rocksdb/table/sst_file_writer.cc

537 lines
21 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 "rocksdb/sst_file_writer.h"
#include <vector>
#include "db/db_impl/db_impl.h"
#include "db/dbformat.h"
#include "db/wide/wide_column_serialization.h"
#include "db/wide/wide_columns_helper.h"
#include "file/writable_file_writer.h"
#include "rocksdb/file_system.h"
#include "rocksdb/table.h"
#include "table/block_based/block_based_table_builder.h"
#include "table/sst_file_writer_collectors.h"
#include "test_util/sync_point.h"
namespace ROCKSDB_NAMESPACE {
const std::string ExternalSstFilePropertyNames::kVersion =
"rocksdb.external_sst_file.version";
const std::string ExternalSstFilePropertyNames::kGlobalSeqno =
"rocksdb.external_sst_file.global_seqno";
const size_t kFadviseTrigger = 1024 * 1024; // 1MB
struct SstFileWriter::Rep {
Rep(const EnvOptions& _env_options, const Options& options,
Env::IOPriority _io_priority, const Comparator* _user_comparator,
Embed original file number in SST table properties (#8686) Summary: I very recently realized that with https://github.com/facebook/rocksdb/issues/8669 we cannot later add file numbers to external SST files (so that more can share db session ids for better uniqueness properties), because of forward compatibility. We would have a version of RocksDB that assumes session IDs are unique on external SST files and therefore can't really break that invariant in future files. This change adds a table property for "orig_file_number" which is populated by normal SST files and also external SST files generated by SstFileWriter. SstFileWriter now keeps a db_session_id for life of the object and increments its own file numbers for embedding in table properties. (They are arguably "fake" file numbers because these numbers and not embedded in the file name.) While updating block_based_table_builder, I removed several unnecessary fields from Rep, because following the pattern would have created another unnecessary field. This change also updates block_based_table_reader to use this new property when available, which means that for newer SST files, we can determine the stable/original <db_session_id,file_number> unique identifier using just the file contents, not the file name. (It's a bit complicated; detailed comments in block_based_table_reader.) Also added DB host id to properties listing by sst_dump, which could be useful in debugging. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8686 Test Plan: majorly overhauled StableCacheKeys test for this change Reviewed By: zhichao-cao Differential Revision: D30457742 Pulled By: pdillinger fbshipit-source-id: 2e5ae7dddeb94fb9d8eac8a928486aed8b8cd445
2021-08-21 03:39:52 +00:00
ColumnFamilyHandle* _cfh, bool _invalidate_page_cache, bool _skip_filters,
std::string _db_session_id)
: env_options(_env_options),
ioptions(options),
mutable_cf_options(options),
io_priority(_io_priority),
internal_comparator(_user_comparator),
cfh(_cfh),
invalidate_page_cache(_invalidate_page_cache),
Embed original file number in SST table properties (#8686) Summary: I very recently realized that with https://github.com/facebook/rocksdb/issues/8669 we cannot later add file numbers to external SST files (so that more can share db session ids for better uniqueness properties), because of forward compatibility. We would have a version of RocksDB that assumes session IDs are unique on external SST files and therefore can't really break that invariant in future files. This change adds a table property for "orig_file_number" which is populated by normal SST files and also external SST files generated by SstFileWriter. SstFileWriter now keeps a db_session_id for life of the object and increments its own file numbers for embedding in table properties. (They are arguably "fake" file numbers because these numbers and not embedded in the file name.) While updating block_based_table_builder, I removed several unnecessary fields from Rep, because following the pattern would have created another unnecessary field. This change also updates block_based_table_reader to use this new property when available, which means that for newer SST files, we can determine the stable/original <db_session_id,file_number> unique identifier using just the file contents, not the file name. (It's a bit complicated; detailed comments in block_based_table_reader.) Also added DB host id to properties listing by sst_dump, which could be useful in debugging. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8686 Test Plan: majorly overhauled StableCacheKeys test for this change Reviewed By: zhichao-cao Differential Revision: D30457742 Pulled By: pdillinger fbshipit-source-id: 2e5ae7dddeb94fb9d8eac8a928486aed8b8cd445
2021-08-21 03:39:52 +00:00
skip_filters(_skip_filters),
Add support in SstFileWriter to not persist user defined timestamps (#12348) Summary: This PR adds support in `SstFileWriter` to create SST files without persisting timestamps when the column family has enabled UDTs in Memtable only feature. The sst files created from flush and compaction do not contain timestamps, we want to make the sst files created by `SstFileWriter` to follow the same pattern and not persist timestamps. This is to prepare for ingesting external SST files for this type of column family. There are timestamp-aware APIs and non timestamp-aware APIs in `SstFileWriter`. The former are exclusively used for when the column family's comparator is timestamp-aware, a.k.a `Comparator::timestamp_size() > 0`, while the latter are exclusively used for the column family's comparator is non timestamp-aware, a.k.a `Comparator::timestamp_size() == 0`. There are sanity checks to make sure these APIs are correctly used. In this PR, the APIs usage continue with above enforcement, where even though timestamps are not eventually persisted, users are still asked to use only the timestamp-aware APIs. But because data points will logically all have minimum timestamps, we don't allow multiple versions of the same user key (without timestamp) to be added. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12348 Test Plan: Added unit tests Manual inspection of generated sst files with `sst_dump` Reviewed By: ltamasi Differential Revision: D53732667 Pulled By: jowlyzhang fbshipit-source-id: e43beba0d3a1736b94ee5c617163a6280efd65b7
2024-02-14 04:30:07 +00:00
db_session_id(_db_session_id),
ts_sz(_user_comparator->timestamp_size()),
strip_timestamp(ts_sz > 0 &&
!ioptions.persist_user_defined_timestamps) {
Group SST write in flush, compaction and db open with new stats (#11910) Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
// TODO (hx235): pass in `WriteOptions` instead of `rate_limiter_priority`
// during construction
write_options.rate_limiter_priority = io_priority;
}
std::unique_ptr<WritableFileWriter> file_writer;
std::unique_ptr<TableBuilder> builder;
EnvOptions env_options;
ImmutableOptions ioptions;
MutableCFOptions mutable_cf_options;
Env::IOPriority io_priority;
Group SST write in flush, compaction and db open with new stats (#11910) Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
WriteOptions write_options;
InternalKeyComparator internal_comparator;
ExternalSstFileInfo file_info;
