| |
|
 |
|
 |
|
|
|
| |
|
|
xen-ia64-devel
RE: Transparent paravirtualization vs. xen paravirtualization(was:RE: [X
|
To: |
"Yang, Fred" <fred.yang@xxxxxxxxx>, "Dong, Eddie" <eddie.dong@xxxxxxxxx>, "Tristan Gingold" <Tristan.Gingold@xxxxxxxx>, <xen-ia64-devel@xxxxxxxxxxxxxxxxxxx> |
|
Subject: |
RE: Transparent paravirtualization vs. xen paravirtualization(was:RE: [Xen-ia64-devel] IRQ management) |
|
From: |
"Magenheimer, Dan (HP Labs Fort Collins)" <dan.magenheimer@xxxxxx> |
|
Date: |
Tue, 25 Oct 2005 19:45:52 -0700 |
|
Delivery-date: |
Wed, 26 Oct 2005 02:43:25 +0000 |
|
Envelope-to: |
www-data@xxxxxxxxxxxxxxxxxxx |
|
List-help: |
<mailto:xen-ia64-devel-request@lists.xensource.com?subject=help> |
|
List-id: |
Discussion of the ia64 port of Xen <xen-ia64-devel.lists.xensource.com> |
|
List-post: |
<mailto:xen-ia64-devel@lists.xensource.com> |
|
List-subscribe: |
<http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-ia64-devel>, <mailto:xen-ia64-devel-request@lists.xensource.com?subject=subscribe> |
|
List-unsubscribe: |
<http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-ia64-devel>, <mailto:xen-ia64-devel-request@lists.xensource.com?subject=unsubscribe> |
|
Sender: |
xen-ia64-devel-bounces@xxxxxxxxxxxxxxxxxxx |
|
Thread-index: |
AcXYoH5VC58JP0jcTAKD11ElTp2+BAADaykAABRR42AAGmYeQAAVNmjAAAVaOgA= |
|
Thread-topic: |
Transparent paravirtualization vs. xen paravirtualization(was:RE: [Xen-ia64-devel] IRQ management) |
> The community should try to reduce recurrent effort.
I agree entirely but I think the correct way to do this is
to determine and implement a proper interface between
arch-dep and arch-neutral functionality for Xen, as was done on
Linux. We were successful at doing this for the core hypervisor.
We need to do this for drivers too.
> Key issue on
> gnttab is Domain0 should also have PMT table support, which shouldn't
> access machine physical with gpn=mpn directly. This issue is also the
> key reason causing major effort in porting VBD/DomainU for
> each upstream
> merge. This also blocks the forward VNIF effort due to page flipping
> issue.
> PMT is a must for gnttab to support VBD, VNIF and forward
> development of
> Xen/ia64. PMT would need to be shared between Domain and Xen for
> performance
I guess I disagree. I've seen all the patches for each upstream
merge and it doesn't look to me as if a major design change
is required, just a clarification of the arch-specific boundaries.
Could you explain what you mean by "blocks the forward VNIF effort
due to page flipping issue"? Page flipping should work just fine
in the current design; Matt had it almost working (out of tree)
before he went back to school.
> > By fixing irq handling and clearly understanding and properly
> > implementing architectural neutrality in event channels and
> > grant tables, I think we will eliminate most of the rebasing
> > difficulties.
> Key issue is Xen/ia64 shouldn't derail from basic grant table design
I don't see that it is significantly different. We moved to
a separate file only as a temporary measure because there were
a handful of x86-specific lines of code in the core gnttab.c.
Unfortunately, we have not yet merged back, and that is the
source of some of the upstream merge issues.
_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ia64-devel
|
|
|
| |
|
Home