/** @file lmdb.h
* @brief Lightning memory-mapped database library
*
- * @mainpage Lightning Memory-Mapped Database Manager (MDB)
+ * @mainpage Lightning Memory-Mapped Database Manager (LMDB)
*
* @section intro_sec Introduction
- * MDB is a Btree-based database management library modeled loosely on the
+ * LMDB is a Btree-based database management library modeled loosely on the
* BerkeleyDB API, but much simplified. The entire database is exposed
* in a memory map, and all data fetches return data directly
* from the mapped memory, so no malloc's or memcpy's occur during
* readers, and readers don't block writers.
*
* Unlike other well-known database mechanisms which use either write-ahead
- * transaction logs or append-only data writes, MDB requires no maintenance
+ * transaction logs or append-only data writes, LMDB requires no maintenance
* during operation. Both write-ahead loggers and append-only databases
* require periodic checkpointing and/or compaction of their log or database
- * files otherwise they grow without bound. MDB tracks free pages within
+ * files otherwise they grow without bound. LMDB tracks free pages within
* the database and re-uses them for new write operations, so the database
* size does not grow without bound in normal use.
*
* corrupt the database. Of course if your application code is known to
* be bug-free (...) then this is not an issue.
*
+ * If this is your first time using a transactional embedded key/value
+ * store, you may find the \ref starting page to be helpful.
+ *
* @section caveats_sec Caveats
* Troubleshooting the lock file, plus semaphores on BSD systems:
*
* cause further writes to grow the database quickly, and
* stale locks can block further operation.
*
- * Fix: Terminate all programs using the database, or make
- * them close it. Next database user will reset the lockfile.
+ * Fix: Check for stale readers periodically, using the
+ * #mdb_reader_check function or the \ref mdb_stat_1 "mdb_stat" tool.
+ * Stale writers will be cleared automatically on some systems:
+ * - Windows - automatic
+ * - Linux, systems using POSIX mutexes with Robust option - automatic
+ * - not on BSD, systems using POSIX semaphores.
+ * Otherwise just make all programs using the database close it;
+ * the lockfile is always reset on first open of the environment.
*
* - On BSD systems or others configured with MDB_USE_POSIX_SEM,
* startup can fail due to semaphores owned by another userid.
* BSD systems or when otherwise configured with MDB_USE_POSIX_SEM.
* Multiple users can cause startup to fail later, as noted above.
*
+ * - There is normally no pure read-only mode, since readers need write
+ * access to locks and lock file. Exceptions: On read-only filesystems
+ * or with the #MDB_NOLOCK flag described under #mdb_env_open().
+ *
+ * - An LMDB configuration will often reserve considerable \b unused
+ * memory address space and maybe file size for future growth.
+ * This does not use actual memory or disk space, but users may need
+ * to understand the difference so they won't be scared off.
+ *
+ * - By default, in versions before 0.9.10, unused portions of the data
+ * file might receive garbage data from memory freed by other code.
+ * (This does not happen when using the #MDB_WRITEMAP flag.) As of
+ * 0.9.10 the default behavior is to initialize such memory before
+ * writing to the data file. Since there may be a slight performance
+ * cost due to this initialization, applications may disable it using
+ * the #MDB_NOMEMINIT flag. Applications handling sensitive data
+ * which must not be written should not use this flag. This flag is
+ * irrelevant when using #MDB_WRITEMAP.
+ *
* - A thread can only use one transaction at a time, plus any child
* transactions. Each transaction belongs to one thread. See below.
* The #MDB_NOTLS flag changes this for read-only transactions.
*
- * - Use an MDB_env* in the process which opened it, without fork()ing.
+ * - Use an MDB_env* in the process which opened it, not after fork().
*
- * - Do not have open an MDB database twice in the same process at
+ * - Do not have open an LMDB database twice in the same process at
* the same time. Not even from a plain open() call - close()ing it
- * breaks flock() advisory locking.
+ * breaks fcntl() advisory locking. (It is OK to reopen it after
+ * fork() - exec*(), since the lockfile has FD_CLOEXEC set.)
*
* - Avoid long-lived transactions. Read transactions prevent
* reuse of pages freed by newer write transactions, thus the
* ...when several processes can use a database concurrently:
*
* - Avoid aborting a process with an active transaction.
- * The transaction becomes "long-lived" as above until the lockfile
- * is reset, since the process may not remove it from the lockfile.
+ * The transaction becomes "long-lived" as above until a check
+ * for stale readers is performed or the lockfile is reset,
+ * since the process may not remove it from the lockfile.
*
- * - If you do that anyway, close the environment once in a while,
- * so the lockfile can get reset.
+ * This does not apply to write transactions if the system clears
+ * stale writers, see above.
*
- * - Do not use MDB databases on remote filesystems, even between
+ * - If you do that anyway, do a periodic check for stale readers. Or
+ * close the environment once in a while, so the lockfile can get reset.
+ *
+ * - Do not use LMDB databases on remote filesystems, even between
* processes on the same host. This breaks flock() on some OSes,
* possibly memory map sync, and certainly sync between programs
* on different hosts.
