rocksdb/table/sst_file_reader.cc
Peter Dillinger 9d490593d0 Preliminary support for custom compression algorithms (#13659)
Summary:
This change builds on https://github.com/facebook/rocksdb/issues/13540 and https://github.com/facebook/rocksdb/issues/13626 in allowing a CompressionManager / Compressor / Decompressor to use a custom compression algorithm, with a distinct CompressionType. For background, review the API comments on CompressionManager and its CompatibilityName() function.

Highlights:
* Reserve and name 127 new CompressionTypes that can be used for custom compression algorithms / schemas. In many or most cases I expect the enumerators such as `kCustomCompression8F` to be used in user code rather than casting between integers and CompressionTypes, as I expect the supported custom compression algorithms to be identifiable / enumerable at compile time.
* When using these custom compression types, a CompressionManager must use a CompatibilityName() other than the built-in one AND new format_version=7 (see below).
* When building new SST files, track the full set of CompressionTypes actually used (usually just one aside from kNoCompression), using our efficient bitset SmallEnumSet, which supports fast iteration over the bits set to 1. Ideally, to support mixed or non-mixed compression algorithms in a file as efficiently as possible, we would know the set of CompressionTypes as SST file open time.
* New schema for `TableProperties::compression_name` in format_version=7 to represent the CompressionManager's CompatibilityName(), the set of CompressionTypes used, and potentially more in the future, while keeping the data relatively human-readable.
  * It would be possible to do this without a new format_version, but then the only way to ensure incompatible versions fail is with an unsupported CompressionType tag, not with a compression_name property. Therefore, (a) I prefer not to put something misleading in the `compression_name` property (a built-in compression name) when there is nuance because of a CompressionManager, and (b) I prefer better, more consistent error messages that refer to either format_version or the CompressionManager's CompatibilityName(), rather than an unrecognized custom CompressionType value (which could have come from various CompressionManagers).
* The current configured CompressionManager is passed in to TableReaders so that it (or one it knows about) can be used if it matches the CompatibilityName() used for compression in the SST file. Until the connection with ObjectRegistry is implemented, the only way to read files generated with a particular CompressionManager using custom compression algorithms is to configure it (or a known relative; see FindCompatibleCompressionManager()) in the ColumnFamilyOptions.
* Optimized snappy compression with BuiltinDecompressorV2SnappyOnly, to offset some small added overheads with the new tracking. This is essentially an early part of the planned refactoring that will get rid of the old internal compression APIs.
* Another small optimization in eliminating an unnecessary key copy in flush (builder.cc).
* Fix some handling of named CompressionManagers in CompressionManager::CreateFromString() (problem seen in https://github.com/facebook/rocksdb/issues/13647)

Smaller things:
* Adds Name() and GetId() functions to Compressor for debugging/logging purposes. (Compressor and Decompressor are not expected to be Customizable because they are only instantiated by a CompressionManager.)
* When using an explicit compression_manager, the GetId() of the CompressionManager and the Compressor used to build the file are stored as bonus entries in the compression_options table property. This table property is not parsed anywhere, so it is currently for human reading, but still could be parsed with the new underscore-prefixed bonus entries. IMHO, this is preferable to additional table properties, which would increase memory fragmentation in the TableProperties objects and likely take slightly more CPU on SST open and slightly more storage.
* ReleaseWorkingArea() function from protected to public to make wrappers work, because of a quirk in C++ (vs. Java) in which you cannot access protected members of another instance of the same class (sigh)
* Added `CompressionManager:: SupportsCompressionType()` for early options sanity checking.

Follow-up before release:
* Make format_version=7 official / supported
* Stress test coverage

Sooner than later:
* Update tests for RoundRobinManager and SimpleMixedCompressionManager to take advantage of e.g. set of compression types in compression_name property
* ObjectRegistry stuff
* Refactor away old internal compression APIs

Pull Request resolved: https://github.com/facebook/rocksdb/pull/13659

Test Plan:
Basic unit test added.

## Performance

### SST write performance
```
SUFFIX=`tty | sed 's|/|_|g'`; for ARGS in "-compression_type=none" "-compression_type=snappy" "-compression_type=zstd" "-compression_type=snappy -verify_compression=1" "-compression_type=zstd -verify_compression=1" "-compression_type=zstd -compression_max_dict_bytes=8180"; do echo $ARGS; (for I in `seq 1 20`; do BIN=/dev/shm/dbbench${SUFFIX}.bin; rm -f $BIN; cp db_bench $BIN; $BIN -db=/dev/shm/dbbench$SUFFIX --benchmarks=fillseq -num=10000000 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=1000 -fifo_compaction_allow_compaction=0 -disable_wal -write_buffer_size=12000000 -format_version=7 $ARGS 2>&1 | grep micros/op; done) | awk '{n++; sum += $5;} END { print int(sum / n); }'; done
```