Miscellaneous performance improvements Summary: I was investigating performance issues in the SstFileWriter and found all of the following: - The SstFileWriter::Add() function created a local InternalKey every time it was called generating a allocation and free each time. Changed to have an InternalKey member variable that can be reset with the new InternalKey::Set() function. - In SstFileWriter::Add() the smallest_key and largest_key values were assigned the result of a ToString() call, but it is simpler to just assign them directly from the user's key. - The Slice class had no move constructor so each time one was returned from a function a new one had to be allocated, the old data copied to the new, and the old one was freed. I added the move constructor which also required a copy constructor and assignment operator. - The BlockBuilder::CurrentSizeEstimate() function calculates the current estimate size, but was being called 2 or 3 times for each key added. I changed the class to maintain a running estimate (equal to the original calculation) so that the function can return an already calculated value. - The code in BlockBuilder::Add() that calculated the shared bytes between the last key and the new key duplicated what Slice::difference_offset does, so I replaced it with the standard function. - BlockBuilder::Add() had code to copy just the changed portion into the last key value (and asserted that it now matched the new key). It is more efficient just to copy the whole new key over. - Moved this same code up into the 'if (use_delta_encoding_)' since the last key value is only needed when delta encoding is on. - FlushBlockBySizePolicy::BlockAlmostFull calculated a standard deviation value each time it was called, but this information would only change if block_size of block_size_deviation changed, so I created a member variable to hold the value to avoid the calculation each time. - Each PutVarint??() function has a buffer and calls std::string::append(). Two or three calls in a row could share a buffer and a single call to std::string::append(). Some of these will be helpful outside of the SstFileWriter. I'm not 100% the addition of the move constructor is appropriate as I wonder why this wasn't done before - maybe because of compiler compatibility? I tried it on gcc 4.8 and 4.9. Test Plan: The changes should not affect the results so the existing tests should all still work and no new tests were added. The value of the changes was seen by manually testing the SstFileWriter class through MyRocks and adding timing code to identify problem areas. Reviewers: sdong, IslamAbdelRahman Reviewed By: IslamAbdelRahman Subscribers: andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D59607
2016-06-13 16:57:43 +00:00
InternalKey ikey;
std::string column_family_name;
ColumnFamilyHandle* cfh;
// If true, We will give the OS a hint that this file pages is not needed
// every time we write 1MB to the file.
bool invalidate_page_cache;
// The size of the file during the last time we called Fadvise to remove
// cached pages from page cache.
Embed original file number in SST table properties (#8686) Summary: I very recently realized that with https://github.com/facebook/rocksdb/issues/8669 we cannot later add file numbers to external SST files (so that more can share db session ids for better uniqueness properties), because of forward compatibility. We would have a version of RocksDB that assumes session IDs are unique on external SST files and therefore can't really break that invariant in future files. This change adds a table property for "orig_file_number" which is populated by normal SST files and also external SST files generated by SstFileWriter. SstFileWriter now keeps a db_session_id for life of the object and increments its own file numbers for embedding in table properties. (They are arguably "fake" file numbers because these numbers and not embedded in the file name.) While updating block_based_table_builder, I removed several unnecessary fields from Rep, because following the pattern would have created another unnecessary field. This change also updates block_based_table_reader to use this new property when available, which means that for newer SST files, we can determine the stable/original <db_session_id,file_number> unique identifier using just the file contents, not the file name. (It's a bit complicated; detailed comments in block_based_table_reader.) Also added DB host id to properties listing by sst_dump, which could be useful in debugging. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8686 Test Plan: majorly overhauled StableCacheKeys test for this change Reviewed By: zhichao-cao Differential Revision: D30457742 Pulled By: pdillinger fbshipit-source-id: 2e5ae7dddeb94fb9d8eac8a928486aed8b8cd445
2021-08-21 03:39:52 +00:00
uint64_t last_fadvise_size = 0;
bool skip_filters;
Embed original file number in SST table properties (#8686) Summary: I very recently realized that with https://github.com/facebook/rocksdb/issues/8669 we cannot later add file numbers to external SST files (so that more can share db session ids for better uniqueness properties), because of forward compatibility. We would have a version of RocksDB that assumes session IDs are unique on external SST files and therefore can't really break that invariant in future files. This change adds a table property for "orig_file_number" which is populated by normal SST files and also external SST files generated by SstFileWriter. SstFileWriter now keeps a db_session_id for life of the object and increments its own file numbers for embedding in table properties. (They are arguably "fake" file numbers because these numbers and not embedded in the file name.) While updating block_based_table_builder, I removed several unnecessary fields from Rep, because following the pattern would have created another unnecessary field. This change also updates block_based_table_reader to use this new property when available, which means that for newer SST files, we can determine the stable/original <db_session_id,file_number> unique identifier using just the file contents, not the file name. (It's a bit complicated; detailed comments in block_based_table_reader.) Also added DB host id to properties listing by sst_dump, which could be useful in debugging. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8686 Test Plan: majorly overhauled StableCacheKeys test for this change Reviewed By: zhichao-cao Differential Revision: D30457742 Pulled By: pdillinger fbshipit-source-id: 2e5ae7dddeb94fb9d8eac8a928486aed8b8cd445
2021-08-21 03:39:52 +00:00
std::string db_session_id;
uint64_t next_file_number = 1;
Add support in SstFileWriter to not persist user defined timestamps (#12348) Summary: This PR adds support in `SstFileWriter` to create SST files without persisting timestamps when the column family has enabled UDTs in Memtable only feature. The sst files created from flush and compaction do not contain timestamps, we want to make the sst files created by `SstFileWriter` to follow the same pattern and not persist timestamps. This is to prepare for ingesting external SST files for this type of column family. There are timestamp-aware APIs and non timestamp-aware APIs in `SstFileWriter`. The former are exclusively used for when the column family's comparator is timestamp-aware, a.k.a `Comparator::timestamp_size() > 0`, while the latter are exclusively used for the column family's comparator is non timestamp-aware, a.k.a `Comparator::timestamp_size() == 0`. There are sanity checks to make sure these APIs are correctly used. In this PR, the APIs usage continue with above enforcement, where even though timestamps are not eventually persisted, users are still asked to use only the timestamp-aware APIs. But because data points will logically all have minimum timestamps, we don't allow multiple versions of the same user key (without timestamp) to be added. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12348 Test Plan: Added unit tests Manual inspection of generated sst files with `sst_dump` Reviewed By: ltamasi Differential Revision: D53732667 Pulled By: jowlyzhang fbshipit-source-id: e43beba0d3a1736b94ee5c617163a6280efd65b7
2024-02-14 04:30:07 +00:00
size_t ts_sz;
bool strip_timestamp;
