From 61948b6fb276ad95ad63f82863e607719a31a628 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Wed, 6 May 2020 13:25:21 -0700 Subject: xfs: ratelimit unmount time per-buffer I/O error alert At unmount time, XFS emits an alert for every in-core buffer that might have undergone a write error. In practice this behavior is probably reasonable given that the filesystem is likely short lived once I/O errors begin to occur consistently. Under certain test or otherwise expected error conditions, this can spam the logs and slow down the unmount. Now that we have a ratelimit mechanism specifically for buffer alerts, reuse it for the per-buffer alerts in xfs_wait_buftarg(). Also lift the final repair message out of the loop so it always prints and assert that the metadata error handling code has shut down the fs. Signed-off-by: Brian Foster Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Allison Collins Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_buf.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 594d5e1df6f8..3918270f4eab 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1657,7 +1657,8 @@ xfs_wait_buftarg( struct xfs_buftarg *btp) { LIST_HEAD(dispose); - int loop = 0; + int loop = 0; + bool write_fail = false; /* * First wait on the buftarg I/O count for all in-flight buffers to be @@ -1685,17 +1686,29 @@ xfs_wait_buftarg( bp = list_first_entry(&dispose, struct xfs_buf, b_lru); list_del_init(&bp->b_lru); if (bp->b_flags & XBF_WRITE_FAIL) { - xfs_alert(btp->bt_mount, + write_fail = true; + xfs_buf_alert_ratelimited(bp, + "XFS: Corruption Alert", "Corruption Alert: Buffer at daddr 0x%llx had permanent write failures!", (long long)bp->b_bn); - xfs_alert(btp->bt_mount, -"Please run xfs_repair to determine the extent of the problem."); } xfs_buf_rele(bp); } if (loop++ != 0) delay(100); } + + /* + * If one or more failed buffers were freed, that means dirty metadata + * was thrown away. This should only ever happen after I/O completion + * handling has elevated I/O error(s) to permanent failures and shuts + * down the fs. + */ + if (write_fail) { + ASSERT(XFS_FORCED_SHUTDOWN(btp->bt_mount)); + xfs_alert(btp->bt_mount, + "Please run xfs_repair to determine the extent of the problem."); + } } static enum lru_status -- cgit v1.2.3