[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20060821221145.ff88769f.akpm@osdl.org>
Date: Mon, 21 Aug 2006 22:11:45 -0700
From: Andrew Morton <akpm@...l.org>
To: Nathan Lynch <ntl@...ox.com>
Cc: Paul Jackson <pj@....com>, Anton Blanchard <anton@...ba.org>,
simon.derr@...l.net, nathanl@...tin.ibm.com,
linux-kernel@...r.kernel.org
Subject: Re: cpusets not cpu hotplug aware
On Tue, 22 Aug 2006 00:04:01 -0500
Nathan Lynch <ntl@...ox.com> wrote:
> > If the kernel provider (ie: distro) has enabled cpusets then it would be
> > appropriate that they also provide a hotplug script which detects whether their
> > user is actually using cpusets and if not, to take some sensible default action.
> > ie: add the newly-added CPU to the system's single cpuset, no?
>
> I think it would be more sensible for the default (i.e. user hasn't
> explicitly configured any cpusets) behavior on a CONFIG_CPUSETS=y
> kernel to match the behavior with a CONFIG_CPUSETS=n kernel.
Well... why? If he-who-configured the kernel chose cpusets then it's
reasonable to expect he-who-configures to have appropriate userspace
support for that kernel.
> Right
> now we don't have that. Binding a task to a newly added cpu just
> fails if CONFIG_CPUSETS=y, but it works if CONFIG_CPUSETS=n.
Sure. That's because we're not taking appropriate (ie any) action when a
CPU is added.
-
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/
Powered by blists - more mailing lists