linux-kernel - Re: [git pull] scheduler changes for v2.6.26

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <200804211831.29976.elendil@planet.nl>
Date:	Mon, 21 Apr 2008 18:31:28 +0200
From:	Frans Pop <elendil@...net.nl>
To:	Ingo Molnar <mingo@...e.hu>
Cc:	torvalds@...ux-foundation.org, linux-kernel@...r.kernel.org,
	akpm@...ux-foundation.org, Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Mike Galbraith <efault@....de>,
	Richard Jonsson <richie@...erworld.net>,
	"Rafael J. Wysocki" <rjw@...k.pl>
Subject: Re: [git pull] scheduler changes for v2.6.26

On Monday 21 April 2008, you wrote:
> * Frans Pop <elendil@...net.nl> wrote:
> > Ingo Molnar wrote:
> > > Ingo Molnar (12):
> > >       sched: re-do "sched: fix fair sleepers"
> >
> > Has the regression [1] that was traced to this change been fixed now?
> >
> > The regression was confirmed to be also present in sched-devel.git at
> > the time of -rc8, so I'd expect it still to be valid unless of course
> > the cause was found since then.
>
> Peter reported a similar interactivity problem to be gone, so lets
> re-try this again - the change makes sense and if you see problems it's
> hiding something we really want to fix.

IIRC he mentioned seeing something himself during 2.6.25, but we'd already 
established that was unrelated to what I was seeing as his workaround 
(booting with nohz) did not work for me.

I can again reproduce the issue with sched-devel/latest :-(
latencytop regularly reports 500-700 msec latencies for amarokapp again 
while compiling glibc.

I expect that means it's also back in mainline?
What would be preferred for bugzilla: reopening the existing report (#10428) 
or opening a new one?

> It would be nice if you could 
> try sched-devel/latest because it has an improved ftrace "sched_switch"
> tracer where you can generate much longer traces of this incident. Try
> the new /debug/trace_entries runtime tunable.

I'll try to get the trace and will reply on the private thread we had.
I may need additional instructions though.

Cheers,
FJP
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/