Home » Mailing list archives » linux-kernel » 2007 » October » 23

Re: SLUB 0:1 SLAB (OOM during massive parallel kernel builds)

!MAILaRCHIVE_VOTE_RePLACE
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
[view in full thread]
From: Pekka Enberg <penberg@...>
To: Christoph Lameter <clameter@...>
Cc: Alexey Dobriyan <adobriyan@...>, <linux-kernel@...>, Linux MM <linux-mm@...>
Subject: Re: SLUB 0:1 SLAB (OOM during massive parallel kernel builds)
Date: Tuesday, October 23, 2007 - 4:41 pm

Hi Christoph,

(I fixed linux-mm cc to kvack.org.)

On 10/23/07, Christoph Lameter <clameter@sgi.com> wrote:

Yeah, but we're _not failing_ when debugging is enabled. Thus, it's
likely, that the _failing_ (non-debug) case has potential for more
order 0 allocs, no? I am just guessing here but maybe it's
slab_order() behaving differently from calculate_slab_order() so that
we see more order 0 pressure in SLUB than SLAB?

                                     Pekka
-
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
Messages in current thread:
SLUB 0:1 SLAB (OOM during massive parallel kernel builds), Alexey Dobriyan, (Tue Oct 23, 2:16 pm)
Re: SLUB 0:1 SLAB (OOM during massive parallel kernel builds), Christoph Lameter, (Tue Oct 23, 3:35 pm)
Re: SLUB 0:1 SLAB (OOM during massive parallel kernel builds), Pekka Enberg, (Tue Oct 23, 4:04 pm)
Re: SLUB 0:1 SLAB (OOM during massive parallel kernel builds), Christoph Lameter, (Tue Oct 23, 4:09 pm)
Re: SLUB 0:1 SLAB (OOM during massive parallel kernel builds), Pekka Enberg, (Tue Oct 23, 4:41 pm)
Re: SLUB 0:1 SLAB (OOM during massive parallel kernel builds), Christoph Lameter, (Wed Oct 24, 12:56 pm)
Re: SLUB 0:1 SLAB (OOM during massive parallel kernel builds), Pekka Enberg, (Tue Oct 23, 3:48 pm)
Re: SLUB 0:1 SLAB (OOM during massive parallel kernel builds), Christoph Lameter, (Tue Oct 23, 3:57 pm)
Re: SLUB 0:1 SLAB (OOM during massive parallel kernel builds), Mel Gorman, (Wed Oct 24, 4:09 am)
Re: SLUB 0:1 SLAB (OOM during massive parallel kernel builds), Alexey Dobriyan, (Wed Oct 24, 3:28 pm)
Re: SLUB 0:1 SLAB (OOM during massive parallel kernel builds), Christoph Lameter, (Wed Oct 24, 10:15 pm)
Re: SLUB 0:1 SLAB (OOM during massive parallel kernel builds), Nick Piggin, (Wed Oct 24, 10:34 pm)
Re: SLUB 0:1 SLAB (OOM during massive parallel kernel builds), Christoph Lameter, (Wed Oct 24, 10:43 pm)
Re: SLUB 0:1 SLAB (OOM during massive parallel kernel builds), Nick Piggin, (Wed Oct 24, 11:06 pm)