Re: [PATCH] xfs: introduce "metasync" api to sync metadata to fsblock

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Sun, Oct 13, 2019 at 10:37:00PM +0800, Pingfan Liu wrote:
> When using fadump (fireware assist dump) mode on powerpc, a mismatch
> between grub xfs driver and kernel xfs driver has been obsevered.  Note:
> fadump boots up in the following sequence: fireware -> grub reads kernel
> and initramfs -> kernel boots.
> 
> The process to reproduce this mismatch:
>   - On powerpc, boot kernel with fadump=on and edit /etc/kdump.conf.
>   - Replacing "path /var/crash" with "path /var/crashnew", then, "kdumpctl
>     restart" to rebuild the initramfs. Detail about the rebuilding looks
>     like: mkdumprd /boot/initramfs-`uname -r`.img.tmp;
>           mv /boot/initramfs-`uname -r`.img.tmp /boot/initramfs-`uname -r`.img
>           sync
>   - "echo c >/proc/sysrq-trigger".
> 
> The result:
> The dump image will not be saved under /var/crashnew/* as expected, but
> still saved under /var/crash.
> 
> The root cause:
> As Eric pointed out that on xfs, 'sync' ensures the consistency by writing
> back metadata to xlog, but not necessary to fsblock. This raises issue if
> grub can not replay the xlog before accessing the xfs files. Since the
> above dir entry of initramfs should be saved as inline data with xfs_inode,
> so xfs_fs_sync_fs() does not guarantee it written to fsblock.
> 
> umount can be used to write metadata fsblock, but the filesystem can not be
> umounted if still in use.
> 
> There are two ways to fix this mismatch, either grub or xfs. It may be
> easier to do this in xfs side by introducing an interface to flush metadata
> to fsblock explicitly.
> 
> With this patch, metadata can be written to fsblock by:
>   # update AIL
>   sync
>   # new introduced interface to flush metadata to fsblock
>   mount -o remount,metasync mountpoint

I think this ought to be an ioctl or some sort of generic call since the
jbd2 filesystems (ext3, ext4, ocfs2) suffer from the same "$BOOTLOADER
is too dumb to recover logs but still wants to write to the fs"
checkpointing problem.

(Or maybe we should just put all that stuff in a vfat filesystem, I
don't know...)

--D

> Signed-off-by: Pingfan Liu <kernelfans@xxxxxxxxx>
> Cc: "Darrick J. Wong" <darrick.wong@xxxxxxxxxx>
> Cc: Dave Chinner <dchinner@xxxxxxxxxx>
> Cc: Eric Sandeen <esandeen@xxxxxxxxxx>
> Cc: Hari Bathini <hbathini@xxxxxxxxxxxxx>
> Cc: linuxppc-dev@xxxxxxxxxxxxxxxx
> To: linux-xfs@xxxxxxxxxxxxxxx
> ---
>  fs/xfs/xfs_mount.h      |  1 +
>  fs/xfs/xfs_super.c      | 15 ++++++++++++++-
>  fs/xfs/xfs_trans.h      |  2 ++
>  fs/xfs/xfs_trans_ail.c  | 26 +++++++++++++++++++++++++-
>  fs/xfs/xfs_trans_priv.h |  1 +
>  5 files changed, 43 insertions(+), 2 deletions(-)
> 
> diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
> index fdb60e0..85f32e6 100644
> --- a/fs/xfs/xfs_mount.h
> +++ b/fs/xfs/xfs_mount.h
> @@ -243,6 +243,7 @@ typedef struct xfs_mount {
>  #define XFS_MOUNT_FILESTREAMS	(1ULL << 24)	/* enable the filestreams
>  						   allocator */
>  #define XFS_MOUNT_NOATTR2	(1ULL << 25)	/* disable use of attr2 format */
> +#define XFS_MOUNT_METASYNC	(1ull << 26)	/* write meta to fsblock */
>  
>  #define XFS_MOUNT_DAX		(1ULL << 62)	/* TEST ONLY! */
>  
> diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
> index 8d1df9f..41df810 100644
> --- a/fs/xfs/xfs_super.c
> +++ b/fs/xfs/xfs_super.c
> @@ -59,7 +59,7 @@ enum {
>  	Opt_filestreams, Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota,
>  	Opt_prjquota, Opt_uquota, Opt_gquota, Opt_pquota,
>  	Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce,
> -	Opt_discard, Opt_nodiscard, Opt_dax, Opt_err,
> +	Opt_discard, Opt_nodiscard, Opt_dax, Opt_metasync, Opt_err
>  };
>  
>  static const match_table_t tokens = {
> @@ -106,6 +106,7 @@ static const match_table_t tokens = {
>  	{Opt_discard,	"discard"},	/* Discard unused blocks */
>  	{Opt_nodiscard,	"nodiscard"},	/* Do not discard unused blocks */
>  	{Opt_dax,	"dax"},		/* Enable direct access to bdev pages */
> +	{Opt_metasync,	"metasync"},	/* one shot to write meta to fsblock */
>  	{Opt_err,	NULL},
>  };
>  
> @@ -338,6 +339,9 @@ xfs_parseargs(
>  			mp->m_flags |= XFS_MOUNT_DAX;
>  			break;
>  #endif
> +		case Opt_metasync:
> +			mp->m_flags |= XFS_MOUNT_METASYNC;
> +			break;
>  		default:
>  			xfs_warn(mp, "unknown mount option [%s].", p);
>  			return -EINVAL;
> @@ -1259,6 +1263,9 @@ xfs_fs_remount(
>  			mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
>  			mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
>  			break;
> +		case Opt_metasync:
> +			mp->m_flags |= XFS_MOUNT_METASYNC;
> +			break;
>  		default:
>  			/*
>  			 * Logically we would return an error here to prevent
> @@ -1286,6 +1293,12 @@ xfs_fs_remount(
>  		}
>  	}
>  
> +	if (mp->m_flags & XFS_MOUNT_METASYNC) {
> +		xfs_ail_push_sync(mp->m_ail);
> +		/* one shot flag */
> +		mp->m_flags &= ~XFS_MOUNT_METASYNC;

