rocksdb/include/leveldb/options.h

// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.

#ifndef STORAGE_LEVELDB_INCLUDE_OPTIONS_H_
#define STORAGE_LEVELDB_INCLUDE_OPTIONS_H_

#include <stddef.h>

namespace leveldb {

class Cache;
class Comparator;
class Env;
class FilterPolicy;
class Logger;
class Snapshot;
class Statistics;

// DB contents are stored in a set of blocks, each of which holds a
// sequence of key,value pairs.  Each block may be compressed before
// being stored in a file.  The following enum describes which
// compression method (if any) is used to compress a block.
enum CompressionType {
  // NOTE: do not change the values of existing entries, as these are
  // part of the persistent format on disk.
  kNoCompression     = 0x0,
  kSnappyCompression = 0x1,
  kZlibCompression = 0x2,
  kBZip2Compression = 0x3
};

// Options to control the behavior of a database (passed to DB::Open)
struct Options {
  // -------------------
  // Parameters that affect behavior

  // Comparator used to define the order of keys in the table.
  // Default: a comparator that uses lexicographic byte-wise ordering
  //
  // REQUIRES: The client must ensure that the comparator supplied
  // here has the same name and orders keys *exactly* the same as the
  // comparator provided to previous open calls on the same DB.
  const Comparator* comparator;

  // If true, the database will be created if it is missing.
  // Default: false
  bool create_if_missing;

  // If true, an error is raised if the database already exists.
  // Default: false
  bool error_if_exists;

  // If true, the implementation will do aggressive checking of the
  // data it is processing and will stop early if it detects any
  // errors.  This may have unforeseen ramifications: for example, a
  // corruption of one DB entry may cause a large number of entries to
  // become unreadable or for the entire DB to become unopenable.
  // Default: false
  bool paranoid_checks;

  // Use the specified object to interact with the environment,
  // e.g. to read/write files, schedule background work, etc.
  // Default: Env::Default()
  Env* env;

  // Any internal progress/error information generated by the db will
  // be written to info_log if it is non-NULL, or to a file stored
  // in the same directory as the DB contents if info_log is NULL.
  // Default: NULL
  Logger* info_log;

  // -------------------
  // Parameters that affect performance

  // Amount of data to build up in memory (backed by an unsorted log
  // on disk) before converting to a sorted on-disk file.
  //
  // Larger values increase performance, especially during bulk loads.
  // Up to two write buffers may be held in memory at the same time,
  // so you may wish to adjust this parameter to control memory usage.
  // Also, a larger write buffer will result in a longer recovery time
  // the next time the database is opened.
  //
  // Default: 4MB
  size_t write_buffer_size;

  // Number of open files that can be used by the DB.  You may need to
  // increase this if your database has a large working set (budget
  // one open file per 2MB of working set).
  //
  // Default: 1000
  int max_open_files;

  // Control over blocks (user data is stored in a set of blocks, and
  // a block is the unit of reading from disk).

  // If non-NULL, use the specified cache for blocks.
  // If NULL, leveldb will automatically create and use an 8MB internal cache.
  // Default: NULL
  Cache* block_cache;

  // Approximate size of user data packed per block.  Note that the
  // block size specified here corresponds to uncompressed data.  The
  // actual size of the unit read from disk may be smaller if
  // compression is enabled.  This parameter can be changed dynamically.
  //
  // Default: 4K
  size_t block_size;

  // Number of keys between restart points for delta encoding of keys.
  // This parameter can be changed dynamically.  Most clients should
  // leave this parameter alone.
  //
  // Default: 16
  int block_restart_interval;


  // Compress blocks using the specified compression algorithm.  This
  // parameter can be changed dynamically.
  //
  // Default: kSnappyCompression, which gives lightweight but fast
  // compression.
  //
  // Typical speeds of kSnappyCompression on an Intel(R) Core(TM)2 2.4GHz:
  //    ~200-500MB/s compression
  //    ~400-800MB/s decompression
  // Note that these speeds are significantly faster than most
  // persistent storage speeds, and therefore it is typically never
  // worth switching to kNoCompression.  Even if the input data is
  // incompressible, the kSnappyCompression implementation will
  // efficiently detect that and will switch to uncompressed mode.
  CompressionType compression;

  // If non-NULL, use the specified filter policy to reduce disk reads.
  // Many applications will benefit from passing the result of
  // NewBloomFilterPolicy() here.
  //
  // Default: NULL
  const FilterPolicy* filter_policy;

  // Number of levels for this database
  int num_levels;

  // Number of files to trigger level-0 compaction. A value <0 means that
  // level-0 compaction will not be triggered by number of files at all.
  int level0_file_num_compaction_trigger;

