2020-03-13 04:39:36 +00:00
|
|
|
// 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/index_reader_common.h"
|
|
|
|
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
Status BlockBasedTable::IndexReaderCommon::ReadIndexBlock(
|
|
|
|
const BlockBasedTable* table, FilePrefetchBuffer* prefetch_buffer,
|
|
|
|
const ReadOptions& read_options, bool use_cache, GetContext* get_context,
|
|
|
|
BlockCacheLookupContext* lookup_context,
|
|
|
|
CachableEntry<Block>* index_block) {
|
|
|
|
PERF_TIMER_GUARD(read_index_block_nanos);
|
|
|
|
|
|
|
|
assert(table != nullptr);
|
|
|
|
assert(index_block != nullptr);
|
|
|
|
assert(index_block->IsEmpty());
|
|
|
|
|
|
|
|
const Rep* const rep = table->get_rep();
|
|
|
|
assert(rep != nullptr);
|
|
|
|
|
|
|
|
const Status s = table->RetrieveBlock(
|
|
|
|
prefetch_buffer, read_options, rep->footer.index_handle(),
|
|
|
|
UncompressionDict::GetEmptyDict(), index_block, BlockType::kIndex,
|
2021-06-18 16:35:03 +00:00
|
|
|
get_context, lookup_context, /* for_compaction */ false, use_cache,
|
2022-05-20 23:09:33 +00:00
|
|
|
/* wait_for_cache */ true, /* async_read */ false);
|
2020-03-13 04:39:36 +00:00
|
|
|
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
|
|
|
Status BlockBasedTable::IndexReaderCommon::GetOrReadIndexBlock(
|
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
|
|
|
bool no_io, Env::IOPriority rate_limiter_priority, GetContext* get_context,
|
2020-03-13 04:39:36 +00:00
|
|
|
BlockCacheLookupContext* lookup_context,
|
|
|
|
CachableEntry<Block>* index_block) const {
|
|
|
|
assert(index_block != nullptr);
|
|
|
|
|
|
|
|
if (!index_block_.IsEmpty()) {
|
|
|
|
index_block->SetUnownedValue(index_block_.GetValue());
|
|
|
|
return Status::OK();
|
|
|
|
}
|
|
|
|
|
|
|
|
ReadOptions read_options;
|
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
|
|
|
read_options.rate_limiter_priority = rate_limiter_priority;
|
2020-03-13 04:39:36 +00:00
|
|
|
if (no_io) {
|
|
|
|
read_options.read_tier = kBlockCacheTier;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ReadIndexBlock(table_, /*prefetch_buffer=*/nullptr, read_options,
|
|
|
|
cache_index_blocks(), get_context, lookup_context,
|
|
|
|
index_block);
|
|
|
|
}
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|