linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
* [PATCH 0/3] Fix boot_pageset sharing issue for new populated zones of hotadded nodes
@ 2010-05-17  8:17 Haicheng Li
  2010-05-17 10:34 ` Andi Kleen
  0 siblings, 1 reply; 2+ messages in thread
From: Haicheng Li @ 2010-05-17  8:17 UTC (permalink / raw)
  To: linux-mm@kvack.org, akpm@linux-foundation.org
  Cc: linux-kernel@vger.kernel.org, Wu, Fengguang, Andi Kleen,
	Mel Gorman, Christoph Lameter, Tejun Heo

In our recent cpu/memory hotadd testing, with multiple nodes hotadded,
kernel easily panics under stress workload like kernel building.

The root cause is that the new populated zones of hotadded nodes are
sharing same per_cpu_pageset, i.e. boot strapping boot_pageset, which
finally causes page state wrong.

The following three patches will setup the pagesets for hotadded nodes
with dynamically allocated per_cpu_pageset struct.

---
  include/linux/memory_hotplug.h |    8 +++++
  include/linux/mmzone.h         |    2 +-
  init/main.c                    |    2 +-
  mm/memory_hotplug.c            |   27 +++++++++++-----
  mm/page_alloc.c                |   66 +++++++++++++++++++++++++++-------------
  5 files changed, 74 insertions(+), 31 deletions(-)

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

^ permalink raw reply	[flat|nested] 2+ messages in thread

* Re: [PATCH 0/3] Fix boot_pageset sharing issue for new populated zones of hotadded nodes
  2010-05-17  8:17 [PATCH 0/3] Fix boot_pageset sharing issue for new populated zones of hotadded nodes Haicheng Li
@ 2010-05-17 10:34 ` Andi Kleen
  0 siblings, 0 replies; 2+ messages in thread
From: Andi Kleen @ 2010-05-17 10:34 UTC (permalink / raw)
  To: Haicheng Li
  Cc: linux-mm@kvack.org, akpm@linux-foundation.org,
	linux-kernel@vger.kernel.org, Wu, Fengguang, Andi Kleen,
	Mel Gorman, Christoph Lameter, Tejun Heo

On Mon, May 17, 2010 at 04:17:52PM +0800, Haicheng Li wrote:
> In our recent cpu/memory hotadd testing, with multiple nodes hotadded,
> kernel easily panics under stress workload like kernel building.
>
> The root cause is that the new populated zones of hotadded nodes are
> sharing same per_cpu_pageset, i.e. boot strapping boot_pageset, which
> finally causes page state wrong.
>
> The following three patches will setup the pagesets for hotadded nodes
> with dynamically allocated per_cpu_pageset struct.

Patches look good, thanks.

-Andi

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2010-05-17 10:34 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2010-05-17  8:17 [PATCH 0/3] Fix boot_pageset sharing issue for new populated zones of hotadded nodes Haicheng Li
2010-05-17 10:34 ` Andi Kleen

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).