|
|
|
// 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.
|
|
|
|
#pragma once
|
|
|
|
|
|
|
|
#include "table/block_based/block_based_table_reader.h"
|
|
|
|
|
|
|
|
#include "table/block_based/reader_common.h"
|
|
|
|
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
// Encapsulates common functionality for the various index reader
|
|
|
|
// implementations. Provides access to the index block regardless of whether
|
|
|
|
// it is owned by the reader or stored in the cache, or whether it is pinned
|
|
|
|
// in the cache or not.
|
|
|
|
class BlockBasedTable::IndexReaderCommon : public BlockBasedTable::IndexReader {
|
|
|
|
public:
|
|
|
|
IndexReaderCommon(const BlockBasedTable* t,
|
|
|
|
CachableEntry<Block>&& index_block)
|
|
|
|
: table_(t), index_block_(std::move(index_block)) {
|
|
|
|
assert(table_ != nullptr);
|
|
|
|
}
|
|
|
|
|
|
|
|
protected:
|
|
|
|
static Status ReadIndexBlock(const BlockBasedTable* table,
|
|
|
|
FilePrefetchBuffer* prefetch_buffer,
|
|
|
|
const ReadOptions& read_options, bool use_cache,
|
|
|
|
GetContext* get_context,
|
|
|
|
BlockCacheLookupContext* lookup_context,
|
|
|
|
CachableEntry<Block>* index_block);
|
|
|
|
|
|
|
|
const BlockBasedTable* table() const { return table_; }
|
|
|
|
|
|
|
|
const InternalKeyComparator* internal_comparator() const {
|
|
|
|
assert(table_ != nullptr);
|
|
|
|
assert(table_->get_rep() != nullptr);
|
|
|
|
|
|
|
|
return &table_->get_rep()->internal_comparator;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool index_has_first_key() const {
|
|
|
|
assert(table_ != nullptr);
|
|
|
|
assert(table_->get_rep() != nullptr);
|
|
|
|
return table_->get_rep()->index_has_first_key;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool index_key_includes_seq() const {
|
|
|
|
assert(table_ != nullptr);
|
|
|
|
assert(table_->get_rep() != nullptr);
|
|
|
|
return table_->get_rep()->index_key_includes_seq;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool index_value_is_full() const {
|
|
|
|
assert(table_ != nullptr);
|
|
|
|
assert(table_->get_rep() != nullptr);
|
|
|
|
return table_->get_rep()->index_value_is_full;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool cache_index_blocks() const {
|
|
|
|
assert(table_ != nullptr);
|
|
|
|
assert(table_->get_rep() != nullptr);
|
|
|
|
return table_->get_rep()->table_options.cache_index_and_filter_blocks;
|
|
|
|
}
|
|
|
|
|
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
3 years ago
|
|
|
Status GetOrReadIndexBlock(bool no_io, Env::IOPriority rate_limiter_priority,
|
|
|
|
GetContext* get_context,
|
|
|
|
BlockCacheLookupContext* lookup_context,
|
|
|
|
CachableEntry<Block>* index_block) const;
|
|
|
|
|
|
|
|
size_t ApproximateIndexBlockMemoryUsage() const {
|
|
|
|
assert(!index_block_.GetOwnValue() || index_block_.GetValue() != nullptr);
|
|
|
|
return index_block_.GetOwnValue()
|
|
|
|
? index_block_.GetValue()->ApproximateMemoryUsage()
|
|
|
|
: 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
private:
|
|
|
|
const BlockBasedTable* table_;
|
|
|
|
CachableEntry<Block> index_block_;
|
|
|
|
};
|
|
|
|
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|