rocksdb/db/arena_wrapped_db_iter.cc
Changyu Bi 9d77bf8f7b Fragment memtable range tombstone in the write path (#10380)
Summary:
- Right now each read fragments the memtable range tombstones https://github.com/facebook/rocksdb/issues/4808. This PR explores the idea of fragmenting memtable range tombstones in the write path and reads can just read this cached fragmented tombstone without any fragmenting cost. This PR only does the caching for immutable memtable, and does so right before a memtable is added to an immutable memtable list. The fragmentation is done without holding mutex to minimize its performance impact.
- db_bench is updated to print out the number of range deletions executed if there is any.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/10380

Test Plan:
- CI, added asserts in various places to check whether a fragmented range tombstone list should have been constructed.
- Benchmark: as this PR only optimizes immutable memtable path, the number of writes in the benchmark is chosen such  an immutable memtable is created and range tombstones are in that memtable.

```
single thread:
./db_bench --benchmarks=fillrandom,readrandom --writes_per_range_tombstone=1 --max_write_buffer_number=100 --min_write_buffer_number_to_merge=100 --writes=500000 --reads=100000 --max_num_range_tombstones=100

multi_thread
./db_bench --benchmarks=fillrandom,readrandom --writes_per_range_tombstone=1 --max_write_buffer_number=100 --min_write_buffer_number_to_merge=100 --writes=15000 --reads=20000 --threads=32 --max_num_range_tombstones=100
```
Commit 99cdf16464 is included in benchmark result. It was an earlier attempt where tombstones are fragmented for each write operation. Reader threads share it using a shared_ptr which would slow down multi-thread read performance as seen in benchmark results.
Results are averaged over 5 runs.

Single thread result:
| Max # tombstones  | main fillrandom micros/op | 99cdf16464 | Post PR | main readrandom micros/op |  99cdf16464 | Post PR |
| ------------- | ------------- |------------- |------------- |------------- |------------- |------------- |
| 0    |6.68     |6.57     |6.72     |4.72     |4.79     |4.54     |
| 1    |6.67     |6.58     |6.62     |5.41     |4.74     |4.72     |
| 10   |6.59     |6.5      |6.56     |7.83     |4.69     |4.59     |
| 100  |6.62     |6.75     |6.58     |29.57    |5.04     |5.09     |
| 1000 |6.54     |6.82     |6.61     |320.33   |5.22     |5.21     |

32-thread result: note that "Max # tombstones" is per thread.
| Max # tombstones  | main fillrandom micros/op | 99cdf16464 | Post PR | main readrandom micros/op |  99cdf16464 | Post PR |
| ------------- | ------------- |------------- |------------- |------------- |------------- |------------- |
| 0    |234.52   |260.25   |239.42   |5.06     |5.38     |5.09     |
| 1    |236.46   |262.0    |231.1    |19.57    |22.14    |5.45     |
| 10   |236.95   |263.84   |251.49   |151.73   |21.61    |5.73     |
| 100  |268.16   |296.8    |280.13   |2308.52  |22.27    |6.57     |

Reviewed By: ajkr

Differential Revision: D37916564

Pulled By: cbi42

fbshipit-source-id: 05d6d2e16df26c374c57ddcca13a5bfe9d5b731e
2022-08-05 12:02:33 -07:00

