rocksdb/table/block_based/hash_index_reader.cc

149 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(
file, prefetch_buffer, footer, ReadOptions(), 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(
file, prefetch_buffer, footer, ReadOptions(), 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;
const Status s =
Set Read rate limiter priority dynamically and pass it to FS (#9996) Summary: ### Context: Background compactions and flush generate large reads and writes, and can be long running, especially for universal compaction. In some cases, this can impact foreground reads and writes by users. ### Solution User, Flush, and Compaction reads share some code path. For this task, we update the rate_limiter_priority in ReadOptions for code paths (e.g. FindTable (mainly in BlockBasedTable::Open()) and various iterators), and eventually update the rate_limiter_priority in IOOptions for FSRandomAccessFile. **This PR is for the Read path.** The **Read:** dynamic priority for different state are listed as follows: | State | Normal | Delayed | Stalled | | ----- | ------ | ------- | ------- | | Flush (verification read in BuildTable()) | IO_USER | IO_USER | IO_USER | | Compaction | IO_LOW | IO_USER | IO_USER | | User | User provided | User provided | User provided | We will respect the read_options that the user provided and will not set it. The only sst read for Flush is the verification read in BuildTable(). It claims to be "regard as user read". **Details** 1. Set read_options.rate_limiter_priority dynamically: - User: Do not update the read_options. Use the read_options that the user provided. - Compaction: Update read_options in CompactionJob::ProcessKeyValueCompaction(). - Flush: Update read_options in BuildTable(). 2. Pass the rate limiter priority to FSRandomAccessFile functions: - After calling the FindTable(), read_options is passed through GetTableReader(table_cache.cc), BlockBasedTableFactory::NewTableReader(block_based_table_factory.cc), and BlockBasedTable::Open(). The Open() needs some updates for the ReadOptions variable and the updates are also needed for the called functions, including PrefetchTail(), PrepareIOOptions(), ReadFooterFromFile(), ReadMetaIndexblock(), ReadPropertiesBlock(), PrefetchIndexAndFilterBlocks(), and ReadRangeDelBlock(). - In RandomAccessFileReader, the functions to be updated include Read(), MultiRead(), ReadAsync(), and Prefetch(). - Update the downstream functions of NewIndexIterator(), NewDataBlockIterator(), and BlockBasedTableIterator(). ### Test Plans Add unit tests. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9996 Reviewed By: anand1976 Differential Revision: D36452483 Pulled By: gitbw95 fbshipit-source-id: 60978204a4f849bb9261cb78d9bc1cb56d6008cf
2022-05-19 02:41:44 +00:00
GetOrReadIndexBlock(no_io, read_options.rate_limiter_priority,
get_context, lookup_context, &index_block);
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 */,
prefix_index_.get());
assert(it != nullptr);
index_block.TransferTo(it);
return it;
}
} // namespace ROCKSDB_NAMESPACE