[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <49D65647.2000502@novell.com>
Date: Fri, 03 Apr 2009 14:32:39 -0400
From: Gregory Haskins <ghaskins@...ell.com>
To: Chris Wright <chrisw@...s-sol.org>
CC: Avi Kivity <avi@...hat.com>,
Patrick Mullaney <pmullaney@...ell.com>, anthony@...emonkey.ws,
andi@...stfloor.org, herbert@...dor.apana.org.au,
Peter Morreale <PMorreale@...ell.com>, rusty@...tcorp.com.au,
agraf@...e.de, kvm@...r.kernel.org, linux-kernel@...r.kernel.org,
netdev@...r.kernel.org
Subject: Re: [RFC PATCH 00/17] virtual-bus
Chris Wright wrote:
> * Gregory Haskins (ghaskins@...ell.com) wrote:
>
>> Let me ask you this: If you had a clean slate and were designing a
>> hypervisor and a guest OS from scratch: What would you make the bus
>> look like?
>>
>
> Well, virtio did have a relatively clean slate. And PCI (as _one_
> transport option) is what it looks like. It's not the only transport
> (as Avi already mentioned it works for s390, for example).
>
Got it. Thanks.
> BTW, from my brief look at vbus, it seems pretty similar to xenbus.
>
If you are referring to the guest side interface, it was actually
inspired by lguest's bus (I forget what Rusty called it now, though).
I think I actually declared that in the original patch series I put out
1.5 years ago, but I might have inadvertently omitted that on this
go-round.
I think XenBus is more of an event channel infrastructure, isn't it?
But in any case, I think the nature of getting PV drivers into a guest
is relatively similar, so I wouldn't be surprised if there were
parallels in quite a few of the implementations. In fact, I chose a
generic name like "vbus" in hopes that it could be used across different
hypervisors. :)
-Greg
Download attachment "signature.asc" of type "application/pgp-signature" (258 bytes)
Powered by blists - more mailing lists