Bug 14621

Summary:	specjbb2005 and aim7 regression with 2.6.32-rc kernels
Product:	Process Management	Reporter:	Rafael J. Wysocki (rjw)
Component:	Scheduler	Assignee:	Ingo Molnar (mingo)
Status:	CLOSED OBSOLETE
Severity:	normal	CC:	alan, yanmin_zhang
Priority:	P1
Hardware:	All
OS:	Linux
Kernel Version:	2.6.32-rc	Subsystem:
Regression:	Yes	Bisected commit-id:
Bug Depends on:
Bug Blocks:	14230

Description Rafael J. Wysocki 2009-11-16 21:39:41 UTC

Subject    : specjbb2005 and aim7 regression with 2.6.32-rc kernels
Submitter  : "Zhang, Yanmin" <yanmin_zhang@linux.intel.com>
Date       : 2009-11-06 7:38
References : http://marc.info/?l=linux-kernel&m=125749310413174&w=4
Notify-Also : Mike Galbraith <efault@gmx.de>
Notify-Also : Ingo Molnar <mingo@elte.hu>
Notify-Also : Peter Zijlstra <peterz@infradead.org>
Notify-Also : Gautham R Shenoy <ego@in.ibm.com>

This entry is being used for tracking a regression from 2.6.31.  Please don't
close it until the problem is fixed in the mainline.

Comment 1 Yanmin Zhang 2009-11-23 00:59:07 UTC

It's not resolved on core2 machines yet. The key is it will hurt Nehalem performance if we revert to old values on these schedule parameters.

Comment 2 Rafael J. Wysocki 2010-01-11 19:42:40 UTC

On Monday 11 January 2010, Mike Galbraith wrote:
> On Sun, 2010-01-10 at 23:56 +0100, Rafael J. Wysocki wrote:
> > This message has been generated automatically as a part of a report
> > of regressions introduced between 2.6.31 and 2.6.32.
> > 
> > The following bug entry is on the current list of known regressions
> > introduced between 2.6.31 and 2.6.32.  Please verify if it still should
> > be listed and let me know (either way).
> > 
> > 
> > Bug-Entry   : http://bugzilla.kernel.org/show_bug.cgi?id=14621
> > Subject             : specjbb2005 and aim7 regression with 2.6.32-rc
> kernels
> > Submitter   : Zhang, Yanmin <yanmin_zhang@linux.intel.com>
> > Date                : 2009-11-06 7:38 (66 days old)
> > References  : http://marc.info/?l=linux-kernel&m=125749310413174&w=4
> 
> FWIW, I couldn't reproduce the aim7 regression with my one little disk,
> the opposite in fact, attributable to cfq low_latency switch.
> 
> (don't have specjbb2005, can't try to reproduce that one)

Comment 3 Rafael J. Wysocki 2010-02-02 20:56:36 UTC

On Monday 01 February 2010, Mike Galbraith wrote:
> On Mon, 2010-02-01 at 01:43 +0100, Rafael J. Wysocki wrote:
> > This message has been generated automatically as a part of a report
> > of regressions introduced between 2.6.31 and 2.6.32.
> > 
> > The following bug entry is on the current list of known regressions
> > introduced between 2.6.31 and 2.6.32.  Please verify if it still should
> > be listed and let me know (either way).
> 
> Yes, it should remain open.  Aim7 regression isn't reproducible here,
> specjbb2005 unknown, not available to the general public.