You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/options/cf_options.h

242 lines
7.7 KiB

// 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 "db/dbformat.h"
#include "options/db_options.h"
#include "rocksdb/options.h"
#include "util/compression.h"
namespace rocksdb {
// ImmutableCFOptions is a data struct used by RocksDB internal. It contains a
// subset of Options that should not be changed during the entire lifetime
// of DB. Raw pointers defined in this struct do not have ownership to the data
// they point to. Options contains shared_ptr to these data.
struct ImmutableCFOptions {
ImmutableCFOptions();
explicit ImmutableCFOptions(const Options& options);
ImmutableCFOptions(const ImmutableDBOptions& db_options,
const ColumnFamilyOptions& cf_options);
CompactionStyle compaction_style;
CompactionPri compaction_pri;
CompactionOptionsUniversal compaction_options_universal;
const SliceTransform* prefix_extractor;
const Comparator* user_comparator;
InternalKeyComparator internal_comparator;
MergeOperator* merge_operator;
const CompactionFilter* compaction_filter;
CompactionFilterFactory* compaction_filter_factory;
int min_write_buffer_number_to_merge;
int max_write_buffer_number_to_maintain;
bool inplace_update_support;
UpdateStatus (*inplace_callback)(char* existing_value,
uint32_t* existing_value_size,
Slice delta_value,
std::string* merged_value);
Logger* info_log;
Statistics* statistics;
RateLimiter* rate_limiter;
InfoLogLevel info_log_level;
Env* env;
// Allow the OS to mmap file for reading sst tables. Default: false
bool allow_mmap_reads;
// Allow the OS to mmap file for writing. Default: false
bool allow_mmap_writes;
std::vector<DbPath> db_paths;
MemTableRepFactory* memtable_factory;
TableFactory* table_factory;
Options::TablePropertiesCollectorFactories
table_properties_collector_factories;
bool advise_random_on_open;
// This options is required by PlainTableReader. May need to move it
// to PlainTableOptions just like bloom_bits_per_key
uint32_t bloom_locality;
bool purge_redundant_kvs_while_flush;
bool use_fsync;
std::vector<CompressionType> compression_per_level;
CompressionType bottommost_compression;
CompressionOptions compression_opts;
bool level_compaction_dynamic_level_bytes;
Options::AccessHint access_hint_on_compaction_start;
bool new_table_reader_for_compaction_inputs;
int num_levels;
bool optimize_filters_for_hits;
bool force_consistency_checks;
bool allow_ingest_behind;
Added support for differential snapshots Summary: The motivation for this PR is to add to RocksDB support for differential (incremental) snapshots, as snapshot of the DB changes between two points in time (one can think of it as diff between to sequence numbers, or the diff D which can be thought of as an SST file or just set of KVs that can be applied to sequence number S1 to get the database to the state at sequence number S2). This feature would be useful for various distributed storages layers built on top of RocksDB, as it should help reduce resources (time and network bandwidth) needed to recover and rebuilt DB instances as replicas in the context of distributed storages. From the API standpoint that would like client app requesting iterator between (start seqnum) and current DB state, and reading the "diff". This is a very draft PR for initial review in the discussion on the approach, i'm going to rework some parts and keep updating the PR. For now, what's done here according to initial discussions: Preserving deletes: - We want to be able to optionally preserve recent deletes for some defined period of time, so that if a delete came in recently and might need to be included in the next incremental snapshot it would't get dropped by a compaction. This is done by adding new param to Options (preserve deletes flag) and new variable to DB Impl where we keep track of the sequence number after which we don't want to drop tombstones, even if they are otherwise eligible for deletion. - I also added a new API call for clients to be able to advance this cutoff seqnum after which we drop deletes; i assume it's more flexible to let clients control this, since otherwise we'd need to keep some kind of timestamp < -- > seqnum mapping inside the DB, which sounds messy and painful to support. Clients could make use of it by periodically calling GetLatestSequenceNumber(), noting the timestamp, doing some calculation and figuring out by how much we need to advance the cutoff seqnum. - Compaction codepath in compaction_iterator.cc has been modified to avoid dropping tombstones with seqnum > cutoff seqnum. Iterator changes: - couple params added to ReadOptions, to optionally allow client to request internal keys instead of user keys (so that client can get the latest value of a key, be it delete marker or a put), as well as min timestamp and min seqnum. TableCache changes: - I modified table_cache code to be able to quickly exclude SST files from iterators heep if creation_time on the file is less then iter_start_ts as passed in ReadOptions. That would help a lot in some DB settings (like reading very recent data only or using FIFO compactions), but not so much for universal compaction with more or less long iterator time span. What's left: - Still looking at how to best plug that inside DBIter codepath. So far it seems that FindNextUserKeyInternal only parses values as UserKeys, and iter->key() call generally returns user key. Can we add new API to DBIter as internal_key(), and modify this internal method to optionally set saved_key_ to point to the full internal key? I don't need to store actual seqnum there, but I do need to store type. Closes https://github.com/facebook/rocksdb/pull/2999 Differential Revision: D6175602 Pulled By: mikhail-antonov fbshipit-source-id: c779a6696ee2d574d86c69cec866a3ae095aa900
7 years ago
bool preserve_deletes;
// A vector of EventListeners which call-back functions will be called
// when specific RocksDB event happens.
