[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] alloc_heap_pages is low efficient with more CPUs

  • To: Mukesh Rathor <mukesh.rathor@xxxxxxxxxx>, tupeng212 <tupeng212@xxxxxxxxx>
  • From: Keir Fraser <keir.xen@xxxxxxxxx>
  • Date: Sat, 13 Oct 2012 07:03:30 +0100
  • Cc: xen-devel <xen-devel@xxxxxxxxxxxxx>
  • Delivery-date: Sat, 13 Oct 2012 06:04:10 +0000
  • List-id: Xen developer discussion <xen-devel.lists.xen.org>
  • Thread-index: Ac2pCHflfx8hdg+JxEacF67a9ay1yg==
  • Thread-topic: [Xen-devel] alloc_heap_pages is low efficient with more CPUs

On 12/10/2012 23:39, "Mukesh Rathor" <mukesh.rathor@xxxxxxxxxx> wrote:

> On Fri, 12 Oct 2012 20:24:16 +0800
> tupeng212 <tupeng212@xxxxxxxxx> wrote:
>> With 16 CPUs you find domain startup takes 3s always.
>> :No
>> With 16CPUs, first 0.3s, second 3s
>> With 64CPUs, first 3s, second 30s.
>> With 64 CPUs you find it takes 3s first time, then 30s in future?
>> : Yes
> ...........
> I had seen this a while ago, it was always page scrubbing. That
> algoright was changed IIRC, so not sure if still could be the cause.


If the tlbflush_filter() and cpumask_or() lines are commented out from the
if(need_tlbflush) block in alloc_heap_pages(), what are the domain creation
times like then? By the way it looks like you are not using xen-unstable or
xen-4.2, can you try with one of these later versions of Xen?

 -- Keir

> My 2 cents,
> thanks
> Mukesh

Xen-devel mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.