rocksdb/table/sst_file_writer_collectors.h

96 lines
3.2 KiB
C
Raw Normal View History

// 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).
#pragma once
#include <string>
#include "db/table_properties_collector.h"
#include "rocksdb/types.h"
#include "util/coding.h"
#include "util/string_util.h"
namespace ROCKSDB_NAMESPACE {
// Table Properties that are specific to tables created by SstFileWriter.
struct ExternalSstFilePropertyNames {
// value of this property is a fixed uint32 number.
static const std::string kVersion;
// value of this property is a fixed uint64 number.
static const std::string kGlobalSeqno;
};
// PropertiesCollector used to add properties specific to tables
// generated by SstFileWriter
class SstFileWriterPropertiesCollector : public IntTblPropCollector {
public:
explicit SstFileWriterPropertiesCollector(int32_t version,
SequenceNumber global_seqno)
: version_(version), global_seqno_(global_seqno) {}
virtual Status InternalAdd(const Slice& /*key*/, const Slice& /*value*/,
uint64_t /*file_size*/) override {
// Intentionally left blank. Have no interest in collecting stats for
// individual key/value pairs.
return Status::OK();
}
Refactor to avoid confusing "raw block" (#10408) Summary: We have a lot of confusing code because of mixed, sometimes completely opposite uses of of the term "raw block" or "raw contents", sometimes within the same source file. For example, in `BlockBasedTableBuilder`, `raw_block_contents` and `raw_size` generally referred to uncompressed block contents and size, while `WriteRawBlock` referred to writing a block that is already compressed if it is going to be. Meanwhile, in `BlockBasedTable`, `raw_block_contents` either referred to a (maybe compressed) block with trailer, or a maybe compressed block maybe without trailer. (Note: left as follow-up work to use C++ typing to better sort out the various kinds of BlockContents.) This change primarily tries to apply some consistent terminology around the kinds of block representations, avoiding the unclear "raw". (Any meaning of "raw" assumes some bias toward the storage layer or toward the logical data layer.) Preferred terminology: * **Serialized block** - bytes that go into storage. For block-based table (usually the case) this includes the block trailer. WART: block `size` may or may not include the trailer; need to be clear about whether it does or not. * **Maybe compressed block** - like a serialized block, but without the trailer (or no promise of including a trailer). Must be accompanied by a CompressionType. * **Uncompressed block** - "payload" bytes that are either stored with no compression, used as input to compression function, or result of decompression function. * **Parsed block** - an in-memory form of a block in block cache, as it is used by the table reader. Different C++ types are used depending on the block type (see block_like_traits.h). Other refactorings: * Misc corrections/improvements of internal API comments * Remove a few misleading / unhelpful / redundant comments. * Use move semantics in some places to simplify contracts * Use better parameter names to indicate which parameters are used for outputs * Remove some extraneous `extern` * Various clean-ups to `CacheDumperImpl` (mostly unnecessary code) Pull Request resolved: https://github.com/facebook/rocksdb/pull/10408 Test Plan: existing tests Reviewed By: akankshamahajan15 Differential Revision: D38172617 Pulled By: pdillinger fbshipit-source-id: ccb99299f324ac5ca46996d34c5089621a4f260c
2022-09-22 18:25:32 +00:00
virtual void BlockAdd(uint64_t /* block_uncomp_bytes */,
uint64_t /* block_compressed_bytes_fast */,
uint64_t /* block_compressed_bytes_slow */) override {
// Intentionally left blank. No interest in collecting stats for
// blocks.
return;
}
virtual Status Finish(UserCollectedProperties* properties) override {
// File version
std::string version_val;
PutFixed32(&version_val, static_cast<uint32_t>(version_));
properties->insert({ExternalSstFilePropertyNames::kVersion, version_val});
// Global Sequence number
std::string seqno_val;
PutFixed64(&seqno_val, static_cast<uint64_t>(global_seqno_));
properties->insert({ExternalSstFilePropertyNames::kGlobalSeqno, seqno_val});
return Status::OK();
}
virtual const char* Name() const override {
return "SstFileWriterPropertiesCollector";
}
virtual UserCollectedProperties GetReadableProperties() const override {
return {{ExternalSstFilePropertyNames::kVersion, std::to_string(version_)}};
}
private:
int32_t version_;
SequenceNumber global_seqno_;
};
class SstFileWriterPropertiesCollectorFactory
: public IntTblPropCollectorFactory {
public:
explicit SstFileWriterPropertiesCollectorFactory(int32_t version,
SequenceNumber global_seqno)
: version_(version), global_seqno_(global_seqno) {}
virtual IntTblPropCollector* CreateIntTblPropCollector(
Support "level_at_creation" in TablePropertiesCollectorFactory::Context (#8919) Summary: Context: Exposing the level of the sst file (i.e, table) where it is created in `TablePropertiesCollectorFactory::Context` allows users of `TablePropertiesCollectorFactory` to customize some implementation details of `TablePropertiesCollectorFactory` and `TablePropertiesCollector` based on the level of creation. For example, `TablePropertiesCollector::NeedCompact()` can return different values based on level of creation. - Declared an extra field `level_at_creation` in `TablePropertiesCollectorFactory::Context` - Allowed `level_at_creation` to be passed in as an argument in `IntTblPropCollectorFactory::CreateIntTblPropCollector()` and `UserKeyTablePropertiesCollectorFactory::CreateIntTblPropCollector()`, the latter of which is an internal wrapper of user's passed-in `TablePropertiesCollectorFactory::CreateTablePropertiesCollector()` used in table-building process - Called `IntTblPropCollectorFactory::CreateIntTblPropCollector()` with `level_at_creation` passed into both `BlockBasedTableBuilder` and `PlainTableBuilder` - `PlainTableBuilder` previously did not capture `level_at_creation` from `TableBuilderOptions` in `PlainTableFactory`. In order for it to call the method with this parameter, this PR also made `PlainTableBuilder` capture `level_at_creation` as a required parameter - Called `IntTblPropCollectorFactory::CreateIntTblPropCollector()` with `level_at_creation` its overridden functions in its derived classes, including `RegularKeysStartWithAFactory::CreateIntTblPropCollector()` in `table_properties_collector_test.cc`, `SstFileWriterPropertiesCollectorFactory::CreateIntTblPropCollector()` in `sst_file_writer_collectors.h` Pull Request resolved: https://github.com/facebook/rocksdb/pull/8919 Test Plan: - Passed the added assertion for `context.level_at_creation` - Passed existing tests - Run `Make` to make sure adding a required parameter to `PlainTableBuilder`'s constructor does not break anything Reviewed By: anand1976 Differential Revision: D30951729 Pulled By: hx235 fbshipit-source-id: c4a0173b0d9344a4cf47e1b987d759c1c73cb474
2021-09-28 19:33:03 +00:00
uint32_t /*column_family_id*/, int /* level_at_creation */) override {
return new SstFileWriterPropertiesCollector(version_, global_seqno_);
}
virtual const char* Name() const override {
return "SstFileWriterPropertiesCollector";
}
private:
int32_t version_;
SequenceNumber global_seqno_;
};
} // namespace ROCKSDB_NAMESPACE