rocksdb/table/plain/plain_table_builder.h
zhangyuxiang.ax 1567108fc1 Add missing table properties in plaintable GetTableProperties() (#11267)
Summary:
Plaintable will miss properties.
It should have some behavior like blockbasedtable.
Here is a unit test for reproduce this bug.

```
#include <gflags/gflags.h>
#include "rocksdb/db.h"
#include "rocksdb/options.h"
#include "rocksdb/table.h"
#include "rocksdb/slice_transform.h"
#include <iostream>
#include <thread>
#include <csignal>
const std::string kKey = "key";

DEFINE_bool(use_plaintable, true, "use plain table");
DEFINE_string(db_path, "/dev/shm/test_zyx_path", "db_path");

rocksdb::DB* db = nullptr;

class NoopTransform : public rocksdb::SliceTransform {
public:
    explicit NoopTransform() {
    }

    virtual const char* Name() const override {
        return "rocksdb.Noop";
    }

    virtual rocksdb::Slice Transform(const rocksdb::Slice& src) const override {
        return src;
    }

    virtual bool InDomain(const rocksdb::Slice& src) const override {
        return true;
    }

    virtual bool InRange(const rocksdb::Slice& dst) const override {
        return true;
    }

    virtual bool SameResultWhenAppended(const rocksdb::Slice& prefix) const override {
        return false;
    }
};

class TestPropertiesCollector : public ::rocksdb::TablePropertiesCollector {
public:
    explicit TestPropertiesCollector() {
    }

private:
    ::rocksdb::Status AddUserKey(const ::rocksdb::Slice& key, const ::rocksdb::Slice& value, ::rocksdb::EntryType type,
                                 ::rocksdb::SequenceNumber seq, uint64_t file_size) override {
        count++;
        return ::rocksdb::Status::OK();
    }

    ::rocksdb::Status Finish(::rocksdb::UserCollectedProperties* properties) override {
        properties->insert({kKey, std::to_string(count)});
        return ::rocksdb::Status::OK();
    }

    ::rocksdb::UserCollectedProperties GetReadableProperties() const override {
        ::rocksdb::UserCollectedProperties properties;
        properties.insert({kKey, std::to_string(count)});
        return properties;
    }

    const char* Name() const override {
        return "TestPropertiesCollector";
    }
    int count = 0;
};

class TestTablePropertiesCollectorFactory : public ::rocksdb::TablePropertiesCollectorFactory {
public:
    explicit TestTablePropertiesCollectorFactory() {
    }

private:
    ::rocksdb::TablePropertiesCollector* CreateTablePropertiesCollector(
            ::rocksdb::TablePropertiesCollectorFactory::Context context) override {
        return new TestPropertiesCollector();
    }

    const char* Name() const override {
        return "test.TablePropertiesCollectorFactory";
    }
};

class TestFlushListener : rocksdb::EventListener {
public:
    const char* Name() const override {
        return "TestFlushListener";
    }
    void OnFlushCompleted(rocksdb::DB* /*db*/, const rocksdb::FlushJobInfo& flush_job_info) override {
        if (flush_job_info.table_properties.user_collected_properties.find(kKey) ==
            flush_job_info.table_properties.user_collected_properties.end()) {
            std::cerr << "OnFlushCompleted: properties not found" << std::endl;
            return;
        }
        std::cerr << "OnFlushCompleted: properties found "
                  << flush_job_info.table_properties.user_collected_properties.at(kKey) << std::endl;
    }
    explicit TestFlushListener() {
    }
};

int main(int argc, char* argv[]) {
    gflags::ParseCommandLineFlags(&argc, &argv, true);
    rocksdb::DBOptions rocksdb_options;
    std::shared_ptr<rocksdb::EventListener> flush_offset;
    rocksdb_options.create_if_missing = true;
    rocksdb_options.create_missing_column_families = true;
    std::shared_ptr<::rocksdb::TablePropertiesCollectorFactory> properties_collector(
            new TestTablePropertiesCollectorFactory());
    rocksdb::ColumnFamilyOptions cfoptions;
    cfoptions.table_properties_collector_factories.emplace_back(properties_collector);
    std::shared_ptr<rocksdb::EventListener> test_cleaner;
    test_cleaner.reset((rocksdb::EventListener*)new TestFlushListener());
    rocksdb_options.listeners.emplace_back(test_cleaner);

    std::vector<rocksdb::ColumnFamilyDescriptor> cf_desc_;
    cf_desc_.emplace_back(rocksdb::kDefaultColumnFamilyName, cfoptions);
    std::vector<rocksdb::ColumnFamilyHandle*> cfhs;
    cfoptions.prefix_extractor.reset(new NoopTransform());
    if (FLAGS_use_plaintable) {
        cfoptions.table_factory.reset(rocksdb::NewPlainTableFactory());
        std::cerr << "use plaintable" << std::endl;
    } else {
        cfoptions.table_factory.reset(rocksdb::NewBlockBasedTableFactory());
        std::cerr << "use blockbasedtable" << std::endl;
    }

    auto s = rocksdb::DB::Open(rocksdb_options, FLAGS_db_path, cf_desc_, &cfhs, &db);
    if (s.ok()) {
        rocksdb::WriteOptions wops;
        wops.disableWAL = true;
        for (int i = 0; i < 1000000; i++) {
            auto status = db->Put(wops, std::to_string(i), std::string(1024, '3'));
            if (!status.ok()) {
                std::cerr << "write fail " << status.getState() << std::endl;
            }
        }
    } else {
        std::cerr << "open rocksdb failed" << s.getState() << std::endl;
    }
    std::this_thread::sleep_for(std::chrono::seconds(1000));
    delete db;
}
```