*
* @author Howard Chu, Symas Corporation.
*
- * @copyright Copyright 2011-2013 Howard Chu, Symas Corp. All rights reserved.
+ * @copyright Copyright 2011-2017 Howard Chu, Symas Corp. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted only as authorized by the OpenLDAP
typedef int mdb_filehandle_t;
#endif
-/** @defgroup mdb MDB API
+/** @defgroup mdb LMDB API
* @{
* @brief OpenLDAP Lightning Memory-Mapped Database Manager
*/
/** Library minor version */
#define MDB_VERSION_MINOR 9
/** Library patch version */
-#define MDB_VERSION_PATCH 7
+#define MDB_VERSION_PATCH 22
/** Combine args a,b,c into a single integer for easy version comparisons */
#define MDB_VERINT(a,b,c) (((a) << 24) | ((b) << 16) | (c))
MDB_VERINT(MDB_VERSION_MAJOR,MDB_VERSION_MINOR,MDB_VERSION_PATCH)
/** The release date of this library version */
-#define MDB_VERSION_DATE "January 10, 2013"
+#define MDB_VERSION_DATE "March 21, 2018"
/** A stringifier for the version info */
-#define MDB_VERSTR(a,b,c,d) "MDB " #a "." #b "." #c ": (" d ")"
+#define MDB_VERSTR(a,b,c,d) "LMDB " #a "." #b "." #c ": (" d ")"
/** A helper for the stringifier macro */
#define MDB_VERFOO(a,b,c,d) MDB_VERSTR(a,b,c,d)
/** @brief Generic structure used for passing keys and data in and out
* of the database.
*
- * Key sizes must be between 1 and the liblmdb build-time constant
- * #MDB_MAXKEYSIZE inclusive. This currently defaults to 511. The
- * same applies to data sizes in databases with the #MDB_DUPSORT flag.
- * Other data items can in theory be from 0 to 0xffffffff bytes long.
- *
* Values returned from the database are valid only until a subsequent
- * update operation, or the end of the transaction.
+ * update operation, or the end of the transaction. Do not modify or
+ * free them, they commonly point into the database itself.
+ *
+ * Key sizes must be between 1 and #mdb_env_get_maxkeysize() inclusive.
+ * The same applies to data sizes in databases with the #MDB_DUPSORT flag.
+ * Other data items can in theory be from 0 to 0xffffffff bytes long.
*/
typedef struct MDB_val {
size_t mv_size; /**< size of the data item */
typedef void (MDB_rel_func)(MDB_val *item, void *oldptr, void *newptr, void *relctx);
/** @defgroup mdb_env Environment Flags
- *
- * Values do not overlap Database Flags.
* @{
*/
/** mmap at a fixed address (experimental) */
#define MDB_NOMETASYNC 0x40000
/** use writable mmap */
#define MDB_WRITEMAP 0x80000
- /** use asynchronous msync when MDB_WRITEMAP is used */
+ /** use asynchronous msync when #MDB_WRITEMAP is used */
#define MDB_MAPASYNC 0x100000
/** tie reader locktable slots to #MDB_txn objects instead of to threads */
#define MDB_NOTLS 0x200000
+ /** don't do any locking, caller must manage their own locks */
+#define MDB_NOLOCK 0x400000
+ /** don't do readahead (no effect on Windows) */
+#define MDB_NORDAHEAD 0x800000
+ /** don't initialize malloc'd memory before writing to datafile */
+#define MDB_NOMEMINIT 0x1000000
/** @} */
/** @defgroup mdb_dbi_open Database Flags
- *
- * Values do not overlap Environment Flags.
* @{
*/
/** use reverse string keys */
#define MDB_REVERSEKEY 0x02
/** use sorted duplicates */
#define MDB_DUPSORT 0x04
- /** numeric keys in native byte order.
+ /** numeric keys in native byte order: either unsigned int or size_t.
* The keys must all be of the same size. */
#define MDB_INTEGERKEY 0x08
/** with #MDB_DUPSORT, sorted dup items have fixed size */
#define MDB_DUPFIXED 0x10
- /** with #MDB_DUPSORT, dups are numeric in native byte order */
+ /** with #MDB_DUPSORT, dups are #MDB_INTEGERKEY-style integers */
#define MDB_INTEGERDUP 0x20
/** with #MDB_DUPSORT, use reverse string dups */
#define MDB_REVERSEDUP 0x40
#define MDB_MULTIPLE 0x80000
/* @} */
+/** @defgroup mdb_copy Copy Flags
+ * @{
+ */
+/** Compacting copy: Omit free space from copy, and renumber all
+ * pages sequentially.
+ */
+#define MDB_CP_COMPACT 0x01
+/* @} */
+
/** @brief Cursor Get operations.
