WARNING - OLD ARCHIVES

This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
   
 
 
Xen 
 
Home Products Support Community News
 
   
 

xen-devel

RE: [Xen-devel] [Patch 2 of 2]: PV-domain SMP performance Linux-part

To: "Juergen Gross" <juergen.gross@xxxxxxxxxxxxxxxxxxx>, "Venefax" <venefax@xxxxxxxxx>
Subject: RE: [Xen-devel] [Patch 2 of 2]: PV-domain SMP performance Linux-part
From: "James Harper" <james.harper@xxxxxxxxxxxxxxxx>
Date: Fri, 16 Jan 2009 21:16:19 +1100
Cc: George Dunlap <George.Dunlap@xxxxxxxxxxxxx>, xen-devel@xxxxxxxxxxxxxxxxxxx, Keir Fraser <keir.fraser@xxxxxxxxxxxxx>
Delivery-date: Fri, 16 Jan 2009 02:17:02 -0800
Envelope-to: www-data@xxxxxxxxxxxxxxxxxxx
In-reply-to: <49703BDB.4090805@xxxxxxxxxxxxxxxxxxx>
List-help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-id: Xen developer discussion <xen-devel.lists.xensource.com>
List-post: <mailto:xen-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
References: <C5712030.206AD%keir.fraser@xxxxxxxxxxxxx><4970344D.7030009@xxxxxxxxxxxxxxxxxxx><059f01c977ad$5e40c380$1ac24a80$@com> <49703BDB.4090805@xxxxxxxxxxxxxxxxxxx>
Sender: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx
Thread-index: Acl3rwQU85YH/4sVSvS2s/NknOY4ggAEnvzw
Thread-topic: [Xen-devel] [Patch 2 of 2]: PV-domain SMP performance Linux-part
> 
> Venefax wrote:
> > I can test it a real-world situation.
> > I have SUSE 10-SP2 and have terrible performance issues with fully
> > virtualized SMP machines. I had to start using Standard PC as HAL to
> avoid
> > the penalty.
> > Federico
> 
> Federico, thanks for your support. But my patches are for PV-domains
(or
> at
> least for domains with PV-drivers) only. I think you are using Windows
as
> guest, so you would have to build a XEN-aware HAL...
> 
> If you are testing with PV-domains, too, you are welcome, of course!
> 

Juergen,

Do you think your changes could be applicable to HVM domains with
appropriately patched kernel spinlock routines?

I had previously wondered about optimizing spinlocks, my idea was
basically for Xen to set a bit in a structure to indicate what vcpus are
currently scheduled, and my modified spinlock acquire routine would
check if the current vcpu wants a spinlock that is held by a currently
unscheduled vcpu, and if so yield to Xen to let the other vcpu schedule.

The only thing I would need from Xen is to know which vcpus were
currently scheduled, the rest would be DomU based.

Does that approximate what you do? I'll re-read your patch, I seem to
remember something about borrowing time from Xen to keep the vcpu a
little longer if a spinlock was held, so maybe you are taking a
proactive approach to my reactive approach?

The likelihood of this actually doing anything useful assumes that:
. Windows always uses the KeAcquireXxx and KeReleaseXxx calls and there
is no inlined spinlock access in the kernel (which would bypass my
hooks)
. That when Windows spins, it doesn't yield already
. That Xen actually deschedules a vcpu with a spinlock held often enough
for this to matter

Kernel patching only works on 32 bits though, so I'm not sure I'll
bother.

James 


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel

<Prev in Thread] Current Thread [Next in Thread>