Re: [5/8,v3] NUMA Hotplug Emulator: support cpu probe/release inx86
From: Shaohui Zheng
Date: Mon Nov 22 2010 - 19:51:41 EST
On Mon, Nov 22, 2010 at 11:51:52PM +0800, Américo Wang wrote:
> On Mon, Nov 22, 2010 at 08:01:04AM +0800, Shaohui Zheng wrote:
> >On Sun, Nov 21, 2010 at 10:45:11PM +0800, Américo Wang wrote:
> >> On Wed, Nov 17, 2010 at 10:08:04AM +0800, shaohui.zheng@xxxxxxxxx wrote:
> >> >From: Shaohui Zheng <shaohui.zheng@xxxxxxxxx>
> >> >
> >> >Add cpu interface probe/release under sysfs for x86. User can use this
> >> >interface to emulate the cpu hot-add process, it is for cpu hotplug
> >> >test purpose. Add a kernel option CONFIG_ARCH_CPU_PROBE_RELEASE for this
> >> >feature.
> >> >
> >> >This interface provides a mechanism to emulate cpu hotplug with software
> >> > methods, it becomes possible to do cpu hotplug automation and stress
> >> >testing.
> >> >
> >>
> >> Huh? We already have CPU online/offline...
> >>
> >> Can you describe more about the difference?
> >>
> >> Thanks.
> >
> >Again, we already try to discribe the difference between logcial cpu
> >online/offline and physical cpu online/offline many times.
> >
>
> I see, with "maxcpus=" we will only have the specified number
> of CPU's which can be online/offline, you are trying to bring
> the rest of CPU's hidden by "maxcpus=". :) Correct?
Yes, when we online the rest CPUs, it test our cpu hot-add code logical.
>
> I think the idea is cool, but I think you need to improve
> the documetion, for people who don't follow the hardware
> concepts like me. ;)
CPU hot-add is supported by only a few hardwares, so many users might never
see such hardware, we should document it better. thanks for the remind.
>
> Thanks.
>
> --
> Live like a child, think like the god.
>
--
Thanks & Regards,
Shaohui
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/