ChangeOptions (etc.) updated from two to one configuration changing from default CRC32c ChecksumType. The point of this test code is to detect possible interactions among features, and the likelihood of some bad interaction being detected by including configurations other than XXH3 and CRC32c--and then not detected by stress/crash test--is extremely low. Stress/crash test also updated (manual run long enough to see it accepts new checksum type). db_bench also updated for microbenchmarking checksums. ### Performance microbenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) ./db_bench -benchmarks=crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3 crc32c : 0.200 micros/op 5005220 ops/sec; 19551.6 MB/s (4096 per op) xxhash : 0.807 micros/op 1238408 ops/sec; 4837.5 MB/s (4096 per op) xxhash64 : 0.421 micros/op 2376514 ops/sec; 9283.3 MB/s (4096 per op) xxh3 : 0.171 micros/op 5858391 ops/sec; 22884.3 MB/s (4096 per op) crc32c : 0.206 micros/op 4859566 ops/sec; 18982.7 MB/s (4096 per op) xxhash : 0.793 micros/op 1260850 ops/sec; 4925.2 MB/s (4096 per op) xxhash64 : 0.410 micros/op 2439182 ops/sec; 9528.1 MB/s (4096 per op) xxh3 : 0.161 micros/op 6202872 ops/sec; 24230.0 MB/s (4096 per op) crc32c : 0.203 micros/op 4924686 ops/sec; 19237.1 MB/s (4096 per op) xxhash : 0.839 micros/op 1192388 ops/sec; 4657.8 MB/s (4096 per op) xxhash64 : 0.424 micros/op 2357391 ops/sec; 9208.6 MB/s (4096 per op) xxh3 : 0.162 micros/op 6182678 ops/sec; 24151.1 MB/s (4096 per op) As you can see, especially once warmed up, xxh3 is fastest. ### Performance macrobenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) Test for I in `seq 1 50`; do for CHK in 0 1 2 3 4; do TEST_TMPDIR=/dev/shm/rocksdb$CHK ./db_bench -benchmarks=fillseq -memtablerep=vector -allow_concurrent_memtable_write=false -num=30000000 -checksum_type=$CHK 2>&1 | grep 'micros/op' | tee -a results-$CHK & done; wait; done Results (ops/sec) for FILE in results*; do echo -n "$FILE "; awk '{ s += $5; c++; } END { print 1.0 * s / c; }' < $FILE; done results-0 252118 # kNoChecksum results-1 251588 # kCRC32c results-2 251863 # kxxHash results-3 252016 # kxxHash64 results-4 252038 # kXXH3 Reviewed By: mrambacher Differential Revision: D31905249 Pulled By: pdillinger fbshipit-source-id: cb9b998ebe2523fc7c400eedf62124a78bf4b4d1
2021-10-29 05:13:47 +00:00
// std::set internally to deduplicate potential name aliases
std::set<CompressionType> supported_compressions;
for (const auto& comp_to_name : OptionsHelper::compression_type_string_map) {
CompressionType t = comp_to_name.second;
if (t != kDisableCompressionOption && CompressionTypeSupported(t)) {
Implement XXH3 block checksum type (#9069) Summary: XXH3 - latest hash function that is extremely fast on large data, easily faster than crc32c on most any x86_64 hardware. In integrating this hash function, I have handled the compression type byte in a non-standard way to avoid using the streaming API (extra data movement and active code size because of hash function complexity). This approach got a thumbs-up from Yann Collet. Existing functionality change: * reject bad ChecksumType in options with InvalidArgument This change split off from https://github.com/facebook/rocksdb/issues/9058 because context-aware checksum is likely to be handled through different configuration than ChecksumType. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9069 Test Plan: tests updated, and substantially expanded. Unit tests now check that we don't accidentally change the values generated by the checksum algorithms ("schema test") and that we properly handle invalid/unrecognized checksum types in options or in file footer. DBTestBase::ChangeOptions (etc.) updated from two to one configuration changing from default CRC32c ChecksumType. The point of this test code is to detect possible interactions among features, and the likelihood of some bad interaction being detected by including configurations other than XXH3 and CRC32c--and then not detected by stress/crash test--is extremely low. Stress/crash test also updated (manual run long enough to see it accepts new checksum type). db_bench also updated for microbenchmarking checksums. ### Performance microbenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) ./db_bench -benchmarks=crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3 crc32c : 0.200 micros/op 5005220 ops/sec; 19551.6 MB/s (4096 per op) xxhash : 0.807 micros/op 1238408 ops/sec; 4837.5 MB/s (4096 per op) xxhash64 : 0.421 micros/op 2376514 ops/sec; 9283.3 MB/s (4096 per op) xxh3 : 0.171 micros/op 5858391 ops/sec; 22884.3 MB/s (4096 per op) crc32c : 0.206 micros/op 4859566 ops/sec; 18982.7 MB/s (4096 per op) xxhash : 0.793 micros/op 1260850 ops/sec; 4925.2 MB/s (4096 per op) xxhash64 : 0.410 micros/op 2439182 ops/sec; 9528.1 MB/s (4096 per op) xxh3 : 0.161 micros/op 6202872 ops/sec; 24230.0 MB/s (4096 per op) crc32c : 0.203 micros/op 4924686 ops/sec; 19237.1 MB/s (4096 per op) xxhash : 0.839 micros/op 1192388 ops/sec; 4657.8 MB/s (4096 per op) xxhash64 : 0.424 micros/op 2357391 ops/sec; 9208.6 MB/s (4096 per op) xxh3 : 0.162 micros/op 6182678 ops/sec; 24151.1 MB/s (4096 per op) As you can see, especially once warmed up, xxh3 is fastest. ### Performance macrobenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) Test for I in `seq 1 50`; do for CHK in 0 1 2 3 4; do TEST_TMPDIR=/dev/shm/rocksdb$CHK ./db_bench -benchmarks=fillseq -memtablerep=vector -allow_concurrent_memtable_write=false -num=30000000 -checksum_type=$CHK 2>&1 | grep 'micros/op' | tee -a results-$CHK & done; wait; done Results (ops/sec) for FILE in results*; do echo -n "$FILE "; awk '{ s += $5; c++; } END { print 1.0 * s / c; }' < $FILE; done results-0 252118 # kNoChecksum results-1 251588 # kCRC32c results-2 251863 # kxxHash results-3 252016 # kxxHash64 results-4 252038 # kXXH3 Reviewed By: mrambacher Differential Revision: D31905249 Pulled By: pdillinger fbshipit-source-id: cb9b998ebe2523fc7c400eedf62124a78bf4b4d1
2021-10-29 05:13:47 +00:00
supported_compressions.insert(t);
}
}
Implement XXH3 block checksum type (#9069) Summary: XXH3 - latest hash function that is extremely fast on large data, easily faster than crc32c on most any x86_64 hardware. In integrating this hash function, I have handled the compression type byte in a non-standard way to avoid using the streaming API (extra data movement and active code size because of hash function complexity). This approach got a thumbs-up from Yann Collet. Existing functionality change: * reject bad ChecksumType in options with InvalidArgument This change split off from https://github.com/facebook/rocksdb/issues/9058 because context-aware checksum is likely to be handled through different configuration than ChecksumType. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9069 Test Plan: tests updated, and substantially expanded. Unit tests now check that we don't accidentally change the values generated by the checksum algorithms ("schema test") and that we properly handle invalid/unrecognized checksum types in options or in file footer. DBTestBase::ChangeOptions (etc.) updated from two to one configuration changing from default CRC32c ChecksumType. The point of this test code is to detect possible interactions among features, and the likelihood of some bad interaction being detected by including configurations other than XXH3 and CRC32c--and then not detected by stress/crash test--is extremely low. Stress/crash test also updated (manual run long enough to see it accepts new checksum type). db_bench also updated for microbenchmarking checksums. ### Performance microbenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) ./db_bench -benchmarks=crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3 crc32c : 0.200 micros/op 5005220 ops/sec; 19551.6 MB/s (4096 per op) xxhash : 0.807 micros/op 1238408 ops/sec; 4837.5 MB/s (4096 per op) xxhash64 : 0.421 micros/op 2376514 ops/sec; 9283.3 MB/s (4096 per op) xxh3 : 0.171 micros/op 5858391 ops/sec; 22884.3 MB/s (4096 per op) crc32c : 0.206 micros/op 4859566 ops/sec; 18982.7 MB/s (4096 per op) xxhash : 0.793 micros/op 1260850 ops/sec; 4925.2 MB/s (4096 per op) xxhash64 : 0.410 micros/op 2439182 ops/sec; 9528.1 MB/s (4096 per op) xxh3 : 0.161 micros/op 6202872 ops/sec; 24230.0 MB/s (4096 per op) crc32c : 0.203 micros/op 4924686 ops/sec; 19237.1 MB/s (4096 per op) xxhash : 0.839 micros/op 1192388 ops/sec; 4657.8 MB/s (4096 per op) xxhash64 : 0.424 micros/op 2357391 ops/sec; 9208.6 MB/s (4096 per op) xxh3 : 0.162 micros/op 6182678 ops/sec; 24151.1 MB/s (4096 per op) As you can see, especially once warmed up, xxh3 is fastest. ### Performance macrobenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) Test for I in `seq 1 50`; do for CHK in 0 1 2 3 4; do TEST_TMPDIR=/dev/shm/rocksdb$CHK ./db_bench -benchmarks=fillseq -memtablerep=vector -allow_concurrent_memtable_write=false -num=30000000 -checksum_type=$CHK 2>&1 | grep 'micros/op' | tee -a results-$CHK & done; wait; done Results (ops/sec) for FILE in results*; do echo -n "$FILE "; awk '{ s += $5; c++; } END { print 1.0 * s / c; }' < $FILE; done results-0 252118 # kNoChecksum results-1 251588 # kCRC32c results-2 251863 # kxxHash results-3 252016 # kxxHash64 results-4 252038 # kXXH3 Reviewed By: mrambacher Differential Revision: D31905249 Pulled By: pdillinger fbshipit-source-id: cb9b998ebe2523fc7c400eedf62124a78bf4b4d1
2021-10-29 05:13:47 +00:00
return std::vector<CompressionType>(supported_compressions.begin(),
supported_compressions.end());
}
std::vector<CompressionType> GetSupportedDictCompressions() {
Implement XXH3 block checksum type (#9069) Summary: XXH3 - latest hash function that is extremely fast on large data, easily faster than crc32c on most any x86_64 hardware. In integrating this hash function, I have handled the compression type byte in a non-standard way to avoid using the streaming API (extra data movement and active code size because of hash function complexity). This approach got a thumbs-up from Yann Collet. Existing functionality change: * reject bad ChecksumType in options with InvalidArgument This change split off from https://github.com/facebook/rocksdb/issues/9058 because context-aware checksum is likely to be handled through different configuration than ChecksumType. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9069 Test Plan: tests updated, and substantially expanded. Unit tests now check that we don't accidentally change the values generated by the checksum algorithms ("schema test") and that we properly handle invalid/unrecognized checksum types in options or in file footer. DBTestBase::ChangeOptions (etc.) updated from two to one configuration changing from default CRC32c ChecksumType. The point of this test code is to detect possible interactions among features, and the likelihood of some bad interaction being detected by including configurations other than XXH3 and CRC32c--and then not detected by stress/crash test--is extremely low. Stress/crash test also updated (manual run long enough to see it accepts new checksum type). db_bench also updated for microbenchmarking checksums. ### Performance microbenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) ./db_bench -benchmarks=crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3 crc32c : 0.200 micros/op 5005220 ops/sec; 19551.6 MB/s (4096 per op) xxhash : 0.807 micros/op 1238408 ops/sec; 4837.5 MB/s (4096 per op) xxhash64 : 0.421 micros/op 2376514 ops/sec; 9283.3 MB/s (4096 per op) xxh3 : 0.171 micros/op 5858391 ops/sec; 22884.3 MB/s (4096 per op) crc32c : 0.206 micros/op 4859566 ops/sec; 18982.7 MB/s (4096 per op) xxhash : 0.793 micros/op 1260850 ops/sec; 4925.2 MB/s (4096 per op) xxhash64 : 0.410 micros/op 2439182 ops/sec; 9528.1 MB/s (4096 per op) xxh3 : 0.161 micros/op 6202872 ops/sec; 24230.0 MB/s (4096 per op) crc32c : 0.203 micros/op 4924686 ops/sec; 19237.1 MB/s (4096 per op) xxhash : 0.839 micros/op 1192388 ops/sec; 4657.8 MB/s (4096 per op) xxhash64 : 0.424 micros/op 2357391 ops/sec; 9208.6 MB/s (4096 per op) xxh3 : 0.162 micros/op 6182678 ops/sec; 24151.1 MB/s (4096 per op) As you can see, especially once warmed up, xxh3 is fastest. ### Performance macrobenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) Test for I in `seq 1 50`; do for CHK in 0 1 2 3 4; do TEST_TMPDIR=/dev/shm/rocksdb$CHK ./db_bench -benchmarks=fillseq -memtablerep=vector -allow_concurrent_memtable_write=false -num=30000000 -checksum_type=$CHK 2>&1 | grep 'micros/op' | tee -a results-$CHK & done; wait; done Results (ops/sec) for FILE in results*; do echo -n "$FILE "; awk '{ s += $5; c++; } END { print 1.0 * s / c; }' < $FILE; done results-0 252118 # kNoChecksum results-1 251588 # kCRC32c results-2 251863 # kxxHash results-3 252016 # kxxHash64 results-4 252038 # kXXH3 Reviewed By: mrambacher Differential Revision: D31905249 Pulled By: pdillinger fbshipit-source-id: cb9b998ebe2523fc7c400eedf62124a78bf4b4d1
2021-10-29 05:13:47 +00:00
std::set<CompressionType> dict_compression_types;
for (const auto& comp_to_name : OptionsHelper::compression_type_string_map) {
CompressionType t = comp_to_name.second;
if (t != kDisableCompressionOption && DictCompressionTypeSupported(t)) {
Implement XXH3 block checksum type (#9069) Summary: XXH3 - latest hash function that is extremely fast on large data, easily faster than crc32c on most any x86_64 hardware. In integrating this hash function, I have handled the compression type byte in a non-standard way to avoid using the streaming API (extra data movement and active code size because of hash function complexity). This approach got a thumbs-up from Yann Collet. Existing functionality change: * reject bad ChecksumType in options with InvalidArgument This change split off from https://github.com/facebook/rocksdb/issues/9058 because context-aware checksum is likely to be handled through different configuration than ChecksumType. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9069 Test Plan: tests updated, and substantially expanded. Unit tests now check that we don't accidentally change the values generated by the checksum algorithms ("schema test") and that we properly handle invalid/unrecognized checksum types in options or in file footer. DBTestBase::ChangeOptions (etc.) updated from two to one configuration changing from default CRC32c ChecksumType. The point of this test code is to detect possible interactions among features, and the likelihood of some bad interaction being detected by including configurations other than XXH3 and CRC32c--and then not detected by stress/crash test--is extremely low. Stress/crash test also updated (manual run long enough to see it accepts new checksum type). db_bench also updated for microbenchmarking checksums. ### Performance microbenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) ./db_bench -benchmarks=crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3 crc32c : 0.200 micros/op 5005220 ops/sec; 19551.6 MB/s (4096 per op) xxhash : 0.807 micros/op 1238408 ops/sec; 4837.5 MB/s (4096 per op) xxhash64 : 0.421 micros/op 2376514 ops/sec; 9283.3 MB/s (4096 per op) xxh3 : 0.171 micros/op 5858391 ops/sec; 22884.3 MB/s (4096 per op) crc32c : 0.206 micros/op 4859566 ops/sec; 18982.7 MB/s (4096 per op) xxhash : 0.793 micros/op 1260850 ops/sec; 4925.2 MB/s (4096 per op) xxhash64 : 0.410 micros/op 2439182 ops/sec; 9528.1 MB/s (4096 per op) xxh3 : 0.161 micros/op 6202872 ops/sec; 24230.0 MB/s (4096 per op) crc32c : 0.203 micros/op 4924686 ops/sec; 19237.1 MB/s (4096 per op) xxhash : 0.839 micros/op 1192388 ops/sec; 4657.8 MB/s (4096 per op) xxhash64 : 0.424 micros/op 2357391 ops/sec; 9208.6 MB/s (4096 per op) xxh3 : 0.162 micros/op 6182678 ops/sec; 24151.1 MB/s (4096 per op) As you can see, especially once warmed up, xxh3 is fastest. ### Performance macrobenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) Test for I in `seq 1 50`; do for CHK in 0 1 2 3 4; do TEST_TMPDIR=/dev/shm/rocksdb$CHK ./db_bench -benchmarks=fillseq -memtablerep=vector -allow_concurrent_memtable_write=false -num=30000000 -checksum_type=$CHK 2>&1 | grep 'micros/op' | tee -a results-$CHK & done; wait; done Results (ops/sec) for FILE in results*; do echo -n "$FILE "; awk '{ s += $5; c++; } END { print 1.0 * s / c; }' < $FILE; done results-0 252118 # kNoChecksum results-1 251588 # kCRC32c results-2 251863 # kxxHash results-3 252016 # kxxHash64 results-4 252038 # kXXH3 Reviewed By: mrambacher Differential Revision: D31905249 Pulled By: pdillinger fbshipit-source-id: cb9b998ebe2523fc7c400eedf62124a78bf4b4d1
2021-10-29 05:13:47 +00:00
dict_compression_types.insert(t);
}
}
Implement XXH3 block checksum type (#9069) Summary: XXH3 - latest hash function that is extremely fast on large data, easily faster than crc32c on most any x86_64 hardware. In integrating this hash function, I have handled the compression type byte in a non-standard way to avoid using the streaming API (extra data movement and active code size because of hash function complexity). This approach got a thumbs-up from Yann Collet. Existing functionality change: * reject bad ChecksumType in options with InvalidArgument This change split off from https://github.com/facebook/rocksdb/issues/9058 because context-aware checksum is likely to be handled through different configuration than ChecksumType. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9069 Test Plan: tests updated, and substantially expanded. Unit tests now check that we don't accidentally change the values generated by the checksum algorithms ("schema test") and that we properly handle invalid/unrecognized checksum types in options or in file footer. DBTestBase::ChangeOptions (etc.) updated from two to one configuration changing from default CRC32c ChecksumType. The point of this test code is to detect possible interactions among features, and the likelihood of some bad interaction being detected by including configurations other than XXH3 and CRC32c--and then not detected by stress/crash test--is extremely low. Stress/crash test also updated (manual run long enough to see it accepts new checksum type). db_bench also updated for microbenchmarking checksums. ### Performance microbenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) ./db_bench -benchmarks=crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3,crc32c,xxhash,xxhash64,xxh3 crc32c : 0.200 micros/op 5005220 ops/sec; 19551.6 MB/s (4096 per op) xxhash : 0.807 micros/op 1238408 ops/sec; 4837.5 MB/s (4096 per op) xxhash64 : 0.421 micros/op 2376514 ops/sec; 9283.3 MB/s (4096 per op) xxh3 : 0.171 micros/op 5858391 ops/sec; 22884.3 MB/s (4096 per op) crc32c : 0.206 micros/op 4859566 ops/sec; 18982.7 MB/s (4096 per op) xxhash : 0.793 micros/op 1260850 ops/sec; 4925.2 MB/s (4096 per op) xxhash64 : 0.410 micros/op 2439182 ops/sec; 9528.1 MB/s (4096 per op) xxh3 : 0.161 micros/op 6202872 ops/sec; 24230.0 MB/s (4096 per op) crc32c : 0.203 micros/op 4924686 ops/sec; 19237.1 MB/s (4096 per op) xxhash : 0.839 micros/op 1192388 ops/sec; 4657.8 MB/s (4096 per op) xxhash64 : 0.424 micros/op 2357391 ops/sec; 9208.6 MB/s (4096 per op) xxh3 : 0.162 micros/op 6182678 ops/sec; 24151.1 MB/s (4096 per op) As you can see, especially once warmed up, xxh3 is fastest. ### Performance macrobenchmark (PORTABLE=0 DEBUG_LEVEL=0, Broadwell processor) Test for I in `seq 1 50`; do for CHK in 0 1 2 3 4; do TEST_TMPDIR=/dev/shm/rocksdb$CHK ./db_bench -benchmarks=fillseq -memtablerep=vector -allow_concurrent_memtable_write=false -num=30000000 -checksum_type=$CHK 2>&1 | grep 'micros/op' | tee -a results-$CHK & done; wait; done Results (ops/sec) for FILE in results*; do echo -n "$FILE "; awk '{ s += $5; c++; } END { print 1.0 * s / c; }' < $FILE; done results-0 252118 # kNoChecksum results-1 251588 # kCRC32c results-2 251863 # kxxHash results-3 252016 # kxxHash64 results-4 252038 # kXXH3 Reviewed By: mrambacher Differential Revision: D31905249 Pulled By: pdillinger fbshipit-source-id: cb9b998ebe2523fc7c400eedf62124a78bf4b4d1
2021-10-29 05:13:47 +00:00
return std::vector<CompressionType>(dict_compression_types.begin(),
dict_compression_types.end());
}
std::vector<ChecksumType> GetSupportedChecksums() {
std::set<ChecksumType> checksum_types;
for (const auto& e : OptionsHelper::checksum_type_string_map) {
checksum_types.insert(e.second);
}
return std::vector<ChecksumType>(checksum_types.begin(),
checksum_types.end());
}
static bool ParseOptionHelper(void* opt_address, const OptionType& opt_type,
const std::string& value) {
switch (opt_type) {
case OptionType::kBoolean:
*static_cast<bool*>(opt_address) = ParseBoolean("", value);
break;
case OptionType::kInt:
*static_cast<int*>(opt_address) = ParseInt(value);
break;
case OptionType::kInt32T:
*static_cast<int32_t*>(opt_address) = ParseInt32(value);
break;
case OptionType::kInt64T:
PutUnaligned(static_cast<int64_t*>(opt_address), ParseInt64(value));
break;
case OptionType::kUInt:
*static_cast<unsigned int*>(opt_address) = ParseUint32(value);
break;
case OptionType::kUInt8T:
*static_cast<uint8_t*>(opt_address) = ParseUint8(value);
break;
case OptionType::kUInt32T:
*static_cast<uint32_t*>(opt_address) = ParseUint32(value);
break;
case OptionType::kUInt64T:
PutUnaligned(static_cast<uint64_t*>(opt_address), ParseUint64(value));
break;
case OptionType::kSizeT:
PutUnaligned(static_cast<size_t*>(opt_address), ParseSizeT(value));
break;
case OptionType::kAtomicInt:
static_cast<std::atomic<int>*>(opt_address)
->store(ParseInt(value), std::memory_order_release);
break;
case OptionType::kString:
*static_cast<std::string*>(opt_address) = value;
break;
case OptionType::kDouble:
*static_cast<double*>(opt_address) = ParseDouble(value);
break;
case OptionType::kCompactionStyle:
