Subject: Re: [PATCH] softlockup detection vs. cpu hotplug
From: Shaohua Li <shaohua.li@intel.com>
To: Nathan Lynch <ntl@pobox.com>
Cc: linux-kernel@vger.kernel.org, Ingo Molnar <mingo@elte.hu>,
       Andrew Morton <akpm@osdl.org>
In-Reply-To: <20060224003146.GJ3293@localhost.localdomain>
References: <20060224003146.GJ3293@localhost.localdomain>
Content-Type: text/plain
Date: Fri, 24 Feb 2006 09:31:53 +0800
Message-Id: <1140744713.16880.4.camel@sli10-desk.sh.intel.com>
Mime-Version: 1.0
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 772
Lines: 19

On Fri, 2006-02-24 at 08:31 +0800, Nathan Lynch wrote:
> 
> In the watchdog thread, do touch_softlockup_watchdog in a 
> non-preemptible section so that it won't touch another cpu's 
> timestamp.  This can happen in the window between the watchdog thread 
> getting forcefully migrated during a cpu offline operation and 
> kthread_should_stop.
Could we stop the thread in CPU_DOWN_PREPARE case, so it will not be
migrated to other CPUs? I suppose it's better the per-cpu thread only
runs on the specific cpu.

Thanks,
Shaohua

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