kernel-fxtec-pro1x/fs/xfs/linux-2.6/xfs_vfs.h

103 lines
4.1 KiB
C
Raw Normal View History

/*
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* All Rights Reserved.
*
* This program 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.
*
* This program is distributed in the hope that it would 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 this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#ifndef __XFS_VFS_H__
#define __XFS_VFS_H__
#include <linux/vfs.h>
#include "xfs_fs.h"
struct bhv_vfs;
struct inode;
struct fid;
struct cred;
struct seq_file;
struct super_block;
struct xfs_inode;
struct xfs_mount;
struct xfs_mount_args;
typedef struct kstatfs bhv_statvfs_t;
typedef struct bhv_vfs_sync_work {
struct list_head w_list;
struct bhv_vfs *w_vfs;
void *w_data; /* syncer routine argument */
void (*w_syncer)(struct bhv_vfs *, void *);
} bhv_vfs_sync_work_t;
typedef struct bhv_vfs {
struct xfs_mount *vfs_mount;
u_int vfs_flag; /* flags */
struct super_block *vfs_super; /* generic superblock pointer */
struct task_struct *vfs_sync_task; /* generalised sync thread */
bhv_vfs_sync_work_t vfs_sync_work; /* work item for VFS_SYNC */
struct list_head vfs_sync_list; /* sync thread work item list */
spinlock_t vfs_sync_lock; /* work item list lock */
int vfs_sync_seq; /* sync thread generation no. */
wait_queue_head_t vfs_wait_single_sync_task;
} bhv_vfs_t;
#define VFS_RDONLY 0x0001 /* read-only vfs */
#define VFS_GRPID 0x0002 /* group-ID assigned from directory */
#define VFS_DMI 0x0004 /* filesystem has the DMI enabled */
/* ---- VFS_UMOUNT ---- 0x0008 -- unneeded, fixed via kthread APIs */
#define VFS_32BITINODES 0x0010 /* do not use inums above 32 bits */
#define VFS_END 0x0010 /* max flag */
#define SYNC_ATTR 0x0001 /* sync attributes */
#define SYNC_CLOSE 0x0002 /* close file system down */
#define SYNC_DELWRI 0x0004 /* look at delayed writes */
#define SYNC_WAIT 0x0008 /* wait for i/o to complete */
#define SYNC_BDFLUSH 0x0010 /* BDFLUSH is calling -- don't block */
#define SYNC_FSDATA 0x0020 /* flush fs data (e.g. superblocks) */
#define SYNC_REFCACHE 0x0040 /* prune some of the nfs ref cache */
#define SYNC_REMOUNT 0x0080 /* remount readonly, no dummy LRs */
#define SYNC_IOWAIT 0x0100 /* wait for all I/O to complete */
[XFS] Lazy Superblock Counters When we have a couple of hundred transactions on the fly at once, they all typically modify the on disk superblock in some way. create/unclink/mkdir/rmdir modify inode counts, allocation/freeing modify free block counts. When these counts are modified in a transaction, they must eventually lock the superblock buffer and apply the mods. The buffer then remains locked until the transaction is committed into the incore log buffer. The result of this is that with enough transactions on the fly the incore superblock buffer becomes a bottleneck. The result of contention on the incore superblock buffer is that transaction rates fall - the more pressure that is put on the superblock buffer, the slower things go. The key to removing the contention is to not require the superblock fields in question to be locked. We do that by not marking the superblock dirty in the transaction. IOWs, we modify the incore superblock but do not modify the cached superblock buffer. In short, we do not log superblock modifications to critical fields in the superblock on every transaction. In fact we only do it just before we write the superblock to disk every sync period or just before unmount. This creates an interesting problem - if we don't log or write out the fields in every transaction, then how do the values get recovered after a crash? the answer is simple - we keep enough duplicate, logged information in other structures that we can reconstruct the correct count after log recovery has been performed. It is the AGF and AGI structures that contain the duplicate information; after recovery, we walk every AGI and AGF and sum their individual counters to get the correct value, and we do a transaction into the log to correct them. An optimisation of this is that if we have a clean unmount record, we know the value in the superblock is correct, so we can avoid the summation walk under normal conditions and so mount/recovery times do not change under normal operation. One wrinkle that was discovered during development was that the blocks used in the freespace btrees are never accounted for in the AGF counters. This was once a valid optimisation to make; when the filesystem is full, the free space btrees are empty and consume no space. Hence when it matters, the "accounting" is correct. But that means the when we do the AGF summations, we would not have a correct count and xfs_check would complain. Hence a new counter was added to track the number of blocks used by the free space btrees. This is an *on-disk format change*. As a result of this, lazy superblock counters are a mkfs option and at the moment on linux there is no way to convert an old filesystem. This is possible - xfs_db can be used to twiddle the right bits and then xfs_repair will do the format conversion for you. Similarly, you can convert backwards as well. At some point we'll add functionality to xfs_admin to do the bit twiddling easily.... SGI-PV: 964999 SGI-Modid: xfs-linux-melb:xfs-kern:28652a Signed-off-by: David Chinner <dgc@sgi.com> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Tim Shimmin <tes@sgi.com>
2007-05-23 23:26:31 -06:00
#define SYNC_SUPER 0x0200 /* flush superblock to disk */
/*
* When remounting a filesystem read-only or freezing the filesystem,
* we have two phases to execute. This first phase is syncing the data
* before we quiesce the fielsystem, and the second is flushing all the
* inodes out after we've waited for all the transactions created by
* the first phase to complete. The second phase uses SYNC_INODE_QUIESCE
* to ensure that the inodes are written to their location on disk
* rather than just existing in transactions in the log. This means
* after a quiesce there is no log replay required to write the inodes
* to disk (this is the main difference between a sync and a quiesce).
*/
#define SYNC_DATA_QUIESCE (SYNC_DELWRI|SYNC_FSDATA|SYNC_WAIT|SYNC_IOWAIT)
#define SYNC_INODE_QUIESCE (SYNC_REMOUNT|SYNC_ATTR|SYNC_WAIT)
#define SHUTDOWN_META_IO_ERROR 0x0001 /* write attempt to metadata failed */
#define SHUTDOWN_LOG_IO_ERROR 0x0002 /* write attempt to the log failed */
#define SHUTDOWN_FORCE_UMOUNT 0x0004 /* shutdown from a forced unmount */
#define SHUTDOWN_CORRUPT_INCORE 0x0008 /* corrupt in-memory data structures */
#define SHUTDOWN_REMOTE_REQ 0x0010 /* shutdown came from remote cell */
#define SHUTDOWN_DEVICE_REQ 0x0020 /* failed all paths to the device */
#define vfs_test_for_freeze(vfs) ((vfs)->vfs_super->s_frozen)
#define vfs_wait_for_freeze(vfs,l) vfs_check_frozen((vfs)->vfs_super, (l))
extern bhv_vfs_t *vfs_allocate(struct super_block *);
extern bhv_vfs_t *vfs_from_sb(struct super_block *);
extern void vfs_deallocate(bhv_vfs_t *);
#endif /* __XFS_VFS_H__ */