return ParseEnum<CompactionStyle>(
compaction_style_string_map, value,
static_cast<CompactionStyle*>(opt_address));
case OptionType::kCompactionPri:
return ParseEnum<CompactionPri>(compaction_pri_string_map, value,
static_cast<CompactionPri*>(opt_address));
case OptionType::kCompressionType:
return ParseEnum<CompressionType>(
compression_type_string_map, value,
static_cast<CompressionType*>(opt_address));
case OptionType::kChecksumType:
return ParseEnum<ChecksumType>(checksum_type_string_map, value,
static_cast<ChecksumType*>(opt_address));
case OptionType::kEncodingType:
return ParseEnum<EncodingType>(encoding_type_string_map, value,
static_cast<EncodingType*>(opt_address));
case OptionType::kCompactionStopStyle:
return ParseEnum<CompactionStopStyle>(
compaction_stop_style_string_map, value,
static_cast<CompactionStopStyle*>(opt_address));
case OptionType::kEncodedString: {
std::string* output_addr = static_cast<std::string*>(opt_address);
(Slice(value)).DecodeHex(output_addr);
break;
}
case OptionType::kTemperature: {
return ParseEnum<Temperature>(temperature_string_map, value,
static_cast<Temperature*>(opt_address));
}
default:
return false;
}
return true;
}
bool SerializeSingleOptionHelper(const void* opt_address,
const OptionType opt_type,
std::string* value) {
assert(value);
switch (opt_type) {
case OptionType::kBoolean:
*value = *(static_cast<const bool*>(opt_address)) ? "true" : "false";
break;
case OptionType::kInt:
*value = std::to_string(*(static_cast<const int*>(opt_address)));
break;
case OptionType::kInt32T:
*value = std::to_string(*(static_cast<const int32_t*>(opt_address)));
break;
case OptionType::kInt64T:
{
int64_t v;
GetUnaligned(static_cast<const int64_t*>(opt_address), &v);
*value = std::to_string(v);
}
break;
case OptionType::kUInt:
*value = std::to_string(*(static_cast<const unsigned int*>(opt_address)));
break;
case OptionType::kUInt8T:
*value = std::to_string(*(static_cast<const uint8_t*>(opt_address)));
break;
case OptionType::kUInt32T:
*value = std::to_string(*(static_cast<const uint32_t*>(opt_address)));
break;
case OptionType::kUInt64T:
{
uint64_t v;
GetUnaligned(static_cast<const uint64_t*>(opt_address), &v);
*value = std::to_string(v);
}
break;
case OptionType::kSizeT:
{
size_t v;
GetUnaligned(static_cast<const size_t*>(opt_address), &v);
*value = std::to_string(v);
}
break;
case OptionType::kDouble:
*value = std::to_string(*(static_cast<const double*>(opt_address)));
break;
case OptionType::kAtomicInt:
*value = std::to_string(static_cast<const std::atomic<int>*>(opt_address)
->load(std::memory_order_acquire));
break;
case OptionType::kString:
*value =
EscapeOptionString(*(static_cast<const std::string*>(opt_address)));
break;
case OptionType::kCompactionStyle:
return SerializeEnum<CompactionStyle>(
compaction_style_string_map,
*(static_cast<const CompactionStyle*>(opt_address)), value);
case OptionType::kCompactionPri:
return SerializeEnum<CompactionPri>(
compaction_pri_string_map,
*(static_cast<const CompactionPri*>(opt_address)), value);
case OptionType::kCompressionType:
return SerializeEnum<CompressionType>(
compression_type_string_map,
*(static_cast<const CompressionType*>(opt_address)), value);
break;
case OptionType::kChecksumType:
return SerializeEnum<ChecksumType>(
checksum_type_string_map,
*static_cast<const ChecksumType*>(opt_address), value);
case OptionType::kEncodingType:
return SerializeEnum<EncodingType>(
encoding_type_string_map,
*static_cast<const EncodingType*>(opt_address), value);
case OptionType::kCompactionStopStyle:
return SerializeEnum<CompactionStopStyle>(
compaction_stop_style_string_map,
*static_cast<const CompactionStopStyle*>(opt_address), value);
case OptionType::kEncodedString: {
const auto* ptr = static_cast<const std::string*>(opt_address);
*value = (Slice(*ptr)).ToString(true);
break;
}
case OptionType::kTemperature: {
return SerializeEnum<Temperature>(
temperature_string_map, *static_cast<const Temperature*>(opt_address),
value);
}
default:
return false;
}
return true;
}
template <typename T>
Status ConfigureFromMap(
const ConfigOptions& config_options,
const std::unordered_map<std::string, std::string>& opt_map,
const std::string& option_name, Configurable* config, T* new_opts) {
Status s = config->ConfigureFromMap(config_options, opt_map);
if (s.ok()) {
*new_opts = *(config->GetOptions<T>(option_name));
}
return s;
}
Status StringToMap(const std::string& opts_str,
std::unordered_map<std::string, std::string>* opts_map) {
assert(opts_map);
// Example:
// opts_str = "write_buffer_size=1024;max_write_buffer_number=2;"
// "nested_opt={opt1=1;opt2=2};max_bytes_for_level_base=100"
size_t pos = 0;
std::string opts = trim(opts_str);
// If the input string starts and ends with "{...}", strip off the brackets
while (opts.size() > 2 && opts[0] == '{' && opts[opts.size() - 1] == '}') {
opts = trim(opts.substr(1, opts.size() - 2));
}
while (pos < opts.size()) {
size_t eq_pos = opts.find_first_of("={};", pos);
if (eq_pos == std::string::npos) {
return Status::InvalidArgument("Mismatched key value pair, '=' expected");
} else if (opts[eq_pos] != '=') {
return Status::InvalidArgument("Unexpected char in key");
}
std::string key = trim(opts.substr(pos, eq_pos - pos));
if (key.empty()) {
return Status::InvalidArgument("Empty key found");
}
std::string value;
Status s = OptionTypeInfo::NextToken(opts, ';', eq_pos + 1, &pos, &value);
if (!s.ok()) {
return s;
} else {
(*opts_map)[key] = value;
if (pos == std::string::npos) {
break;
} else {
pos++;
}
}
}
return Status::OK();
}
Status GetStringFromDBOptions(std::string* opt_string,
const DBOptions& db_options,
const std::string& delimiter) {
ConfigOptions config_options(db_options);
config_options.delimiter = delimiter;
return GetStringFromDBOptions(config_options, db_options, opt_string);
}
Status GetStringFromDBOptions(const ConfigOptions& config_options,
const DBOptions& db_options,
std::string* opt_string) {
assert(opt_string);
opt_string->clear();
auto config = DBOptionsAsConfigurable(db_options);
return config->GetOptionString(config_options, opt_string);
}
RocksDB Options file format and its serialization / deserialization. Summary: This patch defines the format of RocksDB options file, which follows the INI file format, and implements functions for its serialization and deserialization. An example RocksDB options file can be found in examples/rocksdb_option_file_example.ini. A typical RocksDB options file has three sections, which are Version, DBOptions, and more than one CFOptions. The RocksDB options file in general follows the basic INI file format with the following extensions / modifications: * Escaped characters We escaped the following characters: - \n -- line feed - new line - \r -- carriage return - \\ -- backslash \ - \: -- colon symbol : - \# -- hash tag # * Comments We support # style comments. Comments can appear at the ending part of a line. * Statements A statement is of the form option_name = value. Each statement contains a '=', where extra white-spaces are supported. However, we don't support multi-lined statement. Furthermore, each line can only contain at most one statement. * Section Sections are of the form [SecitonTitle "SectionArgument"], where section argument is optional. * List We use colon-separated string to represent a list. For instance, n1:n2:n3:n4 is a list containing four values. Below is an example of a RocksDB options file: [Version] rocksdb_version=4.0.0 options_file_version=1.0 [DBOptions] max_open_files=12345 max_background_flushes=301 [CFOptions "default"] [CFOptions "the second column family"] [CFOptions "the third column family"] Test Plan: Added many tests in options_test.cc Reviewers: igor, IslamAbdelRahman, sdong, anthony Reviewed By: anthony Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D46059
