You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/db/arena_wrapped_db_iter.cc

159 lines
6.7 KiB

// 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;
memtable_range_tombstone_iter_ = nullptr;
}
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");
auto reinit_internal_iter = [&]() {
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_, latest_seq,
/* allow_unprepared_value */ true, /* db_iter */ this);
SetIterUnderDBIter(internal_iter);
};
while (true) {
if (sv_number_ != cur_sv_number) {
reinit_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_);
auto t = sv->mem->NewRangeTombstoneIterator(
read_options_, latest_seq, false /* immutable_memtable */);
if (!t || t->empty()) {
// If memtable_range_tombstone_iter_ points to a non-empty tombstone
// iterator, then it means sv->mem is not the memtable that
// memtable_range_tombstone_iter_ points to, so SV must have changed
// after the sv_number_ != cur_sv_number check above. We will fall
// back to re-init the InternalIterator, and the tombstone iterator
// will be freed during db_iter destruction there.
if (memtable_range_tombstone_iter_) {
assert(!*memtable_range_tombstone_iter_ ||
sv_number_ != cfd_->GetSuperVersionNumber());
}
delete t;
} else { // current mutable memtable has range tombstones
if (!memtable_range_tombstone_iter_) {
delete t;
cfd_->ReturnThreadLocalSuperVersion(sv);
// The memtable under DBIter did not have range tombstone before
// refresh.
reinit_internal_iter();
break;
Skip swaths of range tombstone covered keys in merging iterator (2022 edition) (#10449) Summary: Delete range logic is moved from `DBIter` to `MergingIterator`, and `MergingIterator` will seek to the end of a range deletion if possible instead of scanning through each key and check with `RangeDelAggregator`. With the invariant that a key in level L (consider memtable as the first level, each immutable and L0 as a separate level) has a larger sequence number than all keys in any level >L, a range tombstone `[start, end)` from level L covers all keys in its range in any level >L. This property motivates optimizations in iterator: - in `Seek(target)`, if level L has a range tombstone `[start, end)` that covers `target.UserKey`, then for all levels > L, we can do Seek() on `end` instead of `target` to skip some range tombstone covered keys. - in `Next()/Prev()`, if the current key is covered by a range tombstone `[start, end)` from level L, we can do `Seek` to `end` for all levels > L. This PR implements the above optimizations in `MergingIterator`. As all range tombstone covered keys are now skipped in `MergingIterator`, the range tombstone logic is removed from `DBIter`. The idea in this PR is similar to https://github.com/facebook/rocksdb/issues/7317, but this PR leaves `InternalIterator` interface mostly unchanged. **Credit**: the cascading seek optimization and the sentinel key (discussed below) are inspired by [Pebble](https://github.com/cockroachdb/pebble/blob/master/merging_iter.go) and suggested by ajkr in https://github.com/facebook/rocksdb/issues/7317. The two optimizations are mostly implemented in `SeekImpl()/SeekForPrevImpl()` and `IsNextDeleted()/IsPrevDeleted()` in `merging_iterator.cc`. See comments for each method for more detail. One notable change is that the minHeap/maxHeap used by `MergingIterator` now contains range tombstone end keys besides point key iterators. This helps to reduce the number of key comparisons. For example, for a range tombstone `[start, end)`, a `start` and an `end` `HeapItem` are inserted into the heap. When a `HeapItem` for range tombstone start key is popped from the minHeap, we know this range tombstone becomes "active" in the sense that, before the range tombstone's end key is popped from the minHeap, all the keys popped from this heap is covered by the range tombstone's internal key range `[start, end)`. Another major change, *delete range sentinel key*, is made to `LevelIterator`. Before this PR, when all point keys in an SST file are iterated through in `MergingIterator`, a level iterator would advance to the next SST file in its level. In the case when an SST file has a range tombstone that covers keys beyond the SST file's last point key, advancing to the next SST file would lose this range tombstone. Consequently, `MergingIterator` could return keys that should have been deleted by some range tombstone. We prevent this by pretending that file boundaries in each SST file are sentinel keys. A `LevelIterator` now only advance the file iterator once the sentinel key is processed. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10449 Test Plan: - Added many unit tests in db_range_del_test - Stress test: `./db_stress --readpercent=5 --prefixpercent=19 --writepercent=20 -delpercent=10 --iterpercent=44 --delrangepercent=2` - Additional iterator stress test is added to verify against iterators against expected state: https://github.com/facebook/rocksdb/issues/10538. This is based on ajkr's previous attempt https://github.com/facebook/rocksdb/pull/5506#issuecomment-506021913. ``` python3 ./tools/db_crashtest.py blackbox --simple --write_buffer_size=524288 --target_file_size_base=524288 --max_bytes_for_level_base=2097152 --compression_type=none --max_background_compactions=8 --value_size_mult=33 --max_key=5000000 --interval=10 --duration=7200 --delrangepercent=3 --delpercent=9 --iterpercent=25 --writepercent=60 --readpercent=3 --prefixpercent=0 --num_iterations=1000 --range_deletion_width=100 --verify_iterator_with_expected_state_one_in=1 ``` - Performance benchmark: I used a similar setup as in the blog [post](http://rocksdb.org/blog/2018/11/21/delete-range.html) that introduced DeleteRange, "a database with 5 million data keys, and 10000 range tombstones (ignoring those dropped during compaction) that were written in regular intervals after 4.5 million data keys were written". As expected, the performance with this PR depends on the range tombstone width. ``` # Setup: TEST_TMPDIR=/dev/shm ./db_bench_main --benchmarks=fillrandom --writes=4500000 --num=5000000 TEST_TMPDIR=/dev/shm ./db_bench_main --benchmarks=overwrite --writes=500000 --num=5000000 --use_existing_db=true --writes_per_range_tombstone=50 # Scan entire DB TEST_TMPDIR=/dev/shm ./db_bench_main --benchmarks=readseq[-X5] --use_existing_db=true --num=5000000 --disable_auto_compactions=true # Short range scan (10 Next()) TEST_TMPDIR=/dev/shm/width-100/ ./db_bench_main --benchmarks=seekrandom[-X5] --use_existing_db=true --num=500000 --reads=100000 --seek_nexts=10 --disable_auto_compactions=true # Long range scan(1000 Next()) TEST_TMPDIR=/dev/shm/width-100/ ./db_bench_main --benchmarks=seekrandom[-X5] --use_existing_db=true --num=500000 --reads=2500 --seek_nexts=1000 --disable_auto_compactions=true ``` Avg over of 10 runs (some slower tests had fews runs): For the first column (tombstone), 0 means no range tombstone, 100-10000 means width of the 10k range tombstones, and 1 means there is a single range tombstone in the entire DB (width is 1000). The 1 tombstone case is to test regression when there's very few range tombstones in the DB, as no range tombstone is likely to take a different code path than with range tombstones. - Scan entire DB | tombstone width | Pre-PR ops/sec | Post-PR ops/sec | ±% | | ------------- | ------------- | ------------- | ------------- | | 0 range tombstone |2525600 (± 43564) |2486917 (± 33698) |-1.53% | | 100 |1853835 (± 24736) |2073884 (± 32176) |+11.87% | | 1000 |422415 (± 7466) |1115801 (± 22781) |+164.15% | | 10000 |22384 (± 227) |227919 (± 6647) |+918.22% | | 1 range tombstone |2176540 (± 39050) |2434954 (± 24563) |+11.87% | - Short range scan | tombstone width | Pre-PR ops/sec | Post-PR ops/sec | ±% | | ------------- | ------------- | ------------- | ------------- | | 0 range tombstone |35398 (± 533) |35338 (± 569) |-0.17% | | 100 |28276 (± 664) |31684 (± 331) |+12.05% | | 1000 |7637 (± 77) |25422 (± 277) |+232.88% | | 10000 |1367 |28667 |+1997.07% | | 1 range tombstone |32618 (± 581) |32748 (± 506) |+0.4% | - Long range scan | tombstone width | Pre-PR ops/sec | Post-PR ops/sec | ±% | | ------------- | ------------- | ------------- | ------------- | | 0 range tombstone |2262 (± 33) |2353 (± 20) |+4.02% | | 100 |1696 (± 26) |1926 (± 18) |+13.56% | | 1000 |410 (± 6) |1255 (± 29) |+206.1% | | 10000 |25 |414 |+1556.0% | | 1 range tombstone |1957 (± 30) |2185 (± 44) |+11.65% | - Microbench does not show significant regression: https://gist.github.com/cbi42/59f280f85a59b678e7e5d8561e693b61 Reviewed By: ajkr Differential Revision: D38450331 Pulled By: cbi42 fbshipit-source-id: b5ef12e8d8c289ed2e163ccdf277f5039b511fca
