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] SWIOMMU redundant copies?

To: "Stephen C. Tweedie" <sct@xxxxxxxxxx>, "xen-devel@xxxxxxxxxxxxxxxxxxx" <xen-devel@xxxxxxxxxxxxxxxxxxx>
Subject: Re: [Xen-devel] SWIOMMU redundant copies?
From: Keir Fraser <keir.fraser@xxxxxxxxxxxxx>
Date: Fri, 14 Mar 2008 16:26:26 +0000
Delivery-date: Fri, 14 Mar 2008 09:27:51 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxx
In-reply-to: <1205509828.8010.31.camel@xxxxxxxxxxxxxxxxxxxxx>
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: AciF8CY5ZMs/bfHjEdyPnAAWy6hiGQ==
Thread-topic: [Xen-devel] SWIOMMU redundant copies?
User-agent: Microsoft-Entourage/11.3.6.070618
Yes, the swiotlb check could be relaxed. Do we really do many mergeable
page-straddling I/Os in practice though? I would expect most block I/O to be
scattered by the page cache.

 -- Keir

On 14/3/08 15:50, "Stephen C. Tweedie" <sct@xxxxxxxxxx> wrote:

> So we'll create bios which span multiple pages, assuming that that's
> more efficient; but then we'll force them to be copied because they span
> multiple pages!
> 
> Have I missed something, or is this an oversight in the swiotlb.c patch
> above?
> 
> The reason I discovered this is that including the patch seems to be
> causing SWIOTLB overflows on some hardware.  Adding an extra test to
> swiotlb_map_sg() to catch sg segments which are truly machine-contig and
> don't need mapping, and avoid copying those, cures those symptoms for
> me, but I suspect there may be other issues lurking in this area.



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

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