std::vector<std::shared_ptr<EventListener>> listeners;
std::shared_ptr<Cache> row_cache;
uint32_t max_subcompactions;
const SliceTransform* memtable_insert_with_hint_prefix_extractor;
};
struct MutableCFOptions {
explicit MutableCFOptions(const ColumnFamilyOptions& options)
: write_buffer_size(options.write_buffer_size),
max_write_buffer_number(options.max_write_buffer_number),
arena_block_size(options.arena_block_size),
memtable_prefix_bloom_size_ratio(
options.memtable_prefix_bloom_size_ratio),
memtable_huge_page_size(options.memtable_huge_page_size),
max_successive_merges(options.max_successive_merges),
inplace_update_num_locks(options.inplace_update_num_locks),
disable_auto_compactions(options.disable_auto_compactions),
soft_pending_compaction_bytes_limit(
options.soft_pending_compaction_bytes_limit),
hard_pending_compaction_bytes_limit(
options.hard_pending_compaction_bytes_limit),
level0_file_num_compaction_trigger(
options.level0_file_num_compaction_trigger),
level0_slowdown_writes_trigger(options.level0_slowdown_writes_trigger),
level0_stop_writes_trigger(options.level0_stop_writes_trigger),
max_compaction_bytes(options.max_compaction_bytes),
target_file_size_base(options.target_file_size_base),
target_file_size_multiplier(options.target_file_size_multiplier),
max_bytes_for_level_base(options.max_bytes_for_level_base),
max_bytes_for_level_multiplier(options.max_bytes_for_level_multiplier),
max_bytes_for_level_multiplier_additional(
options.max_bytes_for_level_multiplier_additional),
compaction_options_fifo(options.compaction_options_fifo),
max_sequential_skip_in_iterations(
options.max_sequential_skip_in_iterations),
paranoid_file_checks(options.paranoid_file_checks),
report_bg_io_stats(options.report_bg_io_stats),
compression(options.compression) {
RefreshDerivedOptions(options.num_levels, options.compaction_style);
}
MutableCFOptions()
: write_buffer_size(0),
max_write_buffer_number(0),
arena_block_size(0),
memtable_prefix_bloom_size_ratio(0),
memtable_huge_page_size(0),
max_successive_merges(0),
inplace_update_num_locks(0),
disable_auto_compactions(false),
soft_pending_compaction_bytes_limit(0),
hard_pending_compaction_bytes_limit(0),
level0_file_num_compaction_trigger(0),
level0_slowdown_writes_trigger(0),
level0_stop_writes_trigger(0),
max_compaction_bytes(0),
target_file_size_base(0),
target_file_size_multiplier(0),
max_bytes_for_level_base(0),
max_bytes_for_level_multiplier(0),
compaction_options_fifo(),
max_sequential_skip_in_iterations(0),
paranoid_file_checks(false),
report_bg_io_stats(false),
compression(Snappy_Supported() ? kSnappyCompression : kNoCompression) {}
// Must be called after any change to MutableCFOptions
void RefreshDerivedOptions(int num_levels, CompactionStyle compaction_style);
void RefreshDerivedOptions(const ImmutableCFOptions& ioptions) {
RefreshDerivedOptions(ioptions.num_levels, ioptions.compaction_style);
}
// Get the max file size in a given level.
uint64_t MaxFileSizeForLevel(int level) const;
int MaxBytesMultiplerAdditional(int level) const {
if (level >=
static_cast<int>(max_bytes_for_level_multiplier_additional.size())) {
return 1;
}
return max_bytes_for_level_multiplier_additional[level];
}
void Dump(Logger* log) const;
// Memtable related options
size_t write_buffer_size;
int max_write_buffer_number;
size_t arena_block_size;
double memtable_prefix_bloom_size_ratio;
size_t memtable_huge_page_size;
size_t max_successive_merges;
size_t inplace_update_num_locks;
// Compaction related options
bool disable_auto_compactions;
uint64_t soft_pending_compaction_bytes_limit;
uint64_t hard_pending_compaction_bytes_limit;
int level0_file_num_compaction_trigger;
int level0_slowdown_writes_trigger;
int level0_stop_writes_trigger;
uint64_t max_compaction_bytes;
uint64_t target_file_size_base;
int target_file_size_multiplier;
uint64_t max_bytes_for_level_base;
double max_bytes_for_level_multiplier;
std::vector<int> max_bytes_for_level_multiplier_additional;
CompactionOptionsFIFO compaction_options_fifo;
// Misc options
uint64_t max_sequential_skip_in_iterations;
bool paranoid_file_checks;
bool report_bg_io_stats;
CompressionType compression;
// Derived options
// Per-level target file size.
std::vector<uint64_t> max_file_size;
};
uint64_t MultiplyCheckOverflow(uint64_t op1, double op2);
} // namespace rocksdb