Ops/sec, Before -> After, both fv=6:
-compression_type=none
1894386 -> 1858403 (-2.0%)
-compression_type=snappy
1859131 -> 1807469 (-2.8%)
-compression_type=zstd
1191428 -> 1214374 (+1.9%)
-compression_type=snappy -verify_compression=1
1861819 -> 1858342 (+0.2%)
-compression_type=zstd -verify_compression=1
979435 -> 995870 (+1.6%)
-compression_type=zstd -compression_max_dict_bytes=8180
905349 -> 940563 (+3.9%)

Ops/sec, Before fv=6 -> After fv=7:
-compression_type=none
1879365 -> 1836159 (-2.3%)
-compression_type=snappy
1865460 -> 1830916 (-1.9%)
-compression_type=zstd
1191428 -> 1210260 (+1.6%)
-compression_type=snappy -verify_compression=1
1866756 -> 1818989 (-2.6%)
-compression_type=zstd -verify_compression=1
982640 -> 997129 (+1.5%)
-compression_type=zstd -compression_max_dict_bytes=8180
912608 -> 937248 (+2.7%)

### SST read performance
Create DBs
```
for COMP in none snappy zstd; do echo $ARGS; ./db_bench -db=/dev/shm/dbbench-7-$COMP --benchmarks=fillseq,flush -num=10000000 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=1000 -fifo_compaction_allow_compaction=0 -disable_wal -write_buffer_size=12000000 -compression_type=$COMP -format_version=7; done
```
And test
```
for COMP in none
snappy zstd none; do echo $COMP; (for I in `seq 1 8`; do ./db_bench -readonly -db=/dev/shm/dbbench
-7-$COMP --benchmarks=readrandom -num=10000000 -duration=20 -threads=8 2>&1 | grep micros/op; done
) | awk '{n++; sum += $5;} END { print int(sum / n); }'; done
```

Ops/sec, Before -> After (both fv=6)
none
1491732 -> 1500209 (+0.6%)
snappy
1157216 -> 1169202 (+1.0%)
zstd
695414 -> 703719 (+1.2%)
none (again)
1491787 -> 1528789 (+2.4%)

Ops/sec, Before fv=6 -> After fv=7:
none
1492278 -> 1508668 (+1.1%)
snappy
1140769 -> 1152613 (+1.0%)
zstd
696437 -> 696511 (+0.0%)
none (again)
1500585 -> 1512037 (+0.7%)

Overall, I think we can take the read CPU improvement in exchange for the hit (in some cases) on background write CPU

Reviewed By: hx235

Differential Revision: D76520739

Pulled By: pdillinger

fbshipit-source-id: e73bd72502ff85c8779cba313f26f7d1fd50be3a
2025-06-16 14:19:03 -07:00