2015-09-29 21:42:40 +00:00
Status GetStringFromColumnFamilyOptions(std::string* opt_string,
const ColumnFamilyOptions& cf_options,
const std::string& delimiter) {
ConfigOptions config_options;
config_options.delimiter = delimiter;
return GetStringFromColumnFamilyOptions(config_options, cf_options,
opt_string);
}
Status GetStringFromColumnFamilyOptions(const ConfigOptions& config_options,
const ColumnFamilyOptions& cf_options,
std::string* opt_string) {
const auto config = CFOptionsAsConfigurable(cf_options);
return config->GetOptionString(config_options, opt_string);
}
Status GetStringFromCompressionType(std::string* compression_str,
CompressionType compression_type) {
bool ok = SerializeEnum<CompressionType>(compression_type_string_map,
compression_type, compression_str);
if (ok) {
return Status::OK();
} else {
return Status::InvalidArgument("Invalid compression types");
}
}
Status GetColumnFamilyOptionsFromMap(
const ConfigOptions& config_options,
const ColumnFamilyOptions& base_options,
const std::unordered_map<std::string, std::string>& opts_map,
ColumnFamilyOptions* new_options) {
assert(new_options);
*new_options = base_options;
const auto config = CFOptionsAsConfigurable(base_options);
Status s = ConfigureFromMap<ColumnFamilyOptions>(
config_options, opts_map, OptionsHelper::kCFOptionsName, config.get(),
new_options);
// Translate any errors (NotFound, NotSupported, to InvalidArgument
if (s.ok() || s.IsInvalidArgument()) {
return s;
} else {
return Status::InvalidArgument(s.getState());
}
}
Status GetColumnFamilyOptionsFromString(const ConfigOptions& config_options,
const ColumnFamilyOptions& base_options,
const std::string& opts_str,
ColumnFamilyOptions* new_options) {
std::unordered_map<std::string, std::string> opts_map;
Status s = StringToMap(opts_str, &opts_map);
if (!s.ok()) {
*new_options = base_options;
return s;
}
return GetColumnFamilyOptionsFromMap(config_options, base_options, opts_map,
new_options);
}
Status GetDBOptionsFromMap(
const ConfigOptions& config_options, const DBOptions& base_options,
const std::unordered_map<std::string, std::string>& opts_map,
DBOptions* new_options) {
assert(new_options);
*new_options = base_options;
auto config = DBOptionsAsConfigurable(base_options);
Status s = ConfigureFromMap<DBOptions>(config_options, opts_map,
OptionsHelper::kDBOptionsName,
config.get(), new_options);
// Translate any errors (NotFound, NotSupported, to InvalidArgument
if (s.ok() || s.IsInvalidArgument()) {
return s;
} else {
return Status::InvalidArgument(s.getState());
}
}
Status GetDBOptionsFromString(const ConfigOptions& config_options,
const DBOptions& base_options,
const std::string& opts_str,
DBOptions* new_options) {
std::unordered_map<std::string, std::string> opts_map;
Status s = StringToMap(opts_str, &opts_map);
if (!s.ok()) {
*new_options = base_options;
return s;
}
return GetDBOptionsFromMap(config_options, base_options, opts_map,
new_options);
}
Status GetOptionsFromString(const Options& base_options,
const std::string& opts_str, Options* new_options) {
ConfigOptions config_options(base_options);
config_options.input_strings_escaped = false;
config_options.ignore_unknown_options = false;
return GetOptionsFromString(config_options, base_options, opts_str,
new_options);
}
Status GetOptionsFromString(const ConfigOptions& config_options,
const Options& base_options,
const std::string& opts_str, Options* new_options) {
ColumnFamilyOptions new_cf_options;
std::unordered_map<std::string, std::string> unused_opts;
std::unordered_map<std::string, std::string> opts_map;
assert(new_options);
*new_options = base_options;
Status s = StringToMap(opts_str, &opts_map);
if (!s.ok()) {
return s;
}
auto config = DBOptionsAsConfigurable(base_options);
s = config->ConfigureFromMap(config_options, opts_map, &unused_opts);
if (s.ok()) {
DBOptions* new_db_options =
config->GetOptions<DBOptions>(OptionsHelper::kDBOptionsName);
if (!unused_opts.empty()) {
s = GetColumnFamilyOptionsFromMap(config_options, base_options,
unused_opts, &new_cf_options);
if (s.ok()) {
*new_options = Options(*new_db_options, new_cf_options);
}
} else {
*new_options = Options(*new_db_options, base_options);
}
}
// Translate any errors (NotFound, NotSupported, to InvalidArgument
if (s.ok() || s.IsInvalidArgument()) {
return s;
} else {
return Status::InvalidArgument(s.getState());
}
}
std::unordered_map<std::string, EncodingType>
OptionsHelper::encoding_type_string_map = {{"kPlain", kPlain},
{"kPrefix", kPrefix}};
std::unordered_map<std::string, CompactionStyle>
OptionsHelper::compaction_style_string_map = {
{"kCompactionStyleLevel", kCompactionStyleLevel},
{"kCompactionStyleUniversal", kCompactionStyleUniversal},
{"kCompactionStyleFIFO", kCompactionStyleFIFO},
{"kCompactionStyleNone", kCompactionStyleNone}};
std::unordered_map<std::string, CompactionPri>
OptionsHelper::compaction_pri_string_map = {
{"kByCompensatedSize", kByCompensatedSize},
{"kOldestLargestSeqFirst", kOldestLargestSeqFirst},
{"kOldestSmallestSeqFirst", kOldestSmallestSeqFirst},
Add basic kRoundRobin compaction policy (#10107) Summary: Add `kRoundRobin` as a compaction priority. The implementation is as follows. - Define a cursor as the smallest Internal key in the successor of the selected file. Add `vector<InternalKey> compact_cursor_` into `VersionStorageInfo` where each element (`InternalKey`) in `compact_cursor_` represents a cursor. In round-robin compaction policy, we just need to select the first file (assuming files are sorted) and also has the smallest InternalKey larger than/equal to the cursor. After a file is chosen, we create a new `Fsize` vector which puts the selected file is placed at the first position in `temp`, the next cursor is then updated as the smallest InternalKey in successor of the selected file (the above logic is implemented in `SortFileByRoundRobin`). - After a compaction succeeds, typically `InstallCompactionResults()`, we choose the next cursor for the input level and save it to `edit`. When calling `LogAndApply`, we save the next cursor with its level into some local variable and finally apply the change to `vstorage` in `SaveTo` function. - Cursors are persist pair by pair (<level, InternalKey>) in `EncodeTo` so that they can be reconstructed when reopening. An empty cursor will not be encoded to MANIFEST Pull Request resolved: https://github.com/facebook/rocksdb/pull/10107 Test Plan: add unit test (`CompactionPriRoundRobin`) in `compaction_picker_test`, add `kRoundRobin` priority in `CompactionPriTest` from `db_compaction_test`, and add `PersistRoundRobinCompactCursor` in `db_compaction_test` Reviewed By: ajkr Differential Revision: D37316037 Pulled By: littlepig2013 fbshipit-source-id: 9f481748190ace416079139044e00df2968fb1ee