  // Soft limit on number of level-0 files. We slow down writes at this point.
  // A value <0 means that no writing slow down will be triggered by number
  // of files in level-0.
  int level0_slowdown_writes_trigger;

  // Maximum number of level-0 files.  We stop writes at this point.
  int level0_stop_writes_trigger;

  // Maximum level to which a new compacted memtable is pushed if it
  // does not create overlap.  We try to push to level 2 to avoid the
  // relatively expensive level 0=>1 compactions and to avoid some
  // expensive manifest file operations.  We do not push all the way to
  // the largest level since that can generate a lot of wasted disk
  // space if the same key space is being repeatedly overwritten.
  int max_mem_compaction_level;

  // Target file size for compaction. Target file size for level L is
  // (target_file_size_base)^(target_file_size_multiplier).
  // For example, if target_file_size_base is 20MB and
  // target_file_size_multiplier is 2^10, then target file size on level 1
  // will be 200MB, and wiil be 2GB on level 2.

  int target_file_size_base;
  int target_file_size_multiplier;

  // Control maximum number of bytes in all compacted files for one level.
  // Maximum number of bytes for level L is
  // (max_bytes_for_level_base)^(max_bytes_for_level_multiplier).

  int max_bytes_for_level_base;
  int max_bytes_for_level_multiplier;

  // Maximum number of bytes in all compacted files.  We avoid expanding
  // the lower level file set of a compaction if it would make the
  // total compaction cover more than
  // (expanded_compaction_factor * targetFileSizeLevel()) many bytes.
  int expanded_compaction_factor;

  // Control maximum bytes of overlaps in grandparent (i.e., level+2) before we
  // stop building a single file in a level->level+1 compaction.
  int max_grandparent_overlap_factor;

  // If non-null, then we should collect metrics about database operations
  Statistics* statistics;

  // If true, then the contents of data files are not synced
  // to stable storage. Their contents remain in the OS buffers till the
  // OS decides to flush them. This option is good for bulk-loading
  // of data. Once the bulk-loading is complete, please issue a
  // sync to the OS to flush all dirty buffesrs to stable storage.
  // Default: false
  bool disableDataSync;

  // If true, then every store to stable storage will issue a fsync.
  // If false, then every store to stable storage will issue a fdatasync.
  // This parameter should be set to true while storing data to
  // filesystem like ext3 which can lose files after a reboot.
  // Default: false
  bool use_fsync;

  // This number controls how often a new scribe log about
  // db deploy stats is written out.
  // -1 indicates no logging at all.
  // Default value is 1800 (half an hour).
  int db_stats_log_interval;

  // Create an Options object with default values for all fields.
  Options();

  void Dump(Logger * log) const;
};

// Options that control read operations
struct ReadOptions {
  // If true, all data read from underlying storage will be
  // verified against corresponding checksums.
  // Default: false
  bool verify_checksums;

  // Should the data read for this iteration be cached in memory?
  // Callers may wish to set this field to false for bulk scans.
  // Default: true
  bool fill_cache;

  // If "snapshot" is non-NULL, read as of the supplied snapshot
  // (which must belong to the DB that is being read and which must
  // not have been released).  If "snapshot" is NULL, use an impliicit
  // snapshot of the state at the beginning of this read operation.
  // Default: NULL
  const Snapshot* snapshot;

  ReadOptions()
      : verify_checksums(false),
        fill_cache(true),
        snapshot(NULL) {
  }
  ReadOptions(bool cksum, bool cache) :
              verify_checksums(cksum), fill_cache(cache),
              snapshot(NULL) {
  }
};

// Options that control write operations
struct WriteOptions {
  // If true, the write will be flushed from the operating system
  // buffer cache (by calling WritableFile::Sync()) before the write
  // is considered complete.  If this flag is true, writes will be
  // slower.
  //
  // If this flag is false, and the machine crashes, some recent
  // writes may be lost.  Note that if it is just the process that
  // crashes (i.e., the machine does not reboot), no writes will be
  // lost even if sync==false.
  //
  // In other words, a DB write with sync==false has similar
  // crash semantics as the "write()" system call.  A DB write
  // with sync==true has similar crash semantics to a "write()"
  // system call followed by "fsync()".
  //
  // Default: false
  bool sync;

  // If true, writes will not first go to the write ahead log,
  // and the write may got lost after a crash.
  bool disableWAL;

  WriteOptions()
      : sync(false),
        disableWAL(false) {
  }
};

// Options that control flush operations
struct FlushOptions {
  // If true, the flush will wait until the flush is done.
  // Default: true
  bool wait;

  FlushOptions()
      : wait(true) {
  }
};

}  // namespace leveldb

#endif  // STORAGE_LEVELDB_INCLUDE_OPTIONS_H_