245 lines
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).
#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_iterator.h"
#include "table/table_reader.h"
namespace ROCKSDB_NAMESPACE {
struct SstFileReader::Rep {
Options options;
EnvOptions soptions;
ImmutableOptions ioptions;
MutableCFOptions moptions;
// Keep a member variable for this, since `NewIterator()` uses a const
// reference of `ReadOptions`.
ReadOptions roptions_for_table_iter;
std::unique_ptr<TableReader> table_reader;
Rep(const Options& opts)
: options(opts),
soptions(options),
ioptions(options),
moptions(ColumnFamilyOptions(options)) {
roptions_for_table_iter =
ReadOptions(/*_verify_checksums=*/true, /*_fill_cache=*/false);
}
};
SstFileReader::SstFileReader(const Options& options) : rep_(new Rep(options)) {}
SstFileReader::~SstFileReader() = default;
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->moptions.compression_manager.get(), r->soptions,
r->ioptions.internal_comparator,
r->moptions.block_protection_bytes_per_key,
/*skip_filters*/ false, /*immortal*/ false,
/*force_direct_prefetch*/ false, /*level*/ -1,
/*block_cache_tracer*/ nullptr,
/*max_file_size_for_l0_meta_pin*/ 0, /*cur_db_session_id*/ "",
/*cur_file_num*/ 0,
/* unique_id */ {}, /* largest_seqno */ 0,
/* tail_size */ 0, r->ioptions.persist_user_defined_timestamps);
// 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;
}
std::vector<Status> SstFileReader::MultiGet(const ReadOptions& roptions,
const std::vector<Slice>& keys,
std::vector<std::string>* values) {
const auto num_keys = keys.size();
std::vector<Status> statuses(num_keys, Status::OK());
std::vector<PinnableSlice> pin_values(num_keys);
auto r = rep_.get();
const Comparator* user_comparator =
r->ioptions.internal_comparator.user_comparator();
autovector<KeyContext, MultiGetContext::MAX_BATCH_SIZE> key_context;
autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE> sorted_keys;
autovector<GetContext, MultiGetContext::MAX_BATCH_SIZE> get_ctx;
autovector<MergeContext, MultiGetContext::MAX_BATCH_SIZE> merge_ctx;
sorted_keys.resize(num_keys);
for (size_t i = 0; i < num_keys; ++i) {
PinnableSlice* val = &pin_values[i];
val->Reset();
merge_ctx.emplace_back();
key_context.emplace_back(nullptr, keys[i], val, nullptr,
nullptr /* timestamp */, &statuses[i]);
get_ctx.emplace_back(user_comparator, r->ioptions.merge_operator.get(),
nullptr, nullptr, GetContext::kNotFound,
*key_context[i].key, val, nullptr, nullptr, nullptr,
&merge_ctx[i], true,
&key_context[i].max_covering_tombstone_seq, nullptr);
key_context[i].get_context = &get_ctx[i];
}
for (size_t i = 0; i < num_keys; ++i) {
sorted_keys[i] = &key_context[i];
}
struct CompareKeyContext {
explicit CompareKeyContext(const Comparator* comp) : comparator(comp) {}
inline bool operator()(const KeyContext* lhs, const KeyContext* rhs) const {
return comparator->CompareWithoutTimestamp(*(lhs->key), false,
*(rhs->key), false) < 0;
}
const Comparator* comparator;
};
std::sort(sorted_keys.begin(), sorted_keys.end(),
CompareKeyContext(user_comparator));
const auto sequence = roptions.snapshot != nullptr
? roptions.snapshot->GetSequenceNumber()
: kMaxSequenceNumber;
MultiGetContext ctx(&sorted_keys, 0, num_keys, sequence, roptions,
r->ioptions.fs.get(), nullptr);
MultiGetRange range = ctx.GetMultiGetRange();
r->table_reader->MultiGet(roptions, &range,
r->moptions.prefix_extractor.get(),
false /* skip filters */);
values->resize(num_keys);
for (size_t i = 0; i < num_keys; ++i) {
if (statuses[i].ok()) {
switch (get_ctx[i].State()) {
case GetContext::kFound:
(*values)[i].assign(pin_values[i].data(), pin_values[i].size());
break;
case GetContext::kNotFound:
case GetContext::kDeleted:
statuses[i] = Status::NotFound();
break;
case GetContext::kMerge:
statuses[i] = Status::MergeInProgress();
break;
case GetContext::kCorrupt:
case GetContext::kUnexpectedBlobIndex:
case GetContext::kMergeOperatorFailed:
statuses[i] = Status::Corruption();
break;
};
}
}
return statuses;
}
Iterator* SstFileReader::NewIterator(const ReadOptions& roptions) {
assert(roptions.io_activity == Env::IOActivity::kUnknown);
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, 0 /* version_number */,
nullptr /* read_callback */, nullptr /* cfh */,
true /* expose_blob_index */, false /* allow_refresh */,
/*active_mem=*/nullptr);
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;
}
std::unique_ptr<Iterator> SstFileReader::NewTableIterator() {
auto r = rep_.get();
InternalIterator* internal_iter = r->table_reader->NewIterator(
r->roptions_for_table_iter, r->moptions.prefix_extractor.get(),
/*arena*/ nullptr, false /* skip_filters */,
TableReaderCaller::kSSTFileReader);
assert(internal_iter);
if (internal_iter == nullptr) {
// Do not attempt to create a TableIterator if we cannot get a valid
// InternalIterator.
return nullptr;
}
return std::make_unique<TableIterator>(internal_iter);
}
std::shared_ptr<const TableProperties> SstFileReader::GetTableProperties()
const {
return rep_->table_reader->GetTableProperties();
}
Status SstFileReader::VerifyChecksum(const ReadOptions& read_options) {
assert(read_options.io_activity == Env::IOActivity::kUnknown);
return rep_->table_reader->VerifyChecksum(read_options,
TableReaderCaller::kSSTFileReader);
}
Status SstFileReader::VerifyNumEntries(const ReadOptions& read_options) {
Rep* r = rep_.get();
std::unique_ptr<InternalIterator> internal_iter{r->table_reader->NewIterator(
read_options, r->moptions.prefix_extractor.get(), nullptr,
false /* skip_filters */, TableReaderCaller::kSSTFileReader)};
internal_iter->SeekToFirst();
Status s = internal_iter->status();
if (!s.ok()) {
return s;
}
uint64_t num_read = 0;
for (; internal_iter->Valid(); internal_iter->Next()) {
++num_read;
}
s = internal_iter->status();
if (!s.ok()) {
return s;
}
std::shared_ptr<const TableProperties> tp = GetTableProperties();
if (!tp) {
s = Status::Corruption("table properties not available");
} else {
// TODO: verify num_range_deletions
uint64_t expected = tp->num_entries - tp->num_range_deletions;
if (num_read != expected) {
std::ostringstream oss;
oss << "Table property expects " << expected
<< " entries when excluding range deletions,"
<< " but scanning the table returned " << std::to_string(num_read)
<< " entries";
s = Status::Corruption(oss.str());
}
}
return s;
}
} // namespace ROCKSDB_NAMESPACE