Re: hanging aio process

2014-06-11 Thread Ming Lei
On Wed, Jun 4, 2014 at 1:24 PM, Gu Zheng wrote: > Hi Guys, > What's the status of this issue? Has it been fixed? Yes, it is fixed by percpu_ref, and is merged to 3.15 already. Thanks, -- Ming Lei -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message

Re: [PATCH] percpu-refcount: fix usage of this_cpu_ops (was Re: hanging aio process)

2014-06-04 Thread Christoph Lameter
On Wed, 4 Jun 2014, Tejun Heo wrote: > Urgh... I really don't like the subtleties around __this_cpu_*(). > It's too easy to get it wrong and fail to notice it. :( Thats why we added the preemption check logic recently. Wonder why it did not trigger in this case. -- To unsubscribe from this lis

Re: [PATCH] percpu-refcount: fix usage of this_cpu_ops (was Re: hanging aio process)

2014-06-04 Thread Tejun Heo
On Wed, Jun 04, 2014 at 06:56:14PM +0200, Sebastian Ott wrote: > In your git tree you've used me as the patch author but that should be > Heiko. Sorry if I didn't annotate this correctly - I just inlined the > git format-patch output.. Oops, updated accordingly. Thanks. -- tejun -- To unsubscri

Re: [PATCH] percpu-refcount: fix usage of this_cpu_ops (was Re: hanging aio process)

2014-06-04 Thread Sebastian Ott
Hi, On Wed, 4 Jun 2014, Tejun Heo wrote: > On Wed, Jun 04, 2014 at 03:58:24PM +0200, Sebastian Ott wrote: > > From 82295633cad58c7d6b9af4e470e3168ed43a6779 Mon Sep 17 00:00:00 2001 > > From: Heiko Carstens > > Date: Wed, 4 Jun 2014 12:53:19 +0200 > > Subject: [PATCH] percpu-refcount: fix usage of

Re: [PATCH] percpu-refcount: fix usage of this_cpu_ops (was Re: hanging aio process)

2014-06-04 Thread Tejun Heo
cc'ing Christoph. Hey! On Wed, Jun 04, 2014 at 03:58:24PM +0200, Sebastian Ott wrote: > From 82295633cad58c7d6b9af4e470e3168ed43a6779 Mon Sep 17 00:00:00 2001 > From: Heiko Carstens > Date: Wed, 4 Jun 2014 12:53:19 +0200 > Subject: [PATCH] percpu-refcount: fix usage of this_cpu_ops > > The perc

Re: [PATCH] percpu-refcount: fix usage of this_cpu_ops (was Re: hanging aio process)

2014-06-04 Thread Tejun Heo
On Wed, Jun 04, 2014 at 03:58:24PM +0200, Sebastian Ott wrote: > From 82295633cad58c7d6b9af4e470e3168ed43a6779 Mon Sep 17 00:00:00 2001 > From: Heiko Carstens > Date: Wed, 4 Jun 2014 12:53:19 +0200 > Subject: [PATCH] percpu-refcount: fix usage of this_cpu_ops > > The percpu-refcount infrastructur

[PATCH] percpu-refcount: fix usage of this_cpu_ops (was Re: hanging aio process)

2014-06-04 Thread Sebastian Ott
Hello, On Wed, 21 May 2014, Anatol Pomozov wrote: > Hi > > On Wed, May 21, 2014 at 1:48 AM, Sebastian Ott > wrote: > > On Wed, 21 May 2014, Sebastian Ott wrote: > >> On Tue, 20 May 2014, Anatol Pomozov wrote: > >> > On Tue, May 20, 2014 at 11:09 AM, Sebastian Ott > >> > wrote: > >> > > On Tue,

Re: hanging aio process

2014-06-03 Thread Gu Zheng
Hi Guys, What's the status of this issue? Has it been fixed? Thanks, Gu On 05/21/2014 10:57 PM, Sebastian Ott wrote: > On Wed, 21 May 2014, Anatol Pomozov wrote: >> On Wed, May 21, 2014 at 1:48 AM, Sebastian Ott >> wrote: >>> On Wed, 21 May 2014, Sebastian Ott wrote: On Tue, 20 May 2014, A

Re: hanging aio process

2014-05-21 Thread Sebastian Ott
On Wed, 21 May 2014, Anatol Pomozov wrote: > On Wed, May 21, 2014 at 1:48 AM, Sebastian Ott > wrote: > > On Wed, 21 May 2014, Sebastian Ott wrote: > >> On Tue, 20 May 2014, Anatol Pomozov wrote: > >> > On Tue, May 20, 2014 at 11:09 AM, Sebastian Ott > >> > wrote: > >> > > On Tue, 20 May 2014, Ana

Re: hanging aio process

2014-05-21 Thread Anatol Pomozov
Hi On Wed, May 21, 2014 at 1:48 AM, Sebastian Ott wrote: > On Wed, 21 May 2014, Sebastian Ott wrote: >> On Tue, 20 May 2014, Anatol Pomozov wrote: >> > On Tue, May 20, 2014 at 11:09 AM, Sebastian Ott >> > wrote: >> > > On Tue, 20 May 2014, Anatol Pomozov wrote: >> > >> On Tue, May 20, 2014 at 6:

