All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Michael S. Tsirkin" <mst@redhat.com>
To: Rusty Russell <rusty@rustcorp.com.au>
Cc: Sasha Levin <levinsasha928@gmail.com>,
	virtualization@lists.linux-foundation.org,
	linux-kernel@vger.kernel.org, avi@redhat.com,
	kvm@vger.kernel.org
Subject: Re: [PATCH v2 2/2] virtio-ring: Allocate indirect buffers from cache when possible
Date: Fri, 7 Sep 2012 03:06:23 +0300	[thread overview]
Message-ID: <20120907000623.GA3000@redhat.com> (raw)
In-Reply-To: <87txvahfv3.fsf@rustcorp.com.au>

On Fri, Sep 07, 2012 at 09:19:04AM +0930, Rusty Russell wrote:
> "Michael S. Tsirkin" <mst@redhat.com> writes:
> 
> > On Thu, Sep 06, 2012 at 05:27:23PM +0930, Rusty Russell wrote:
> >> "Michael S. Tsirkin" <mst@redhat.com> writes:
> >> > Yes without checksum net core always linearizes packets, so yes it is
> >> > screwed.
> >> > For -net, skb always allocates space for 17 frags + linear part so
> >> > it seems sane to do same in virtio core, and allocate, for -net,
> >> > up to max_frags + 1 from cache.
> >> > We can adjust it: no _SG -> 2 otherwise 18.
> >> 
> >> But I thought it used individual buffers these days?
> >
> > Yes for receive, no for transmit. That's probably why
> > we should have the threshold per vq, not per device, BTW.
> 
> Can someone actually run with my histogram patch and see what the real
> numbers are?
> 
> I'm not convinced that the ideal 17-buffer case actually happens as much
> as we think.  And if it's not happening with this netperf test, we're
> testing the wrong thing.
> 
> Thanks,
> Rusty.

hope to play with it next week

WARNING: multiple messages have this Message-ID (diff)
From: "Michael S. Tsirkin" <mst@redhat.com>
To: Rusty Russell <rusty@rustcorp.com.au>
Cc: linux-kernel@vger.kernel.org, avi@redhat.com,
	Sasha Levin <levinsasha928@gmail.com>,
	kvm@vger.kernel.org, virtualization@lists.linux-foundation.org
Subject: Re: [PATCH v2 2/2] virtio-ring: Allocate indirect buffers from cache when possible
Date: Fri, 7 Sep 2012 03:06:23 +0300	[thread overview]
Message-ID: <20120907000623.GA3000@redhat.com> (raw)
In-Reply-To: <87txvahfv3.fsf@rustcorp.com.au>

On Fri, Sep 07, 2012 at 09:19:04AM +0930, Rusty Russell wrote:
> "Michael S. Tsirkin" <mst@redhat.com> writes:
> 
> > On Thu, Sep 06, 2012 at 05:27:23PM +0930, Rusty Russell wrote:
> >> "Michael S. Tsirkin" <mst@redhat.com> writes:
> >> > Yes without checksum net core always linearizes packets, so yes it is
> >> > screwed.
> >> > For -net, skb always allocates space for 17 frags + linear part so
> >> > it seems sane to do same in virtio core, and allocate, for -net,
> >> > up to max_frags + 1 from cache.
> >> > We can adjust it: no _SG -> 2 otherwise 18.
> >> 
> >> But I thought it used individual buffers these days?
> >
> > Yes for receive, no for transmit. That's probably why
> > we should have the threshold per vq, not per device, BTW.
> 
> Can someone actually run with my histogram patch and see what the real
> numbers are?
> 
> I'm not convinced that the ideal 17-buffer case actually happens as much
> as we think.  And if it's not happening with this netperf test, we're
> testing the wrong thing.
> 
> Thanks,
> Rusty.