Embed original file number in SST table properties (#8686) Summary: I very recently realized that with https://github.com/facebook/rocksdb/issues/8669 we cannot later add file numbers to external SST files (so that more can share db session ids for better uniqueness properties), because of forward compatibility. We would have a version of RocksDB that assumes session IDs are unique on external SST files and therefore can't really break that invariant in future files. This change adds a table property for "orig_file_number" which is populated by normal SST files and also external SST files generated by SstFileWriter. SstFileWriter now keeps a db_session_id for life of the object and increments its own file numbers for embedding in table properties. (They are arguably "fake" file numbers because these numbers and not embedded in the file name.) While updating block_based_table_builder, I removed several unnecessary fields from Rep, because following the pattern would have created another unnecessary field. This change also updates block_based_table_reader to use this new property when available, which means that for newer SST files, we can determine the stable/original <db_session_id,file_number> unique identifier using just the file contents, not the file name. (It's a bit complicated; detailed comments in block_based_table_reader.) Also added DB host id to properties listing by sst_dump, which could be useful in debugging. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8686 Test Plan: majorly overhauled StableCacheKeys test for this change Reviewed By: zhichao-cao Differential Revision: D30457742 Pulled By: pdillinger fbshipit-source-id: 2e5ae7dddeb94fb9d8eac8a928486aed8b8cd445
2021-08-21 03:39:52 +00:00
Status AddImpl(const Slice& user_key, const Slice& value,
ValueType value_type) {
if (!builder) {
return Status::InvalidArgument("File is not opened");
}
if (!builder->status().ok()) {
return builder->status();
}
Add support in SstFileWriter to not persist user defined timestamps (#12348) Summary: This PR adds support in `SstFileWriter` to create SST files without persisting timestamps when the column family has enabled UDTs in Memtable only feature. The sst files created from flush and compaction do not contain timestamps, we want to make the sst files created by `SstFileWriter` to follow the same pattern and not persist timestamps. This is to prepare for ingesting external SST files for this type of column family. There are timestamp-aware APIs and non timestamp-aware APIs in `SstFileWriter`. The former are exclusively used for when the column family's comparator is timestamp-aware, a.k.a `Comparator::timestamp_size() > 0`, while the latter are exclusively used for the column family's comparator is non timestamp-aware, a.k.a `Comparator::timestamp_size() == 0`. There are sanity checks to make sure these APIs are correctly used. In this PR, the APIs usage continue with above enforcement, where even though timestamps are not eventually persisted, users are still asked to use only the timestamp-aware APIs. But because data points will logically all have minimum timestamps, we don't allow multiple versions of the same user key (without timestamp) to be added. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12348 Test Plan: Added unit tests Manual inspection of generated sst files with `sst_dump` Reviewed By: ltamasi Differential Revision: D53732667 Pulled By: jowlyzhang fbshipit-source-id: e43beba0d3a1736b94ee5c617163a6280efd65b7
2024-02-14 04:30:07 +00:00
assert(user_key.size() >= ts_sz);
if (strip_timestamp) {
// In this mode, we expect users to always provide a min timestamp.
if (internal_comparator.user_comparator()->CompareTimestamp(
Slice(user_key.data() + user_key.size() - ts_sz, ts_sz),
MinU64Ts()) != 0) {
return Status::InvalidArgument(
"persist_user_defined_timestamps flag is set to false, only "
"minimum timestamp is accepted.");
}
}
if (file_info.num_entries == 0) {
file_info.smallest_key.assign(user_key.data(), user_key.size());
} else {
if (internal_comparator.user_comparator()->Compare(
user_key, file_info.largest_key) <= 0) {
// Make sure that keys are added in order
return Status::InvalidArgument(
"Keys must be added in strict ascending order.");
}
}
assert(value_type == kTypeValue || value_type == kTypeMerge ||
value_type == kTypeDeletion ||
value_type == kTypeDeletionWithTimestamp ||
value_type == kTypeWideColumnEntity);
constexpr SequenceNumber sequence_number = 0;
ikey.Set(user_key, sequence_number, value_type);
builder->Add(ikey.Encode(), value);
// update file info
file_info.num_entries++;
file_info.largest_key.assign(user_key.data(), user_key.size());
file_info.file_size = builder->FileSize();
InvalidatePageCache(false /* closing */).PermitUncheckedError();
return builder->status();
}
Status Add(const Slice& user_key, const Slice& value, ValueType value_type) {
if (internal_comparator.user_comparator()->timestamp_size() != 0) {
return Status::InvalidArgument("Timestamp size mismatch");
}
return AddImpl(user_key, value, value_type);
}
Status Add(const Slice& user_key, const Slice& timestamp, const Slice& value,
ValueType value_type) {
const size_t timestamp_size = timestamp.size();
if (internal_comparator.user_comparator()->timestamp_size() !=
timestamp_size) {
return Status::InvalidArgument("Timestamp size mismatch");
}
const size_t user_key_size = user_key.size();
if (user_key.data() + user_key_size == timestamp.data()) {
Slice user_key_with_ts(user_key.data(), user_key_size + timestamp_size);
return AddImpl(user_key_with_ts, value, value_type);
}
std::string user_key_with_ts;
user_key_with_ts.reserve(user_key_size + timestamp_size);
user_key_with_ts.append(user_key.data(), user_key_size);
user_key_with_ts.append(timestamp.data(), timestamp_size);
return AddImpl(user_key_with_ts, value, value_type);
}
Status AddEntity(const Slice& user_key, const WideColumns& columns) {
WideColumns sorted_columns(columns);
WideColumnsHelper::SortColumns(sorted_columns);
std::string entity;
const Status s = WideColumnSerialization::Serialize(sorted_columns, entity);
if (!s.ok()) {
return s;
}
if (entity.size() > size_t{std::numeric_limits<uint32_t>::max()}) {
return Status::InvalidArgument("wide column entity is too large");
}
return Add(user_key, entity, kTypeWideColumnEntity);
}
User-defined timestamp support for `DeleteRange()` (#10661) Summary: Add user-defined timestamp support for range deletion. The new API is `DeleteRange(opt, cf, begin_key, end_key, ts)`. Most of the change is to update the comparator to compare without timestamp. Other than that, major changes are - internal range tombstone data structures (`FragmentedRangeTombstoneList`, `RangeTombstone`, etc.) to store timestamps. - Garbage collection of range tombstones and range tombstone covered keys during compaction. - Get()/MultiGet() to return the timestamp of a range tombstone when needed. - Get/Iterator with range tombstones bounded by readoptions.timestamp. - timestamp crash test now issues DeleteRange by default. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10661 Test Plan: - Added unit test: `make check` - Stress test: `python3 tools/db_crashtest.py --enable_ts whitebox --readpercent=57 --prefixpercent=4 --writepercent=25 -delpercent=5 --iterpercent=5 --delrangepercent=4` - Ran `db_bench` to measure regression when timestamp is not enabled. The tests are for write (with some range deletion) and iterate with DB fitting in memory: `./db_bench--benchmarks=fillrandom,seekrandom --writes_per_range_tombstone=200 --max_write_buffer_number=100 --min_write_buffer_number_to_merge=100 --writes=500000 --reads=500000 --seek_nexts=10 --disable_auto_compactions -disable_wal=true --max_num_range_tombstones=1000`. Did not see consistent regression in no timestamp case. | micros/op | fillrandom | seekrandom | | --- | --- | --- | |main| 2.58 |10.96| |PR 10661| 2.68 |10.63| Reviewed By: riversand963 Differential Revision: D39441192 Pulled By: cbi42 fbshipit-source-id: f05aca3c41605caf110daf0ff405919f300ddec2
2022-09-30 23:13:03 +00:00
Status DeleteRangeImpl(const Slice& begin_key, const Slice& end_key) {
if (!builder) {
return Status::InvalidArgument("File is not opened");
}
int cmp = internal_comparator.user_comparator()->CompareWithoutTimestamp(
begin_key, end_key);
if (cmp > 0) {
// It's an empty range where endpoints appear mistaken. Don't bother
// applying it to the DB, and return an error to the user.
return Status::InvalidArgument("end key comes before start key");
} else if (cmp == 0) {
// It's an empty range. Don't bother applying it to the DB.
return Status::OK();
}
Add support in SstFileWriter to not persist user defined timestamps (#12348) Summary: This PR adds support in `SstFileWriter` to create SST files without persisting timestamps when the column family has enabled UDTs in Memtable only feature. The sst files created from flush and compaction do not contain timestamps, we want to make the sst files created by `SstFileWriter` to follow the same pattern and not persist timestamps. This is to prepare for ingesting external SST files for this type of column family. There are timestamp-aware APIs and non timestamp-aware APIs in `SstFileWriter`. The former are exclusively used for when the column family's comparator is timestamp-aware, a.k.a `Comparator::timestamp_size() > 0`, while the latter are exclusively used for the column family's comparator is non timestamp-aware, a.k.a `Comparator::timestamp_size() == 0`. There are sanity checks to make sure these APIs are correctly used. In this PR, the APIs usage continue with above enforcement, where even though timestamps are not eventually persisted, users are still asked to use only the timestamp-aware APIs. But because data points will logically all have minimum timestamps, we don't allow multiple versions of the same user key (without timestamp) to be added. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12348 Test Plan: Added unit tests Manual inspection of generated sst files with `sst_dump` Reviewed By: ltamasi Differential Revision: D53732667 Pulled By: jowlyzhang fbshipit-source-id: e43beba0d3a1736b94ee5c617163a6280efd65b7
2024-02-14 04:30:07 +00:00
assert(begin_key.size() >= ts_sz);
assert(end_key.size() >= ts_sz);
Slice begin_key_ts =
Slice(begin_key.data() + begin_key.size() - ts_sz, ts_sz);
Slice end_key_ts = Slice(end_key.data() + end_key.size() - ts_sz, ts_sz);
assert(begin_key_ts.compare(end_key_ts) == 0);
if (strip_timestamp) {
// In this mode, we expect users to always provide a min timestamp.
if (internal_comparator.user_comparator()->CompareTimestamp(
begin_key_ts, MinU64Ts()) != 0) {
return Status::InvalidArgument(
"persist_user_defined_timestamps flag is set to false, only "
"minimum timestamp is accepted for start key.");
}
if (internal_comparator.user_comparator()->CompareTimestamp(
end_key_ts, MinU64Ts()) != 0) {
return Status::InvalidArgument(
"persist_user_defined_timestamps flag is set to false, only "
"minimum timestamp is accepted for end key.");
}
}
RangeTombstone tombstone(begin_key, end_key, 0 /* Sequence Number */);
if (file_info.num_range_del_entries == 0) {
file_info.smallest_range_del_key.assign(tombstone.start_key_.data(),
tombstone.start_key_.size());
file_info.largest_range_del_key.assign(tombstone.end_key_.data(),
tombstone.end_key_.size());
} else {
if (internal_comparator.user_comparator()->Compare(
tombstone.start_key_, file_info.smallest_range_del_key) < 0) {
file_info.smallest_range_del_key.assign(tombstone.start_key_.data(),
tombstone.start_key_.size());
}
if (internal_comparator.user_comparator()->Compare(
tombstone.end_key_, file_info.largest_range_del_key) > 0) {
file_info.largest_range_del_key.assign(tombstone.end_key_.data(),
tombstone.end_key_.size());
}
}
auto ikey_and_end_key = tombstone.Serialize();
builder->Add(ikey_and_end_key.first.Encode(), ikey_and_end_key.second);
// update file info
file_info.num_range_del_entries++;
file_info.file_size = builder->FileSize();
InvalidatePageCache(false /* closing */).PermitUncheckedError();
return Status::OK();
}
User-defined timestamp support for `DeleteRange()` (#10661) Summary: Add user-defined timestamp support for range deletion. The new API is `DeleteRange(opt, cf, begin_key, end_key, ts)`. Most of the change is to update the comparator to compare without timestamp. Other than that, major changes are - internal range tombstone data structures (`FragmentedRangeTombstoneList`, `RangeTombstone`, etc.) to store timestamps. - Garbage collection of range tombstones and range tombstone covered keys during compaction. - Get()/MultiGet() to return the timestamp of a range tombstone when needed. - Get/Iterator with range tombstones bounded by readoptions.timestamp. - timestamp crash test now issues DeleteRange by default. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10661 Test Plan: - Added unit test: `make check` - Stress test: `python3 tools/db_crashtest.py --enable_ts whitebox --readpercent=57 --prefixpercent=4 --writepercent=25 -delpercent=5 --iterpercent=5 --delrangepercent=4` - Ran `db_bench` to measure regression when timestamp is not enabled. The tests are for write (with some range deletion) and iterate with DB fitting in memory: `./db_bench--benchmarks=fillrandom,seekrandom --writes_per_range_tombstone=200 --max_write_buffer_number=100 --min_write_buffer_number_to_merge=100 --writes=500000 --reads=500000 --seek_nexts=10 --disable_auto_compactions -disable_wal=true --max_num_range_tombstones=1000`. Did not see consistent regression in no timestamp case. | micros/op | fillrandom | seekrandom | | --- | --- | --- | |main| 2.58 |10.96| |PR 10661| 2.68 |10.63| Reviewed By: riversand963 Differential Revision: D39441192 Pulled By: cbi42 fbshipit-source-id: f05aca3c41605caf110daf0ff405919f300ddec2
2022-09-30 23:13:03 +00:00
Status DeleteRange(const Slice& begin_key, const Slice& end_key) {
if (internal_comparator.user_comparator()->timestamp_size() != 0) {
return Status::InvalidArgument("Timestamp size mismatch");
}
return DeleteRangeImpl(begin_key, end_key);
}
// begin_key and end_key should be users keys without timestamp.
