rocksdb/db/db_impl/db_impl_experimental.cc
Changyu Bi cc6f323705 Include estimated bytes deleted by range tombstones in compensated file size (#10734)
Summary:
compensate file sizes in compaction picking so files with range tombstones are preferred, such that they get compacted down earlier as they tend to delete a lot of data. This PR adds a `compensated_range_deletion_size` field in FileMeta that is computed during Flush/Compaction and persisted in MANIFEST. This value is added to `compensated_file_size` which will be used for compaction picking. Currently, for a file in level L, `compensated_range_deletion_size` is set to the estimated bytes deleted by range tombstone of this file in all levels > L. This helps to reduce space amp when data in older levels are covered by range tombstones in level L.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/10734

Test Plan:
- Added unit tests.
- benchmark to check if the above definition `compensated_range_deletion_size` is reducing space amp as intended, without affecting write amp too much. The experiment set up favorable for this optimization: large range tombstone issued infrequently. Command used:
```
./db_bench -benchmarks=fillrandom,waitforcompaction,stats,levelstats -use_existing_db=false -avoid_flush_during_recovery=true -write_buffer_size=33554432 -level_compaction_dynamic_level_bytes=true -max_background_jobs=8 -max_bytes_for_level_base=134217728 -target_file_size_base=33554432 -writes_per_range_tombstone=500000 -range_tombstone_width=5000000 -num=50000000 -benchmark_write_rate_limit=8388608 -threads=16 -duration=1800 --max_num_range_tombstones=1000000000
```

In this experiment, each thread wrote 16 range tombstones over the duration of 30 minutes, each range tombstone has width 5M that is the 10% of the key space width. Results shows this PR generates a smaller DB size.

Compaction stats from this PR:
```
Level    Files   Size     Score Read(GB)  Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) CompMergeCPU(sec) Comp(cnt) Avg(sec) KeyIn KeyDrop Rblob(GB) Wblob(GB)
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
  L0      2/0   31.54 MB   0.5      0.0     0.0      0.0       8.4      8.4       0.0   1.0      0.0     63.4    135.56            110.94       544    0.249       0      0       0.0       0.0
  L4      3/0   96.55 MB   0.8     18.5     6.7     11.8      18.4      6.6       0.0   2.7     65.3     64.9    290.08            284.03       108    2.686    284M  1957K       0.0       0.0
  L5     15/0   404.41 MB   1.0     19.1     7.7     11.4      18.8      7.4       0.3   2.5     66.6     65.7    292.93            285.34       220    1.332    293M  3808K       0.0       0.0
  L6    143/0    4.12 GB   0.0     45.0     7.5     37.5      41.6      4.1       0.0   5.5     71.2     65.9    647.00            632.66       251    2.578    739M    47M       0.0       0.0
 Sum    163/0    4.64 GB   0.0     82.6    21.9     60.7      87.2     26.5       0.3  10.4     61.9     65.4   1365.58           1312.97      1123    1.216   1318M    52M       0.0       0.0
```