*
* This is the set of all operations for retrieving data
MDB_GET_BOTH, /**< Position at key/data pair. Only for #MDB_DUPSORT */
MDB_GET_BOTH_RANGE, /**< position at key, nearest data. Only for #MDB_DUPSORT */
MDB_GET_CURRENT, /**< Return key/data at current cursor position */
- MDB_GET_MULTIPLE, /**< Return all the duplicate data items at the current
- cursor position. Only for #MDB_DUPFIXED */
+ MDB_GET_MULTIPLE, /**< Return key and up to a page of duplicate data items
+ from current cursor position. Move cursor to prepare
+ for #MDB_NEXT_MULTIPLE. Only for #MDB_DUPFIXED */
MDB_LAST, /**< Position at last key/data item */
MDB_LAST_DUP, /**< Position at last data item of current key.
Only for #MDB_DUPSORT */
MDB_NEXT, /**< Position at next data item */
MDB_NEXT_DUP, /**< Position at next data item of current key.
Only for #MDB_DUPSORT */
- MDB_NEXT_MULTIPLE, /**< Return all duplicate data items at the next
- cursor position. Only for #MDB_DUPFIXED */
+ MDB_NEXT_MULTIPLE, /**< Return key and up to a page of duplicate data items
+ from next cursor position. Move cursor to prepare
+ for #MDB_NEXT_MULTIPLE. Only for #MDB_DUPFIXED */
MDB_NEXT_NODUP, /**< Position at first data item of next key */
MDB_PREV, /**< Position at previous data item */
MDB_PREV_DUP, /**< Position at previous data item of current key.
MDB_PREV_NODUP, /**< Position at last data item of previous key */
MDB_SET, /**< Position at specified key */
MDB_SET_KEY, /**< Position at specified key, return key + data */
- MDB_SET_RANGE /**< Position at first key greater than or equal to specified key. */
+ MDB_SET_RANGE, /**< Position at first key greater than or equal to specified key. */
+ MDB_PREV_MULTIPLE /**< Position at previous page and return key and up to
+ a page of duplicate data items. Only for #MDB_DUPFIXED */
} MDB_cursor_op;
/** @defgroup errors Return Codes
#define MDB_PAGE_NOTFOUND (-30797)
/** Located page was wrong type */
#define MDB_CORRUPTED (-30796)
- /** Update of meta page failed, probably I/O error */
+ /** Update of meta page failed or environment had fatal error */
#define MDB_PANIC (-30795)
/** Environment version mismatch */
#define MDB_VERSION_MISMATCH (-30794)
- /** File is not a valid MDB file */
+ /** File is not a valid LMDB file */
#define MDB_INVALID (-30793)
/** Environment mapsize reached */
#define MDB_MAP_FULL (-30792)
#define MDB_PAGE_FULL (-30786)
/** Database contents grew beyond environment mapsize */
#define MDB_MAP_RESIZED (-30785)
- /** Database flags changed or would change */
+ /** Operation and DB incompatible, or DB type changed. This can mean:
+ * <ul>
+ * <li>The operation expects an #MDB_DUPSORT / #MDB_DUPFIXED database.
+ * <li>Opening a named DB when the unnamed DB has #MDB_DUPSORT / #MDB_INTEGERKEY.
+ * <li>Accessing a data record as a database, or vice versa.
+ * <li>The database was dropped and recreated with different flags.
+ * </ul>
+ */
#define MDB_INCOMPATIBLE (-30784)
/** Invalid reuse of reader locktable slot */
#define MDB_BAD_RSLOT (-30783)
- /** Transaction cannot recover - it must be aborted */
+ /** Transaction must abort, has a child, or is invalid */
#define MDB_BAD_TXN (-30782)
- /** Too big key/data, key is empty, or wrong DUPFIXED size */
+ /** Unsupported size of key/DB name/data, or wrong DUPFIXED size */
#define MDB_BAD_VALSIZE (-30781)
-#define MDB_LAST_ERRCODE MDB_BAD_VALSIZE
+ /** The specified DBI was changed unexpectedly */
+#define MDB_BAD_DBI (-30780)
+ /** The last defined error code */
+#define MDB_LAST_ERRCODE MDB_BAD_DBI
/** @} */
/** @brief Statistics for a database in the environment */
unsigned int me_numreaders; /**< max reader slots used in the environment */
} MDB_envinfo;
- /** @brief Return the mdb library version information.
+ /** @brief Return the LMDB library version information.
*
* @param[out] major if non-NULL, the library major version number is copied here
* @param[out] minor if non-NULL, the library minor version number is copied here
* This function is a superset of the ANSI C X3.159-1989 (ANSI C) strerror(3)
* function. If the error code is greater than or equal to 0, then the string
* returned by the system function strerror(3) is returned. If the error code
- * is less than 0, an error string corresponding to the MDB library error is
- * returned. See @ref errors for a list of MDB-specific error codes.
+ * is less than 0, an error string corresponding to the LMDB library error is
+ * returned. See @ref errors for a list of LMDB-specific error codes.
* @param[in] err The error code
* @retval "error message" The description of the error
*/
char *mdb_strerror(int err);
- /** @brief Create an MDB environment handle.
+ /** @brief Create an LMDB environment handle.