Status DeleteRange(const Slice& begin_key, const Slice& end_key,
const Slice& timestamp) {
const size_t timestamp_size = timestamp.size();
if (internal_comparator.user_comparator()->timestamp_size() !=
timestamp_size) {
return Status::InvalidArgument("Timestamp size mismatch");
}
const size_t begin_key_size = begin_key.size();
const size_t end_key_size = end_key.size();
if (begin_key.data() + begin_key_size == timestamp.data() ||
end_key.data() + begin_key_size == timestamp.data()) {
assert(memcmp(begin_key.data() + begin_key_size,
end_key.data() + end_key_size, timestamp_size) == 0);
Slice begin_key_with_ts(begin_key.data(),
begin_key_size + timestamp_size);
Slice end_key_with_ts(end_key.data(), end_key.size() + timestamp_size);
return DeleteRangeImpl(begin_key_with_ts, end_key_with_ts);
}
std::string begin_key_with_ts;
begin_key_with_ts.reserve(begin_key_size + timestamp_size);
begin_key_with_ts.append(begin_key.data(), begin_key_size);
begin_key_with_ts.append(timestamp.data(), timestamp_size);
std::string end_key_with_ts;
end_key_with_ts.reserve(end_key_size + timestamp_size);
end_key_with_ts.append(end_key.data(), end_key_size);
end_key_with_ts.append(timestamp.data(), timestamp_size);
return DeleteRangeImpl(begin_key_with_ts, end_key_with_ts);
}
Status InvalidatePageCache(bool closing) {
Status s = Status::OK();
if (invalidate_page_cache == false) {
// Fadvise disabled
return s;
}
uint64_t bytes_since_last_fadvise = builder->FileSize() - last_fadvise_size;
if (bytes_since_last_fadvise > kFadviseTrigger || closing) {
TEST_SYNC_POINT_CALLBACK("SstFileWriter::Rep::InvalidatePageCache",
&(bytes_since_last_fadvise));
// Tell the OS that we don't need this file in page cache
s = file_writer->InvalidateCache(0, 0);
if (s.IsNotSupported()) {
// NotSupported is fine as it could be a file type that doesn't use page
// cache.
s = Status::OK();
}
last_fadvise_size = builder->FileSize();
}
return s;
}
};
SstFileWriter::SstFileWriter(const EnvOptions& env_options,
const Options& options,
const Comparator* user_comparator,
ColumnFamilyHandle* column_family,
bool invalidate_page_cache,
Env::IOPriority io_priority, bool skip_filters)
: rep_(new Rep(env_options, options, io_priority, user_comparator,
Embed original file number in SST table properties (#8686) Summary: I very recently realized that with https://github.com/facebook/rocksdb/issues/8669 we cannot later add file numbers to external SST files (so that more can share db session ids for better uniqueness properties), because of forward compatibility. We would have a version of RocksDB that assumes session IDs are unique on external SST files and therefore can't really break that invariant in future files. This change adds a table property for "orig_file_number" which is populated by normal SST files and also external SST files generated by SstFileWriter. SstFileWriter now keeps a db_session_id for life of the object and increments its own file numbers for embedding in table properties. (They are arguably "fake" file numbers because these numbers and not embedded in the file name.) While updating block_based_table_builder, I removed several unnecessary fields from Rep, because following the pattern would have created another unnecessary field. This change also updates block_based_table_reader to use this new property when available, which means that for newer SST files, we can determine the stable/original <db_session_id,file_number> unique identifier using just the file contents, not the file name. (It's a bit complicated; detailed comments in block_based_table_reader.) Also added DB host id to properties listing by sst_dump, which could be useful in debugging. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8686 Test Plan: majorly overhauled StableCacheKeys test for this change Reviewed By: zhichao-cao Differential Revision: D30457742 Pulled By: pdillinger fbshipit-source-id: 2e5ae7dddeb94fb9d8eac8a928486aed8b8cd445
2021-08-21 03:39:52 +00:00
column_family, invalidate_page_cache, skip_filters,
DBImpl::GenerateDbSessionId(options.env))) {
// SstFileWriter is used to create sst files that can be added to database
// later. Therefore, no real db_id and db_session_id are associated with it.
// Here we mimic the way db_session_id behaves by getting a db_session_id
// for each SstFileWriter, and (later below) assign unique file numbers
// in the table properties. The db_id is set to be "SST Writer" for clarity.
rep_->file_info.file_size = 0;
}
SstFileWriter::~SstFileWriter() {
if (rep_->builder) {
// User did not call Finish() or Finish() failed, we need to
// abandon the builder.
