Commit 036330c9 authored by Bob Peterson's avatar Bob Peterson

gfs2: log error reform

Before this patch, gfs2 kept track of journal io errors in two
places sd_log_error and the SDF_AIL1_IO_ERROR flag in sd_flags.
This patch consolidates the two into sd_log_error so that it
reflects the first error encountered writing to the journal.
In future patches, we will take advantage of this by checking
this value rather than having to check both when reacting to
io errors.

In addition, this fixes a tight loop in unmount: If buffers
get on the ail1 list and an io error occurs elsewhere, the
ail1 list would never be cleared because they were always busy.
So unmount would hang, waiting for the ail1 list to empty.
Signed-off-by: default avatarBob Peterson <rpeterso@redhat.com>
Reviewed-by: default avatarAndreas Gruenbacher <agruenba@redhat.com>
parent b3422cac
...@@ -615,9 +615,8 @@ enum { ...@@ -615,9 +615,8 @@ enum {
SDF_RORECOVERY = 7, /* read only recovery */ SDF_RORECOVERY = 7, /* read only recovery */
SDF_SKIP_DLM_UNLOCK = 8, SDF_SKIP_DLM_UNLOCK = 8,
SDF_FORCE_AIL_FLUSH = 9, SDF_FORCE_AIL_FLUSH = 9,
SDF_AIL1_IO_ERROR = 10, SDF_FS_FROZEN = 10,
SDF_FS_FROZEN = 11, SDF_WITHDRAWING = 11, /* Will withdraw eventually */
SDF_WITHDRAWING = 12, /* Will withdraw eventually */
}; };
enum gfs2_freeze_state { enum gfs2_freeze_state {
...@@ -828,7 +827,7 @@ struct gfs2_sbd { ...@@ -828,7 +827,7 @@ struct gfs2_sbd {
atomic_t sd_log_in_flight; atomic_t sd_log_in_flight;
struct bio *sd_log_bio; struct bio *sd_log_bio;
wait_queue_head_t sd_log_flush_wait; wait_queue_head_t sd_log_flush_wait;
int sd_log_error; int sd_log_error; /* First log error */
atomic_t sd_reserving_log; atomic_t sd_reserving_log;
wait_queue_head_t sd_reserving_log_wait; wait_queue_head_t sd_reserving_log_wait;
......
...@@ -108,8 +108,7 @@ __acquires(&sdp->sd_ail_lock) ...@@ -108,8 +108,7 @@ __acquires(&sdp->sd_ail_lock)
&tr->tr_ail2_list); &tr->tr_ail2_list);
continue; continue;
} }
if (!test_and_set_bit(SDF_AIL1_IO_ERROR, if (!cmpxchg(&sdp->sd_log_error, 0, -EIO)) {
&sdp->sd_flags)) {
gfs2_io_error_bh(sdp, bh); gfs2_io_error_bh(sdp, bh);
gfs2_withdraw_delayed(sdp); gfs2_withdraw_delayed(sdp);
} }
...@@ -205,10 +204,19 @@ static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr) ...@@ -205,10 +204,19 @@ static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
bd_ail_st_list) { bd_ail_st_list) {
bh = bd->bd_bh; bh = bd->bd_bh;
gfs2_assert(sdp, bd->bd_tr == tr); gfs2_assert(sdp, bd->bd_tr == tr);
if (buffer_busy(bh)) /*
* If another process flagged an io error, e.g. writing to the
* journal, error all other bhs and move them off the ail1 to
* prevent a tight loop when unmount tries to flush ail1,
* regardless of whether they're still busy. If no outside
* errors were found and the buffer is busy, move to the next.
* If the ail buffer is not busy and caught an error, flag it
* for others.
*/
if (!sdp->sd_log_error && buffer_busy(bh))
continue; continue;
if (!buffer_uptodate(bh) && if (!buffer_uptodate(bh) &&
!test_and_set_bit(SDF_AIL1_IO_ERROR, &sdp->sd_flags)) { !cmpxchg(&sdp->sd_log_error, 0, -EIO)) {
gfs2_io_error_bh(sdp, bh); gfs2_io_error_bh(sdp, bh);
gfs2_withdraw_delayed(sdp); gfs2_withdraw_delayed(sdp);
} }
......
...@@ -1477,7 +1477,7 @@ static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error) ...@@ -1477,7 +1477,7 @@ static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error)
return; return;
if (!gfs2_withdrawn(sdp)) { if (!gfs2_withdrawn(sdp)) {
fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error); fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error);
sdp->sd_log_error = error; cmpxchg(&sdp->sd_log_error, 0, error);
wake_up(&sdp->sd_logd_waitq); wake_up(&sdp->sd_logd_waitq);
} }
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment