linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Gleb Natapov <gleb@redhat.com>
To: Asias He <asias.hejun@gmail.com>
Cc: Avi Kivity <avi@redhat.com>, Pekka Enberg <penberg@kernel.org>,
	richard -rw- weinberger <richard.weinberger@gmail.com>,
	Ingo Molnar <mingo@kernel.org>,
	Christoph Hellwig <hch@infradead.org>,
	Dave Airlie <airlied@gmail.com>, Borislav Petkov <bp@alien8.de>,
	Stephen Rothwell <sfr@canb.auug.org.au>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-kernel@vger.kernel.org,
	Sasha Levin <levinsasha928@gmail.com>,
	Cyrill Gorcunov <gorcunov@openvz.org>
Subject: Re: [GIT PULL] Linux KVM tool for v3.7-rc0
Date: Wed, 31 Oct 2012 17:05:47 +0200	[thread overview]
Message-ID: <20121031150547.GE25650@redhat.com> (raw)
In-Reply-To: <CAFO3S43HEKiLtRMzYije_8K88zyhiz86HE6bUjWRvaE5cLxviA@mail.gmail.com>

On Tue, Oct 23, 2012 at 10:20:34AM +0800, Asias He wrote:
> On Mon, Oct 22, 2012 at 6:16 PM, Gleb Natapov <gleb@redhat.com> wrote:
> > On Mon, Oct 22, 2012 at 11:24:19AM +0200, Avi Kivity wrote:
> >> On 10/21/2012 05:39 PM, Pekka Enberg wrote:
> >> >
> >> > On Sun, Oct 21, 2012 at 5:02 PM, richard -rw- weinberger
> >> > <richard.weinberger@gmail.com> wrote:
> >> >> qemu supports all these features.
> >> >> E.g. to access the host fs use:
> >> >> qemu ... \
> >> >>   -fsdev local,security_model=passthrough,id=fsdev-root,path=/your/root/,readonly
> >> >> \
> >> >>   -device virtio-9p-pci,id=fs-root,fsdev=fsdev-root,mount_tag=rootshare
> >> >
> >> > IIRC, QEMU uses SLIRP non-root zero-config networking which is much
> >> > more limited than what LKVM offers out of the box.
> >>
> >> Curious, what are the differences?
> >>
> > Me too, especially as we discussed replacing SLIRP with lkvm code for
> > userspace networking and decided (for reasons I do not remember) that it
> > lacks futures SLIRP has. Was it host port redirection?
> 
> Yes.  Currently, there is no host to guest port forward support in lkvm.
> However, it's faster than slirp.
> e.g. tcp bandwidth in a 100Mb/s environment
> lkvm's userspace networking ~90Mb/s  v.s qemu's slirp  ~10Mb/s
> 
This is not entirely slirp fault BTW. If you run QEMU with "-usbdevice tablet", slirp
bandwidth goes up to 80-90Mb too.

--
			Gleb.

  reply	other threads:[~2012-10-31 15:06 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-10-12 11:34 [GIT PULL] Linux KVM tool for v3.7-rc0 Pekka Enberg
2012-10-12 17:27 ` Christoph Hellwig
2012-10-18 10:03   ` Ingo Molnar
2012-10-18 10:31     ` Pekka Enberg
2012-10-16  2:41 ` Stephen Rothwell
2012-10-16 14:50   ` Linus Torvalds
2012-10-20  7:04     ` Stephen Rothwell
2012-10-20 18:14       ` Borislav Petkov
2012-10-21  3:07         ` Dave Airlie
2012-10-21  3:46           ` Yinghai Lu
2012-10-21 11:03           ` Christoph Hellwig
2012-10-21 12:59             ` Ingo Molnar
2012-10-21 14:02               ` richard -rw- weinberger
2012-10-21 15:03                 ` Ingo Molnar
2012-10-21 17:15                   ` Borislav Petkov
2012-10-21 17:40                     ` Markus Trippelsdorf
2012-10-21 17:51                       ` Ingo Molnar
2012-10-21 17:54                         ` Markus Trippelsdorf
2012-10-21 18:04                           ` Markus Trippelsdorf
2012-10-21 18:10                             ` Ingo Molnar
2012-10-22  9:26                               ` Avi Kivity
2012-10-21 18:09                           ` Ingo Molnar
2012-10-21 15:39                 ` Pekka Enberg
2012-10-22  9:24                   ` Avi Kivity
2012-10-22 10:16                     ` Gleb Natapov
2012-10-23  2:20                       ` Asias He
2012-10-31 15:05                         ` Gleb Natapov [this message]
2012-10-21 11:18           ` Borislav Petkov
2012-10-21 11:29             ` richard -rw- weinberger
2012-10-21 22:16               ` Theodore Ts'o
2012-11-14  5:24       ` Stephen Rothwell
2012-11-14  6:02         ` Theodore Ts'o

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=20121031150547.GE25650@redhat.com \
    --to=gleb@redhat.com \
    --cc=airlied@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=asias.hejun@gmail.com \
    --cc=avi@redhat.com \
    --cc=bp@alien8.de \
    --cc=gorcunov@openvz.org \
    --cc=hch@infradead.org \
    --cc=levinsasha928@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=penberg@kernel.org \
    --cc=richard.weinberger@gmail.com \
    --cc=sfr@canb.auug.org.au \
    --cc=torvalds@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).