rep_->builder->Abandon();
}
}
Fix/improve temperature handling for file ingestion (#12402) Summary: Partly following up on leftovers from https://github.com/facebook/rocksdb/issues/12388 In terms of public API: * Make it clear that IngestExternalFileArg::file_temperature is just a hint for opening the existing file, though it was previously used for both copy-from temp hint and copy-to temp, which was bizarre. * Specify how IngestExternalFile assigns temperature to file ingested into DB. (See details in comments.) This approach is not perfect in terms of matching how the DB assigns temperatures, but was the simplest way to get close. The key complication for matching DB temperature assignments is that ingestion files are copied (to a destination temp) before their target level is determined (in general). * Add a temperature option to SstFileWriter::Open so that files intended for ingestion can be initially written to a chosen temperature. * Note that "fail_if_not_bottommost_level" is obsolete/confusing use of "bottommost" In terms of the implementation, there was a similar bit of oddness with the internal CopyFile API, which only took one temperature, ambiguously applicable to the source, destination, or both. This is also fixed. Eventual suggested follow-up: * Before copying files for ingestion, determine a tentative level assignment to use for destination temperature, and keep that even if final level assignment happens to be different at commit time (rare). * More temperature handling for CreateColumnFamilyWithImport and Checkpoints. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12402 Test Plan: Deeply revamped ExternalSSTFileBasicTest.IngestWithTemperature to test the new changes. Previously this test was insufficient because it was only looking at temperatures according to the DB manifest. Incorporating FileTemperatureTestFS allows us to also test the temperatures in the storage layer. Used macros instead of functions for better tracing to critical source location on test failures. Some enhancements to FileTemperatureTestFS in the process of developing the revamped test. Reviewed By: jowlyzhang Differential Revision: D54442794 Pulled By: pdillinger fbshipit-source-id: 41d9d0afdc073e6a983304c10bbc07c70cc7e995
2024-03-06 00:56:08 +00:00
Status SstFileWriter::Open(const std::string& file_path, Temperature temp) {
Rep* r = rep_.get();
Status s;
std::unique_ptr<FSWritableFile> sst_file;
FileOptions cur_file_opts(r->env_options);
Fix/improve temperature handling for file ingestion (#12402) Summary: Partly following up on leftovers from https://github.com/facebook/rocksdb/issues/12388 In terms of public API: * Make it clear that IngestExternalFileArg::file_temperature is just a hint for opening the existing file, though it was previously used for both copy-from temp hint and copy-to temp, which was bizarre. * Specify how IngestExternalFile assigns temperature to file ingested into DB. (See details in comments.) This approach is not perfect in terms of matching how the DB assigns temperatures, but was the simplest way to get close. The key complication for matching DB temperature assignments is that ingestion files are copied (to a destination temp) before their target level is determined (in general). * Add a temperature option to SstFileWriter::Open so that files intended for ingestion can be initially written to a chosen temperature. * Note that "fail_if_not_bottommost_level" is obsolete/confusing use of "bottommost" In terms of the implementation, there was a similar bit of oddness with the internal CopyFile API, which only took one temperature, ambiguously applicable to the source, destination, or both. This is also fixed. Eventual suggested follow-up: * Before copying files for ingestion, determine a tentative level assignment to use for destination temperature, and keep that even if final level assignment happens to be different at commit time (rare). * More temperature handling for CreateColumnFamilyWithImport and Checkpoints. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12402 Test Plan: Deeply revamped ExternalSSTFileBasicTest.IngestWithTemperature to test the new changes. Previously this test was insufficient because it was only looking at temperatures according to the DB manifest. Incorporating FileTemperatureTestFS allows us to also test the temperatures in the storage layer. Used macros instead of functions for better tracing to critical source location on test failures. Some enhancements to FileTemperatureTestFS in the process of developing the revamped test. Reviewed By: jowlyzhang Differential Revision: D54442794 Pulled By: pdillinger fbshipit-source-id: 41d9d0afdc073e6a983304c10bbc07c70cc7e995
2024-03-06 00:56:08 +00:00
cur_file_opts.temperature = temp;
s = r->ioptions.env->GetFileSystem()->NewWritableFile(
file_path, cur_file_opts, &sst_file, nullptr);
if (!s.ok()) {
return s;
}
sst_file->SetIOPriority(r->io_priority);
CompressionType compression_type;
CompressionOptions compression_opts;
if (r->mutable_cf_options.bottommost_compression !=
kDisableCompressionOption) {
compression_type = r->mutable_cf_options.bottommost_compression;
if (r->mutable_cf_options.bottommost_compression_opts.enabled) {
compression_opts = r->mutable_cf_options.bottommost_compression_opts;
} else {
compression_opts = r->mutable_cf_options.compression_opts;
}
} else if (!r->mutable_cf_options.compression_per_level.empty()) {
// Use the compression of the last level if we have per level compression
compression_type = *(r->mutable_cf_options.compression_per_level.rbegin());
compression_opts = r->mutable_cf_options.compression_opts;
} else {
compression_type = r->mutable_cf_options.compression;
compression_opts = r->mutable_cf_options.compression_opts;
}
InternalTblPropCollFactories internal_tbl_prop_coll_factories;
// SstFileWriter properties collector to add SstFileWriter version.
internal_tbl_prop_coll_factories.emplace_back(
new SstFileWriterPropertiesCollectorFactory(2 /* version */,
0 /* global_seqno*/));
// User collector factories
auto user_collector_factories =
r->ioptions.table_properties_collector_factories;
for (size_t i = 0; i < user_collector_factories.size(); i++) {
internal_tbl_prop_coll_factories.emplace_back(
new UserKeyTablePropertiesCollectorFactory(
user_collector_factories[i]));
}
int unknown_level = -1;
uint32_t cf_id;
if (r->cfh != nullptr) {
// user explicitly specified that this file will be ingested into cfh,
// we can persist this information in the file.
cf_id = r->cfh->GetID();
r->column_family_name = r->cfh->GetName();
} else {
r->column_family_name = "";
cf_id = TablePropertiesCollectorFactory::Context::kUnknownColumnFamily;
}
// TODO: it would be better to set oldest_key_time to be used for getting the
// approximate time of ingested keys.
Group SST write in flush, compaction and db open with new stats (#11910) Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
// TODO: plumb Env::IOActivity, Env::IOPriority
TableBuilderOptions table_builder_options(
Group SST write in flush, compaction and db open with new stats (#11910) Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
r->ioptions, r->mutable_cf_options, ReadOptions(), r->write_options,
r->internal_comparator, &internal_tbl_prop_coll_factories,
Group SST write in flush, compaction and db open with new stats (#11910) Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
compression_type, compression_opts, cf_id, r->column_family_name,
unknown_level, false /* is_bottommost */, TableFileCreationReason::kMisc,
0 /* oldest_key_time */, 0 /* file_creation_time */,
"SST Writer" /* db_id */, r->db_session_id, 0 /* target_file_size */,
r->next_file_number);
Embed original file number in SST table properties (#8686) Summary: I very recently realized that with https://github.com/facebook/rocksdb/issues/8669 we cannot later add file numbers to external SST files (so that more can share db session ids for better uniqueness properties), because of forward compatibility. We would have a version of RocksDB that assumes session IDs are unique on external SST files and therefore can't really break that invariant in future files. This change adds a table property for "orig_file_number" which is populated by normal SST files and also external SST files generated by SstFileWriter. SstFileWriter now keeps a db_session_id for life of the object and increments its own file numbers for embedding in table properties. (They are arguably "fake" file numbers because these numbers and not embedded in the file name.) While updating block_based_table_builder, I removed several unnecessary fields from Rep, because following the pattern would have created another unnecessary field. This change also updates block_based_table_reader to use this new property when available, which means that for newer SST files, we can determine the stable/original <db_session_id,file_number> unique identifier using just the file contents, not the file name. (It's a bit complicated; detailed comments in block_based_table_reader.) Also added DB host id to properties listing by sst_dump, which could be useful in debugging. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8686 Test Plan: majorly overhauled StableCacheKeys test for this change Reviewed By: zhichao-cao Differential Revision: D30457742 Pulled By: pdillinger fbshipit-source-id: 2e5ae7dddeb94fb9d8eac8a928486aed8b8cd445
2021-08-21 03:39:52 +00:00
// External SST files used to each get a unique session id. Now for
// slightly better uniqueness probability in constructing cache keys, we
// assign fake file numbers to each file (into table properties) and keep
// the same session id for the life of the SstFileWriter.
