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] RFC: [0/2] Remove netloop by lazy copying in netback

To: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
Subject: Re: [Xen-devel] RFC: [0/2] Remove netloop by lazy copying in netback
From: Keir Fraser <keir@xxxxxxxxxxxxx>
Date: Tue, 27 Mar 2007 11:19:10 +0100
Cc: Isaku Yamahata <yamahata@xxxxxxxxxxxxx>, Xen Development Mailing List <xen-devel@xxxxxxxxxxxxxxxxxxx>
Delivery-date: Tue, 27 Mar 2007 03:18:49 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxx
In-reply-to: <20070327101521.GA25515@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/cgi-bin/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
Sender: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx
Thread-index: AcdwWVvsmnNyGtxMEdu1BgAX8io7RQ==
Thread-topic: [Xen-devel] RFC: [0/2] Remove netloop by lazy copying in netback
User-agent: Microsoft-Entourage/11.2.5.060620


On 27/3/07 11:15, "Herbert Xu" <herbert@xxxxxxxxxxxxxxxxxxx> wrote:

>> Could we shatter the ia64 guest large mappings easily? They have no benefit
>> on Xen anyway apart from some inconsequential memory saving.
> 
> I think large pages are needed in general not to reduce memory usage,
> but to reduce TLB usage.  I'm not sure about ia64, but for other
> architectures it's quite important.
> 
> So getting rid of them will add a non-trivial cost.

Is this a virtual TLB we're talking about? Xen will already have to
implicitly shatter the large mappings before updating the real TLB, since
guest machine memory map is not contiguous at the scale of large pages (even
if we tried at domain build time, it certainly wouldn't be the case when
foreign grant mappings are scattered all over the place).

 -- Keir


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

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