132 lines
5.6 KiB
C++

// 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 "db/arena_wrapped_db_iter.h"
#include "memory/arena.h"
#include "rocksdb/env.h"
#include "rocksdb/iterator.h"
#include "rocksdb/options.h"
#include "table/internal_iterator.h"
#include "table/iterator_wrapper.h"
#include "util/user_comparator_wrapper.h"
namespace ROCKSDB_NAMESPACE {
Status ArenaWrappedDBIter::GetProperty(std::string prop_name,
std::string* prop) {
if (prop_name == "rocksdb.iterator.super-version-number") {
// First try to pass the value returned from inner iterator.
if (!db_iter_->GetProperty(prop_name, prop).ok()) {
*prop = std::to_string(sv_number_);
}
return Status::OK();
}
return db_iter_->GetProperty(prop_name, prop);
}
void ArenaWrappedDBIter::Init(
Env* env, const ReadOptions& read_options, const ImmutableOptions& ioptions,
const MutableCFOptions& mutable_cf_options, const Version* version,
const SequenceNumber& sequence, uint64_t max_sequential_skip_in_iteration,
uint64_t version_number, ReadCallback* read_callback, DBImpl* db_impl,
ColumnFamilyData* cfd, bool expose_blob_index, bool allow_refresh) {
auto mem = arena_.AllocateAligned(sizeof(DBIter));
db_iter_ =
new (mem) DBIter(env, read_options, ioptions, mutable_cf_options,
ioptions.user_comparator, /* iter */ nullptr, version,
sequence, true, max_sequential_skip_in_iteration,
read_callback, db_impl, cfd, expose_blob_index);
sv_number_ = version_number;
read_options_ = read_options;
allow_refresh_ = allow_refresh;
}
Status ArenaWrappedDBIter::Refresh() {
if (cfd_ == nullptr || db_impl_ == nullptr || !allow_refresh_) {
return Status::NotSupported("Creating renew iterator is not allowed.");
}
assert(db_iter_ != nullptr);
// TODO(yiwu): For last_seq_same_as_publish_seq_==false, this is not the
// correct behavior. Will be corrected automatically when we take a snapshot
// here for the case of WritePreparedTxnDB.
uint64_t cur_sv_number = cfd_->GetSuperVersionNumber();
TEST_SYNC_POINT("ArenaWrappedDBIter::Refresh:1");
TEST_SYNC_POINT("ArenaWrappedDBIter::Refresh:2");
while (true) {
if (sv_number_ != cur_sv_number) {
Env* env = db_iter_->env();
db_iter_->~DBIter();
arena_.~Arena();
new (&arena_) Arena();
SuperVersion* sv = cfd_->GetReferencedSuperVersion(db_impl_);
SequenceNumber latest_seq = db_impl_->GetLatestSequenceNumber();
if (read_callback_) {
read_callback_->Refresh(latest_seq);
}
Init(env, read_options_, *(cfd_->ioptions()), sv->mutable_cf_options,
sv->current, latest_seq,
sv->mutable_cf_options.max_sequential_skip_in_iterations,
cur_sv_number, read_callback_, db_impl_, cfd_, expose_blob_index_,
allow_refresh_);
InternalIterator* internal_iter = db_impl_->NewInternalIterator(
read_options_, cfd_, sv, &arena_, db_iter_->GetRangeDelAggregator(),
latest_seq, /* allow_unprepared_value */ true);
SetIterUnderDBIter(internal_iter);
break;
} else {
SequenceNumber latest_seq = db_impl_->GetLatestSequenceNumber();
// Refresh range-tombstones in MemTable
if (!read_options_.ignore_range_deletions) {
SuperVersion* sv = cfd_->GetThreadLocalSuperVersion(db_impl_);
ReadRangeDelAggregator* range_del_agg =
db_iter_->GetRangeDelAggregator();
std::unique_ptr<FragmentedRangeTombstoneIterator> range_del_iter;
range_del_iter.reset(sv->mem->NewRangeTombstoneIterator(
read_options_, latest_seq, false /* immutable_memtable */));
range_del_agg->AddTombstones(std::move(range_del_iter));
cfd_->ReturnThreadLocalSuperVersion(sv);
}
// Refresh latest sequence number
db_iter_->set_sequence(latest_seq);
db_iter_->set_valid(false);
// Check again if the latest super version number is changed
uint64_t latest_sv_number = cfd_->GetSuperVersionNumber();
if (latest_sv_number != cur_sv_number) {
// If the super version number is changed after refreshing,
// fallback to Re-Init the InternalIterator
cur_sv_number = latest_sv_number;
continue;
}
break;
}
}
return Status::OK();
}
ArenaWrappedDBIter* NewArenaWrappedDbIterator(
Env* env, const ReadOptions& read_options, const ImmutableOptions& ioptions,
const MutableCFOptions& mutable_cf_options, const Version* version,
const SequenceNumber& sequence, uint64_t max_sequential_skip_in_iterations,
uint64_t version_number, ReadCallback* read_callback, DBImpl* db_impl,
ColumnFamilyData* cfd, bool expose_blob_index, bool allow_refresh) {
ArenaWrappedDBIter* iter = new ArenaWrappedDBIter();
iter->Init(env, read_options, ioptions, mutable_cf_options, version, sequence,
max_sequential_skip_in_iterations, version_number, read_callback,
db_impl, cfd, expose_blob_index, allow_refresh);
if (db_impl != nullptr && cfd != nullptr && allow_refresh) {
iter->StoreRefreshInfo(db_impl, cfd, read_callback, expose_blob_index);
}
return iter;
}
} // namespace ROCKSDB_NAMESPACE