r->next_file_number++;
Add more LSM info to FilterBuildingContext (#8246) Summary: Add `num_levels`, `is_bottommost`, and table file creation `reason` to `FilterBuildingContext`, in anticipation of more powerful Bloom-like filter support. To support this, added `is_bottommost` and `reason` to `TableBuilderOptions`, which allowed removing `reason` parameter from `rocksdb::BuildTable`. I attempted to remove `skip_filters` from `TableBuilderOptions`, because filter construction decisions should arise from options, not one-off parameters. I could not completely remove it because the public API for SstFileWriter takes a `skip_filters` parameter, and translating this into an option change would mean awkwardly replacing the table_factory if it is BlockBasedTableFactory with new filter_policy=nullptr option. I marked this public skip_filters option as deprecated because of this oddity. (skip_filters on the read side probably makes sense.) At least `skip_filters` is now largely hidden for users of `TableBuilderOptions` and is no longer used for implementing the optimize_filters_for_hits option. Bringing the logic for that option closer to handling of FilterBuildingContext makes it more obvious that hese two are using the same notion of "bottommost." (Planned: configuration options for Bloom-like filters that generalize `optimize_filters_for_hits`) Recommended follow-up: Try to get away from "bottommost level" naming of things, which is inaccurate (see VersionStorageInfo::RangeMightExistAfterSortedRun), and move to "bottommost run" or just "bottommost." Pull Request resolved: https://github.com/facebook/rocksdb/pull/8246 Test Plan: extended an existing unit test to exercise and check various filter building contexts. Also, existing tests for optimize_filters_for_hits validate some of the "bottommost" handling, which is now closely connected to FilterBuildingContext::is_bottommost through TableBuilderOptions::is_bottommost Reviewed By: mrambacher Differential Revision: D28099346 Pulled By: pdillinger fbshipit-source-id: 2c1072e29c24d4ac404c761a7b7663292372600a
2021-04-30 20:49:24 +00:00
// XXX: when we can remove skip_filters from the SstFileWriter public API
// we can remove it from TableBuilderOptions.
table_builder_options.skip_filters = r->skip_filters;
FileTypeSet tmp_set = r->ioptions.checksum_handoff_file_types;
r->file_writer.reset(new WritableFileWriter(
std::move(sst_file), file_path, r->env_options, r->ioptions.clock,
Group SST write in flush, compaction and db open with new stats (#11910) Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
nullptr /* io_tracer */, r->ioptions.stats, Histograms::SST_WRITE_MICROS,
r->ioptions.listeners, r->ioptions.file_checksum_gen_factory.get(),
Using existing crc32c checksum in checksum handoff for Manifest and WAL (#8412) Summary: In PR https://github.com/facebook/rocksdb/issues/7523 , checksum handoff is introduced in RocksDB for WAL, Manifest, and SST files. When user enable checksum handoff for a certain type of file, before the data is written to the lower layer storage system, we calculate the checksum (crc32c) of each piece of data and pass the checksum down with the data, such that data verification can be down by the lower layer storage system if it has the capability. However, it cannot cover the whole lifetime of the data in the memory and also it potentially introduces extra checksum calculation overhead. In this PR, we introduce a new interface in WritableFileWriter::Append, which allows the caller be able to pass the data and the checksum (crc32c) together. In this way, WritableFileWriter can directly use the pass-in checksum (crc32c) to generate the checksum of data being passed down to the storage system. It saves the calculation overhead and achieves higher protection coverage. When a new checksum is added with the data, we use Crc32cCombine https://github.com/facebook/rocksdb/issues/8305 to combine the existing checksum and the new checksum. To avoid the segmenting of data by rate-limiter before it is stored, rate-limiter is called enough times to accumulate enough credits for a certain write. This design only support Manifest and WAL which use log_writer in the current stage. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8412 Test Plan: make check, add new testing cases. Reviewed By: anand1976 Differential Revision: D29151545 Pulled By: zhichao-cao fbshipit-source-id: 75e2278c5126cfd58393c67b1efd18dcc7a30772
2021-06-25 07:46:33 +00:00
tmp_set.Contains(FileType::kTableFile), false));
// TODO(tec) : If table_factory is using compressed block cache, we will
// be adding the external sst file blocks into it, which is wasteful.