*
* This function allocates memory for a #MDB_env structure. To release
* the allocated memory and discard the handle, call #mdb_env_close().
* how the operating system has allocated memory to shared libraries and other uses.
* The feature is highly experimental.
* <li>#MDB_NOSUBDIR
- * By default, MDB creates its environment in a directory whose
+ * By default, LMDB creates its environment in a directory whose
* pathname is given in \b path, and creates its data and lock files
* under that directory. With this option, \b path is used as-is for
* the database main data file. The database lock file is the \b path
* with "-lock" appended.
* <li>#MDB_RDONLY
* Open the environment in read-only mode. No write operations will be
- * allowed. MDB will still modify the lock file - except on read-only
- * filesystems, where MDB does not use locks.
+ * allowed. LMDB will still modify the lock file - except on read-only
+ * filesystems, where LMDB does not use locks.
* <li>#MDB_WRITEMAP
- * Use a writeable memory map unless MDB_RDONLY is set. This is faster
- * and uses fewer mallocs, but loses protection from application bugs
+ * Use a writeable memory map unless MDB_RDONLY is set. This uses
+ * fewer mallocs but loses protection from application bugs
* like wild pointer writes and other bad updates into the database.
+ * This may be slightly faster for DBs that fit entirely in RAM, but
+ * is slower for DBs larger than RAM.
* Incompatible with nested transactions.
+ * Do not mix processes with and without MDB_WRITEMAP on the same
+ * environment. This can defeat durability (#mdb_env_sync etc).
* <li>#MDB_NOMETASYNC
* Flush system buffers to disk only once per transaction, omit the
* metadata flush. Defer that until the system flushes files to disk,
* the user synchronizes its use. Applications that multiplex many
* user threads over individual OS threads need this option. Such an
* application must also serialize the write transactions in an OS
- * thread, since MDB's write locking is unaware of the user threads.
+ * thread, since LMDB's write locking is unaware of the user threads.
+ * <li>#MDB_NOLOCK
+ * Don't do any locking. If concurrent access is anticipated, the
+ * caller must manage all concurrency itself. For proper operation
+ * the caller must enforce single-writer semantics, and must ensure
+ * that no readers are using old transactions while a writer is
+ * active. The simplest approach is to use an exclusive lock so that
+ * no readers may be active at all when a writer begins.
+ * <li>#MDB_NORDAHEAD
+ * Turn off readahead. Most operating systems perform readahead on
+ * read requests by default. This option turns it off if the OS
+ * supports it. Turning it off may help random read performance
+ * when the DB is larger than RAM and system RAM is full.
+ * The option is not implemented on Windows.
+ * <li>#MDB_NOMEMINIT
+ * Don't initialize malloc'd memory before writing to unused spaces
+ * in the data file. By default, memory for pages written to the data
+ * file is obtained using malloc. While these pages may be reused in
+ * subsequent transactions, freshly malloc'd pages will be initialized
+ * to zeroes before use. This avoids persisting leftover data from other
+ * code (that used the heap and subsequently freed the memory) into the
+ * data file. Note that many other system libraries may allocate
+ * and free memory from the heap for arbitrary uses. E.g., stdio may
+ * use the heap for file I/O buffers. This initialization step has a
+ * modest performance cost so some applications may want to disable
+ * it using this flag. This option can be a problem for applications
+ * which handle sensitive data like passwords, and it makes memory
+ * checkers like Valgrind noisy. This flag is not needed with #MDB_WRITEMAP,
+ * which writes directly to the mmap instead of using malloc for pages. The
+ * initialization is also skipped if #MDB_RESERVE is used; the
+ * caller is expected to overwrite all of the memory that was
+ * reserved in that case.
+ * This flag may be changed at any time using #mdb_env_set_flags().
* </ul>
- * @param[in] mode The UNIX permissions to set on created files. This parameter
- * is ignored on Windows.
+ * @param[in] mode The UNIX permissions to set on created files and semaphores.
+ * This parameter is ignored on Windows.
* @return A non-zero error value on failure and 0 on success. Some possible
* errors are:
* <ul>
- * <li>#MDB_VERSION_MISMATCH - the version of the MDB library doesn't match the
+ * <li>#MDB_VERSION_MISMATCH - the version of the LMDB library doesn't match the
* version that created the database environment.
* <li>#MDB_INVALID - the environment file headers are corrupted.
* <li>ENOENT - the directory specified by the path parameter doesn't exist.
*/
int mdb_env_open(MDB_env *env, const char *path, unsigned int flags, mdb_mode_t mode);
- /** @brief Copy an MDB environment to the specified path.
+ /** @brief Copy an LMDB environment to the specified path.
*
* This function may be used to make a backup of an existing environment.
* No lockfile is created, since it gets recreated at need.
*/
int mdb_env_copy(MDB_env *env, const char *path);
- /** @brief Copy an MDB environment to the specified file descriptor.
+ /** @brief Copy an LMDB environment to the specified file descriptor.
*
* This function may be used to make a backup of an existing environment.
* No lockfile is created, since it gets recreated at need.
*/
int mdb_env_copyfd(MDB_env *env, mdb_filehandle_t fd);
- /** @brief Return statistics about the MDB environment.
+ /** @brief Copy an LMDB environment to the specified path, with options.
+ *
+ * This function may be used to make a backup of an existing environment.
+ * No lockfile is created, since it gets recreated at need.
+ * @note This call can trigger significant file size growth if run in
+ * parallel with write transactions, because it employs a read-only
+ * transaction. See long-lived transactions under @ref caveats_sec.
+ * @param[in] env An environment handle returned by #mdb_env_create(). It
+ * must have already been opened successfully.
+ * @param[in] path The directory in which the copy will reside. This
+ * directory must already exist and be writable but must otherwise be
+ * empty.
+ * @param[in] flags Special options for this operation. This parameter
+ * must be set to 0 or by bitwise OR'ing together one or more of the
+ * values described here.
+ * <ul>
+ * <li>#MDB_CP_COMPACT - Perform compaction while copying: omit free
+ * pages and sequentially renumber all pages in output. This option
+ * consumes more CPU and runs more slowly than the default.
+ * Currently it fails if the environment has suffered a page leak.
+ * </ul>
+ * @return A non-zero error value on failure and 0 on success.
+ */
+int mdb_env_copy2(MDB_env *env, const char *path, unsigned int flags);
+
+ /** @brief Copy an LMDB environment to the specified file descriptor,
+ * with options.
+ *
+ * This function may be used to make a backup of an existing environment.
+ * No lockfile is created, since it gets recreated at need. See
+ * #mdb_env_copy2() for further details.
+ * @note This call can trigger significant file size growth if run in
+ * parallel with write transactions, because it employs a read-only
+ * transaction. See long-lived transactions under @ref caveats_sec.
+ * @param[in] env An environment handle returned by #mdb_env_create(). It
+ * must have already been opened successfully.
+ * @param[in] fd The filedescriptor to write the copy to. It must
+ * have already been opened for Write access.
+ * @param[in] flags Special options for this operation.
+ * See #mdb_env_copy2() for options.
+ * @return A non-zero error value on failure and 0 on success.
+ */
+int mdb_env_copyfd2(MDB_env *env, mdb_filehandle_t fd, unsigned int flags);
+
+ /** @brief Return statistics about the LMDB environment.
*
* @param[in] env An environment handle returned by #mdb_env_create()
* @param[out] stat The address of an #MDB_stat structure
*/
int mdb_env_stat(MDB_env *env, MDB_stat *stat);
- /** @brief Return information about the MDB environment.
+ /** @brief Return information about the LMDB environment.
*
* @param[in] env An environment handle returned by #mdb_env_create()
* @param[out] stat The address of an #MDB_envinfo structure
/** @brief Flush the data buffers to disk.
*
* Data is always written to disk when #mdb_txn_commit() is called,
- * but the operating system may keep it buffered. MDB always flushes
+ * but the operating system may keep it buffered. LMDB always flushes
* the OS buffers upon commit as well, unless the environment was
- * opened with #MDB_NOSYNC or in part #MDB_NOMETASYNC.
+ * opened with #MDB_NOSYNC or in part #MDB_NOMETASYNC. This call is
+ * not valid if the environment was opened with #MDB_RDONLY.
* @param[in] env An environment handle returned by #mdb_env_create()
* @param[in] force If non-zero, force a synchronous flush. Otherwise
* if the environment has the #MDB_NOSYNC flag set the flushes
* @return A non-zero error value on failure and 0 on success. Some possible
* errors are:
* <ul>
+ * <li>EACCES - the environment is read-only.
* <li>EINVAL - an invalid parameter was specified.
* <li>EIO - an error occurred during synchronization.
* </ul>
/** @brief Set environment flags.
*
* This may be used to set some flags in addition to those from
- * #mdb_env_open(), or to unset these flags.
+ * #mdb_env_open(), or to unset these flags. If several threads
+ * change the flags at the same time, the result is undefined.
* @param[in] env An environment handle returned by #mdb_env_create()
* @param[in] flags The flags to change, bitwise OR'ed together
* @param[in] onoff A non-zero value sets the flags, zero clears them.
*/
int mdb_env_get_path(MDB_env *env, const char **path);
+ /** @brief Return the filedescriptor for the given environment.
+ *
+ * This function may be called after fork(), so the descriptor can be
+ * closed before exec*(). Other LMDB file descriptors have FD_CLOEXEC.
+ * (Until LMDB 0.9.18, only the lockfile had that.)
+ *
+ * @param[in] env An environment handle returned by #mdb_env_create()
+ * @param[out] fd Address of a mdb_filehandle_t to contain the descriptor.
+ * @return A non-zero error value on failure and 0 on success. Some possible
+ * errors are:
+ * <ul>
+ * <li>EINVAL - an invalid parameter was specified.
+ * </ul>
+ */
+int mdb_env_get_fd(MDB_env *env, mdb_filehandle_t *fd);
+
/** @brief Set the size of the memory map to use for this environment.
