2011-03-18 23:37:00 +01:00
|
|
|
// 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_DB_H_
|
|
|
|
#define STORAGE_LEVELDB_INCLUDE_DB_H_
|
|
|
|
|
|
|
|
#include <stdint.h>
|
|
|
|
#include <stdio.h>
|
2013-01-24 19:54:26 +01:00
|
|
|
#include <memory>
|
2012-09-15 02:11:35 +02:00
|
|
|
#include <vector>
|
2011-03-30 20:49:03 +02:00
|
|
|
#include "leveldb/iterator.h"
|
|
|
|
#include "leveldb/options.h"
|
2012-11-30 02:28:37 +01:00
|
|
|
#include "leveldb/types.h"
|
|
|
|
#include "leveldb/transaction_log_iterator.h"
|
2011-03-18 23:37:00 +01:00
|
|
|
|
|
|
|
namespace leveldb {
|
|
|
|
|
2013-01-24 19:54:26 +01:00
|
|
|
using std::unique_ptr;
|
|
|
|
|
2012-03-30 22:15:49 +02:00
|
|
|
// Update Makefile if you change these
|
2013-06-29 21:51:24 +02:00
|
|
|
static const int kMajorVersion = 2;
|
|
|
|
static const int kMinorVersion = 0;
|
2011-03-22 19:32:49 +01:00
|
|
|
|
2011-03-18 23:37:00 +01:00
|
|
|
struct Options;
|
|
|
|
struct ReadOptions;
|
|
|
|
struct WriteOptions;
|
2012-07-06 20:42:09 +02:00
|
|
|
struct FlushOptions;
|
2011-03-18 23:37:00 +01:00
|
|
|
class WriteBatch;
|
|
|
|
|
2011-05-21 04:17:43 +02:00
|
|
|
// Abstract handle to particular state of a DB.
|
|
|
|
// A Snapshot is an immutable object and can therefore be safely
|
|
|
|
// accessed from multiple threads without any external synchronization.
|
|
|
|
class Snapshot {
|
|
|
|
protected:
|
|
|
|
virtual ~Snapshot();
|
|
|
|
};
|
2011-03-18 23:37:00 +01:00
|
|
|
|
2011-05-21 04:17:43 +02:00
|
|
|
// A range of keys
|
2011-03-18 23:37:00 +01:00
|
|
|
struct Range {
|
2011-05-21 04:17:43 +02:00
|
|
|
Slice start; // Included in the range
|
|
|
|
Slice limit; // Not included in the range
|
2011-03-18 23:37:00 +01:00
|
|
|
|
2011-08-05 22:40:49 +02:00
|
|
|
Range() { }
|
2011-03-18 23:37:00 +01:00
|
|
|
Range(const Slice& s, const Slice& l) : start(s), limit(l) { }
|
|
|
|
};
|
|
|
|
|
|
|
|
// A DB is a persistent ordered map from keys to values.
|
2011-05-21 04:17:43 +02:00
|
|
|
// A DB is safe for concurrent access from multiple threads without
|
|
|
|
// any external synchronization.
|
2011-03-18 23:37:00 +01:00
|
|
|
class DB {
|
|
|
|
public:
|
|
|
|
// Open the database with the specified "name".
|
|
|
|
// Stores a pointer to a heap-allocated database in *dbptr and returns
|
|
|
|
// OK on success.
|
2013-03-01 03:04:58 +01:00
|
|
|
// Stores nullptr in *dbptr and returns a non-OK status on error.
|
2011-03-18 23:37:00 +01:00
|
|
|
// Caller should delete *dbptr when it is no longer needed.
|
|
|
|
static Status Open(const Options& options,
|
|
|
|
const std::string& name,
|
|
|
|
DB** dbptr);
|
|
|
|
|
2012-11-06 04:18:49 +01:00
|
|
|
// Open the database for read only. All DB interfaces
|
|
|
|
// that modify data, like put/delete, will return error.
|
|
|
|
// If the db is opened in read only mode, then no compactions
|
|
|
|
// will happen.
|
|
|
|
static Status OpenForReadOnly(const Options& options,
|
|
|
|
const std::string& name, DB** dbptr,
|
2012-12-18 22:05:39 +01:00
|
|
|
bool error_if_log_file_exist = false);
|
2012-11-06 04:18:49 +01:00
|
|
|
|
2011-03-18 23:37:00 +01:00
|
|
|
DB() { }
|
|
|
|
virtual ~DB();
|
|
|
|
|
|
|
|
// Set the database entry for "key" to "value". Returns OK on success,
|
|
|
|
// and a non-OK status on error.
|
2011-04-12 21:38:58 +02:00
|
|
|
// Note: consider setting options.sync = true.
|
2011-03-18 23:37:00 +01:00
|
|
|
virtual Status Put(const WriteOptions& options,
|
|
|
|
const Slice& key,
|
|
|
|
const Slice& value) = 0;
|
|
|
|
|
|
|
|
// Remove the database entry (if any) for "key". Returns OK on
|
|
|
|
// success, and a non-OK status on error. It is not an error if "key"
|
|
|
|
// did not exist in the database.
|
2011-04-12 21:38:58 +02:00
|
|
|
// Note: consider setting options.sync = true.
|
2011-03-18 23:37:00 +01:00
|
|
|
virtual Status Delete(const WriteOptions& options, const Slice& key) = 0;
|
|
|
|
|
2013-03-21 23:59:47 +01:00
|
|
|
// Merge the database entry for "key" with "value". Returns OK on success,
|
|
|
|
// and a non-OK status on error. The semantics of this operation is
|
|
|
|
// determined by the user provided merge_operator when opening DB.
|
|
|
|
// Note: consider setting options.sync = true.
|
|
|
|
virtual Status Merge(const WriteOptions& options,
|
|
|
|
const Slice& key,
|
|
|
|
const Slice& value) = 0;
|
|
|
|
|
2011-03-18 23:37:00 +01:00
|
|
|
// Apply the specified updates to the database.
|
|
|
|
// Returns OK on success, non-OK on failure.
|
2011-04-12 21:38:58 +02:00
|
|
|
// Note: consider setting options.sync = true.
|
2011-03-18 23:37:00 +01:00
|
|
|
virtual Status Write(const WriteOptions& options, WriteBatch* updates) = 0;
|
|
|
|
|
|
|
|
// If the database contains an entry for "key" store the
|
|
|
|
// corresponding value in *value and return OK.
|
|
|
|
//
|
|
|
|
// If there is no entry for "key" leave *value unchanged and return
|
|
|
|
// a status for which Status::IsNotFound() returns true.
|
|
|
|
//
|
|
|
|
// May return some other Status on an error.
|
|
|
|
virtual Status Get(const ReadOptions& options,
|
|
|
|
const Slice& key, std::string* value) = 0;
|
|
|
|
|
2013-06-05 20:22:38 +02:00
|
|
|
// If keys[i] does not exist in the database, then the i'th returned
|
|
|
|
// status will be one for which Status::IsNotFound() is true, and
|
|
|
|
// (*values)[i] will be set to some arbitrary value (often ""). Otherwise,
|
|
|
|
// the i'th returned status will have Status::ok() true, and (*values)[i]
|
|
|
|
// will store the value associated with keys[i].
|
|
|
|
//
|
|
|
|
// (*values) will always be resized to be the same size as (keys).
|
|
|
|
// Similarly, the number of returned statuses will be the number of keys.
|
|
|
|
// Note: keys will not be "de-duplicated". Duplicate keys will return
|
|
|
|
// duplicate values in order.
|
|
|
|
virtual std::vector<Status> MultiGet(const ReadOptions& options,
|
|
|
|
const std::vector<Slice>& keys,
|
|
|
|
std::vector<std::string>* values) = 0;
|
|
|
|
|
2013-07-06 03:49:18 +02:00
|
|
|
// If the key definitely does not exist in the database, then this method
|
|
|
|
// returns false. Otherwise return true. This check is potentially
|
|
|
|
// lighter-weight than invoking DB::Get(). No IO is performed
|
|
|
|
virtual bool KeyMayExist(const Slice& key) = 0;
|
|
|
|
|
2011-03-18 23:37:00 +01:00
|
|
|
// Return a heap-allocated iterator over the contents of the database.
