![Boaz Harrosh](/assets/img/avatar_default.png)
This patch changes on-disk format, it is accompanied with a parallel patch to mkfs.exofs that enables multi-device capabilities. After this patch, old exofs will refuse to mount a new formatted FS and new exofs will refuse an old format. This is done by moving the magic field offset inside the FSCB. A new FSCB *version* field was added. In the future, exofs will refuse to mount unmatched FSCB version. To up-grade or down-grade an exofs one must use mkfs.exofs --upgrade option before mounting. Introduced, a new object that contains a *device-table*. This object contains the default *data-map* and a linear array of devices information, which identifies the devices used in the filesystem. This object is only written to offline by mkfs.exofs. This is why it is kept separate from the FSCB, since the later is written to while mounted. Same partition number, same object number is used on all devices only the device varies. * define the new format, then load the device table on mount time make sure every thing is supported. * Change I/O engine to now support Mirror IO, .i.e write same data to multiple devices, read from a random device to spread the read-load from multiple clients (TODO: stripe read) Implementation notes: A few points introduced in previous patch should be mentioned here: * Special care was made so absolutlly all operation that have any chance of failing are done before any osd-request is executed. This is to minimize the need for a data consistency recovery, to only real IO errors. * Each IO state has a kref. It starts at 1, any osd-request executed will increment the kref, finally when all are executed the first ref is dropped. At IO-done, each request completion decrements the kref, the last one to return executes the internal _last_io() routine. _last_io() will call the registered io_state_done. On sync mode a caller does not supply a done method, indicating a synchronous request, the caller is put to sleep and a special io_state_done is registered that will awaken the caller. Though also in sync mode all operations are executed in parallel. Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
210 lines
7.1 KiB
C
210 lines
7.1 KiB
C
/*
|
|
* common.h - Common definitions for both Kernel and user-mode utilities
|
|
*
|
|
* Copyright (C) 2005, 2006
|
|
* Avishay Traeger (avishay@gmail.com)
|
|
* Copyright (C) 2008, 2009
|
|
* Boaz Harrosh <bharrosh@panasas.com>
|
|
*
|
|
* Copyrights for code taken from ext2:
|
|
* Copyright (C) 1992, 1993, 1994, 1995
|
|
* Remy Card (card@masi.ibp.fr)
|
|
* Laboratoire MASI - Institut Blaise Pascal
|
|
* Universite Pierre et Marie Curie (Paris VI)
|
|
* from
|
|
* linux/fs/minix/inode.c
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
*
|
|
* This file is part of exofs.
|
|
*
|
|
* exofs is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation. Since it is based on ext2, and the only
|
|
* valid version of GPL for the Linux kernel is version 2, the only valid
|
|
* version of GPL for exofs is version 2.
|
|
*
|
|
* exofs is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with exofs; if not, write to the Free Software
|
|
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
|
|
*/
|
|
|
|
#ifndef __EXOFS_COM_H__
|
|
#define __EXOFS_COM_H__
|
|
|
|
#include <linux/types.h>
|
|
|
|
#include <scsi/osd_attributes.h>
|
|
#include <scsi/osd_initiator.h>
|
|
#include <scsi/osd_sec.h>
|
|
|
|
/****************************************************************************
|
|
* Object ID related defines
|
|
* NOTE: inode# = object ID - EXOFS_OBJ_OFF
|
|
****************************************************************************/
|
|
#define EXOFS_MIN_PID 0x10000 /* Smallest partition ID */
|
|
#define EXOFS_OBJ_OFF 0x10000 /* offset for objects */
|
|
#define EXOFS_SUPER_ID 0x10000 /* object ID for on-disk superblock */
|
|
#define EXOFS_DEVTABLE_ID 0x10001 /* object ID for on-disk device table */
|
|
#define EXOFS_ROOT_ID 0x10002 /* object ID for root directory */
|
|
|
|
/* exofs Application specific page/attribute */
|
|
# define EXOFS_APAGE_FS_DATA (OSD_APAGE_APP_DEFINED_FIRST + 3)
|
|
# define EXOFS_ATTR_INODE_DATA 1
|
|
|
|
/*
|
|
* The maximum number of files we can have is limited by the size of the
|
|
* inode number. This is the largest object ID that the file system supports.
|
|
* Object IDs 0, 1, and 2 are always in use (see above defines).
|
|
*/
|
|
enum {
|
|
EXOFS_MAX_INO_ID = (sizeof(ino_t) * 8 == 64) ? ULLONG_MAX :
|
|
(1ULL << (sizeof(ino_t) * 8ULL - 1ULL)),
|
|
EXOFS_MAX_ID = (EXOFS_MAX_INO_ID - 1 - EXOFS_OBJ_OFF),
|
|
};
|
|
|
|
/****************************************************************************
|
|
* Misc.
|
|
****************************************************************************/
|
|
#define EXOFS_BLKSHIFT 12
|
|
#define EXOFS_BLKSIZE (1UL << EXOFS_BLKSHIFT)
|
|
|
|
/****************************************************************************
|
|
* superblock-related things
|
|
****************************************************************************/
|
|
#define EXOFS_SUPER_MAGIC 0x5DF5
|
|
|
|
/*
|
|
* The file system control block - stored in object EXOFS_SUPER_ID's data.
|
|
* This is where the in-memory superblock is stored on disk.
