rocksdb/table
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
..
adaptive Remove RocksDB LITE (#11147) 2023-01-27 13:14:19 -08:00
block_based Move prefetching responsibility to page cache for compaction read under non directIO usecase (#11631) 2023-07-21 14:52:52 -07:00
cuckoo Group rocksdb.sst.read.micros stat by IOActivity flush and compaction (#11288) 2023-04-21 09:07:18 -07:00
plain Add missing table properties in plaintable GetTableProperties() (#11267) 2023-07-21 17:55:25 -07:00
block_fetcher.cc Change internal headers with duplicate names (#11408) 2023-05-17 11:27:09 -07:00
block_fetcher.h Change internal headers with duplicate names (#11408) 2023-05-17 11:27:09 -07:00
block_fetcher_test.cc Record and use the tail size to prefetch table tail (#11406) 2023-05-08 13:14:28 -07:00
cleanable_test.cc Eliminate unnecessary (slow) block cache Ref()ing in MultiGet (#9899) 2022-04-26 21:59:24 -07:00
compaction_merging_iterator.cc Refactor AddRangeDels() + consider range tombstone during compaction file cutting (#11113) 2023-02-22 12:28:18 -08:00
compaction_merging_iterator.h Refactor AddRangeDels() + consider range tombstone during compaction file cutting (#11113) 2023-02-22 12:28:18 -08:00
format.cc Change internal headers with duplicate names (#11408) 2023-05-17 11:27:09 -07:00
format.h Change internal headers with duplicate names (#11408) 2023-05-17 11:27:09 -07:00
get_context.cc Change internal headers with duplicate names (#11408) 2023-05-17 11:27:09 -07:00
get_context.h Merge operator failed subcode (#11231) 2023-02-17 10:58:46 -08:00
internal_iterator.h remove unused InternalIteratorBase::is_mutable_ (#11104) 2023-01-19 13:28:58 -08:00
iter_heap.h Format files under table/ by clang-format (#10852) 2022-10-25 11:50:38 -07:00
iterator.cc Format files under table/ by clang-format (#10852) 2022-10-25 11:50:38 -07:00
iterator_wrapper.h Format files under table/ by clang-format (#10852) 2022-10-25 11:50:38 -07:00
merger_test.cc Print stack traces on frozen tests in CI (#10828) 2022-10-18 00:35:35 -07:00
merging_iterator.cc Improve documentation for MergingIterator (#11161) 2023-03-03 12:17:30 -08:00
merging_iterator.h Improve documentation for MergingIterator (#11161) 2023-03-03 12:17:30 -08:00
meta_blocks.cc Record the `persist_user_defined_timestamps` flag in manifest (#11515) 2023-06-21 21:49:01 -07:00
meta_blocks.h Group rocksdb.sst.read.micros stat by IOActivity flush and compaction (#11288) 2023-04-21 09:07:18 -07:00
mock_table.cc Group rocksdb.sst.read.micros stat by IOActivity flush and compaction (#11288) 2023-04-21 09:07:18 -07:00
mock_table.h Align compaction output file boundaries to the next level ones (#10655) 2022-09-29 19:43:55 -07:00
multiget_context.h Add a new MultiGetEntity API (#11222) 2023-02-15 09:34:17 -08:00
persistent_cache_helper.cc Format files under table/ by clang-format (#10852) 2022-10-25 11:50:38 -07:00
persistent_cache_helper.h Change internal headers with duplicate names (#11408) 2023-05-17 11:27:09 -07:00
persistent_cache_options.h Change internal headers with duplicate names (#11408) 2023-05-17 11:27:09 -07:00
scoped_arena_iterator.h Format files under table/ by clang-format (#10852) 2022-10-25 11:50:38 -07:00
sst_file_dumper.cc `sst_dump --command=verify` should verify block checksums (#11576) 2023-07-05 14:12:06 -07:00
sst_file_dumper.h Remove RocksDB LITE (#11147) 2023-01-27 13:14:19 -08:00
sst_file_reader.cc Block per key-value checksum (#11287) 2023-04-25 12:08:23 -07:00
sst_file_reader_test.cc Remove RocksDB LITE (#11147) 2023-01-27 13:14:19 -08:00
sst_file_writer.cc validate SstFileWriter range tombstones cover positive ranges (#11322) 2023-03-22 21:03:13 -07:00
sst_file_writer_collectors.h Refactor to avoid confusing "raw block" (#10408) 2022-09-22 11:25:32 -07:00
table_builder.h Add support to strip / pad timestamp when creating / reading a block based table (#11495) 2023-06-01 11:10:03 -07:00
table_factory.cc Remove FactoryFunc from LoadXXXObject (#11203) 2023-02-17 12:54:07 -08:00
table_properties.cc Record the `persist_user_defined_timestamps` flag in manifest (#11515) 2023-06-21 21:49:01 -07:00
table_properties_internal.h Improve / clean up meta block code & integrity (#9163) 2021-11-18 11:43:44 -08:00
table_reader.h Group rocksdb.sst.read.micros stat by IOActivity flush and compaction (#11288) 2023-04-21 09:07:18 -07:00
table_reader_bench.cc Block per key-value checksum (#11287) 2023-04-25 12:08:23 -07:00
table_test.cc Change internal headers with duplicate names (#11408) 2023-05-17 11:27:09 -07:00
two_level_iterator.cc Format files under table/ by clang-format (#10852) 2022-10-25 11:50:38 -07:00
two_level_iterator.h Format files under table/ by clang-format (#10852) 2022-10-25 11:50:38 -07:00
unique_id.cc Derive cache keys from SST unique IDs (#10394) 2022-08-12 13:49:49 -07:00
unique_id_impl.h Derive cache keys from SST unique IDs (#10394) 2022-08-12 13:49:49 -07:00