[lkml]   [2009]   [Sep]   [22]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [RFC PATCH 0/3] Fix SLQB on memoryless configurations V2
On Tue, Sep 22, 2009 at 06:35:05PM +0530, Sachin Sant wrote:
> Mel Gorman wrote:
>> On Tue, Sep 22, 2009 at 10:33:11AM +0530, Sachin Sant wrote:
>>> Mel Gorman wrote:
>>>> On Mon, Sep 21, 2009 at 01:54:12PM -0400, Christoph Lameter wrote:
>>>>> Lets just keep SLQB back until the basic issues with memoryless nodes are
>>>>> resolved.
>>>> It's not even super-clear that the memoryless nodes issues are entirely
>>>> related to SLQB. Sachin for example says that there was a stall issue
>>>> with memoryless nodes that could be triggered without SLQB. Sachin, is
>>>> that still accurate?
>>> I think there are two different problems that we are dealing with.
>>> First one is the SLQB not working on a ppc64 box which seems to be specific
>>> to only one machine and i haven't seen that on other power boxes.The patches
>>> that you have posted seems to allow the box to boot, but eventually it hits
>>> the stall issue(related to percpu dynamic allocator not working on ppc64),
>>> which is the second problem we are dealing with.
>> Ok, I've sent out V3 of this. It's only a partial fix but it's about as
>> far as it can be brought until the other difficulties are resolved.
> Thanks Mel.
>>> The stall issue seems to be much more critical as it is affecting almost
>>> all of the power boxes that i have tested with (4 in all).
>>> This issue is seen with Linus tree as well and was first seen with
>>> 2.6.31-git5 (0cb583fd..)
>>> The stall issue was reported here:
>> Can you bisect this please?
> The problem seems to have been introduced with
> commit ada3fa15057205b7d3f727bba5cd26b5912e350f.
> Specifically this patch : powerpc64: convert to dynamic percpu allocator

That is commit c2a7e818019f20a5cf7fb26a6eb59e212e6c0cd8.

> If i revert this patch i am able to boot latest git
> on a powerpc box.

Ok, this is then independent of the corruption I was seeing which I now
believe is based entirely within SLQBs handling of remote nodes. I was based
on 2.6.31 with SLQB applied on top. This patch was applied in a time after
the baseline I was working from.

Tejun, have you looked at that stall problem? Sorry if you have already,
I haven't dug around for related threads.

Mel Gorman
Part-time Phd Student Linux Technology Center
University of Limerick IBM Dublin Software Lab

 \ /
  Last update: 2009-09-22 15:23    [W:0.087 / U:4.024 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site