|
|
|
// 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>
|
TablePropertiesCollectorFactory
Summary:
This diff addresses task #4296714 and rethinks how users provide us with TablePropertiesCollectors as part of Options.
Here's description of task #4296714:
I'm debugging #4295529 and noticed that our count of user properties kDeletedKeys is wrong. We're sharing one single InternalKeyPropertiesCollector with all Table Builders. In LOG Files, we're outputting number of kDeletedKeys as connected with a single table, while it's actually the total count of deleted keys since creation of the DB.
For example, this table has 3155 entries and 1391828 deleted keys.
The problem with current approach that we call methods on a single TablePropertiesCollector for all the tables we create. Even worse, we could do it from multiple threads at the same time and TablePropertiesCollector has no way of knowing which table we're calling it for.
Good part: Looks like nobody inside Facebook is using Options::table_properties_collectors. This means we should be able to painfully change the API.
In this change, I introduce TablePropertiesCollectorFactory. For every table we create, we call `CreateTablePropertiesCollector`, which creates a TablePropertiesCollector for a single table. We then use it sequentially from a single thread, which means it doesn't have to be thread-safe.
Test Plan:
Added a test in table_properties_collector_test that fails on master (build two tables, assert that kDeletedKeys count is correct for the second one).
Also, all other tests
Reviewers: sdong, dhruba, haobo, kailiu
Reviewed By: kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18579
11 years ago
|
|
|
#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.
|
A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.
Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties
Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.
Reviewers: yhchiang, igor.sugak, rven, igor
Reviewed By: rven, igor
Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D35373
10 years ago
|
|
|
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.
|
Pass IOStatus to write path and set retryable IO Error as hard error in BG jobs (#6487)
Summary:
In the current code base, we use Status to get and store the returned status from the call. Specifically, for IO related functions, the current Status cannot reflect the IO Error details such as error scope, error retryable attribute, and others. With the implementation of https://github.com/facebook/rocksdb/issues/5761, we have the new Wrapper for IO, which returns IOStatus instead of Status. However, the IOStatus is purged at the lower level of write path and transferred to Status.
The first job of this PR is to pass the IOStatus to the write path (flush, WAL write, and Compaction). The second job is to identify the Retryable IO Error as HardError, and set the bg_error_ as HardError. In this case, the DB Instance becomes read only. User is informed of the Status and need to take actions to deal with it (e.g., call db->Resume()).
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6487
Test Plan: Added the testing case to error_handler_fs_test. Pass make asan_check
Reviewed By: anand1976
Differential Revision: D20685017
Pulled By: zhichao-cao
fbshipit-source-id: ff85f042896243abcd6ef37877834e26f36b6eb0
5 years ago
|
|
|
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;
|
|
|
|
|
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
1 year ago
|
|
|
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;
|
|
|
|
}
|
Add more table properties to EventLogger
Summary:
Example output:
{"time_micros": 1431463794310521, "job": 353, "event": "table_file_creation", "file_number": 387, "file_size": 86937, "table_info": {"data_size": "81801", "index_size": "9751", "filter_size": "0", "raw_key_size": "23448", "raw_average_key_size": "24.000000", "raw_value_size": "990571", "raw_average_value_size": "1013.890481", "num_data_blocks": "245", "num_entries": "977", "filter_policy_name": "", "kDeletedKeys": "0"}}
Also fixed a bug where BuildTable() in recovery was passing Env::IOHigh argument into paranoid_checks_file parameter.
Test Plan: make check + check out the output in the log
Reviewers: sdong, rven, yhchiang
Reviewed By: yhchiang
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D38343
10 years ago
|
|
|
|
|
|
|
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_;
|
A new call back to TablePropertiesCollector to allow users know the entry is add, delete or merge
Summary:
Currently users have no idea a key is add, delete or merge from TablePropertiesCollector call back. Add a new function to add it.
Also refactor the codes so that
(1) make table property collector and internal table property collector two separate data structures with the later one now exposed
(2) table builders only receive internal table properties
Test Plan: Add cases in table_properties_collector_test to cover both of old and new ways of using TablePropertiesCollector.
Reviewers: yhchiang, igor.sugak, rven, igor
Reviewed By: rven, igor
Subscribers: meyering, yoshinorim, maykov, leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D35373
10 years ago
|
|
|
std::vector<std::unique_ptr<IntTblPropCollector>>
|
TablePropertiesCollectorFactory
Summary:
This diff addresses task #4296714 and rethinks how users provide us with TablePropertiesCollectors as part of Options.
Here's description of task #4296714:
I'm debugging #4295529 and noticed that our count of user properties kDeletedKeys is wrong. We're sharing one single InternalKeyPropertiesCollector with all Table Builders. In LOG Files, we're outputting number of kDeletedKeys as connected with a single table, while it's actually the total count of deleted keys since creation of the DB.
For example, this table has 3155 entries and 1391828 deleted keys.
The problem with current approach that we call methods on a single TablePropertiesCollector for all the tables we create. Even worse, we could do it from multiple threads at the same time and TablePropertiesCollector has no way of knowing which table we're calling it for.
Good part: Looks like nobody inside Facebook is using Options::table_properties_collectors. This means we should be able to painfully change the API.
In this change, I introduce TablePropertiesCollectorFactory. For every table we create, we call `CreateTablePropertiesCollector`, which creates a TablePropertiesCollector for a single table. We then use it sequentially from a single thread, which means it doesn't have to be thread-safe.
Test Plan:
Added a test in table_properties_collector_test that fails on master (build two tables, assert that kDeletedKeys count is correct for the second one).
Also, all other tests
Reviewers: sdong, dhruba, haobo, kailiu
Reviewed By: kailiu
CC: leveldb
Differential Revision: https://reviews.facebook.net/D18579
11 years ago
|
|
|
table_properties_collectors_;
|
|
|
|
|
|
|
|
BloomBlockBuilder bloom_block_;
|
|
|
|
std::unique_ptr<PlainTableIndexBuilder> index_builder_;
|
|
|
|
|
Move rate_limiter, write buffering, most perf context instrumentation and most random kill out of Env
Summary: We want to keep Env a think layer for better portability. Less platform dependent codes should be moved out of Env. In this patch, I create a wrapper of file readers and writers, and put rate limiting, write buffering, as well as most perf context instrumentation and random kill out of Env. It will make it easier to maintain multiple Env in the future.
Test Plan: Run all existing unit tests.
Reviewers: anthony, kradhakrishnan, IslamAbdelRahman, yhchiang, igor
Reviewed By: igor
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D42321
10 years ago
|
|
|
WritableFileWriter* file_;
|
|
|
|
uint64_t offset_ = 0;
|
|
|
|
uint32_t bloom_bits_per_key_;
|
|
|
|
size_t huge_page_tlb_size_;
|
|
|
|
Status status_;
|
Pass IOStatus to write path and set retryable IO Error as hard error in BG jobs (#6487)
Summary:
In the current code base, we use Status to get and store the returned status from the call. Specifically, for IO related functions, the current Status cannot reflect the IO Error details such as error scope, error retryable attribute, and others. With the implementation of https://github.com/facebook/rocksdb/issues/5761, we have the new Wrapper for IO, which returns IOStatus instead of Status. However, the IOStatus is purged at the lower level of write path and transferred to Status.
The first job of this PR is to pass the IOStatus to the write path (flush, WAL write, and Compaction). The second job is to identify the Retryable IO Error as HardError, and set the bg_error_ as HardError. In this case, the DB Instance becomes read only. User is informed of the Status and need to take actions to deal with it (e.g., call db->Resume()).
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6487
Test Plan: Added the testing case to error_handler_fs_test. Pass make asan_check
Reviewed By: anand1976
Differential Revision: D20685017
Pulled By: zhichao-cao
fbshipit-source-id: ff85f042896243abcd6ef37877834e26f36b6eb0
5 years ago
|
|
|
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
|
|
|
|
|