*
* The size should be a multiple of the OS page size. The default is
* 10485760 bytes. The size of the memory map is also the maximum size
* of the database. The value should be chosen as large as possible,
* to accommodate future growth of the database.
- * This function may only be called after #mdb_env_create() and before #mdb_env_open().
- * The size may be changed by closing and reopening the environment.
+ * This function should be called after #mdb_env_create() and before #mdb_env_open().
+ * It may be called at later times if no transactions are active in
+ * this process. Note that the library does not check for this condition,
+ * the caller must ensure it explicitly.
+ *
+ * The new size takes effect immediately for the current process but
+ * will not be persisted to any others until a write transaction has been
+ * committed by the current process. Also, only mapsize increases are
+ * persisted into the environment.
+ *
+ * If the mapsize is increased by another process, and data has grown
+ * beyond the range of the current mapsize, #mdb_txn_begin() will
+ * return #MDB_MAP_RESIZED. This function may be called with a size
+ * of zero to adopt the new size.
+ *
* Any attempt to set a size smaller than the space already consumed
* by the environment will be silently changed to the current size of the used space.
* @param[in] env An environment handle returned by #mdb_env_create()
* @return A non-zero error value on failure and 0 on success. Some possible
* errors are:
* <ul>
- * <li>EINVAL - an invalid parameter was specified, or the environment is already open.
+ * <li>EINVAL - an invalid parameter was specified, or the environment has
+ * an active write transaction.
* </ul>
*/
int mdb_env_set_mapsize(MDB_env *env, size_t size);
* environment. Simpler applications that use the environment as a single
* unnamed database can ignore this option.
* This function may only be called after #mdb_env_create() and before #mdb_env_open().
+ *
+ * Currently a moderate number of slots are cheap but a huge number gets
+ * expensive: 7-120 words per transaction, and every #mdb_dbi_open()
+ * does a linear search of the opened slots.
* @param[in] env An environment handle returned by #mdb_env_create()
* @param[in] dbs The maximum number of databases
* @return A non-zero error value on failure and 0 on success. Some possible
*/
int mdb_env_set_maxdbs(MDB_env *env, MDB_dbi dbs);
+ /** @brief Get the maximum size of keys and #MDB_DUPSORT data we can write.
+ *
+ * Depends on the compile-time constant #MDB_MAXKEYSIZE. Default 511.
+ * See @ref MDB_val.
+ * @param[in] env An environment handle returned by #mdb_env_create()
+ * @return The maximum size of a key we can write
+ */
+int mdb_env_get_maxkeysize(MDB_env *env);
+
+ /** @brief Set application information associated with the #MDB_env.
+ *
+ * @param[in] env An environment handle returned by #mdb_env_create()
+ * @param[in] ctx An arbitrary pointer for whatever the application needs.
+ * @return A non-zero error value on failure and 0 on success.
+ */
+int mdb_env_set_userctx(MDB_env *env, void *ctx);
+
+ /** @brief Get the application information associated with the #MDB_env.
+ *
+ * @param[in] env An environment handle returned by #mdb_env_create()
+ * @return The pointer set by #mdb_env_set_userctx().
+ */
+void *mdb_env_get_userctx(MDB_env *env);
+
+ /** @brief A callback function for most LMDB assert() failures,
+ * called before printing the message and aborting.
+ *
+ * @param[in] env An environment handle returned by #mdb_env_create().
+ * @param[in] msg The assertion message, not including newline.
+ */
+typedef void MDB_assert_func(MDB_env *env, const char *msg);
+
+ /** Set or reset the assert() callback of the environment.
+ * Disabled if liblmdb is buillt with NDEBUG.
+ * @note This hack should become obsolete as lmdb's error handling matures.
+ * @param[in] env An environment handle returned by #mdb_env_create().
+ * @param[in] func An #MDB_assert_func function, or 0.
+ * @return A non-zero error value on failure and 0 on success.
+ */
+int mdb_env_set_assert(MDB_env *env, MDB_assert_func *func);
+
/** @brief Create a transaction for use with the environment.
*
* The transaction handle may be discarded using #mdb_txn_abort() or #mdb_txn_commit().
* <li>#MDB_PANIC - a fatal error occurred earlier and the environment
* must be shut down.
* <li>#MDB_MAP_RESIZED - another process wrote data beyond this MDB_env's
- * mapsize and the environment must be shut down.
+ * mapsize and this environment's map must be resized as well.
+ * See #mdb_env_set_mapsize().
* <li>#MDB_READERS_FULL - a read-only transaction was requested and
* the reader lock table is full. See #mdb_env_set_maxreaders().
* <li>ENOMEM - out of memory.
*/
int mdb_txn_begin(MDB_env *env, MDB_txn *parent, unsigned int flags, MDB_txn **txn);
+ /** @brief Returns the transaction's #MDB_env
+ *
+ * @param[in] txn A transaction handle returned by #mdb_txn_begin()
+ */
+MDB_env *mdb_txn_env(MDB_txn *txn);
+
+ /** @brief Return the transaction's ID.
+ *
+ * This returns the identifier associated with this transaction. For a
+ * read-only transaction, this corresponds to the snapshot being read;
+ * concurrent readers will frequently have the same transaction ID.
+ *
+ * @param[in] txn A transaction handle returned by #mdb_txn_begin()
+ * @return A transaction ID, valid if input is an active transaction.
+ */
+size_t mdb_txn_id(MDB_txn *txn);
+
/** @brief Commit all the operations of a transaction into the database.
*
* The transaction handle is freed. It and its cursors must not be used
* independently of whether such a database exists.
* The database handle may be discarded by calling #mdb_dbi_close().
* The old database handle is returned if the database was already open.
- * The handle must only be closed once.
+ * The handle may only be closed once.
+ *
* The database handle will be private to the current transaction until
* the transaction is successfully committed. If the transaction is
* aborted the handle will be closed automatically.
- * After a successful commit the
- * handle will reside in the shared environment, and may be used
- * by other transactions. This function must not be called from
- * multiple concurrent transactions. A transaction that uses this function
- * must finish (either commit or abort) before any other transaction may
- * use this function.
+ * After a successful commit the handle will reside in the shared
+ * environment, and may be used by other transactions.
+ *
+ * This function must not be called from multiple concurrent
+ * transactions in the same process. A transaction that uses
+ * this function must finish (either commit or abort) before
+ * any other transaction in the process may use this function.
*
* To use named databases (with name != NULL), #mdb_env_set_maxdbs()
- * must be called before opening the environment.
+ * must be called before opening the environment. Database names are
+ * keys in the unnamed database, and may be read but not written.
+ *
* @param[in] txn A transaction handle returned by #mdb_txn_begin()
* @param[in] name The name of the database to open. If only a single
* database is needed in the environment, this value may be NULL.
* keys may have multiple data items, stored in sorted order.) By default
* keys must be unique and may have only a single data item.
* <li>#MDB_INTEGERKEY
- * Keys are binary integers in native byte order. Setting this option
- * requires all keys to be the same size, typically sizeof(int)
- * or sizeof(size_t).
+ * Keys are binary integers in native byte order, either unsigned int
+ * or size_t, and will be sorted as such.
+ * The keys must all be of the same size.
* <li>#MDB_DUPFIXED
* This flag may only be used in combination with #MDB_DUPSORT. This option
* tells the library that the data items for this database are all the same
* size, which allows further optimizations in storage and retrieval. When
- * all data items are the same size, the #MDB_GET_MULTIPLE and #MDB_NEXT_MULTIPLE
- * cursor operations may be used to retrieve multiple items at once.
+ * all data items are the same size, the #MDB_GET_MULTIPLE, #MDB_NEXT_MULTIPLE
+ * and #MDB_PREV_MULTIPLE cursor operations may be used to retrieve multiple
+ * items at once.
* <li>#MDB_INTEGERDUP
- * This option specifies that duplicate data items are also integers, and
- * should be sorted as such.
+ * This option specifies that duplicate data items are binary integers,
+ * similar to #MDB_INTEGERKEY keys.
* <li>#MDB_REVERSEDUP
* This option specifies that duplicate data items should be compared as
* strings in reverse order.
/** @brief Retrieve the DB flags for a database handle.
*
- * @param[in] env An environment handle returned by #mdb_env_create()
+ * @param[in] txn A transaction handle returned by #mdb_txn_begin()
* @param[in] dbi A database handle returned by #mdb_dbi_open()
* @param[out] flags Address where the flags will be returned.
* @return A non-zero error value on failure and 0 on success.
*/
-int mdb_dbi_flags(MDB_env *env, MDB_dbi dbi, unsigned int *flags);
+int mdb_dbi_flags(MDB_txn *txn, MDB_dbi dbi, unsigned int *flags);
- /** @brief Close a database handle.
+ /** @brief Close a database handle. Normally unnecessary. Use with care:
*
* This call is not mutex protected. Handles should only be closed by
* a single thread, and only if no other threads are going to reference
* the database handle or one of its cursors any further. Do not close
* a handle if an existing transaction has modified its database.
+ * Doing so can cause misbehavior from database corruption to errors
+ * like MDB_BAD_VALSIZE (since the DB name is gone).
+ *
+ * Closing a database handle is not necessary, but lets #mdb_dbi_open()
+ * reuse the handle value. Usually it's better to set a bigger
+ * #mdb_env_set_maxdbs(), unless that value would be large.
+ *
* @param[in] env An environment handle returned by #mdb_env_create()
* @param[in] dbi A database handle returned by #mdb_dbi_open()
*/
/** @brief Empty or delete+close a database.
*
+ * See #mdb_dbi_close() for restrictions about closing the DB handle.
* @param[in] txn A transaction handle returned by #mdb_txn_begin()
* @param[in] dbi A database handle returned by #mdb_dbi_open()
* @param[in] del 0 to empty the DB, 1 to delete it from the
* reserved space, which the caller can fill in later - before
* the next update operation or the transaction ends. This saves
* an extra memcpy if the data is being generated later.
+ * LMDB does nothing else with this memory, the caller is expected
+ * to modify all of the space requested. This flag must not be
+ * specified if the database was opened with #MDB_DUPSORT.
* <li>#MDB_APPEND - append the given key/data pair to the end of the
- * database. No key comparisons are performed. This option allows
- * fast bulk loading when keys are already known to be in the
- * correct order. Loading unsorted keys with this flag will cause
- * data corruption.
+ * database. This option allows fast bulk loading when keys are
+ * already known to be in the correct order. Loading unsorted keys
+ * with this flag will cause a #MDB_KEYEXIST error.
* <li>#MDB_APPENDDUP - as above, but for sorted dup data.
* </ul>
* @return A non-zero error value on failure and 0 on success. Some possible
/** @brief Store by cursor.
*
* This function stores key/data pairs into the database.
- * If the function fails for any reason, the state of the cursor will be
- * unchanged. If the function succeeds and an item is inserted into the
- * database, the cursor is always positioned to refer to the newly inserted item.
+ * The cursor is positioned at the new item, or on failure usually near it.
+ * @note Earlier documentation incorrectly said errors would leave the
+ * state of the cursor unchanged.
* @param[in] cursor A cursor handle returned by #mdb_cursor_open()
* @param[in] key The key operated on.
* @param[in] data The data operated on.
* @param[in] flags Options for this operation. This parameter
* must be set to 0 or one of the values described here.
* <ul>
- * <li>#MDB_CURRENT - overwrite the data of the key/data pair to which
- * the cursor refers with the specified data item. The \b key
- * parameter is ignored.
+ * <li>#MDB_CURRENT - replace the item at the current cursor position.
+ * The \b key parameter must still be provided, and must match it.
+ * If using sorted duplicates (#MDB_DUPSORT) the data item must still
+ * sort into the same place. This is intended to be used when the
+ * new data is the same size as the old. Otherwise it will simply
+ * perform a delete of the old record followed by an insert.
* <li>#MDB_NODUPDATA - enter the new key/data pair only if it does not
* already appear in the database. This flag may only be specified
* if the database was opened with #MDB_DUPSORT. The function will
* the database supports duplicates (#MDB_DUPSORT).
* <li>#MDB_RESERVE - reserve space for data of the given size, but
* don't copy the given data. Instead, return a pointer to the
- * reserved space, which the caller can fill in later. This saves
- * an extra memcpy if the data is being generated later.
+ * reserved space, which the caller can fill in later - before
+ * the next update operation or the transaction ends. This saves
+ * an extra memcpy if the data is being generated later. This flag
+ * must not be specified if the database was opened with #MDB_DUPSORT.
* <li>#MDB_APPEND - append the given key/data pair to the end of the
* database. No key comparisons are performed. This option allows
* fast bulk loading when keys are already known to be in the
* correct order. Loading unsorted keys with this flag will cause
- * data corruption.
+ * a #MDB_KEYEXIST error.
* <li>#MDB_APPENDDUP - as above, but for sorted dup data.
* <li>#MDB_MULTIPLE - store multiple contiguous data elements in a
* single request. This flag may only be specified if the database
* <ul>
* <li>#MDB_MAP_FULL - the database is full, see #mdb_env_set_mapsize().
* <li>#MDB_TXN_FULL - the transaction has too many dirty pages.
- * <li>EACCES - an attempt was made to modify a read-only database.
+ * <li>EACCES - an attempt was made to write in a read-only transaction.
* <li>EINVAL - an invalid parameter was specified.
* </ul>
*/
* @return A non-zero error value on failure and 0 on success. Some possible
* errors are:
* <ul>
- * <li>EACCES - an attempt was made to modify a read-only database.
+ * <li>EACCES - an attempt was made to write in a read-only transaction.
* <li>EINVAL - an invalid parameter was specified.
* </ul>
*/
*
* @param[in] msg The string to be printed.
* @param[in] ctx An arbitrary context pointer for the callback.
- * @return < 0 on failure, 0 on success.
+ * @return < 0 on failure, >= 0 on success.
*/
typedef int (MDB_msg_func)(const char *msg, void *ctx);
* @param[in] env An environment handle returned by #mdb_env_create()
* @param[in] func A #MDB_msg_func function
* @param[in] ctx Anything the message function needs
- * @return < 0 on failure, 0 on success.
+ * @return < 0 on failure, >= 0 on success.
*/
int mdb_reader_list(MDB_env *env, MDB_msg_func *func, void *ctx);
#ifdef __cplusplus
}
#endif
+/** @page tools LMDB Command Line Tools
+ The following describes the command line tools that are available for LMDB.
+ \li \ref mdb_copy_1
+ \li \ref mdb_dump_1
+ \li \ref mdb_load_1
+ \li \ref mdb_stat_1
+*/
+
#endif /* _LMDB_H_ */
projects / openldap / blobdiff