Re: 2.6.23.1: mdadm/raid5 hung/d-state

[Neil Brown <neilb@suse.de>]

On Sunday November 4, jpiszcz@lucidpixels.com wrote:
> # ps auxww | grep D
> USER       PID %CPU %MEM    VSZ   RSS TTY      STAT START   TIME COMMAND
> root       273  0.0  0.0      0     0 ?        D    Oct21  14:40 [pdflush]
> root       274  0.0  0.0      0     0 ?        D    Oct21  13:00 [pdflush]
> 
> After several days/weeks, this is the second time this has happened, while 
> doing regular file I/O (decompressing a file), everything on the device 
> went into D-state.

At a guess (I haven't looked closely) I'd say it is the bug that was
meant to be fixed by

commit 4ae3f847e49e3787eca91bced31f8fd328d50496

except that patch applied badly and needed to be fixed with
the following patch (not in git yet).
These have been sent to stable@ and should be in the queue for 2.6.23.2


NeilBrown

Fix misapplied patch in raid5.c

commit 4ae3f847e49e3787eca91bced31f8fd328d50496 did not get applied
correctly, presumably due to substantial similarities between
handle_stripe5 and handle_stripe6.

This patch (with lots of context) moves the chunk of new code from
handle_stripe6 (where it isn't needed (yet)) to handle_stripe5.


Signed-off-by: Neil Brown <neilb@suse.de>

### Diffstat output
 ./drivers/md/raid5.c |   14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
--- .prev/drivers/md/raid5.c	2007-11-02 12:10:49.000000000 +1100
+++ ./drivers/md/raid5.c	2007-11-02 12:25:31.000000000 +1100
@@ -2607,40 +2607,47 @@ static void handle_stripe5(struct stripe
 	struct bio *return_bi = NULL;
 	struct stripe_head_state s;
 	struct r5dev *dev;
 	unsigned long pending = 0;
 
 	memset(&s, 0, sizeof(s));
 	pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d "
 		"ops=%lx:%lx:%lx\n", (unsigned long long)sh->sector, sh->state,
 		atomic_read(&sh->count), sh->pd_idx,
 		sh->ops.pending, sh->ops.ack, sh->ops.complete);
 
 	spin_lock(&sh->lock);
 	clear_bit(STRIPE_HANDLE, &sh->state);
 	clear_bit(STRIPE_DELAYED, &sh->state);
 
 	s.syncing = test_bit(STRIPE_SYNCING, &sh->state);
 	s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
 	s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
 	/* Now to look around and see what can be done */
 
+	/* clean-up completed biofill operations */
+	if (test_bit(STRIPE_OP_BIOFILL, &sh->ops.complete)) {
+		clear_bit(STRIPE_OP_BIOFILL, &sh->ops.pending);
+		clear_bit(STRIPE_OP_BIOFILL, &sh->ops.ack);
+		clear_bit(STRIPE_OP_BIOFILL, &sh->ops.complete);
+	}
+
 	rcu_read_lock();
 	for (i=disks; i--; ) {
 		mdk_rdev_t *rdev;
 		struct r5dev *dev = &sh->dev[i];
 		clear_bit(R5_Insync, &dev->flags);
 
 		pr_debug("check %d: state 0x%lx toread %p read %p write %p "
 			"written %p\n",	i, dev->flags, dev->toread, dev->read,
 			dev->towrite, dev->written);
 
 		/* maybe we can request a biofill operation
 		 *
 		 * new wantfill requests are only permitted while
 		 * STRIPE_OP_BIOFILL is clear
 		 */
 		if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread &&
 			!test_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
 			set_bit(R5_Wantfill, &dev->flags);
 
 		/* now count some things */
@@ -2880,47 +2887,40 @@ static void handle_stripe6(struct stripe
 	struct stripe_head_state s;
 	struct r6_state r6s;
 	struct r5dev *dev, *pdev, *qdev;
 
 	r6s.qd_idx = raid6_next_disk(pd_idx, disks);
 	pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
 		"pd_idx=%d, qd_idx=%d\n",
 	       (unsigned long long)sh->sector, sh->state,
 	       atomic_read(&sh->count), pd_idx, r6s.qd_idx);
 	memset(&s, 0, sizeof(s));
 
 	spin_lock(&sh->lock);
 	clear_bit(STRIPE_HANDLE, &sh->state);
 	clear_bit(STRIPE_DELAYED, &sh->state);
 
 	s.syncing = test_bit(STRIPE_SYNCING, &sh->state);
 	s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
 	s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
 	/* Now to look around and see what can be done */
 
-	/* clean-up completed biofill operations */
-	if (test_bit(STRIPE_OP_BIOFILL, &sh->ops.complete)) {
-		clear_bit(STRIPE_OP_BIOFILL, &sh->ops.pending);
-		clear_bit(STRIPE_OP_BIOFILL, &sh->ops.ack);
-		clear_bit(STRIPE_OP_BIOFILL, &sh->ops.complete);
-	}
-
 	rcu_read_lock();
 	for (i=disks; i--; ) {
 		mdk_rdev_t *rdev;
 		dev = &sh->dev[i];
 		clear_bit(R5_Insync, &dev->flags);
 
 		pr_debug("check %d: state 0x%lx read %p write %p written %p\n",
 			i, dev->flags, dev->toread, dev->towrite, dev->written);
 		/* maybe we can reply to a read */
 		if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread) {
 			struct bio *rbi, *rbi2;
 			pr_debug("Return read for disc %d\n", i);
 			spin_lock_irq(&conf->device_lock);
 			rbi = dev->toread;
 			dev->toread = NULL;
 			if (test_and_clear_bit(R5_Overlap, &dev->flags))
 				wake_up(&conf->wait_for_overlap);
 			spin_unlock_irq(&conf->device_lock);
 			while (rbi && rbi->bi_sector < dev->sector + STRIPE_SECTORS) {
 				copy_data(0, rbi, dev->page, dev->sector);