rocksdb/table/sst_file_reader.cc
Changyu Bi 9f2363f4c4 User-defined timestamp support for DeleteRange() (#10661)
Summary:
Add user-defined timestamp support for range deletion. The new API is `DeleteRange(opt, cf, begin_key, end_key, ts)`. Most of the change is to update the comparator to compare without timestamp. Other than that, major changes are
- internal range tombstone data structures (`FragmentedRangeTombstoneList`, `RangeTombstone`, etc.) to store timestamps.
- Garbage collection of range tombstones and range tombstone covered keys during compaction.
- Get()/MultiGet() to return the timestamp of a range tombstone when needed.
- Get/Iterator with range tombstones bounded by readoptions.timestamp.
- timestamp crash test now issues DeleteRange by default.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/10661

Test Plan:
- Added unit test: `make check`
- Stress test: `python3 tools/db_crashtest.py --enable_ts whitebox --readpercent=57 --prefixpercent=4 --writepercent=25 -delpercent=5 --iterpercent=5 --delrangepercent=4`
- Ran `db_bench` to measure regression when timestamp is not enabled. The tests are for write (with some range deletion) and iterate with DB fitting in memory: `./db_bench--benchmarks=fillrandom,seekrandom --writes_per_range_tombstone=200 --max_write_buffer_number=100 --min_write_buffer_number_to_merge=100 --writes=500000 --reads=500000 --seek_nexts=10 --disable_auto_compactions -disable_wal=true --max_num_range_tombstones=1000`.  Did not see consistent regression in no timestamp case.

| micros/op | fillrandom | seekrandom |
| --- | --- | --- |
|main| 2.58 |10.96|
|PR 10661| 2.68 |10.63|

Reviewed By: riversand963

Differential Revision: D39441192

Pulled By: cbi42

fbshipit-source-id: f05aca3c41605caf110daf0ff405919f300ddec2
2022-09-30 16:13:03 -07:00

108 lines
3.6 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).
#ifndef ROCKSDB_LITE
#include "rocksdb/sst_file_reader.h"
#include "db/arena_wrapped_db_iter.h"
#include "db/db_iter.h"
#include "db/dbformat.h"
#include "file/random_access_file_reader.h"
#include "options/cf_options.h"
#include "rocksdb/env.h"
#include "rocksdb/file_system.h"
#include "table/get_context.h"
#include "table/table_builder.h"
#include "table/table_reader.h"
namespace ROCKSDB_NAMESPACE {
struct SstFileReader::Rep {
Options options;
EnvOptions soptions;
ImmutableOptions ioptions;
MutableCFOptions moptions;
std::unique_ptr<TableReader> table_reader;
Rep(const Options& opts)
: options(opts),
soptions(options),
ioptions(options),
moptions(ColumnFamilyOptions(options)) {}
};
SstFileReader::SstFileReader(const Options& options) : rep_(new Rep(options)) {}
SstFileReader::~SstFileReader() {}
Status SstFileReader::Open(const std::string& file_path) {
auto r = rep_.get();
Status s;
uint64_t file_size = 0;
std::unique_ptr<FSRandomAccessFile> file;
std::unique_ptr<RandomAccessFileReader> file_reader;
FileOptions fopts(r->soptions);
const auto& fs = r->options.env->GetFileSystem();
s = fs->GetFileSize(file_path, fopts.io_options, &file_size, nullptr);
if (s.ok()) {
s = fs->NewRandomAccessFile(file_path, fopts, &file, nullptr);
}
if (s.ok()) {
file_reader.reset(new RandomAccessFileReader(std::move(file), file_path));
}
if (s.ok()) {
TableReaderOptions t_opt(r->ioptions, r->moptions.prefix_extractor,
r->soptions, r->ioptions.internal_comparator);
// Allow open file with global sequence number for backward compatibility.
t_opt.largest_seqno = kMaxSequenceNumber;
s = r->options.table_factory->NewTableReader(t_opt, std::move(file_reader),
file_size, &r->table_reader);
}
return s;
}
Iterator* SstFileReader::NewIterator(const ReadOptions& roptions) {
auto r = rep_.get();
auto sequence = roptions.snapshot != nullptr
? roptions.snapshot->GetSequenceNumber()
: kMaxSequenceNumber;
ArenaWrappedDBIter* res = new ArenaWrappedDBIter();
res->Init(r->options.env, roptions, r->ioptions, r->moptions,
nullptr /* version */, sequence,
r->moptions.max_sequential_skip_in_iterations,
0 /* version_number */, nullptr /* read_callback */,
nullptr /* db_impl */, nullptr /* cfd */,
true /* expose_blob_index */, false /* allow_refresh */);
auto internal_iter = r->table_reader->NewIterator(
res->GetReadOptions(), r->moptions.prefix_extractor.get(),
res->GetArena(), false /* skip_filters */,
TableReaderCaller::kSSTFileReader);
res->SetIterUnderDBIter(internal_iter);
return res;
}
FragmentedRangeTombstoneIterator* SstFileReader::NewRangeTombstoneIterator(
const ReadOptions& options) {
auto r = rep_.get();
return r->table_reader->NewRangeTombstoneIterator(options);
}
std::shared_ptr<const TableProperties> SstFileReader::GetTableProperties()
const {
return rep_->table_reader->GetTableProperties();
}
Status SstFileReader::VerifyChecksum(const ReadOptions& read_options) {
return rep_->table_reader->VerifyChecksum(read_options,
TableReaderCaller::kSSTFileReader);
}
} // namespace ROCKSDB_NAMESPACE
#endif // !ROCKSDB_LITE