|
|
*/
|
|
enum {EXOFS_FSCB_VER = 1, EXOFS_DT_VER = 1};
|
|
struct exofs_fscb {
|
|
__le64 s_nextid; /* Highest object ID used */
|
|
__le64 s_numfiles; /* Number of files on fs */
|
|
__le32 s_version; /* == EXOFS_FSCB_VER */
|
|
__le16 s_magic; /* Magic signature */
|
|
__le16 s_newfs; /* Non-zero if this is a new fs */
|
|
|
|
/* From here on it's a static part, only written by mkexofs */
|
|
__le64 s_dev_table_oid; /* Resurved, not used */
|
|
__le64 s_dev_table_count; /* == 0 means no dev_table */
|
|
} __packed;
|
|
|
|
/*
|
|
* Describes the raid used in the FS. It is part of the device table.
|
|
* This here is taken from the pNFS-objects definition. In exofs we
|
|
* use one raid policy through-out the filesystem. (NOTE: the funny
|
|
* alignment at begining. We take care of it at exofs_device_table.
|
|
*/
|
|
struct exofs_dt_data_map {
|
|
__le32 cb_num_comps;
|
|
__le64 cb_stripe_unit;
|
|
__le32 cb_group_width;
|
|
__le32 cb_group_depth;
|
|
__le32 cb_mirror_cnt;
|
|
__le32 cb_raid_algorithm;
|
|
} __packed;
|
|
|
|
/*
|
|
* This is an osd device information descriptor. It is a single entry in
|
|
* the exofs device table. It describes an osd target lun which
|
|
* contains data belonging to this FS. (Same partition_id on all devices)
|
|
*/
|
|
struct exofs_dt_device_info {
|
|
__le32 systemid_len;
|
|
u8 systemid[OSD_SYSTEMID_LEN];
|
|
__le64 long_name_offset; /* If !0 then offset-in-file */
|
|
__le32 osdname_len; /* */
|
|
u8 osdname[44]; /* Embbeded, Ususally an asci uuid */
|
|
} __packed;
|
|
|
|
/*
|
|
* The EXOFS device table - stored in object EXOFS_DEVTABLE_ID's data.
|
|
* It contains the raid used for this multy-device FS and an array of
|
|
* participating devices.
|
|
*/
|
|
struct exofs_device_table {
|
|
__le32 dt_version; /* == EXOFS_DT_VER */
|
|
struct exofs_dt_data_map dt_data_map; /* Raid policy to use */
|
|
|
|
/* Resurved space For future use. Total includeing this:
|
|
* (8 * sizeof(le64))
|
|
*/
|
|
__le64 __Resurved[4];
|
|
|
|
__le64 dt_num_devices; /* Array size */
|
|
struct exofs_dt_device_info dt_dev_table[]; /* Array of devices */
|
|
} __packed;
|
|
|
|
/****************************************************************************
|
|
* inode-related things
|
|
****************************************************************************/
|
|
#define EXOFS_IDATA 5
|
|
|
|
/*
|
|
* The file control block - stored in an object's attributes. This is where
|
|
* the in-memory inode is stored on disk.
|
|
*/
|
|
struct exofs_fcb {
|
|
__le64 i_size; /* Size of the file */
|
|
__le16 i_mode; /* File mode */
|
|
__le16 i_links_count; /* Links count */
|
|
__le32 i_uid; /* Owner Uid */
|
|
__le32 i_gid; /* Group Id */
|
|
__le32 i_atime; /* Access time */
|
|
__le32 i_ctime; /* Creation time */
|
|
__le32 i_mtime; /* Modification time */
|
|
__le32 i_flags; /* File flags (unused for now)*/
|
|
__le32 i_generation; /* File version (for NFS) */
|
|
__le32 i_data[EXOFS_IDATA]; /* Short symlink names and device #s */
|
|
};
|
|
|
|
#define EXOFS_INO_ATTR_SIZE sizeof(struct exofs_fcb)
|
|
|
|
/* This is the Attribute the fcb is stored in */
|
|
static const struct __weak osd_attr g_attr_inode_data = ATTR_DEF(
|
|
EXOFS_APAGE_FS_DATA,
|
|
EXOFS_ATTR_INODE_DATA,
|
|
EXOFS_INO_ATTR_SIZE);
|
|
|
|
/****************************************************************************
|
|
* dentry-related things
|
|
****************************************************************************/
|
|
#define EXOFS_NAME_LEN 255
|
|
|
|
/*
|
|
* The on-disk directory entry
|
|
*/
|
|
struct exofs_dir_entry {
|
|
__le64 inode_no; /* inode number */
|
|
__le16 rec_len; /* directory entry length */
|
|
u8 name_len; /* name length */
|
|
u8 file_type; /* umm...file type */
|
|
char name[EXOFS_NAME_LEN]; /* file name */
|
|
};
|
|
|
|
enum {
|
|
EXOFS_FT_UNKNOWN,
|
|
EXOFS_FT_REG_FILE,
|
|
EXOFS_FT_DIR,
|
|
EXOFS_FT_CHRDEV,
|
|
EXOFS_FT_BLKDEV,
|
|
EXOFS_FT_FIFO,
|
|
EXOFS_FT_SOCK,
|
|
EXOFS_FT_SYMLINK,
|
|
EXOFS_FT_MAX
|
|
};
|
|
|
|
#define EXOFS_DIR_PAD 4
|
|
#define EXOFS_DIR_ROUND (EXOFS_DIR_PAD - 1)
|
|
#define EXOFS_DIR_REC_LEN(name_len) \
|
|
(((name_len) + offsetof(struct exofs_dir_entry, name) + \
|
|
EXOFS_DIR_ROUND) & ~EXOFS_DIR_ROUND)
|
|
|
|
#endif /*ifndef __EXOFS_COM_H__*/
|