Re: hanging aio process

2014-05-21 Thread Benjamin LaHaise
On Wed, May 21, 2014 at 10:48:55AM +0200, Sebastian Ott wrote: > > > > I already did that and it didn't change, always 1 + (1UL << 31) in all > > cases, before and after percpu_ref_kill(&ctx->reqs). I'm not really > > familiar with this percpu_ref stuff but it looks like the initial > > reference

Re: hanging aio process

2014-05-21 Thread Sebastian Ott
On Wed, 21 May 2014, Sebastian Ott wrote: > On Tue, 20 May 2014, Anatol Pomozov wrote: > > On Tue, May 20, 2014 at 11:09 AM, Sebastian Ott > > wrote: > > > On Tue, 20 May 2014, Anatol Pomozov wrote: > > >> On Tue, May 20, 2014 at 6:16 AM, Sebastian Ott > > >> wrote: > > >> > On Tue, 20 May 2014,

Re: hanging aio process

2014-05-21 Thread Sebastian Ott
On Tue, 20 May 2014, Anatol Pomozov wrote: > On Tue, May 20, 2014 at 11:09 AM, Sebastian Ott > wrote: > > On Tue, 20 May 2014, Anatol Pomozov wrote: > >> On Tue, May 20, 2014 at 6:16 AM, Sebastian Ott > >> wrote: > >> > On Tue, 20 May 2014, Sebastian Ott wrote: > >> >> On Mon, 19 May 2014, Benjam

Re: hanging aio process

2014-05-20 Thread Anatol Pomozov
Hi On Tue, May 20, 2014 at 11:09 AM, Sebastian Ott wrote: > Hi, > > On Tue, 20 May 2014, Anatol Pomozov wrote: >> On Tue, May 20, 2014 at 6:16 AM, Sebastian Ott >> wrote: >> > On Tue, 20 May 2014, Sebastian Ott wrote: >> >> On Mon, 19 May 2014, Benjamin LaHaise wrote: >> >> > It is entirely poss

Re: hanging aio process

2014-05-20 Thread Sebastian Ott
Hi, On Tue, 20 May 2014, Anatol Pomozov wrote: > On Tue, May 20, 2014 at 6:16 AM, Sebastian Ott > wrote: > > On Tue, 20 May 2014, Sebastian Ott wrote: > >> On Mon, 19 May 2014, Benjamin LaHaise wrote: > >> > It is entirely possible the bug isn't > >> > caused by the referenced commit, as the comm

Re: hanging aio process

2014-05-20 Thread Anatol Pomozov
Hi On Tue, May 20, 2014 at 6:16 AM, Sebastian Ott wrote: > On Tue, 20 May 2014, Sebastian Ott wrote: >> On Mon, 19 May 2014, Benjamin LaHaise wrote: >> > It is entirely possible the bug isn't >> > caused by the referenced commit, as the commit you're pointing to merely >> > makes io_destroy() sys

Re: hanging aio process

2014-05-20 Thread Benjamin LaHaise
On Tue, May 20, 2014 at 03:16:47PM +0200, Sebastian Ott wrote: > On Tue, 20 May 2014, Sebastian Ott wrote: > > On Mon, 19 May 2014, Benjamin LaHaise wrote: > > > It is entirely possible the bug isn't > > > caused by the referenced commit, as the commit you're pointing to merely > > > makes io_des

Re: hanging aio process

2014-05-20 Thread Sebastian Ott
On Tue, 20 May 2014, Sebastian Ott wrote: > On Mon, 19 May 2014, Benjamin LaHaise wrote: > > It is entirely possible the bug isn't > > caused by the referenced commit, as the commit you're pointing to merely > > makes io_destroy() syscall wait for all aio outstanding to complete > > before retur

Re: hanging aio process

2014-05-20 Thread Sebastian Ott
On Mon, 19 May 2014, Benjamin LaHaise wrote: > On Mon, May 19, 2014 at 07:38:51PM +0200, Sebastian Ott wrote: > > Hello, > > > > on the latest kernel a fio job with 4 workers using libaio hangs. > > Is more than one process stuck in state D when the hang occurs? If so, > what does a backtrace s

Re: hanging aio process

2014-05-19 Thread Anatol Pomozov
Hi On Mon, May 19, 2014 at 10:38 AM, Sebastian Ott wrote: > Hello, > > on the latest kernel a fio job with 4 workers using libaio hangs. > > git bisect points to: > commit e02ba72aabfade4c9cd6e3263e9b57bf890ad25c > Author: Anatol Pomozov > Date: Tue Apr 15 11:31:33 2014

Re: hanging aio process

2014-05-19 Thread Benjamin LaHaise
On Mon, May 19, 2014 at 07:38:51PM +0200, Sebastian Ott wrote: > Hello, > > on the latest kernel a fio job with 4 workers using libaio hangs. Is more than one process stuck in state D when the hang occurs? If so, what does a backtrace show for the stuck processes (or are there any hung process

hanging aio process

2014-05-19 Thread Sebastian Ott
Hello, on the latest kernel a fio job with 4 workers using libaio hangs. git bisect points to: commit e02ba72aabfade4c9cd6e3263e9b57bf890ad25c Author: Anatol Pomozov Date: Tue Apr 15 11:31:33 2014 -0700 aio: block io_destroy() until all context requests are