rocksdb/table/block_based/hash_index_reader.cc

148 lines
5.4 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).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
#include "table/block_based/hash_index_reader.h"
#include "table/block_fetcher.h"
#include "table/meta_blocks.h"
namespace ROCKSDB_NAMESPACE {
Status HashIndexReader::Create(const BlockBasedTable* table,
const ReadOptions& ro,
FilePrefetchBuffer* prefetch_buffer,
InternalIterator* meta_index_iter,
bool use_cache, bool prefetch, bool pin,
BlockCacheLookupContext* lookup_context,
std::unique_ptr<IndexReader>* index_reader) {
assert(table != nullptr);
assert(index_reader != nullptr);
assert(!pin || prefetch);
const BlockBasedTable::Rep* rep = table->get_rep();
assert(rep != nullptr);
CachableEntry<Block> index_block;
if (prefetch || !use_cache) {
const Status s =
ReadIndexBlock(table, prefetch_buffer, ro, use_cache,
/*get_context=*/nullptr, lookup_context, &index_block);
if (!s.ok()) {
return s;
}
if (use_cache && !pin) {
index_block.Reset();
}
}
// Note, failure to create prefix hash index does not need to be a
// hard error. We can still fall back to the original binary search index.
// So, Create will succeed regardless, from this point on.
index_reader->reset(new HashIndexReader(table, std::move(index_block)));
// Get prefixes block
BlockHandle prefixes_handle;
Status s =
FindMetaBlock(meta_index_iter, kHashIndexPrefixesBlock, &prefixes_handle);
if (!s.ok()) {
// TODO: log error
return Status::OK();
}
// Get index metadata block
BlockHandle prefixes_meta_handle;
s = FindMetaBlock(meta_index_iter, kHashIndexPrefixesMetadataBlock,
&prefixes_meta_handle);
if (!s.ok()) {
// TODO: log error
return Status::OK();
}
RandomAccessFileReader* const file = rep->file.get();
const Footer& footer = rep->footer;
const ImmutableOptions& ioptions = rep->ioptions;
const PersistentCacheOptions& cache_options = rep->persistent_cache_options;
MemoryAllocator* const memory_allocator =
GetMemoryAllocator(rep->table_options);
// Read contents for the blocks
BlockContents prefixes_contents;
BlockFetcher prefixes_block_fetcher(
Group rocksdb.sst.read.micros stat by IOActivity flush and compaction (#11288) Summary: **Context:** The existing stat rocksdb.sst.read.micros does not reflect each of compaction and flush cases but aggregate them, which is not so helpful for us to understand IO read behavior of each of them. **Summary** - Update `StopWatch` and `RandomAccessFileReader` to record `rocksdb.sst.read.micros` and `rocksdb.file.{flush/compaction}.read.micros` - Fixed the default histogram in `RandomAccessFileReader` - New field `ReadOptions/IOOptions::io_activity`; Pass `ReadOptions` through paths under db open, flush and compaction to where we can prepare `IOOptions` and pass it to `RandomAccessFileReader` - Use `thread_status_util` for assertion in `DbStressFSWrapper` for continuous testing on we are passing correct `io_activity` under db open, flush and compaction Pull Request resolved: https://github.com/facebook/rocksdb/pull/11288 Test Plan: - **Stress test** - **Db bench 1: rocksdb.sst.read.micros COUNT ≈ sum of rocksdb.file.read.flush.micros's and rocksdb.file.read.compaction.micros's.** (without blob) - May not be exactly the same due to `HistogramStat::Add` only guarantees atomic not accuracy across threads. ``` ./db_bench -db=/dev/shm/testdb/ -statistics=true -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -target_file_size_base=655 -disable_auto_compactions=false -compression_type=none -bloom_bits=3 (-use_plain_table=1 -prefix_size=10) ``` ``` // BlockBasedTable rocksdb.sst.read.micros P50 : 2.009374 P95 : 4.968548 P99 : 8.110362 P100 : 43.000000 COUNT : 40456 SUM : 114805 rocksdb.file.read.flush.micros P50 : 1.871841 P95 : 3.872407 P99 : 5.540541 P100 : 43.000000 COUNT : 2250 SUM : 6116 rocksdb.file.read.compaction.micros P50 : 2.023109 P95 : 5.029149 P99 : 8.196910 P100 : 26.000000 COUNT : 38206 SUM : 108689 // PlainTable Does not apply ``` - **Db bench 2: performance** **Read** SETUP: db with 900 files ``` ./db_bench -db=/dev/shm/testdb/ -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=true -target_file_size_base=655 -compression_type=none ```run till convergence ``` ./db_bench -seed=1678564177044286 -use_existing_db=true -db=/dev/shm/testdb -benchmarks=readrandom[-X60] -statistics=true -num=1000000 -disable_auto_compactions=true -compression_type=none -bloom_bits=3 ``` Pre-change `readrandom [AVG 60 runs] : 21568 (± 248) ops/sec` Post-change (no regression, -0.3%) `readrandom [AVG 60 runs] : 21486 (± 236) ops/sec` **Compaction/Flush**run till convergence ``` ./db_bench -db=/dev/shm/testdb2/ -seed=1678564177044286 -benchmarks="fillseq[-X60]" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=false -target_file_size_base=655 -compression_type=none rocksdb.sst.read.micros COUNT : 33820 rocksdb.sst.read.flush.micros COUNT : 1800 rocksdb.sst.read.compaction.micros COUNT : 32020 ``` Pre-change `fillseq [AVG 46 runs] : 1391 (± 214) ops/sec; 0.7 (± 0.1) MB/sec` Post-change (no regression, ~-0.4%) `fillseq [AVG 46 runs] : 1385 (± 216) ops/sec; 0.7 (± 0.1) MB/sec` Reviewed By: ajkr Differential Revision: D44007011 Pulled By: hx235 fbshipit-source-id: a54c89e4846dfc9a135389edf3f3eedfea257132
2023-04-21 16:07:18 +00:00
file, prefetch_buffer, footer, ro, prefixes_handle, &prefixes_contents,
ioptions, true /*decompress*/, true /*maybe_compressed*/,
BlockType::kHashIndexPrefixes, UncompressionDict::GetEmptyDict(),
cache_options, memory_allocator);
s = prefixes_block_fetcher.ReadBlockContents();
if (!s.ok()) {
return s;
}
BlockContents prefixes_meta_contents;
BlockFetcher prefixes_meta_block_fetcher(
Group rocksdb.sst.read.micros stat by IOActivity flush and compaction (#11288) Summary: **Context:** The existing stat rocksdb.sst.read.micros does not reflect each of compaction and flush cases but aggregate them, which is not so helpful for us to understand IO read behavior of each of them. **Summary** - Update `StopWatch` and `RandomAccessFileReader` to record `rocksdb.sst.read.micros` and `rocksdb.file.{flush/compaction}.read.micros` - Fixed the default histogram in `RandomAccessFileReader` - New field `ReadOptions/IOOptions::io_activity`; Pass `ReadOptions` through paths under db open, flush and compaction to where we can prepare `IOOptions` and pass it to `RandomAccessFileReader` - Use `thread_status_util` for assertion in `DbStressFSWrapper` for continuous testing on we are passing correct `io_activity` under db open, flush and compaction Pull Request resolved: https://github.com/facebook/rocksdb/pull/11288 Test Plan: - **Stress test** - **Db bench 1: rocksdb.sst.read.micros COUNT ≈ sum of rocksdb.file.read.flush.micros's and rocksdb.file.read.compaction.micros's.