[prev in list] [next in list] [prev in thread] [next in thread] 

List:       lhcs-devel
Subject:    [lhcs-devel] Re: [PATCH] check_for_tasks
From:       Rusty Russell <rusty () au1 ! ibm ! com>
Date:       2004-01-19 5:04:04
Message-ID: 20040119065950.AAC7717DE4 () ozlabs ! au ! ibm ! com
[Download RAW message or body]

In message <20040113153259.A9316@in.ibm.com> you write:
> 	BUG_ON(old_rq->nr_running != 0);
> 
> So please consider including the above patch.

I have fixed both versions.  Sorry, last week was spent at
linux.conf.au.

In particular, I chose to still *migrate* the exiting tasks (we don't
want them to get stuck!) but I don't printk, or send them a signal.

> > My question is, why are you seeing this?  Unless you have processes
> > which are bound to the downed CPU and are exiting, I can't see how
> > this happens.
> 
> I am seeing this because of cpu_run_sbin_hotplug(). If this 
> was invoked from the dying CPU, then the hotplug script
> will be run with a cpus_allowed set to run _only_ on
> the dying CPU.

Right, thanks for explaining.

Rusty.
--
  Anyone who quotes me in their sig is an idiot. -- Rusty Russell.


-------------------------------------------------------
The SF.Net email is sponsored by EclipseCon 2004
Premiere Conference on Open Tools Development and Integration
See the breadth of Eclipse activity. February 3-5 in Anaheim, CA.
http://www.eclipsecon.org/osdn
_______________________________________________
lhcs-devel mailing list
lhcs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/lhcs-devel
[prev in list] [next in list] [prev in thread] [next in thread]