Re: [PATCHSET] blkcg: accumulated blkcg updates

[Vivek Goyal <vgoyal@redhat.com>]

On Tue, Mar 06, 2012 at 01:39:42PM -0500, Vivek Goyal wrote:
> On Tue, Mar 06, 2012 at 11:24:55AM -0500, Vivek Goyal wrote:
> > On Tue, Mar 06, 2012 at 10:07:09AM -0500, Vivek Goyal wrote:
> > 
> > [..]
> > > 
> > > My system is hanging during reboot. Last message I see is "Detaching DM
> > > devices" and nothing happens after that. I shall have to do some more 
> > > testing to figure out when did that start happening.
> > 
> > Ok, git bisect shows that very first patch to drain the queue is culprit.
> > 
> > 9e5b9f8 block: blk-throttle should be drained regardless of q->elevator
> > 
> > Will do some more debugging.
> 
> Hmm..., haven't reached to the bottom of the issue yet, but there is more
> data.

Ok, found it. Basically we have not initialized the q->queue_head during
queue creation. Hence we end up thinking that q->queue_head is not empty.

So following fixed the issue for me. I still don't understand the special
cased code (q->queue_head is not empty but don't kick queue).

 block/blk-core.c |    1 +
 1 file changed, 1 insertion(+)

Index: tejun-misc/block/blk-core.c
===================================================================
--- tejun-misc.orig/block/blk-core.c	2012-03-07 00:47:14.325852192 -0500
+++ tejun-misc/block/blk-core.c	2012-03-07 00:47:15.998853132 -0500
@@ -558,6 +558,7 @@ struct request_queue *blk_alloc_queue_no
 	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
 	INIT_LIST_HEAD(&q->timeout_list);
 	INIT_LIST_HEAD(&q->icq_list);
+	INIT_LIST_HEAD(&q->queue_head);
 #ifdef CONFIG_BLK_CGROUP
 	INIT_LIST_HEAD(&q->blkg_list);
 #endif

Thanks
Vivek