2022-06-21 18:56:53 +00:00
{"kMinOverlappingRatio", kMinOverlappingRatio},
{"kRoundRobin", kRoundRobin}};
std::unordered_map<std::string, CompactionStopStyle>
OptionsHelper::compaction_stop_style_string_map = {
{"kCompactionStopStyleSimilarSize", kCompactionStopStyleSimilarSize},
{"kCompactionStopStyleTotalSize", kCompactionStopStyleTotalSize}};
std::unordered_map<std::string, Temperature>
OptionsHelper::temperature_string_map = {
{"kUnknown", Temperature::kUnknown},
{"kHot", Temperature::kHot},
{"kWarm", Temperature::kWarm},
{"kCold", Temperature::kCold}};
std::unordered_map<std::string, PrepopulateBlobCache>
OptionsHelper::prepopulate_blob_cache_string_map = {
{"kDisable", PrepopulateBlobCache::kDisable},
{"kFlushOnly", PrepopulateBlobCache::kFlushOnly}};
Status OptionTypeInfo::NextToken(const std::string& opts, char delimiter,
size_t pos, size_t* end, std::string* token) {
while (pos < opts.size() && isspace(opts[pos])) {
++pos;
}
// Empty value at the end
if (pos >= opts.size()) {
*token = "";
*end = std::string::npos;
return Status::OK();
} else if (opts[pos] == '{') {
int count = 1;
size_t brace_pos = pos + 1;
while (brace_pos < opts.size()) {
if (opts[brace_pos] == '{') {
++count;
} else if (opts[brace_pos] == '}') {
--count;
if (count == 0) {
break;
}
}
++brace_pos;
}
// found the matching closing brace
if (count == 0) {
*token = trim(opts.substr(pos + 1, brace_pos - pos - 1));
// skip all whitespace and move to the next delimiter
// brace_pos points to the next position after the matching '}'
pos = brace_pos + 1;
while (pos < opts.size() && isspace(opts[pos])) {
++pos;
}
if (pos < opts.size() && opts[pos] != delimiter) {
return Status::InvalidArgument("Unexpected chars after nested options");
}
*end = pos;
} else {
return Status::InvalidArgument(
"Mismatched curly braces for nested options");
}
} else {
*end = opts.find(delimiter, pos);
if (*end == std::string::npos) {
// It either ends with a trailing semi-colon or the last key-value pair
*token = trim(opts.substr(pos));
} else {
*token = trim(opts.substr(pos, *end - pos));
}
}
return Status::OK();
}
Status OptionTypeInfo::Parse(const ConfigOptions& config_options,
const std::string& opt_name,
const std::string& value, void* opt_ptr) const {
if (IsDeprecated()) {
return Status::OK();
}
try {
const std::string& opt_value = config_options.input_strings_escaped
? UnescapeOptionString(value)
: value;
if (opt_ptr == nullptr) {
return Status::NotFound("Could not find option", opt_name);
} else if (parse_func_ != nullptr) {
ConfigOptions copy = config_options;
copy.invoke_prepare_options = false;
void* opt_addr = GetOffset(opt_ptr);
return parse_func_(copy, opt_name, opt_value, opt_addr);
} else if (ParseOptionHelper(GetOffset(opt_ptr), type_, opt_value)) {
return Status::OK();
} else if (IsConfigurable()) {
// The option is <config>.<name>
Configurable* config = AsRawPointer<Configurable>(opt_ptr);
if (opt_value.empty()) {
return Status::OK();
} else if (config == nullptr) {
return Status::NotFound("Could not find configurable: ", opt_name);
} else {
ConfigOptions copy = config_options;
copy.ignore_unknown_options = false;
copy.invoke_prepare_options = false;
if (opt_value.find("=") != std::string::npos) {
return config->ConfigureFromString(copy, opt_value);
} else {
return config->ConfigureOption(copy, opt_name, opt_value);
}
}
} else if (IsByName()) {
return Status::NotSupported("Deserializing the option " + opt_name +
" is not supported");
} else {
return Status::InvalidArgument("Error parsing:", opt_name);
}
} catch (std::exception& e) {
return Status::InvalidArgument("Error parsing " + opt_name + ":" +
std::string(e.what()));
}
}
Status OptionTypeInfo::ParseType(
const ConfigOptions& config_options, const std::string& opts_str,
const std::unordered_map<std::string, OptionTypeInfo>& type_map,
void* opt_addr, std::unordered_map<std::string, std::string>* unused) {
std::unordered_map<std::string, std::string> opts_map;
Status status = StringToMap(opts_str, &opts_map);
if (!status.ok()) {
return status;
} else {
return ParseType(config_options, opts_map, type_map, opt_addr, unused);
}
}
Status OptionTypeInfo::ParseType(
const ConfigOptions& config_options,
const std::unordered_map<std::string, std::string>& opts_map,
const std::unordered_map<std::string, OptionTypeInfo>& type_map,
void* opt_addr, std::unordered_map<std::string, std::string>* unused) {
for (const auto& opts_iter : opts_map) {
std::string opt_name;
const auto* opt_info = Find(opts_iter.first, type_map, &opt_name);
if (opt_info != nullptr) {
Status status =
opt_info->Parse(config_options, opt_name, opts_iter.second, opt_addr);
if (!status.ok()) {
return status;
}
} else if (unused != nullptr) {
(*unused)[opts_iter.first] = opts_iter.second;
} else if (!config_options.ignore_unknown_options) {
return Status::NotFound("Unrecognized option", opts_iter.first);
}
}
return Status::OK();
}
Status OptionTypeInfo::ParseStruct(
const ConfigOptions& config_options, const std::string& struct_name,
const std::unordered_map<std::string, OptionTypeInfo>* struct_map,
const std::string& opt_name, const std::string& opt_value, void* opt_addr) {
assert(struct_map);
Status status;
if (opt_name == struct_name || EndsWith(opt_name, "." + struct_name)) {
// This option represents the entire struct
std::unordered_map<std::string, std::string> unused;
status =
ParseType(config_options, opt_value, *struct_map, opt_addr, &unused);
if (status.ok() && !unused.empty()) {
status = Status::InvalidArgument(
"Unrecognized option", struct_name + "." + unused.begin()->first);
}
} else if (StartsWith(opt_name, struct_name + ".")) {
// This option represents a nested field in the struct (e.g, struct.field)
std::string elem_name;
const auto opt_info =
Find(opt_name.substr(struct_name.size() + 1), *struct_map, &elem_name);
if (opt_info != nullptr) {
status = opt_info->Parse(config_options, elem_name, opt_value, opt_addr);
} else {
status = Status::InvalidArgument("Unrecognized option", opt_name);
}
} else {
// This option represents a field in the struct (e.g. field)
std::string elem_name;
const auto opt_info = Find(opt_name, *struct_map, &elem_name);
if (opt_info != nullptr) {
status = opt_info->Parse(config_options, elem_name, opt_value, opt_addr);
} else {
status = Status::InvalidArgument("Unrecognized option",
struct_name + "." + opt_name);
}
}
return status;
}
Status OptionTypeInfo::Serialize(const ConfigOptions& config_options,
const std::string& opt_name,
const void* const opt_ptr,
std::string* opt_value) const {
// If the option is no longer used in rocksdb and marked as deprecated,
// we skip it in the serialization.
if (opt_ptr == nullptr || IsDeprecated()) {
return Status::OK();
} else if (IsEnabled(OptionTypeFlags::kDontSerialize)) {
return Status::NotSupported("Cannot serialize option: ", opt_name);
} else if (serialize_func_ != nullptr) {
const void* opt_addr = GetOffset(opt_ptr);
return serialize_func_(config_options, opt_name, opt_addr, opt_value);
} else if (IsCustomizable()) {
const Customizable* custom = AsRawPointer<Customizable>(opt_ptr);
opt_value->clear();
if (custom == nullptr) {
// We do not have a custom object to serialize.
