From: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
To: Avi Kivity <avi@qumranet.com>
Cc: kvm-ppc-devel <kvm-ppc-devel@lists.sourceforge.net>,
kvm-devel <kvm-devel@lists.sourceforge.net>,
Hollis Blanchard <hollisb@us.ibm.com>
Subject: Re: [kvm-ppc-devel] virtio-net working on PowerPC KVM
Date: Mon, 31 Mar 2008 06:52:04 +0200 [thread overview]
Message-ID: <47F06DF4.3090200@linux.vnet.ibm.com> (raw)
In-Reply-To: <47EF6BE8.80202@qumranet.com>
Avi Kivity wrote:
> Hollis Blanchard wrote:
>> I'm pleased to report that we now have working network support in the
>> guest, via the virtio-net driver. In fact, we can use NFS for the
>> guest's root filesystem. :) Boot log attached.
>>
>>
>
> Congrats!
>
>> The bad news is that it's very slow, but the good news is that it's nice
>> to be improving performance rather than debugging mysterious
>> crashes... ;)
>>
>> With this milestone reached, in the near future I intend to start
>> sending patches to Avi and linuxppc-dev for review, hopefully for
>> inclusion in 2.6.26. However, I do want to see if we can improve the
>> performance a little bit first...
>>
>
> Low virtio net performance may be due to the virtio net host timer.
> What's your guest/host ping latency?
I would be happy about 0.25ms atm :-). The current ping latency to the Host or other PC's is around 7-8ms (native sys is ~0.15ms).
We are investigating performance improvements in general and also some changes in the setup e.g. booting from virtio-block as alternative for some speedup.
> Even if you have a good hrtimer implementation, I think you'll see
> 0.25ms latency, and that may be enough to slow down nfs. Unfortunately
> virtio is tuned for throughput at this time (it should be easy to
> disable the timer when we detect the queue is usually empty).
>
--
Grüsse / regards,
Christian Ehrhardt
IBM Linux Technology Center, Open Virtualization
-------------------------------------------------------------------------
Check out the new SourceForge.net Marketplace.
It's the best place to buy or sell services for
just about anything Open Source.
http://ad.doubleclick.net/clk;164216239;13503038;w?http://sf.net/marketplace
next prev parent reply other threads:[~2008-03-31 4:52 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-03-28 22:33 virtio-net working on PowerPC KVM Hollis Blanchard
2008-03-29 9:04 ` [kvm-ppc-devel] " Zhang Wei
2008-03-30 10:31 ` Avi Kivity
2008-03-31 4:52 ` Christian Ehrhardt [this message]
2008-03-31 7:45 ` [kvm-ppc-devel] " Alexander Graf
2008-03-31 7:43 ` Avi Kivity
2008-03-31 8:17 ` Alexander Graf
2008-03-31 8:28 ` Avi Kivity
2008-03-31 9:09 ` Dor Laor
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=47F06DF4.3090200@linux.vnet.ibm.com \
--to=ehrhardt@linux.vnet.ibm.com \
--cc=avi@qumranet.com \
--cc=hollisb@us.ibm.com \
--cc=kvm-devel@lists.sourceforge.net \
--cc=kvm-ppc-devel@lists.sourceforge.net \
/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