From: Avi Kivity <avi@redhat.com>
To: Gregory Haskins <gregory.haskins@gmail.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>,
"Ira W. Snyder" <iws@ovro.caltech.edu>,
netdev@vger.kernel.org,
virtualization@lists.linux-foundation.org, kvm@vger.kernel.org,
linux-kernel@vger.kernel.org, mingo@elte.hu, linux-mm@kvack.org,
akpm@linux-foundation.org, hpa@zytor.com,
Rusty Russell <rusty@rustcorp.com.au>,
s.hetze@linux-ag.com, alacrityvm-devel@lists.sourceforge.net
Subject: Re: [PATCHv5 3/3] vhost_net: a kernel-level virtio server
Date: Thu, 17 Sep 2009 00:00:07 +0300 [thread overview]
Message-ID: <4AB151D7.10402@redhat.com> (raw)
In-Reply-To: <4AB13B09.5040308@gmail.com>
On 09/16/2009 10:22 PM, Gregory Haskins wrote:
> Avi Kivity wrote:
>
>> On 09/16/2009 05:10 PM, Gregory Haskins wrote:
>>
>>>> If kvm can do it, others can.
>>>>
>>>>
>>> The problem is that you seem to either hand-wave over details like this,
>>> or you give details that are pretty much exactly what vbus does already.
>>> My point is that I've already sat down and thought about these issues
>>> and solved them in a freely available GPL'ed software package.
>>>
>>>
>> In the kernel. IMO that's the wrong place for it.
>>
> 3) "in-kernel": You can do something like virtio-net to vhost to
> potentially meet some of the requirements, but not all.
>
> In order to fully meet (3), you would need to do some of that stuff you
> mentioned in the last reply with muxing device-nr/reg-nr. In addition,
> we need to have a facility for mapping eventfds and establishing a
> signaling mechanism (like PIO+qid), etc. KVM does this with
> IRQFD/IOEVENTFD, but we dont have KVM in this case so it needs to be
> invented.
>
irqfd/eventfd is the abstraction layer, it doesn't need to be reabstracted.
> To meet performance, this stuff has to be in kernel and there has to be
> a way to manage it.
and management belongs in userspace.
> Since vbus was designed to do exactly that, this is
> what I would advocate. You could also reinvent these concepts and put
> your own mux and mapping code in place, in addition to all the other
> stuff that vbus does. But I am not clear why anyone would want to.
>
Maybe they like their backward compatibility and Windows support.
> So no, the kernel is not the wrong place for it. Its the _only_ place
> for it. Otherwise, just use (1) and be done with it.
>
>
I'm talking about the config stuff, not the data path.
>> Further, if we adopt
>> vbus, if drop compatibility with existing guests or have to support both
>> vbus and virtio-pci.
>>
> We already need to support both (at least to support Ira). virtio-pci
> doesn't work here. Something else (vbus, or vbus-like) is needed.
>
virtio-ira.
>>> So the question is: is your position that vbus is all wrong and you wish
>>> to create a new bus-like thing to solve the problem?
>>>
>> I don't intend to create anything new, I am satisfied with virtio. If
>> it works for Ira, excellent. If not, too bad.
>>
> I think that about sums it up, then.
>
Yes. I'm all for reusing virtio, but I'm not going switch to vbus or
support both for this esoteric use case.
>>> If so, how is it
>>> different from what Ive already done? More importantly, what specific
>>> objections do you have to what Ive done, as perhaps they can be fixed
>>> instead of starting over?
>>>
>>>
>> The two biggest objections are:
>> - the host side is in the kernel
>>
> As it needs to be.
>
vhost-net somehow manages to work without the config stuff in the kernel.
> With all due respect, based on all of your comments in aggregate I
> really do not think you are truly grasping what I am actually building here.
>
Thanks.
>>> Bingo. So now its a question of do you want to write this layer from
>>> scratch, or re-use my framework.
>>>
>>>
>> You will have to implement a connector or whatever for vbus as well.
>> vbus has more layers so it's probably smaller for vbus.
>>
> Bingo!
(addictive, isn't it)
> That is precisely the point.
>
> All the stuff for how to map eventfds, handle signal mitigation, demux
> device/function pointers, isolation, etc, are built in. All the
> connector has to do is transport the 4-6 verbs and provide a memory
> mapping/copy function, and the rest is reusable. The device models
> would then work in all environments unmodified, and likewise the
> connectors could use all device-models unmodified.
>
Well, virtio has a similar abstraction on the guest side. The host side
abstraction is limited to signalling since all configuration is in
userspace. vhost-net ought to work for lguest and s390 without change.
>> It was already implemented three times for virtio, so apparently that's
>> extensible too.
>>
> And to my point, I'm trying to commoditize as much of that process as
> possible on both the front and backends (at least for cases where
> performance matters) so that you don't need to reinvent the wheel for
> each one.
>
Since you're interested in any-to-any connectors it makes sense to you.
I'm only interested in kvm-host-to-kvm-guest, so reducing the already
minor effort to implement a new virtio binding has little appeal to me.
>> You mean, if the x86 board was able to access the disks and dma into the
>> ppb boards memory? You'd run vhost-blk on x86 and virtio-net on ppc.
>>
> But as we discussed, vhost doesn't work well if you try to run it on the
> x86 side due to its assumptions about pagable "guest" memory, right? So
> is that even an option? And even still, you would still need to solve
> the aggregation problem so that multiple devices can coexist.
>
I don't know. Maybe it can be made to work and maybe it cannot. It
probably can with some determined hacking.
--
I have a truly marvellous patch that fixes the bug which this
signature is too narrow to contain.
next prev parent reply other threads:[~2009-09-16 21:01 UTC|newest]
Thread overview: 83+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <cover.1251388414.git.mst@redhat.com>
2009-08-27 16:06 ` [PATCHv5 1/3] mm: export use_mm/unuse_mm to modules Michael S. Tsirkin
2009-08-28 15:31 ` Gregory Haskins
2009-08-27 16:07 ` [PATCHv5 2/3] mm: reduce atomic use on use_mm fast path Michael S. Tsirkin
2009-08-27 16:07 ` [PATCHv5 3/3] vhost_net: a kernel-level virtio server Michael S. Tsirkin
2009-09-03 18:39 ` Ira W. Snyder
2009-09-07 10:15 ` Michael S. Tsirkin
2009-09-08 17:20 ` Ira W. Snyder
2009-09-08 20:14 ` Michael S. Tsirkin
2009-09-11 15:17 ` Xin, Xiaohui
2009-09-13 5:46 ` Michael S. Tsirkin
2009-09-14 5:57 ` Xin, Xiaohui
2009-09-14 7:05 ` Michael S. Tsirkin
2009-09-11 16:00 ` Gregory Haskins
2009-09-11 16:14 ` Gregory Haskins
2009-09-13 12:01 ` Michael S. Tsirkin
2009-09-14 16:08 ` Gregory Haskins
2009-09-14 16:47 ` Michael S. Tsirkin
2009-09-14 19:14 ` Gregory Haskins
2009-09-15 12:35 ` Avi Kivity
2009-09-15 13:03 ` Gregory Haskins
2009-09-15 13:25 ` Avi Kivity
2009-09-15 13:50 ` Gregory Haskins
2009-09-15 14:28 ` Michael S. Tsirkin
2009-09-15 15:03 ` Avi Kivity
2009-09-15 20:08 ` Gregory Haskins
2009-09-15 20:40 ` Michael S. Tsirkin
2009-09-15 20:43 ` Gregory Haskins
2009-09-15 21:25 ` Michael S. Tsirkin
2009-09-15 21:39 ` Gregory Haskins
2009-09-15 21:38 ` Michael S. Tsirkin
2009-09-15 21:55 ` Gregory Haskins
2009-09-16 14:57 ` Arnd Bergmann
2009-09-16 15:13 ` Michael S. Tsirkin
2009-09-16 15:22 ` Arnd Bergmann
2009-09-16 16:08 ` Michael S. Tsirkin
2009-09-16 8:23 ` Avi Kivity
2009-09-16 11:44 ` Gregory Haskins
2009-09-16 13:05 ` Avi Kivity
2009-09-16 14:10 ` Gregory Haskins
2009-09-16 15:59 ` Avi Kivity
2009-09-16 19:22 ` Gregory Haskins
2009-09-16 21:00 ` Avi Kivity [this message]
2009-09-17 3:11 ` Gregory Haskins
2009-09-17 7:49 ` Avi Kivity
2009-09-17 14:16 ` Javier Guerra
2009-09-21 21:43 ` Ira W. Snyder
2009-09-22 9:43 ` Avi Kivity
2009-09-22 15:25 ` Ira W. Snyder
2009-09-22 15:56 ` Avi Kivity
2009-09-23 14:26 ` Gregory Haskins
2009-09-23 14:37 ` Avi Kivity
2009-09-23 15:10 ` Gregory Haskins
2009-09-23 17:58 ` Gregory Haskins
2009-09-23 19:37 ` Avi Kivity
2009-09-23 21:15 ` Gregory Haskins
2009-09-24 7:18 ` Avi Kivity
2009-09-24 18:03 ` Gregory Haskins
2009-09-25 8:22 ` Avi Kivity
2009-09-25 21:32 ` Gregory Haskins
2009-09-27 9:43 ` Avi Kivity
2009-09-30 20:04 ` Gregory Haskins
2009-10-01 8:34 ` Avi Kivity
2009-10-01 9:28 ` Michael S. Tsirkin
2009-10-01 19:24 ` Gregory Haskins
2009-10-03 10:00 ` Avi Kivity
2009-09-24 19:27 ` Ira W. Snyder
2009-09-25 7:43 ` Avi Kivity
2009-09-24 8:03 ` Avi Kivity
2009-09-24 18:04 ` Gregory Haskins
2009-09-17 3:57 ` Michael S. Tsirkin
2009-09-17 4:13 ` Gregory Haskins
2009-09-15 12:32 ` Avi Kivity
2009-09-14 16:53 ` Michael S. Tsirkin
2009-09-14 19:28 ` Gregory Haskins
2009-09-25 17:01 ` Ira W. Snyder
2009-09-27 7:43 ` Michael S. Tsirkin
[not found] <E88DD564E9DC5446A76B2B47C3BCCA150219600F9B@pdsmsx503.ccr.corp.intel.com>
2009-08-31 11:42 ` Xin, Xiaohui
2009-08-31 15:23 ` Arnd Bergmann
2009-09-01 14:58 ` Xin, Xiaohui
2009-08-31 17:52 ` Avi Kivity
2009-08-31 21:56 ` Anthony Liguori
2009-09-01 15:37 ` Xin, Xiaohui
2009-09-01 5:04 ` Xin, Xiaohui
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4AB151D7.10402@redhat.com \
--to=avi@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=alacrityvm-devel@lists.sourceforge.net \
--cc=gregory.haskins@gmail.com \
--cc=hpa@zytor.com \
--cc=iws@ovro.caltech.edu \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mingo@elte.hu \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=rusty@rustcorp.com.au \
--cc=s.hetze@linux-ag.com \
--cc=virtualization@lists.linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).