Compaction stats from main:
```
Level    Files   Size     Score Read(GB)  Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) CompMergeCPU(sec) Comp(cnt) Avg(sec) KeyIn KeyDrop Rblob(GB) Wblob(GB)
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
  L0      0/0    0.00 KB   0.0      0.0     0.0      0.0       8.4      8.4       0.0   1.0      0.0     60.5    142.12            115.89       569    0.250       0      0       0.0       0.0
  L4      3/0   85.68 MB   1.0     17.7     6.8     10.9      17.6      6.7       0.0   2.6     62.7     62.3    289.05            281.79       112    2.581    272M  2309K       0.0       0.0
  L5     11/0   293.73 MB   1.0     18.8     7.5     11.2      18.5      7.2       0.5   2.5     64.9     63.9    296.07            288.50       220    1.346    288M  4365K       0.0       0.0
  L6    130/0    3.94 GB   0.0     51.5     7.6     43.9      47.9      3.9       0.0   6.3     67.2     62.4    784.95            765.92       258    3.042    848M    51M       0.0       0.0
 Sum    144/0    4.31 GB   0.0     88.0    21.9     66.0      92.3     26.3       0.5  11.0     59.6     62.5   1512.19           1452.09      1159    1.305   1409M    58M       0.0       0.0```

Reviewed By: ajkr

Differential Revision: D39834713

Pulled By: cbi42

fbshipit-source-id: fe9341040b8704a8fbb10cad5cf5c43e962c7e6b
2022-12-29 13:28:24 -08:00

160 lines
5.9 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 <cinttypes>
#include <vector>
#include "db/column_family.h"
#include "db/db_impl/db_impl.h"
#include "db/job_context.h"
#include "db/version_set.h"
#include "logging/logging.h"
#include "rocksdb/status.h"
#include "util/cast_util.h"
namespace ROCKSDB_NAMESPACE {
#ifndef ROCKSDB_LITE
Status DBImpl::SuggestCompactRange(ColumnFamilyHandle* column_family,
const Slice* begin, const Slice* end) {
auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
auto cfd = cfh->cfd();
InternalKey start_key, end_key;
if (begin != nullptr) {
start_key.SetMinPossibleForUserKey(*begin);
}
if (end != nullptr) {
end_key.SetMaxPossibleForUserKey(*end);
}
{
InstrumentedMutexLock l(&mutex_);
auto vstorage = cfd->current()->storage_info();
for (int level = 0; level < vstorage->num_non_empty_levels() - 1; ++level) {
std::vector<FileMetaData*> inputs;
vstorage->GetOverlappingInputs(
level, begin == nullptr ? nullptr : &start_key,
end == nullptr ? nullptr : &end_key, &inputs);
for (auto f : inputs) {
f->marked_for_compaction = true;
}
}
// Since we have some more files to compact, we should also recompute
// compaction score
vstorage->ComputeCompactionScore(*cfd->ioptions(),
*cfd->GetLatestMutableCFOptions());
SchedulePendingCompaction(cfd);
MaybeScheduleFlushOrCompaction();
}
return Status::OK();
}
Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
assert(column_family);
if (target_level < 1) {
ROCKS_LOG_INFO(immutable_db_options_.info_log,
"PromoteL0 FAILED. Invalid target level %d\n", target_level);
return Status::InvalidArgument("Invalid target level");
}
Status status;
VersionEdit edit;
JobContext job_context(next_job_id_.fetch_add(1), true);
{
InstrumentedMutexLock l(&mutex_);
auto* cfd = static_cast<ColumnFamilyHandleImpl*>(column_family)->cfd();
const auto* vstorage = cfd->current()->storage_info();
if (target_level >= vstorage->num_levels()) {
ROCKS_LOG_INFO(immutable_db_options_.info_log,
"PromoteL0 FAILED. Target level %d does not exist\n",
target_level);
job_context.Clean();
status = Status::InvalidArgument("Target level does not exist");
return status;
}
// Sort L0 files by range.
const InternalKeyComparator* icmp = &cfd->internal_comparator();
auto l0_files = vstorage->LevelFiles(0);
std::sort(l0_files.begin(), l0_files.end(),
[icmp](FileMetaData* f1, FileMetaData* f2) {
return icmp->Compare(f1->largest, f2->largest) < 0;
});
// Check that no L0 file is being compacted and that they have
// non-overlapping ranges.
for (size_t i = 0; i < l0_files.size(); ++i) {
auto f = l0_files[i];
if (f->being_compacted) {
ROCKS_LOG_INFO(immutable_db_options_.info_log,
"PromoteL0 FAILED. File %" PRIu64 " being compacted\n",
f->fd.GetNumber());
job_context.Clean();
status =
Status::InvalidArgument("PromoteL0 called during L0 compaction");
return status;
}
if (i == 0) continue;
auto prev_f = l0_files[i - 1];
if (icmp->Compare(prev_f->largest, f->smallest) >= 0) {
ROCKS_LOG_INFO(immutable_db_options_.info_log,
"PromoteL0 FAILED. Files %" PRIu64 " and %" PRIu64
" have overlapping ranges\n",
prev_f->fd.GetNumber(), f->fd.GetNumber());
job_context.Clean();
status = Status::InvalidArgument("L0 has overlapping files");
return status;
}
}
// Check that all levels up to target_level are empty.
for (int level = 1; level <= target_level; ++level) {
if (vstorage->NumLevelFiles(level) > 0) {
ROCKS_LOG_INFO(immutable_db_options_.info_log,
"PromoteL0 FAILED. Level %d not empty\n", level);
job_context.Clean();
status = Status::InvalidArgument(
"All levels up to target_level "
"must be empty");
return status;
}
}
edit.SetColumnFamily(cfd->GetID());
for (const auto& f : l0_files) {
edit.DeleteFile(0, f->fd.GetNumber());
edit.AddFile(target_level, f->fd.GetNumber(), f->fd.GetPathId(),
f->fd.GetFileSize(), f->smallest, f->largest,
f->fd.smallest_seqno, f->fd.largest_seqno,
f->marked_for_compaction, f->temperature,
f->oldest_blob_file_number, f->oldest_ancester_time,
f->file_creation_time, f->epoch_number, f->file_checksum,
f->file_checksum_func_name, f->unique_id,
f->compensated_range_deletion_size);
}
status = versions_->LogAndApply(cfd, *cfd->GetLatestMutableCFOptions(),
&edit, &mutex_, directories_.GetDbDir());
if (status.ok()) {
InstallSuperVersionAndScheduleWork(cfd,
&job_context.superversion_contexts[0],
*cfd->GetLatestMutableCFOptions());
}
} // lock released here
LogFlush(immutable_db_options_.info_log);
job_context.Clean();
return status;
}
#endif // ROCKSDB_LITE
} // namespace ROCKSDB_NAMESPACE