** (without blob) - May not be exactly the same due to `HistogramStat::Add` only guarantees atomic not accuracy across threads. ``` ./db_bench -db=/dev/shm/testdb/ -statistics=true -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -target_file_size_base=655 -disable_auto_compactions=false -compression_type=none -bloom_bits=3 (-use_plain_table=1 -prefix_size=10) ``` ``` // BlockBasedTable rocksdb.sst.read.micros P50 : 2.009374 P95 : 4.968548 P99 : 8.110362 P100 : 43.000000 COUNT : 40456 SUM : 114805 rocksdb.file.read.flush.micros P50 : 1.871841 P95 : 3.872407 P99 : 5.540541 P100 : 43.000000 COUNT : 2250 SUM : 6116 rocksdb.file.read.compaction.micros P50 : 2.023109 P95 : 5.029149 P99 : 8.196910 P100 : 26.000000 COUNT : 38206 SUM : 108689 // PlainTable Does not apply ``` - **Db bench 2: performance** **Read** SETUP: db with 900 files ``` ./db_bench -db=/dev/shm/testdb/ -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=true -target_file_size_base=655 -compression_type=none ```run till convergence ``` ./db_bench -seed=1678564177044286 -use_existing_db=true -db=/dev/shm/testdb -benchmarks=readrandom[-X60] -statistics=true -num=1000000 -disable_auto_compactions=true -compression_type=none -bloom_bits=3 ``` Pre-change `readrandom [AVG 60 runs] : 21568 (± 248) ops/sec` Post-change (no regression, -0.3%) `readrandom [AVG 60 runs] : 21486 (± 236) ops/sec` **Compaction/Flush**run till convergence ``` ./db_bench -db=/dev/shm/testdb2/ -seed=1678564177044286 -benchmarks="fillseq[-X60]" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=false -target_file_size_base=655 -compression_type=none rocksdb.sst.read.micros COUNT : 33820 rocksdb.sst.read.flush.micros COUNT : 1800 rocksdb.sst.read.compaction.micros COUNT : 32020 ``` Pre-change `fillseq [AVG 46 runs] : 1391 (± 214) ops/sec; 0.7 (± 0.1) MB/sec` Post-change (no regression, ~-0.4%) `fillseq [AVG 46 runs] : 1385 (± 216) ops/sec; 0.7 (± 0.1) MB/sec` Reviewed By: ajkr Differential Revision: D44007011 Pulled By: hx235 fbshipit-source-id: a54c89e4846dfc9a135389edf3f3eedfea257132
2023-04-21 16:07:18 +00:00
file, prefetch_buffer, footer, ro, prefixes_meta_handle,
&prefixes_meta_contents, ioptions, true /*decompress*/,
true /*maybe_compressed*/, BlockType::kHashIndexMetadata,
UncompressionDict::GetEmptyDict(), cache_options, memory_allocator);
s = prefixes_meta_block_fetcher.ReadBlockContents();
if (!s.ok()) {
// TODO: log error
return Status::OK();
}
BlockPrefixIndex* prefix_index = nullptr;
assert(rep->table_prefix_extractor);
s = BlockPrefixIndex::Create(rep->table_prefix_extractor.get(),
prefixes_contents.data,
prefixes_meta_contents.data, &prefix_index);
// TODO: log error
if (s.ok()) {
HashIndexReader* const hash_index_reader =
static_cast<HashIndexReader*>(index_reader->get());
hash_index_reader->prefix_index_.reset(prefix_index);
}
return Status::OK();
}
InternalIteratorBase<IndexValue>* HashIndexReader::NewIterator(
const ReadOptions& read_options, bool disable_prefix_seek,
IndexBlockIter* iter, GetContext* get_context,
BlockCacheLookupContext* lookup_context) {