Wait, so the mount flag magically disables itself?

This really sounds like a system call, not the kinds of long term
behavioral modifications that mount options are for.

> +	}
> +
>  	/* ro -> rw */
>  	if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & SB_RDONLY)) {
>  		if (mp->m_flags & XFS_MOUNT_NORECOVERY) {
> diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
> index 64d7f17..fcdb902 100644
> --- a/fs/xfs/xfs_trans.h
> +++ b/fs/xfs/xfs_trans.h
> @@ -242,6 +242,8 @@ void		xfs_trans_buf_set_type(struct xfs_trans *, struct xfs_buf *,
>  void		xfs_trans_buf_copy_type(struct xfs_buf *dst_bp,
>  					struct xfs_buf *src_bp);
>  
> +void		xfs_ail_push_sync(struct xfs_ail *ailp);
> +
>  extern kmem_zone_t	*xfs_trans_zone;
>  
>  #endif	/* __XFS_TRANS_H__ */
> diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
> index 6ccfd75..b8d8df1 100644
> --- a/fs/xfs/xfs_trans_ail.c
> +++ b/fs/xfs/xfs_trans_ail.c
> @@ -488,7 +488,11 @@ xfsaild_push(
>  	xfs_trans_ail_cursor_done(&cur);
>  	spin_unlock(&ailp->ail_lock);
>  
> -	if (xfs_buf_delwri_submit_nowait(&ailp->ail_buf_list))
> +	if (unlikely(mp->m_flags & XFS_MOUNT_METASYNC)) {
> +		xfs_buf_delwri_submit(&ailp->ail_buf_list);

I guess this never fails, because write IO is 100% successful?

--D

> +		ailp->ail_log_flush++;
> +		wake_up_all(&ailp->pushed_que);
> +	} else if (xfs_buf_delwri_submit_nowait(&ailp->ail_buf_list))
>  		ailp->ail_log_flush++;
>  
>  	if (!count || XFS_LSN_CMP(lsn, target) >= 0) {
> @@ -641,6 +645,25 @@ xfs_ail_push(
>  	wake_up_process(ailp->ail_task);
>  }
>  
> +void
> +xfs_ail_push_sync(
> +	struct xfs_ail		*ailp)
> +{
> +	xfs_lsn_t		sync_lsn;
> +	DEFINE_WAIT(wait);
> +
> +	sync_lsn = xfs_ail_max_lsn(ailp);
> +	for (;;) {
> +		xfs_ail_push(ailp, sync_lsn);
> +		prepare_to_wait(&ailp->pushed_que, &wait, TASK_INTERRUPTIBLE);
> +		if (XFS_LSN_CMP(READ_ONCE(ailp->ail_target_prev),
> +			sync_lsn) >= 0)
> +			break;
> +		schedule();
> +	}
> +	finish_wait(&ailp->pushed_que, &wait);
> +}
> +
>  /*
>   * Push out all items in the AIL immediately
>   */
> @@ -834,6 +857,7 @@ xfs_trans_ail_init(
>  	spin_lock_init(&ailp->ail_lock);
>  	INIT_LIST_HEAD(&ailp->ail_buf_list);
>  	init_waitqueue_head(&ailp->ail_empty);
> +	init_waitqueue_head(&ailp->pushed_que);
>  
>  	ailp->ail_task = kthread_run(xfsaild, ailp, "xfsaild/%s",
>  			ailp->ail_mount->m_fsname);
> diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
> index 2e073c1..9fe3cc6 100644
> --- a/fs/xfs/xfs_trans_priv.h
> +++ b/fs/xfs/xfs_trans_priv.h
> @@ -61,6 +61,7 @@ struct xfs_ail {
>  	int			ail_log_flush;
>  	struct list_head	ail_buf_list;
>  	wait_queue_head_t	ail_empty;
> +	wait_queue_head_t	pushed_que;
>  };
>  
>  /*
> -- 
> 2.7.5
> 



[Index of Archives]     [XFS Filesystem Development (older mail)]     [Linux Filesystem Development]     [Linux Audio Users]     [Yosemite Trails]     [Linux Kernel]     [Linux RAID]     [Linux SCSI]


  Powered by Linux