// If the option is not mutable and we are doing only mutable options,
// we return an empty string (which will cause the option not to be
// printed). Otherwise, we return the "nullptr" string, which will result
// in "option=nullptr" being printed.
if (IsMutable() || !config_options.mutable_options_only) {
*opt_value = kNullptrString;
} else {
*opt_value = "";
}
} else if (IsEnabled(OptionTypeFlags::kStringNameOnly) &&
!config_options.IsDetailed()) {
if (!config_options.mutable_options_only || IsMutable()) {
*opt_value = custom->GetId();
}
} else {
ConfigOptions embedded = config_options;
embedded.delimiter = ";";
// If this option is mutable, everything inside it should be considered
// mutable
if (IsMutable()) {
embedded.mutable_options_only = false;
}
std::string value = custom->ToString(embedded);
if (!embedded.mutable_options_only ||
value.find("=") != std::string::npos) {
*opt_value = value;
} else {
*opt_value = "";
}
}
return Status::OK();
} else if (IsConfigurable()) {
const Configurable* config = AsRawPointer<Configurable>(opt_ptr);
if (config != nullptr) {
ConfigOptions embedded = config_options;
embedded.delimiter = ";";
*opt_value = config->ToString(embedded);
}
return Status::OK();
} else if (config_options.mutable_options_only && !IsMutable()) {
return Status::OK();
} else if (SerializeSingleOptionHelper(GetOffset(opt_ptr), type_,
opt_value)) {
return Status::OK();
} else {
return Status::InvalidArgument("Cannot serialize option: ", opt_name);
}
}
Status OptionTypeInfo::SerializeType(
const ConfigOptions& config_options,
const std::unordered_map<std::string, OptionTypeInfo>& type_map,
const void* opt_addr, std::string* result) {
Status status;
for (const auto& iter : type_map) {
std::string single;
const auto& opt_info = iter.second;
if (opt_info.ShouldSerialize()) {
status =
opt_info.Serialize(config_options, iter.first, opt_addr, &single);
if (!status.ok()) {
return status;
} else {
result->append(iter.first + "=" + single + config_options.delimiter);
}
}
}
return status;
}
Status OptionTypeInfo::SerializeStruct(
const ConfigOptions& config_options, const std::string& struct_name,
const std::unordered_map<std::string, OptionTypeInfo>* struct_map,
const std::string& opt_name, const void* opt_addr, std::string* value) {
assert(struct_map);
Status status;
if (EndsWith(opt_name, struct_name)) {
// We are going to write the struct as "{ prop1=value1; prop2=value2;}.
// Set the delimiter to ";" so that the everything will be on one line.
ConfigOptions embedded = config_options;
embedded.delimiter = ";";
// This option represents the entire struct
std::string result;
status = SerializeType(embedded, *struct_map, opt_addr, &result);
if (!status.ok()) {
return status;
} else {
*value = "{" + result + "}";
}
} else if (StartsWith(opt_name, struct_name + ".")) {
// This option represents a nested field in the struct (e.g, struct.field)
std::string elem_name;
const auto opt_info =
Find(opt_name.substr(struct_name.size() + 1), *struct_map, &elem_name);
if (opt_info != nullptr) {
status = opt_info->Serialize(config_options, elem_name, opt_addr, value);
} else {
status = Status::InvalidArgument("Unrecognized option", opt_name);
}
} else {
// This option represents a field in the struct (e.g. field)
std::string elem_name;
const auto opt_info = Find(opt_name, *struct_map, &elem_name);
if (opt_info == nullptr) {
status = Status::InvalidArgument("Unrecognized option", opt_name);
} else if (opt_info->ShouldSerialize()) {
status = opt_info->Serialize(config_options, opt_name + "." + elem_name,
opt_addr, value);
}
}
return status;
}
template <typename T>
bool IsOptionEqual(const void* offset1, const void* offset2) {
return (*static_cast<const T*>(offset1) == *static_cast<const T*>(offset2));
}
static bool AreEqualDoubles(const double a, const double b) {
return (fabs(a - b) < 0.00001);
}
static bool AreOptionsEqual(OptionType type, const void* this_offset,
const void* that_offset) {
switch (type) {
case OptionType::kBoolean:
return IsOptionEqual<bool>(this_offset, that_offset);
case OptionType::kInt:
return IsOptionEqual<int>(this_offset, that_offset);
case OptionType::kUInt:
return IsOptionEqual<unsigned int>(this_offset, that_offset);
case OptionType::kInt32T:
return IsOptionEqual<int32_t>(this_offset, that_offset);
case OptionType::kInt64T: {
int64_t v1, v2;
GetUnaligned(static_cast<const int64_t*>(this_offset), &v1);
GetUnaligned(static_cast<const int64_t*>(that_offset), &v2);
return (v1 == v2);
}
case OptionType::kUInt8T:
return IsOptionEqual<uint8_t>(this_offset, that_offset);
case OptionType::kUInt32T:
return IsOptionEqual<uint32_t>(this_offset, that_offset);
case OptionType::kUInt64T: {
uint64_t v1, v2;
GetUnaligned(static_cast<const uint64_t*>(this_offset), &v1);
GetUnaligned(static_cast<const uint64_t*>(that_offset), &v2);
return (v1 == v2);
}
case OptionType::kSizeT: {
size_t v1, v2;
GetUnaligned(static_cast<const size_t*>(this_offset), &v1);
GetUnaligned(static_cast<const size_t*>(that_offset), &v2);
return (v1 == v2);
}
case OptionType::kAtomicInt:
return IsOptionEqual<std::atomic<int>>(this_offset, that_offset);
case OptionType::kString:
return IsOptionEqual<std::string>(this_offset, that_offset);
case OptionType::kDouble:
return AreEqualDoubles(*static_cast<const double*>(this_offset),
*static_cast<const double*>(that_offset));
case OptionType::kCompactionStyle:
return IsOptionEqual<CompactionStyle>(this_offset, that_offset);
case OptionType::kCompactionStopStyle:
return IsOptionEqual<CompactionStopStyle>(this_offset, that_offset);
case OptionType::kCompactionPri:
return IsOptionEqual<CompactionPri>(this_offset, that_offset);
case OptionType::kCompressionType:
return IsOptionEqual<CompressionType>(this_offset, that_offset);
case OptionType::kChecksumType:
return IsOptionEqual<ChecksumType>(this_offset, that_offset);
case OptionType::kEncodingType:
return IsOptionEqual<EncodingType>(this_offset, that_offset);
case OptionType::kEncodedString:
return IsOptionEqual<std::string>(this_offset, that_offset);
case OptionType::kTemperature:
return IsOptionEqual<Temperature>(this_offset, that_offset);
default:
return false;
} // End switch
}
bool OptionTypeInfo::AreEqual(const ConfigOptions& config_options,
const std::string& opt_name,
const void* const this_ptr,
const void* const that_ptr,
std::string* mismatch) const {
auto level = GetSanityLevel();
if (!config_options.IsCheckEnabled(level)) {
return true; // If the sanity level is not being checked, skip it
}
if (this_ptr == nullptr || that_ptr == nullptr) {
if (this_ptr == that_ptr) {
return true;
}
} else if (equals_func_ != nullptr) {