const BlockBasedTable::Rep* rep = table()->get_rep();
const bool no_io = (read_options.read_tier == kBlockCacheTier);
CachableEntry<Block> index_block;
Use user-provided ReadOptions for metadata block reads more often (#11208) Summary: This is mostly taken from https://github.com/facebook/rocksdb/issues/10427 with my own comments addressed. This PR plumbs the user’s `ReadOptions` down to `GetOrReadIndexBlock()`, `GetOrReadFilterBlock()`, and `GetFilterPartitionBlock()`. Now those functions no longer have to make up a `ReadOptions` with incomplete information. I also let `PartitionIndexReader::NewIterator()` pass through its caller's `ReadOptions::verify_checksums`, which was inexplicably dropped previously. Fixes https://github.com/facebook/rocksdb/issues/10463 Pull Request resolved: https://github.com/facebook/rocksdb/pull/11208 Test Plan: Functional: - Measured `-verify_checksum=false` applies to metadata blocks read outside of table open - setup command: `TEST_TMPDIR=/tmp/100M-DB/ ./db_bench -benchmarks=filluniquerandom,waitforcompaction -write_buffer_size=1048576 -target_file_size_base=1048576 -max_bytes_for_level_base=4194304 -compression_type=none -num=1638400 -key_size=8 -value_size=56` - run command: `TEST_TMPDIR=/tmp/100M-DB/ ./db_bench -benchmarks=readrandom -use_existing_db=true -write_buffer_size=1048576 -target_file_size_base=1048576 -max_bytes_for_level_base=4194304 -compression_type=none -num=1638400 -key_size=8 -value_size=56 -duration=10 -threads=32 -cache_size=131072 -statistics=true -verify_checksum=false -open_files=20 -cache_index_and_filter_blocks=true` - before: `rocksdb.block.checksum.compute.count COUNT : 384353` - after: `rocksdb.block.checksum.compute.count COUNT : 22` Performance: - Setup command (tmpfs, 128MB logical data size, cache indexes/filters without pinning so index/filter lookups go through table reader): `TEST_TMPDIR=/dev/shm/128M-DB/ ./db_bench -benchmarks=filluniquerandom,waitforcompaction -write_buffer_size=131072 -target_file_size_base=131072 -max_bytes_for_level_base=524288 -compression_type=none -num=4194304 -key_size=8 -value_size=24 -bloom_bits=8 -whole_key_filtering=1` - Measured point lookup performance. Database is fully cached to emphasize any new callstack overheads - Command: `TEST_TMPDIR=/dev/shm/128M-DB/ ./db_bench -benchmarks=readrandom[-W1][-X20] -use_existing_db=true -cache_index_and_filter_blocks=true -disable_auto_compactions=true -num=4194304 -key_size=8 -value_size=24 -bloom_bits=8 -whole_key_filtering=1 -duration=10 -cache_size=1048576000` - Before: `readrandom [AVG 20 runs] : 274848 (± 3717) ops/sec; 8.4 (± 0.1) MB/sec` - After: `readrandom [AVG 20 runs] : 277904 (± 4474) ops/sec; 8.5 (± 0.1) MB/sec` Reviewed By: hx235 Differential Revision: D43145366 Pulled By: ajkr fbshipit-source-id: 75ec062ece86a82cd788783de9de2c72df57f994
2023-04-04 23:53:14 +00:00
const Status s = GetOrReadIndexBlock(no_io, get_context, lookup_context,
&index_block, read_options);
if (!s.ok()) {
if (iter != nullptr) {
iter->Invalidate(s);
return iter;
}
return NewErrorInternalIterator<IndexValue>(s);
}
Statistics* kNullStats = nullptr;
const bool total_order_seek =
read_options.total_order_seek || disable_prefix_seek;
// We don't return pinned data from index blocks, so no need
// to set `block_contents_pinned`.