r->builder.reset(r->ioptions.table_factory->NewTableBuilder(
table_builder_options, r->file_writer.get()));
r->file_info = ExternalSstFileInfo();
r->file_info.file_path = file_path;
r->file_info.version = 2;
return s;
}
Status SstFileWriter::Add(const Slice& user_key, const Slice& value) {
return rep_->Add(user_key, value, ValueType::kTypeValue);
}
Status SstFileWriter::Put(const Slice& user_key, const Slice& value) {
return rep_->Add(user_key, value, ValueType::kTypeValue);
}
Status SstFileWriter::Put(const Slice& user_key, const Slice& timestamp,
const Slice& value) {
return rep_->Add(user_key, timestamp, value, ValueType::kTypeValue);
}
Status SstFileWriter::PutEntity(const Slice& user_key,
const WideColumns& columns) {
return rep_->AddEntity(user_key, columns);
}
Status SstFileWriter::Merge(const Slice& user_key, const Slice& value) {
return rep_->Add(user_key, value, ValueType::kTypeMerge);
}
Status SstFileWriter::Delete(const Slice& user_key) {
return rep_->Add(user_key, Slice(), ValueType::kTypeDeletion);
}
Status SstFileWriter::Delete(const Slice& user_key, const Slice& timestamp) {
return rep_->Add(user_key, timestamp, Slice(),
ValueType::kTypeDeletionWithTimestamp);
}
Status SstFileWriter::DeleteRange(const Slice& begin_key,
const Slice& end_key) {
return rep_->DeleteRange(begin_key, end_key);
}
User-defined timestamp support for `DeleteRange()` (#10661) Summary: Add user-defined timestamp support for range deletion. The new API is `DeleteRange(opt, cf, begin_key, end_key, ts)`. Most of the change is to update the comparator to compare without timestamp. Other than that, major changes are - internal range tombstone data structures (`FragmentedRangeTombstoneList`, `RangeTombstone`, etc.) to store timestamps. - Garbage collection of range tombstones and range tombstone covered keys during compaction. - Get()/MultiGet() to return the timestamp of a range tombstone when needed. - Get/Iterator with range tombstones bounded by readoptions.timestamp. - timestamp crash test now issues DeleteRange by default. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10661 Test Plan: - Added unit test: `make check` - Stress test: `python3 tools/db_crashtest.py --enable_ts whitebox --readpercent=57 --prefixpercent=4 --writepercent=25 -delpercent=5 --iterpercent=5 --delrangepercent=4` - Ran `db_bench` to measure regression when timestamp is not enabled. The tests are for write (with some range deletion) and iterate with DB fitting in memory: `./db_bench--benchmarks=fillrandom,seekrandom --writes_per_range_tombstone=200 --max_write_buffer_number=100 --min_write_buffer_number_to_merge=100 --writes=500000 --reads=500000 --seek_nexts=10 --disable_auto_compactions -disable_wal=true --max_num_range_tombstones=1000`. Did not see consistent regression in no timestamp case. | micros/op | fillrandom | seekrandom | | --- | --- | --- | |main| 2.58 |10.96| |PR 10661| 2.68 |10.63| Reviewed By: riversand963 Differential Revision: D39441192 Pulled By: cbi42 fbshipit-source-id: f05aca3c41605caf110daf0ff405919f300ddec2
2022-09-30 23:13:03 +00:00
Status SstFileWriter::DeleteRange(const Slice& begin_key, const Slice& end_key,
const Slice& timestamp) {
return rep_->DeleteRange(begin_key, end_key, timestamp);
}
Status SstFileWriter::Finish(ExternalSstFileInfo* file_info) {
Rep* r = rep_.get();
if (!r->builder) {
return Status::InvalidArgument("File is not opened");
}
if (r->file_info.num_entries == 0 &&
r->file_info.num_range_del_entries == 0) {
return Status::InvalidArgument("Cannot create sst file with no entries");
}
Status s = r->builder->Finish();
r->file_info.file_size = r->builder->FileSize();
Group SST write in flush, compaction and db open with new stats (#11910) Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
IOOptions opts;
if (s.ok()) {
s = WritableFileWriter::PrepareIOOptions(r->write_options, opts);
}
if (s.ok()) {
Group SST write in flush, compaction and db open with new stats (#11910) Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
s = r->file_writer->Sync(opts, r->ioptions.use_fsync);
r->InvalidatePageCache(true /* closing */).PermitUncheckedError();
if (s.ok()) {
Group SST write in flush, compaction and db open with new stats (#11910) Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
s = r->file_writer->Close(opts);
}
}
if (s.ok()) {
r->file_info.file_checksum = r->file_writer->GetFileChecksum();
r->file_info.file_checksum_func_name =
r->file_writer->GetFileChecksumFuncName();
}
if (!s.ok()) {
r->ioptions.env->DeleteFile(r->file_info.file_path);
}
if (file_info != nullptr) {
*file_info = r->file_info;
Add support in SstFileWriter to not persist user defined timestamps (#12348) Summary: This PR adds support in `SstFileWriter` to create SST files without persisting timestamps when the column family has enabled UDTs in Memtable only feature. The sst files created from flush and compaction do not contain timestamps, we want to make the sst files created by `SstFileWriter` to follow the same pattern and not persist timestamps. This is to prepare for ingesting external SST files for this type of column family. There are timestamp-aware APIs and non timestamp-aware APIs in `SstFileWriter`. The former are exclusively used for when the column family's comparator is timestamp-aware, a.k.a `Comparator::timestamp_size() > 0`, while the latter are exclusively used for the column family's comparator is non timestamp-aware, a.k.a `Comparator::timestamp_size() == 0`. There are sanity checks to make sure these APIs are correctly used. In this PR, the APIs usage continue with above enforcement, where even though timestamps are not eventually persisted, users are still asked to use only the timestamp-aware APIs. But because data points will logically all have minimum timestamps, we don't allow multiple versions of the same user key (without timestamp) to be added. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12348 Test Plan: Added unit tests Manual inspection of generated sst files with `sst_dump` Reviewed By: ltamasi Differential Revision: D53732667 Pulled By: jowlyzhang fbshipit-source-id: e43beba0d3a1736b94ee5c617163a6280efd65b7
2024-02-14 04:30:07 +00:00
Slice smallest_key = r->file_info.smallest_key;
Slice largest_key = r->file_info.largest_key;
Slice smallest_range_del_key = r->file_info.smallest_range_del_key;
Slice largest_range_del_key = r->file_info.largest_range_del_key;
assert(smallest_key.empty() == largest_key.empty());
assert(smallest_range_del_key.empty() == largest_range_del_key.empty());
// Remove user-defined timestamps from external file metadata too when they
// should not be persisted.
if (r->strip_timestamp) {
if (!smallest_key.empty()) {
assert(smallest_key.size() >= r->ts_sz);
assert(largest_key.size() >= r->ts_sz);
file_info->smallest_key.resize(smallest_key.size() - r->ts_sz);
file_info->largest_key.resize(largest_key.size() - r->ts_sz);
}
if (!smallest_range_del_key.empty()) {
assert(smallest_range_del_key.size() >= r->ts_sz);
assert(largest_range_del_key.size() >= r->ts_sz);
file_info->smallest_range_del_key.resize(smallest_range_del_key.size() -
r->ts_sz);
file_info->largest_range_del_key.resize(largest_range_del_key.size() -
r->ts_sz);
}
}
}
r->builder.reset();
return s;
}
uint64_t SstFileWriter::FileSize() { return rep_->file_info.file_size; }
} // namespace ROCKSDB_NAMESPACE