2 years ago
} else {
delete *memtable_range_tombstone_iter_;
Skip swaths of range tombstone covered keys in merging iterator (2022 edition) (#10449) Summary: Delete range logic is moved from `DBIter` to `MergingIterator`, and `MergingIterator` will seek to the end of a range deletion if possible instead of scanning through each key and check with `RangeDelAggregator`. With the invariant that a key in level L (consider memtable as the first level, each immutable and L0 as a separate level) has a larger sequence number than all keys in any level >L, a range tombstone `[start, end)` from level L covers all keys in its range in any level >L. This property motivates optimizations in iterator: - in `Seek(target)`, if level L has a range tombstone `[start, end)` that covers `target.UserKey`, then for all levels > L, we can do Seek() on `end` instead of `target` to skip some range tombstone covered keys. - in `Next()/Prev()`, if the current key is covered by a range tombstone `[start, end)` from level L, we can do `Seek` to `end` for all levels > L. This PR implements the above optimizations in `MergingIterator`. As all range tombstone covered keys are now skipped in `MergingIterator`, the range tombstone logic is removed from `DBIter`. The idea in this PR is similar to https://github.com/facebook/rocksdb/issues/7317, but this PR leaves `InternalIterator` interface mostly unchanged. **Credit**: the cascading seek optimization and the sentinel key (discussed below) are inspired by [Pebble](https://github.com/cockroachdb/pebble/blob/master/merging_iter.go) and suggested by ajkr in https://github.com/facebook/rocksdb/issues/7317. The two optimizations are mostly implemented in `SeekImpl()/SeekForPrevImpl()` and `IsNextDeleted()/IsPrevDeleted()` in `merging_iterator.cc`. See comments for each method for more detail. One notable change is that the minHeap/maxHeap used by `MergingIterator` now contains range tombstone end keys besides point key iterators. This helps to reduce the number of key comparisons. For example, for a range tombstone `[start, end)`, a `start` and an `end` `HeapItem` are inserted into the heap. When a `HeapItem` for range tombstone start key is popped from the minHeap, we know this range tombstone becomes "active" in the sense that, before the range tombstone's end key is popped from the minHeap, all the keys popped from this heap is covered by the range tombstone's internal key range `[start, end)`. Another major change, *delete range sentinel key*, is made to `LevelIterator`. Before this PR, when all point keys in an SST file are iterated through in `MergingIterator`, a level iterator would advance to the next SST file in its level. In the case when an SST file has a range tombstone that covers keys beyond the SST file's last point key, advancing to the next SST file would lose this range tombstone. Consequently, `MergingIterator` could return keys that should have been deleted by some range tombstone. We prevent this by pretending that file boundaries in each SST file are sentinel keys. A `LevelIterator` now only advance the file iterator once the sentinel key is processed. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10449 Test Plan: - Added many unit tests in db_range_del_test - Stress test: `./db_stress --readpercent=5 --prefixpercent=19 --writepercent=20 -delpercent=10 --iterpercent=44 --delrangepercent=2` - Additional iterator stress test is added to verify against iterators against expected state: https://github.com/facebook/rocksdb/issues/10538. This is based on ajkr's previous attempt https://github.com/facebook/rocksdb/pull/5506#issuecomment-506021913. ``` python3 ./tools/db_crashtest.py blackbox --simple --write_buffer_size=524288 --target_file_size_base=524288 --max_bytes_for_level_base=2097152 --compression_type=none --max_background_compactions=8 --value_size_mult=33 --max_key=5000000 --interval=10 --duration=7200 --delrangepercent=3 --delpercent=9 --iterpercent=25 --writepercent=60 --readpercent=3 --prefixpercent=0 --num_iterations=1000 --range_deletion_width=100 --verify_iterator_with_expected_state_one_in=1 ``` - Performance benchmark: I used a similar setup as in the blog [post](http://rocksdb.org/blog/2018/11/21/delete-range.html) that introduced DeleteRange, "a database with 5 million data keys, and 10000 range tombstones (ignoring those dropped during compaction) that were written in regular intervals after 4.5 million data keys were written". As expected, the performance with this PR depends on the range tombstone width. ``` # Setup: TEST_TMPDIR=/dev/shm ./db_bench_main --benchmarks=fillrandom --writes=4500000 --num=5000000 TEST_TMPDIR=/dev/shm ./db_bench_main --benchmarks=overwrite --writes=500000 --num=5000000 --use_existing_db=true --writes_per_range_tombstone=50 # Scan entire DB TEST_TMPDIR=/dev/shm ./db_bench_main --benchmarks=readseq[-X5] --use_existing_db=true --num=5000000 --disable_auto_compactions=true # Short range scan (10 Next()) TEST_TMPDIR=/dev/shm/width-100/ ./db_bench_main --benchmarks=seekrandom[-X5] --use_existing_db=true --num=500000 --reads=100000 --seek_nexts=10 --disable_auto_compactions=true # Long range scan(1000 Next()) TEST_TMPDIR=/dev/shm/width-100/ ./db_bench_main --benchmarks=seekrandom[-X5] --use_existing_db=true --num=500000 --reads=2500 --seek_nexts=1000 --disable_auto_compactions=true ``` Avg over of 10 runs (some slower tests had fews runs): For the first column (tombstone), 0 means no range tombstone, 100-10000 means width of the 10k range tombstones, and 1 means there is a single range tombstone in the entire DB (width is 1000). The 1 tombstone case is to test regression when there's very few range tombstones in the DB, as no range tombstone is likely to take a different code path than with range tombstones. - Scan entire DB | tombstone width | Pre-PR ops/sec | Post-PR ops/sec | ±% | | ------------- | ------------- | ------------- | ------------- | | 0 range tombstone |2525600 (± 43564) |2486917 (± 33698) |-1.53% | | 100 |1853835 (± 24736) |2073884 (± 32176) |+11.87% | | 1000 |422415 (± 7466) |1115801 (± 22781) |+164.15% | | 10000 |22384 (± 227) |227919 (± 6647) |+918.22% | | 1 range tombstone |2176540 (± 39050) |2434954 (± 24563) |+11.87% | - Short range scan | tombstone width | Pre-PR ops/sec | Post-PR ops/sec | ±% | | ------------- | ------------- | ------------- | ------------- | | 0 range tombstone |35398 (± 533) |35338 (± 569) |-0.17% | | 100 |28276 (± 664) |31684 (± 331) |+12.05% | | 1000 |7637 (± 77) |25422 (± 277) |+232.88% | | 10000 |1367 |28667 |+1997.07% | | 1 range tombstone |32618 (± 581) |32748 (± 506) |+0.4% | - Long range scan | tombstone width | Pre-PR ops/sec | Post-PR ops/sec | ±% | | ------------- | ------------- | ------------- | ------------- | | 0 range tombstone |2262 (± 33) |2353 (± 20) |+4.02% | | 100 |1696 (± 26) |1926 (± 18) |+13.56% | | 1000 |410 (± 6) |1255 (± 29) |+206.1% | | 10000 |25 |414 |+1556.0% | | 1 range tombstone |1957 (± 30) |2185 (± 44) |+11.65% | - Microbench does not show significant regression: https://gist.github.com/cbi42/59f280f85a59b678e7e5d8561e693b61 Reviewed By: ajkr Differential Revision: D38450331 Pulled By: cbi42 fbshipit-source-id: b5ef12e8d8c289ed2e163ccdf277f5039b511fca
2 years ago
*memtable_range_tombstone_iter_ = new TruncatedRangeDelIterator(
std::unique_ptr<FragmentedRangeTombstoneIterator>(t),
&cfd_->internal_comparator(), nullptr, nullptr);
}
}
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