auto it = index_block.GetValue()->NewIndexIterator(
Separate internal and user key comparators in `BlockIter` (#6944) Summary: Replace `BlockIter::comparator_` and `IndexBlockIter::user_comparator_wrapper_` with a concrete `UserComparatorWrapper` and `InternalKeyComparator`. The motivation for this change was the inconvenience of not knowing the concrete type of `BlockIter::comparator_`, which prevented calling specialized internal key comparison functions to optimize comparison of keys with global seqno applied. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6944 Test Plan: benchmark setup -- single file DBs, in-memory, no compression. "normal_db" created by regular flush; "ingestion_db" created by ingesting a file. Both DBs have same contents. ``` $ TEST_TMPDIR=/dev/shm/normal_db/ ./db_bench -benchmarks=fillrandom,compact -write_buffer_size=10485760000 -disable_auto_compactions=true -compression_type=none -num=1000000 $ ./ldb write_extern_sst ./tmp.sst --db=/dev/shm/ingestion_db/dbbench/ --compression_type=no --hex --create_if_missing < <(./sst_dump --command=scan --output_hex --file=/dev/shm/normal_db/dbbench/000007.sst | awk 'began {print "0x" substr($1, 2, length($1) - 2), "==>", "0x" $5} ; /^Sst file format: block-based/ {began=1}') $ ./ldb ingest_extern_sst ./tmp.sst --db=/dev/shm/ingestion_db/dbbench/ ``` benchmark run command: ``` $ TEST_TMPDIR=/dev/shm/$DB/ ./db_bench -benchmarks=seekrandom -seek_nexts=$SEEK_NEXT -use_existing_db=true -cache_index_and_filter_blocks=false -num=1000000 -cache_size=0 -threads=1 -reads=200000000 -mmap_read=1 -verify_checksum=false ``` results: perf improved marginally for ingestion_db and did not change significantly for normal_db: SEEK_NEXT | DB | code | ops/sec | % change -- | -- | -- | -- | -- 0 | normal_db | master | 350880 |   0 | normal_db | PR6944 | 351040 | 0.0 0 | ingestion_db | master | 343255 |   0 | ingestion_db | PR6944 | 349424 | 1.8 10 | normal_db | master | 218711 |   10 | normal_db | PR6944 | 217892 | -0.4 10 | ingestion_db | master | 220334 |   10 | ingestion_db | PR6944 | 226437 | 2.8 Reviewed By: pdillinger Differential Revision: D21924676 Pulled By: ajkr fbshipit-source-id: ea4288a2eefa8112eb6c651a671c1de18c12e538
2020-07-08 00:25:08 +00:00
internal_comparator()->user_comparator(),
rep->get_global_seqno(BlockType::kIndex), iter, kNullStats,
total_order_seek, index_has_first_key(), index_key_includes_seq(),
index_value_is_full(), false /* block_contents_pinned */,
Add support to strip / pad timestamp when creating / reading a block based table (#11495) Summary: Add support to strip timestamp in block based table builder and pad timestamp in block based table reader. On the write path, use the per column family option `AdvancedColumnFamilyOptions.persist_user_defined_timestamps` to indicate whether user-defined timestamps should be stripped for all block based tables created for the column family. On the read path, added a per table `TableReadOption.user_defined_timestamps_persisted` to flag whether the user keys in the table contains user defined timestamps. This patch is mostly passing the related flags down to the block building/parsing level with the exception of handling the `first_internal_key` in `IndexValue`, which is included in the `IndexBuilder` level. The value part of range deletion entries should have a similar handling, I haven't decided where to best fit this piece of logic, I will do it in a follow up. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11495 Test Plan: Existing test `BlockBasedTableReaderTest` is parameterized to run with: 1) different UDT test modes: kNone, kNormal, kStripUserDefinedTimestamp 2) all four index types, when index type is `kTwoLevelIndexSearch`, also enables partitioned filters 3) parallel vs non-parallel compression 4) enable/disable compression dictionary. Also added tests for API `BlockBasedTableReader::NewIterator`. `PartitionedFilterBlockTest` is parameterized to run with different UDT test modes:kNone, kNormal, kStripUserDefinedTimestamp. ``` make all check ./block_based_table_reader_test ./partitioned_filter_block_test ``` Reviewed By: ltamasi Differential Revision: D46344577 Pulled By: jowlyzhang fbshipit-source-id: 93ac8542b19319d1298712b8bed908c8831ba675
2023-06-01 18:10:03 +00:00
user_defined_timestamps_persisted(), prefix_index_.get());
assert(it != nullptr);
index_block.TransferTo(it);
return it;
}
} // namespace ROCKSDB_NAMESPACE