const void* this_addr = GetOffset(this_ptr);
const void* that_addr = GetOffset(that_ptr);
if (equals_func_(config_options, opt_name, this_addr, that_addr,
mismatch)) {
return true;
}
} else {
const void* this_addr = GetOffset(this_ptr);
const void* that_addr = GetOffset(that_ptr);
if (AreOptionsEqual(type_, this_addr, that_addr)) {
return true;
} else if (IsConfigurable()) {
const auto* this_config = AsRawPointer<Configurable>(this_ptr);
const auto* that_config = AsRawPointer<Configurable>(that_ptr);
if (this_config == that_config) {
return true;
} else if (this_config != nullptr && that_config != nullptr) {
std::string bad_name;
bool matches;
if (level < config_options.sanity_level) {
ConfigOptions copy = config_options;
copy.sanity_level = level;
matches = this_config->AreEquivalent(copy, that_config, &bad_name);
} else {
matches = this_config->AreEquivalent(config_options, that_config,
&bad_name);
}
if (!matches) {
*mismatch = opt_name + "." + bad_name;
}
return matches;
}
}
}
if (mismatch->empty()) {
*mismatch = opt_name;
}
return false;
}
bool OptionTypeInfo::TypesAreEqual(
const ConfigOptions& config_options,
const std::unordered_map<std::string, OptionTypeInfo>& type_map,
const void* this_addr, const void* that_addr, std::string* mismatch) {
for (const auto& iter : type_map) {
const auto& opt_info = iter.second;
if (!opt_info.AreEqual(config_options, iter.first, this_addr, that_addr,
mismatch)) {
return false;
}
}
return true;
}
bool OptionTypeInfo::StructsAreEqual(
const ConfigOptions& config_options, const std::string& struct_name,
const std::unordered_map<std::string, OptionTypeInfo>* struct_map,
const std::string& opt_name, const void* this_addr, const void* that_addr,
std::string* mismatch) {
assert(struct_map);
bool matches = true;
std::string result;
if (EndsWith(opt_name, struct_name)) {
// This option represents the entire struct
matches = TypesAreEqual(config_options, *struct_map, this_addr, that_addr,
&result);
if (!matches) {
*mismatch = struct_name + "." + result;
return false;
}
} else if (StartsWith(opt_name, struct_name + ".")) {
// This option represents a nested field in the struct (e.g, struct.field)
std::string elem_name;
const auto opt_info =
Find(opt_name.substr(struct_name.size() + 1), *struct_map, &elem_name);
assert(opt_info);
if (opt_info == nullptr) {
*mismatch = opt_name;
matches = false;
} else if (!opt_info->AreEqual(config_options, elem_name, this_addr,
that_addr, &result)) {
matches = false;
*mismatch = struct_name + "." + result;
}
} else {
// This option represents a field in the struct (e.g. field)
std::string elem_name;
const auto opt_info = Find(opt_name, *struct_map, &elem_name);
assert(opt_info);
if (opt_info == nullptr) {
*mismatch = struct_name + "." + opt_name;
matches = false;
} else if (!opt_info->AreEqual(config_options, elem_name, this_addr,
that_addr, &result)) {
matches = false;
*mismatch = struct_name + "." + result;
}
}
return matches;
}
bool MatchesOptionsTypeFromMap(
const ConfigOptions& config_options,
const std::unordered_map<std::string, OptionTypeInfo>& type_map,
const void* const this_ptr, const void* const that_ptr,
std::string* mismatch) {
for (auto& pair : type_map) {
// We skip checking deprecated variables as they might
// contain random values since they might not be initialized
if (config_options.IsCheckEnabled(pair.second.GetSanityLevel())) {
if (!pair.second.AreEqual(config_options, pair.first, this_ptr, that_ptr,
mismatch) &&
!pair.second.AreEqualByName(config_options, pair.first, this_ptr,
that_ptr)) {
return false;
}
}
}
return true;
}
bool OptionTypeInfo::AreEqualByName(const ConfigOptions& config_options,
const std::string& opt_name,
const void* const this_ptr,
const void* const that_ptr) const {
if (IsByName()) {
std::string that_value;
if (Serialize(config_options, opt_name, that_ptr, &that_value).ok()) {
return AreEqualByName(config_options, opt_name, this_ptr, that_value);
}
}
return false;
}
bool OptionTypeInfo::AreEqualByName(const ConfigOptions& config_options,
const std::string& opt_name,
const void* const opt_ptr,
const std::string& that_value) const {
std::string this_value;
if (!IsByName()) {
return false;
} else if (!Serialize(config_options, opt_name, opt_ptr, &this_value).ok()) {
return false;
} else if (IsEnabled(OptionVerificationType::kByNameAllowFromNull)) {
if (that_value == kNullptrString) {
return true;
}
} else if (IsEnabled(OptionVerificationType::kByNameAllowNull)) {
if (that_value == kNullptrString) {
return true;
}
}
return (this_value == that_value);
}
Status OptionTypeInfo::Prepare(const ConfigOptions& config_options,
const std::string& name, void* opt_ptr) const {
if (ShouldPrepare()) {
if (prepare_func_ != nullptr) {
void* opt_addr = GetOffset(opt_ptr);
return prepare_func_(config_options, name, opt_addr);
} else if (IsConfigurable()) {
Configurable* config = AsRawPointer<Configurable>(opt_ptr);
if (config != nullptr) {
return config->PrepareOptions(config_options);
} else if (!CanBeNull()) {
return Status::NotFound("Missing configurable object", name);
}
}
}
return Status::OK();
}
Status OptionTypeInfo::Validate(const DBOptions& db_opts,
const ColumnFamilyOptions& cf_opts,
const std::string& name,
const void* opt_ptr) const {
if (ShouldValidate()) {
if (validate_func_ != nullptr) {
const void* opt_addr = GetOffset(opt_ptr);
return validate_func_(db_opts, cf_opts, name, opt_addr);
} else if (IsConfigurable()) {
const Configurable* config = AsRawPointer<Configurable>(opt_ptr);
if (config != nullptr) {
return config->ValidateOptions(db_opts, cf_opts);
} else if (!CanBeNull()) {
return Status::NotFound("Missing configurable object", name);
}
}
}
return Status::OK();
}
const OptionTypeInfo* OptionTypeInfo::Find(
const std::string& opt_name,
const std::unordered_map<std::string, OptionTypeInfo>& opt_map,
std::string* elem_name) {
const auto iter = opt_map.find(opt_name); // Look up the value in the map
if (iter != opt_map.end()) { // Found the option in the map
*elem_name = opt_name; // Return the name
return &(iter->second); // Return the contents of the iterator
} else {
auto idx = opt_name.find("."); // Look for a separator
if (idx > 0 && idx != std::string::npos) { // We found a separator
auto siter =
opt_map.find(opt_name.substr(0, idx)); // Look for the short name
if (siter != opt_map.end()) { // We found the short name
if (siter->second.IsStruct() || // If the object is a struct
siter->second.IsConfigurable()) { // or a Configurable
*elem_name = opt_name.substr(idx + 1); // Return the rest
return &(siter->second); // Return the contents of the iterator
}
}
}
}
return nullptr;
}
} // namespace ROCKSDB_NAMESPACE