aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorNeilBrown <neilb@suse.de>2008-03-04 14:29:35 -0800
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2008-03-04 16:35:18 -0800
commit1c830532f6b44d10a1743ccd00e990c6b83396f5 (patch)
tree506c8fef4d84f54e76b533756cff86c45bb61746
parent8ed3a19563b6c05b7625649b1769ddb063d53253 (diff)
downloadlinux-stericsson-1c830532f6b44d10a1743ccd00e990c6b83396f5.tar.gz
md: fix possible raid1/raid10 deadlock on read error during resync
Thanks to K.Tanaka and the scsi fault injection framework, here is a fix for another possible deadlock in raid1/raid10 error handing. If a read request returns an error while a resync is happening and a resync request is pending, the attempt to fix the error will block until the resync progresses, and the resync will block until the read request completes. Thus a deadlock. This patch fixes the problem. Cc: "K.Tanaka" <k-tanaka@ce.jp.nec.com> Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--drivers/md/raid1.c11
-rw-r--r--drivers/md/raid10.c11
2 files changed, 18 insertions, 4 deletions
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 38f076a3400d..ff61b309129a 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -704,13 +704,20 @@ static void freeze_array(conf_t *conf)
/* stop syncio and normal IO and wait for everything to
* go quite.
* We increment barrier and nr_waiting, and then
- * wait until barrier+nr_pending match nr_queued+2
+ * wait until nr_pending match nr_queued+1
+ * This is called in the context of one normal IO request
+ * that has failed. Thus any sync request that might be pending
+ * will be blocked by nr_pending, and we need to wait for
+ * pending IO requests to complete or be queued for re-try.
+ * Thus the number queued (nr_queued) plus this request (1)
+ * must match the number of pending IOs (nr_pending) before
+ * we continue.
*/
spin_lock_irq(&conf->resync_lock);
conf->barrier++;
conf->nr_waiting++;
wait_event_lock_irq(conf->wait_barrier,
- conf->barrier+conf->nr_pending == conf->nr_queued+2,
+ conf->nr_pending == conf->nr_queued+1,
conf->resync_lock,
({ flush_pending_writes(conf);
raid1_unplug(conf->mddev->queue); }));
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 6c486d839c99..8e5671d2f3d3 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -747,13 +747,20 @@ static void freeze_array(conf_t *conf)
/* stop syncio and normal IO and wait for everything to
* go quiet.
* We increment barrier and nr_waiting, and then
- * wait until barrier+nr_pending match nr_queued+2
+ * wait until nr_pending match nr_queued+1
+ * This is called in the context of one normal IO request
+ * that has failed. Thus any sync request that might be pending
+ * will be blocked by nr_pending, and we need to wait for
+ * pending IO requests to complete or be queued for re-try.
+ * Thus the number queued (nr_queued) plus this request (1)
+ * must match the number of pending IOs (nr_pending) before
+ * we continue.
*/
spin_lock_irq(&conf->resync_lock);
conf->barrier++;
conf->nr_waiting++;
wait_event_lock_irq(conf->wait_barrier,
- conf->barrier+conf->nr_pending == conf->nr_queued+2,
+ conf->nr_pending == conf->nr_queued+1,
conf->resync_lock,
({ flush_pending_writes(conf);
raid10_unplug(conf->mddev->queue); }));