|
|
|
|
// The result of NewIterator() is initially invalid (caller must
|
|
|
|
// call one of the Seek methods on the iterator before using it).
|
|
|
|
//
|
|
|
|
// Caller should delete the iterator when it is no longer needed.
|
|
|
|
// The returned iterator should be deleted before this db is deleted.
|
|
|
|
virtual Iterator* NewIterator(const ReadOptions& options) = 0;
|
|
|
|
|
|
|
|
// Return a handle to the current DB state. Iterators created with
|
|
|
|
// this handle will all observe a stable snapshot of the current DB
|
|
|
|
// state. The caller must call ReleaseSnapshot(result) when the
|
|
|
|
// snapshot is no longer needed.
|
|
|
|
virtual const Snapshot* GetSnapshot() = 0;
|
|
|
|
|
|
|
|
// Release a previously acquired snapshot. The caller must not
|
|
|
|
// use "snapshot" after this call.
|
|
|
|
virtual void ReleaseSnapshot(const Snapshot* snapshot) = 0;
|
|
|
|
|
|
|
|
// DB implementations can export properties about their state
|
|
|
|
// via this method. If "property" is a valid property understood by this
|
|
|
|
// DB implementation, fills "*value" with its current value and returns
|
|
|
|
// true. Otherwise returns false.
|
|
|
|
//
|
|
|
|
//
|
|
|
|
// Valid property names include:
|
|
|
|
//
|
|
|
|
// "leveldb.num-files-at-level<N>" - return the number of files at level <N>,
|
|
|
|
// where <N> is an ASCII representation of a level number (e.g. "0").
|
2011-04-12 21:38:58 +02:00
|
|
|
// "leveldb.stats" - returns a multi-line string that describes statistics
|
|
|
|
// about the internal operation of the DB.
|
2011-10-06 01:30:28 +02:00
|
|
|
// "leveldb.sstables" - returns a multi-line string that describes all
|
|
|
|
// of the sstables that make up the db contents.
|
2011-04-12 21:38:58 +02:00
|
|
|
virtual bool GetProperty(const Slice& property, std::string* value) = 0;
|
2011-03-18 23:37:00 +01:00
|
|
|
|
|
|
|
// For each i in [0,n-1], store in "sizes[i]", the approximate
|
|
|
|
// file system space used by keys in "[range[i].start .. range[i].limit)".
|
|
|
|
//
|
|
|
|
// Note that the returned sizes measure file system space usage, so
|
|
|
|
// if the user data compresses by a factor of ten, the returned
|
|
|
|
// sizes will be one-tenth the size of the corresponding user data size.
|
|
|
|
//
|
|
|
|
// The results may not include the sizes of recently written data.
|
|
|
|
virtual void GetApproximateSizes(const Range* range, int n,
|
|
|
|
uint64_t* sizes) = 0;
|
|
|
|
|
2011-10-06 01:30:28 +02:00
|
|
|
// Compact the underlying storage for the key range [*begin,*end].
|
|
|
|
// In particular, deleted and overwritten versions are discarded,
|
|
|
|
// and the data is rearranged to reduce the cost of operations
|
|
|
|
// needed to access the data. This operation should typically only
|
|
|
|
// be invoked by users who understand the underlying implementation.
|
|
|
|
//
|
2013-03-01 03:04:58 +01:00
|
|
|
// begin==nullptr is treated as a key before all keys in the database.
|
|
|
|
// end==nullptr is treated as a key after all keys in the database.
|
2011-10-06 01:30:28 +02:00
|
|
|
// Therefore the following call will compact the entire database:
|
2013-03-01 03:04:58 +01:00
|
|
|
// db->CompactRange(nullptr, nullptr);
|
2011-10-06 01:30:28 +02:00
|
|
|
virtual void CompactRange(const Slice* begin, const Slice* end) = 0;
|
2011-03-18 23:37:00 +01:00
|
|
|
|
2012-06-23 04:30:03 +02:00
|
|
|
// Number of levels used for this DB.
|
|
|
|
virtual int NumberLevels() = 0;
|
|
|
|
|
|
|
|
// Maximum level to which a new compacted memtable is pushed if it
|
|
|
|
// does not create overlap.
|
|
|
|
virtual int MaxMemCompactionLevel() = 0;
|
|
|
|
|
|
|
|
// Number of files in level-0 that would stop writes.
|
|
|
|
virtual int Level0StopWriteTrigger() = 0;
|
|
|
|
|
2012-07-06 20:42:09 +02:00
|
|
|
// Flush all mem-table data.
|
|
|
|
virtual Status Flush(const FlushOptions& options) = 0;
|
|
|
|
|
2012-09-15 02:11:35 +02:00
|
|
|
// Prevent file deletions. Compactions will continue to occur,
|
|
|
|
// but no obsolete files will be deleted. Calling this multiple
|
|
|
|
// times have the same effect as calling it once.
|
|
|
|
virtual Status DisableFileDeletions() = 0;
|
|
|
|
|
|
|
|
// Allow compactions to delete obselete files.
|
|
|
|
virtual Status EnableFileDeletions() = 0;
|
|
|
|
|
|
|
|
// Retrieve the list of all files in the database. The files are
|
2012-09-24 23:01:01 +02:00
|
|
|
// relative to the dbname and are not absolute paths. This list
|
|
|
|
// can be used to generate a backup. The valid size of the manifest
|
|
|
|
// file is returned in manifest_file_size. The manifest file is
|
|
|
|
// an ever growing file, but only the portion specified
|
|
|
|
// by manifest_file_size is valid for this snapshot.
|
|
|
|
virtual Status GetLiveFiles(std::vector<std::string>&,
|
|
|
|
uint64_t* manifest_file_size) = 0;
|
2012-09-15 02:11:35 +02:00
|
|
|
|
2013-03-21 23:59:47 +01:00
|
|
|
// The sequence number of the most recent transaction.
|
2012-12-11 00:37:00 +01:00
|
|
|
virtual SequenceNumber GetLatestSequenceNumber() = 0;
|
|
|
|
|
2012-11-30 02:28:37 +01:00
|
|
|
// Return's an iterator for all writes since the sequence number
|
|
|
|
// Status::ok if iterator is valid.
|
|
|
|
// The iterator internally holds references to the available log files.
|
|
|
|
// It automatically takes care of closing a file with no-updates left, and
|
|
|
|
// opening the next one.
|
|
|
|
// If the sequence number is non existent. it returns an iterator at a seq_no
|
|
|
|
// just greater than the requested seq_no.
|
|
|
|
// Must set WAL_ttl_seconds to a large value to use this api.
|
|
|
|
// else the WAL files will get
|
|
|
|
// cleared aggressively and the iterator might keep getting invalid before
|
|
|
|
// an update is read.
|
|
|
|
virtual Status GetUpdatesSince(SequenceNumber seq_number,
|
2013-01-24 19:54:26 +01:00
|
|
|
unique_ptr<TransactionLogIterator>* iter) = 0;
|
2011-03-18 23:37:00 +01:00
|
|
|
private:
|
|
|
|
// No copying allowed
|
|
|
|
DB(const DB&);
|
|
|
|
void operator=(const DB&);
|
|
|
|
};
|
|
|
|
|
|
|
|
// Destroy the contents of the specified database.
|
|
|
|
// Be very careful using this method.
|
|
|
|
Status DestroyDB(const std::string& name, const Options& options);
|
|
|
|
|
|
|
|
// If a DB cannot be opened, you may attempt to call this method to
|
|
|
|
// resurrect as much of the contents of the database as possible.
|
|
|
|
// Some data may be lost, so be careful when calling this function
|
|
|
|
// on a database that contains important information.
|
|
|
|
Status RepairDB(const std::string& dbname, const Options& options);
|
|
|
|
|
2011-10-31 18:22:06 +01:00
|
|
|
} // namespace leveldb
|
2011-03-18 23:37:00 +01:00
|
|
|
|
|
|
|
#endif // STORAGE_LEVELDB_INCLUDE_DB_H_
|