At unmount time, XFS emits a warning 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.
We already have a ratelimit state defined for buffers failing
writeback. Fold this state into the buftarg and reuse it for the
unmount time errors.
Signed-off-by: Brian Foster <bfoster@xxxxxxxxxx>
---
fs/xfs/xfs_buf.c | 13 +++++++++++--
fs/xfs/xfs_buf.h | 1 +
fs/xfs/xfs_buf_item.c | 10 +---------
3 files changed, 13 insertions(+), 11 deletions(-)
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 7a6bc617f0a9..c28a93d2fd8c 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1684,10 +1684,12 @@ xfs_wait_buftarg(
struct xfs_buf *bp;
bp = list_first_entry(&dispose, struct xfs_buf, b_lru);
list_del_init(&bp->b_lru);
- if (bp->b_flags & XBF_WRITE_FAIL) {
+ if (bp->b_flags & XBF_WRITE_FAIL &&
+ ___ratelimit(&bp->b_target->bt_ioerror_rl,
+ "XFS: Corruption Alert")) {
xfs_alert(btp->bt_mount,
"Corruption Alert: Buffer at daddr 0x%llx had permanent write failures!",
- (long long)bp->b_bn);
+ (long long)bp->b_bn);
xfs_alert(btp->bt_mount,
"Please run xfs_repair to determine the extent of the problem.");
}
@@ -1828,6 +1830,13 @@ xfs_alloc_buftarg(
btp->bt_bdev = bdev;
btp->bt_daxdev = dax_dev;
+ /*
+ * Buffer IO error rate limiting. Limit it to no more than 10 messages
+ * per 30 seconds so as to not spam logs too much on repeated errors.
+ */
+ ratelimit_state_init(&btp->bt_ioerror_rl, 30 * HZ,
+ DEFAULT_RATELIMIT_BURST);
+
if (xfs_setsize_buftarg_early(btp, bdev))
goto error_free;
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 598b93b17d95..10492f68fd4b 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -91,6 +91,7 @@ typedef struct xfs_buftarg {
struct list_lru bt_lru;
struct percpu_counter bt_io_count;
+ struct ratelimit_state bt_ioerror_rl;
} xfs_buftarg_t;
struct xfs_buf;
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index e34298227f87..23cbfeb82183 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -480,14 +480,6 @@ xfs_buf_item_unpin(
}
}
-/*
- * Buffer IO error rate limiting. Limit it to no more than 10 messages per 30
- * seconds so as to not spam logs too much on repeated detection of the same
- * buffer being bad..
- */
-
-static DEFINE_RATELIMIT_STATE(xfs_buf_write_fail_rl_state, 30 * HZ, 10);
-
STATIC uint
xfs_buf_item_push(
struct xfs_log_item *lip,
@@ -518,7 +510,7 @@ xfs_buf_item_push(
/* has a previous flush failed due to IO errors? */
if ((bp->b_flags & XBF_WRITE_FAIL) &&
- ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS: Failing async write")) {
+ ___ratelimit(&bp->b_target->bt_ioerror_rl, "XFS: Failing async write")) {
xfs_warn(bp->b_mount,
"Failing async write on buffer block 0x%llx. Retrying async write.",
(long long)bp->b_bn);
--
2.21.1
