Re: [PATCH v2] Xen: Spread boot time page scrubbing across all available CPU's

[Dario Faggioli <dario.faggioli@citrix.com>]

[-- Attachment #1.1: Type: text/plain, Size: 1468 bytes --]

On Wed, 2014-04-09 at 10:20 -0400, Konrad Rzeszutek Wilk wrote:
> On Thu, Apr 03, 2014 at 11:00:07AM +0200, Tim Deegan wrote:

> An option would be for the worker to do:
> 
> void __init smp_scrub_heap_pages(void *data)
> {
> 	bool_t scrub_bsp = (bool_t)data;
> 	unsigned long node_id = cpu_to_node(smp_processor_id());
> 	struct scrub_region *data;
> 
> 	if (node_id == NUMA_NO_NODE)
> 		if (scrub_bsp)
> 			data = region[0];
> 		else
> 			goto out;
> 	else
> 		data = region[node_id];
> 
> and use that. Then the parameter passed in is just whether this
> is the first loop (false) or the second loop (true).
> 
> 
> Or perhaps:
> 
> >You're struggling a little to force this information into the SMP
> >protocol; I think it would be cleaner if you carved the central loop of
> >smp_scrub_heap_pages() out into its own funciton and called that here
> >instead.
> 
> Just do that and then the workers will just quit if they detect
> (node_id == NUMA_NO_NODE) and there is no parameter parsing.
> 
FWIW, I think this option would look a lot better.

> Let me try that.		
> 
Let us know how it goes... I'm also interested in this patch.

Thanks and Regards,
Dario

-- 
<<This happens because I choose it to happen!>> (Raistlin Majere)
-----------------------------------------------------------------
Dario Faggioli, Ph.D, http://about.me/dario.faggioli
Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK)


[-- Attachment #1.2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 198 bytes --]

[-- Attachment #2: Type: text/plain, Size: 126 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel