afa2420c2b
Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
117 lines
3.4 KiB
C++
117 lines
3.4 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 <string>
|
|
#include <vector>
|
|
|
|
#include "rocksdb/options.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
struct ImmutableDBOptions {
|
|
ImmutableDBOptions();
|
|
explicit ImmutableDBOptions(const DBOptions& options);
|
|
|
|
void Dump(Logger* log) const;
|
|
|
|
bool create_if_missing;
|
|
bool create_missing_column_families;
|
|
bool error_if_exists;
|
|
bool paranoid_checks;
|
|
Env* env;
|
|
std::shared_ptr<FileSystem> fs;
|
|
std::shared_ptr<RateLimiter> rate_limiter;
|
|
std::shared_ptr<SstFileManager> sst_file_manager;
|
|
std::shared_ptr<Logger> info_log;
|
|
InfoLogLevel info_log_level;
|
|
int max_file_opening_threads;
|
|
std::shared_ptr<Statistics> statistics;
|
|
bool use_fsync;
|
|
std::vector<DbPath> db_paths;
|
|
std::string db_log_dir;
|
|
std::string wal_dir;
|
|
uint32_t max_subcompactions;
|
|
int max_background_flushes;
|
|
size_t max_log_file_size;
|
|
size_t log_file_time_to_roll;
|
|
size_t keep_log_file_num;
|
|
size_t recycle_log_file_num;
|
|
uint64_t max_manifest_file_size;
|
|
int table_cache_numshardbits;
|
|
uint64_t wal_ttl_seconds;
|
|
uint64_t wal_size_limit_mb;
|
|
uint64_t max_write_batch_group_size_bytes;
|
|
size_t manifest_preallocation_size;
|
|
bool allow_mmap_reads;
|
|
bool allow_mmap_writes;
|
|
bool use_direct_reads;
|
|
bool use_direct_io_for_flush_and_compaction;
|
|
bool allow_fallocate;
|
|
bool is_fd_close_on_exec;
|
|
bool advise_random_on_open;
|
|
size_t db_write_buffer_size;
|
|
std::shared_ptr<WriteBufferManager> write_buffer_manager;
|
|
DBOptions::AccessHint access_hint_on_compaction_start;
|
|
bool new_table_reader_for_compaction_inputs;
|
|
size_t random_access_max_buffer_size;
|
|
bool use_adaptive_mutex;
|
|
std::vector<std::shared_ptr<EventListener>> listeners;
|
|
bool enable_thread_tracking;
|
|
bool enable_pipelined_write;
|
|
bool unordered_write;
|
|
bool allow_concurrent_memtable_write;
|
|
bool enable_write_thread_adaptive_yield;
|
|
uint64_t write_thread_max_yield_usec;
|
|
uint64_t write_thread_slow_yield_usec;
|
|
bool skip_stats_update_on_db_open;
|
|
WALRecoveryMode wal_recovery_mode;
|
|
bool allow_2pc;
|
|
std::shared_ptr<Cache> row_cache;
|
|
#ifndef ROCKSDB_LITE
|
|
WalFilter* wal_filter;
|
|
#endif // ROCKSDB_LITE
|
|
bool fail_if_options_file_error;
|
|
bool dump_malloc_stats;
|
|
bool avoid_flush_during_recovery;
|
|
bool allow_ingest_behind;
|
|
bool preserve_deletes;
|
|
bool two_write_queues;
|
|
bool manual_wal_flush;
|
|
bool atomic_flush;
|
|
bool avoid_unnecessary_blocking_io;
|
|
bool persist_stats_to_disk;
|
|
bool write_dbid_to_manifest;
|
|
size_t log_readahead_size;
|
|
};
|
|
|
|
struct MutableDBOptions {
|
|
MutableDBOptions();
|
|
explicit MutableDBOptions(const MutableDBOptions& options) = default;
|
|
explicit MutableDBOptions(const DBOptions& options);
|
|
|
|
void Dump(Logger* log) const;
|
|
|
|
int max_background_jobs;
|
|
int base_background_compactions;
|
|
int max_background_compactions;
|
|
bool avoid_flush_during_shutdown;
|
|
size_t writable_file_max_buffer_size;
|
|
uint64_t delayed_write_rate;
|
|
uint64_t max_total_wal_size;
|
|
uint64_t delete_obsolete_files_period_micros;
|
|
unsigned int stats_dump_period_sec;
|
|
unsigned int stats_persist_period_sec;
|
|
size_t stats_history_buffer_size;
|
|
int max_open_files;
|
|
uint64_t bytes_per_sync;
|
|
uint64_t wal_bytes_per_sync;
|
|
bool strict_bytes_per_sync;
|
|
size_t compaction_readahead_size;
|
|
};
|
|
|
|
} // namespace rocksdb
|