From: Rusty Russell <rusty@rustcorp.com.au>
To: Arnd Bergmann <arnd@arndb.de>
Cc: Chris Wright <chrisw@sous-sol.org>,
Herbert Xu <herbert@gondor.apana.org.au>,
kvm@vger.kernel.org
Subject: Re: copyless virtio net thoughts?
Date: Thu, 19 Feb 2009 21:26:42 +1030 [thread overview]
Message-ID: <200902192126.43174.rusty@rustcorp.com.au> (raw)
In-Reply-To: <200902181724.07655.arnd@arndb.de>
On Thursday 19 February 2009 02:54:06 Arnd Bergmann wrote:
> On Wednesday 18 February 2009, Rusty Russell wrote:
>
> > 2) Direct NIC attachment
> > This is particularly interesting with SR-IOV or other multiqueue nics,
> > but for boutique cases or benchmarks, could be for normal NICs. So
> > far I have some very sketched-out patches: for the attached nic
> > dev_alloc_skb() gets an skb from the guest (which supplies them via
> > some kind of AIO interface), and a branch in netif_receive_skb()
> > which returned it to the guest. This bypasses all firewalling in
> > the host though; we're basically having the guest process drive
> > the NIC directly.
>
> If this is not passing the PCI device directly to the guest, but
> uses your concept, wouldn't it still be possible to use the firewalling
> in the host? You can always inspect the headers, drop the frame, etc
> without copying the whole frame at any point.
It's possible, but you don't want routing or parsing, etc: the NIC
is just "directly" attached to the guest.
You could do it in qemu or whatever, but it would not be the kernel scheme
(netfilter/iptables).
> > 3) Direct interguest networking
> > Anthony has been thinking here: vmsplice has already been mentioned.
> > The idea of passing directly from one guest to another is an
> > interesting one: using dma engines might be possible too. Again,
> > host can't firewall this traffic. Simplest as a dedicated "internal
> > lan" NIC, but we could theoretically do a fast-path for certain MAC
> > addresses on a general guest NIC.
>
> Another option would be to use an SR-IOV adapter from multiple guests,
> with a virtual ethernet bridge in the adapter. This moves the overhead
> from the CPU to the bus and/or adapter, so it may or may not be a real
> benefit depending on the workload.
Yes, I guess this should work. Even different SR-IOV adapters will simply
send to one another. I'm not sure this obviates the desire to have direct
inter-guest which is more generic though.
Thanks!
Rusty.
next prev parent reply other threads:[~2009-02-19 10:56 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-02-05 2:07 copyless virtio net thoughts? Chris Wright
2009-02-05 12:37 ` Avi Kivity
2009-02-05 14:25 ` Anthony Liguori
2009-02-06 5:40 ` Herbert Xu
2009-02-06 8:46 ` Avi Kivity
2009-02-06 9:19 ` Herbert Xu
2009-02-06 14:55 ` Avi Kivity
2009-02-07 11:56 ` Arnd Bergmann
2009-02-08 3:01 ` David Miller
2009-02-18 11:38 ` Rusty Russell
2009-02-18 12:17 ` Herbert Xu
2009-02-18 16:24 ` Arnd Bergmann
2009-02-19 10:56 ` Rusty Russell [this message]
2009-02-18 23:31 ` Simon Horman
2009-02-19 1:03 ` Dong, Eddie
2009-02-19 11:36 ` Rusty Russell
2009-02-19 14:51 ` Arnd Bergmann
2009-02-19 23:09 ` Simon Horman
2009-02-19 11:37 ` Chris Wright
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=200902192126.43174.rusty@rustcorp.com.au \
--to=rusty@rustcorp.com.au \
--cc=arnd@arndb.de \
--cc=chrisw@sous-sol.org \
--cc=herbert@gondor.apana.org.au \
--cc=kvm@vger.kernel.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