hope to play with it next week

  reply	other threads:[~2012-09-07  0:05 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-08-28 13:04 [PATCH v2 1/2] virtio-ring: Use threshold for switching to indirect descriptors Sasha Levin
2012-08-28 13:04 ` Sasha Levin
2012-08-28 13:04 ` [PATCH v2 2/2] virtio-ring: Allocate indirect buffers from cache when possible Sasha Levin
2012-08-28 13:04   ` Sasha Levin
2012-08-28 13:20   ` Michael S. Tsirkin
2012-08-28 13:20     ` Michael S. Tsirkin
2012-08-28 13:35     ` Sasha Levin
2012-08-28 13:35       ` Sasha Levin
2012-08-29 11:07       ` Michael S. Tsirkin
2012-08-29 11:07         ` Michael S. Tsirkin
2012-08-29 15:03         ` Sasha Levin
2012-08-29 15:03           ` Sasha Levin
2012-08-29 15:14           ` Michael S. Tsirkin
2012-08-29 15:14             ` Michael S. Tsirkin
2012-08-30 10:34             ` Sasha Levin
2012-08-30 10:34               ` Sasha Levin
2012-08-29 15:38           ` Michael S. Tsirkin
2012-08-29 15:38             ` Michael S. Tsirkin
2012-08-29 16:50             ` Sasha Levin
2012-08-29 16:50               ` Sasha Levin
2012-09-06  1:02               ` Rusty Russell
2012-09-06  1:02                 ` Rusty Russell
2012-09-06  5:02                 ` Michael S. Tsirkin
2012-09-06  5:02                   ` Michael S. Tsirkin
2012-09-06  7:57                   ` Rusty Russell
2012-09-06  7:57                   ` Rusty Russell
2012-09-06  8:45                     ` Michael S. Tsirkin
2012-09-06  8:45                       ` Michael S. Tsirkin
2012-09-06 23:49                       ` Rusty Russell
2012-09-07  0:06                         ` Michael S. Tsirkin [this message]
2012-09-07  0:06                           ` Michael S. Tsirkin
2012-09-10 15:47                         ` Thomas Lendacky
2012-09-10 16:08                           ` Michael S. Tsirkin
2012-09-10 16:08                             ` Michael S. Tsirkin
2012-09-12  6:13                           ` Rusty Russell
2012-09-12 10:44                             ` Sasha Levin
2012-09-12 10:44                               ` Sasha Levin
2012-10-23 15:14                               ` Michael S. Tsirkin
2012-10-23 15:14                                 ` Michael S. Tsirkin
2012-09-12  6:13                           ` Rusty Russell
2012-09-10 16:01                         ` Thomas Lendacky
2012-09-10 16:01                         ` Thomas Lendacky
2012-09-06 23:49                       ` Rusty Russell
2012-09-10 15:52                   ` Paolo Bonzini
2012-09-10 15:52                     ` Paolo Bonzini
2012-09-06  0:02       ` Rusty Russell
2012-09-06  0:02       ` Rusty Russell
2012-08-29 15:38   ` Michael S. Tsirkin
2012-08-29 15:38     ` Michael S. Tsirkin
2012-08-29 17:14     ` Sasha Levin
2012-08-29 17:14       ` Sasha Levin
2012-08-29 18:12       ` Michael S. Tsirkin
2012-08-29 18:12         ` Michael S. Tsirkin
2012-08-29 20:46         ` Sasha Levin
2012-08-29 20:46           ` Sasha Levin
2012-08-29 22:52           ` Michael S. Tsirkin
2012-08-29 22:52             ` Michael S. Tsirkin
2012-08-28 13:20 ` [PATCH v2 1/2] virtio-ring: Use threshold for switching to indirect descriptors Michael S. Tsirkin
2012-08-28 13:20   ` Michael S. Tsirkin

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=20120907000623.GA3000@redhat.com \
    --to=mst@redhat.com \
    --cc=avi@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=levinsasha928@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rusty@rustcorp.com.au \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.