linux-kernel - Re: [PATCH] [RSDL-mm 0/6] RSDL cpu scheduler for -mm

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]

Date:	Thu, 8 Mar 2007 16:25:05 +1100
From:	Con Kolivas <kernel@...ivas.org>
To:	Andrew Morton <akpm@...ux-foundation.org>
Cc:	linux-kernel@...r.kernel.org, ck@....kolivas.org
Subject: Re: [PATCH] [RSDL-mm 0/6] RSDL cpu scheduler for -mm

On Thursday 08 March 2007 15:15, Andrew Morton wrote:
> On Wed, 7 Mar 2007 18:54:30 -0800 Andrew Morton <akpm@...ux-foundation.org> 
wrote:
> > On Wed, 7 Mar 2007 17:43:45 -0800 Andrew Morton 
<akpm@...ux-foundation.org> wrote:
> > > On Wed, 7 Mar 2007 12:26:42 +1100
> > >
> > > Con Kolivas <kernel@...ivas.org> wrote:
> > > > What follows is the same patch series that constitutes the RDSL
> > > > "Rotating Staircase DeadLine" cpu scheduler resynced for
> > > > 2.6.21-rc2-mm2.
> > >
> > > Big oops early in boot on x86_64 SMP, in rq_bitmap_error+0x97/0x9f.
> > >
> > > I stubbed it out with a `return MAX_RT_PRIO;' (I think) but it then
> > > oopsed differently.  Before netconsole had come up, no serial console,
> > > no digital camera.
> > >
> > > There's stuff in http://userweb.kernel.org/~akpm/ck/ - you can probably
> > > boot that kernel on your own machine.
> > >
> > > I need to do rc3-mm1 now.  I might find some time to poke at this
> > > further after that, but I have to leave for a week in .jp and it'll be
> > > squeezy, sorry.
> >
> > well it boots os dual pIII and quad powerpc.
>
> It also boots OK on a very similar but somewhat older Nocona machine. 
> Perhaps due to config changes: 
> http://userweb.kernel.org/~akpm/ck/config-ok.txt

Ok I just remembered that not only did I expect the cpu task to never be 
scheduled and it _might_ be scheduled on sched_init, it is actually 
_consciously_ scheduled on hotplug cpu which I have no way of handling at the 
moment. On both your configs I noticed you had hotplug cpu enabled, but 
perhaps it isn't really being used on the more conservative config. So this 
is something I already know I need to handle. Did your ppc that had 
the "bitmap error" have hotplug cpu enabled? It might be an unrelated 
bug^Wphenomenon.

-- 
-ck
-
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/