Pull Request resolved: https://github.com/facebook/rocksdb/pull/11267

Reviewed By: jowlyzhang

Differential Revision: D47689943

Pulled By: hx235

fbshipit-source-id: 585589cc48f8b26c7dd2323fc7ac4a0c3d4df6bb
2023-07-21 17:55:25 -07:00

162 lines
5.6 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).
#pragma once
#include <stdint.h>
#include <string>
#include <vector>
#include "db/version_edit.h"
#include "rocksdb/options.h"
#include "rocksdb/status.h"
#include "rocksdb/table.h"
#include "rocksdb/table_properties.h"
#include "table/plain/plain_table_bloom.h"
#include "table/plain/plain_table_index.h"
#include "table/plain/plain_table_key_coding.h"
#include "table/table_builder.h"
namespace ROCKSDB_NAMESPACE {
class BlockBuilder;
class BlockHandle;
class WritableFile;
class TableBuilder;
// The builder class of PlainTable. For description of PlainTable format
// See comments of class PlainTableFactory, where instances of
// PlainTableReader are created.
class PlainTableBuilder : public TableBuilder {
public:
// Create a builder that will store the contents of the table it is
// building in *file. Does not close the file. It is up to the
// caller to close the file after calling Finish(). The output file
// will be part of level specified by 'level'. A value of -1 means
// that the caller does not know which level the output file will reside.
PlainTableBuilder(
const ImmutableOptions& ioptions, const MutableCFOptions& moptions,
const IntTblPropCollectorFactories* int_tbl_prop_collector_factories,
uint32_t column_family_id, int level_at_creation,
WritableFileWriter* file, uint32_t user_key_size,
EncodingType encoding_type, size_t index_sparseness,
uint32_t bloom_bits_per_key, const std::string& column_family_name,
uint32_t num_probes = 6, size_t huge_page_tlb_size = 0,
double hash_table_ratio = 0, bool store_index_in_file = false,
const std::string& db_id = "", const std::string& db_session_id = "",
uint64_t file_number = 0);
// No copying allowed
PlainTableBuilder(const PlainTableBuilder&) = delete;
void operator=(const PlainTableBuilder&) = delete;
// REQUIRES: Either Finish() or Abandon() has been called.
~PlainTableBuilder();
// Add key,value to the table being constructed.
// REQUIRES: key is after any previously added key according to comparator.
// REQUIRES: Finish(), Abandon() have not been called
void Add(const Slice& key, const Slice& value) override;
// Return non-ok iff some error has been detected.
Status status() const override { return status_; }
// Return non-ok iff some error happens during IO.
IOStatus io_status() const override { return io_status_; }
// Finish building the table. Stops using the file passed to the
// constructor after this function returns.
// REQUIRES: Finish(), Abandon() have not been called
Status Finish() override;
// Indicate that the contents of this builder should be abandoned. Stops
// using the file passed to the constructor after this function returns.
// If the caller is not going to call Finish(), it must call Abandon()
// before destroying this builder.
// REQUIRES: Finish(), Abandon() have not been called
void Abandon() override;
// Number of calls to Add() so far.
uint64_t NumEntries() const override;
// Size of the file generated so far. If invoked after a successful
// Finish() call, returns the size of the final generated file.
uint64_t FileSize() const override;
TableProperties GetTableProperties() const override {
TableProperties ret = properties_;
for (const auto& collector : table_properties_collectors_) {
for (const auto& prop : collector->GetReadableProperties()) {
ret.readable_properties.insert(prop);
}
collector->Finish(&ret.user_collected_properties).PermitUncheckedError();
}
return ret;
}
bool SaveIndexInFile() const { return store_index_in_file_; }
// Get file checksum
std::string GetFileChecksum() const override;
// Get file checksum function name
const char* GetFileChecksumFuncName() const override;
void SetSeqnoTimeTableProperties(const std::string& string,
uint64_t uint_64) override;
private:
Arena arena_;
const ImmutableOptions& ioptions_;
const MutableCFOptions& moptions_;
std::vector<std::unique_ptr<IntTblPropCollector>>
table_properties_collectors_;
BloomBlockBuilder bloom_block_;
std::unique_ptr<PlainTableIndexBuilder> index_builder_;
WritableFileWriter* file_;
uint64_t offset_ = 0;
uint32_t bloom_bits_per_key_;
size_t huge_page_tlb_size_;
Status status_;
IOStatus io_status_;
TableProperties properties_;
PlainTableKeyEncoder encoder_;
bool store_index_in_file_;
std::vector<uint32_t> keys_or_prefixes_hashes_;
bool closed_ = false; // Either Finish() or Abandon() has been called.
const SliceTransform* prefix_extractor_;
Slice GetPrefix(const Slice& target) const {
assert(target.size() >= 8); // target is internal key
return GetPrefixFromUserKey(ExtractUserKey(target));
}
Slice GetPrefix(const ParsedInternalKey& target) const {
return GetPrefixFromUserKey(target.user_key);
}
Slice GetPrefixFromUserKey(const Slice& user_key) const {
if (!IsTotalOrderMode()) {
return prefix_extractor_->Transform(user_key);
} else {
// Use empty slice as prefix if prefix_extractor is not set.
// In that case,
// it falls back to pure binary search and
// total iterator seek is supported.
return Slice();
}
}
bool IsTotalOrderMode() const { return (prefix_extractor_ == nullptr); }
};
} // namespace ROCKSDB_NAMESPACE