From: Anthony Liguori <anthony@codemonkey•ws>
To: Rusty Russell <rusty@rustcorp•com.au>,
"Michael S. Tsirkin" <mst@redhat•com>,
Thomas Lendacky <tahm@linux•vnet.ibm.com>
Cc: Sasha Levin <levinsasha928@gmail•com>,
virtualization@lists•linux-foundation.org,
linux-kernel@vger•kernel.org, avi@redhat•com,
kvm@vger•kernel.org, netdev@vger•kernel.org
Subject: Re: [PATCH 0/3] virtio-net: inline header support
Date: Wed, 03 Oct 2012 23:29:47 -0500 [thread overview]
Message-ID: <87wqz6kgg4.fsf@codemonkey.ws> (raw)
In-Reply-To: <87391u3o67.fsf@rustcorp.com.au>
Rusty Russell <rusty@rustcorp•com.au> writes:
> Anthony Liguori <anthony@codemonkey•ws> writes:
>> Rusty Russell <rusty@rustcorp•com.au> writes:
>>
>>> "Michael S. Tsirkin" <mst@redhat•com> writes:
>>>
>>>> Thinking about Sasha's patches, we can reduce ring usage
>>>> for virtio net small packets dramatically if we put
>>>> virtio net header inline with the data.
>>>> This can be done for free in case guest net stack allocated
>>>> extra head room for the packet, and I don't see
>>>> why would this have any downsides.
>>>
>>> I've been wanting to do this for the longest time... but...
>>>
>>>> Even though with my recent patches qemu
>>>> no longer requires header to be the first s/g element,
>>>> we need a new feature bit to detect this.
>>>> A trivial qemu patch will be sent separately.
>>>
>>> There's a reason I haven't done this. I really, really dislike "my
>>> implemention isn't broken" feature bits. We could have an infinite
>>> number of them, for each bug in each device.
>>
>> This is a bug in the specification.
>>
>> The QEMU implementation pre-dates the specification. All of the actual
>> implementations of virtio relied on the semantics of s/g elements and
>> still do.
>
> lguest fix is pending in my queue. lkvm and qemu are broken; lkvm isn't
> ever going to be merged, so I'm not sure what its status is? But I'm
> determined to fix qemu, and hence my torture patch to make sure this
> doesn't creep in again.
There are even more implementations out there and I'd wager they all
rely on framing.
>> What's in the specification really doesn't matter when it doesn't agree
>> with all of the existing implementations.
>>
>> Users use implementations, not specifications. The specification really
>> ought to be changed here.
>
> I'm sorely tempted, except that we're losing a real optimization because
> of this :(
What optimizations? What Michael is proposing is still achievable with
a device feature. Are there other optimizations that can be achieved by
changing framing that we can't achieve with feature bits?
As I mentioned in another note, bad framing decisions can cause
performance issues too...
> The specification has long contained the footnote:
>
> The current qemu device implementations mistakenly insist that
> the first descriptor cover the header in these cases exactly, so
> a cautious driver should arrange it so.
I seem to recall this being a compromise between you and I.. I think
I objected strongly to this back when you first wrote the spec and you
added this to appease me ;-)
Regards,
Anthony Liguori
>
> I'd like to tie this caveat to the PCI capability change, so this note
> will move to the appendix with the old PCI layout.
>
> Cheers,
> Rusty.
next prev parent reply other threads:[~2012-10-04 4:29 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-09-28 9:26 [PATCH 0/3] virtio-net: inline header support Michael S. Tsirkin
2012-09-28 9:26 ` [PATCH 1/3] virtio: add API to query ring capacity Michael S. Tsirkin
2012-09-28 9:26 ` [PATCH 2/3] virtio-net: correct capacity math on ring full Michael S. Tsirkin
2012-10-04 0:24 ` Rusty Russell
2012-09-28 9:26 ` [PATCH 3/3] virtio-net: put virtio net header inline with data Michael S. Tsirkin
2012-10-03 6:44 ` [PATCH 0/3] virtio-net: inline header support Rusty Russell
2012-10-03 7:10 ` Rusty Russell
2012-10-04 1:24 ` Anthony Liguori
2012-10-04 3:34 ` Rusty Russell
2012-10-04 4:29 ` Anthony Liguori [this message]
2012-10-04 7:44 ` Rusty Russell
2012-10-05 7:47 ` Paolo Bonzini
2012-10-08 21:31 ` Michael S. Tsirkin
2012-10-04 1:35 ` Anthony Liguori
2012-10-04 5:17 ` Rusty Russell
2012-10-08 20:41 ` Michael S. Tsirkin
[not found] ` <87vces2gxq.fsf__45058.6618776017$1349247807$gmane$org@rustcorp.com.au>
2012-10-03 10:53 ` Paolo Bonzini
2012-10-04 0:11 ` Rusty Russell
2012-10-04 7:09 ` Paolo Bonzini
2012-10-04 12:51 ` Rusty Russell
2012-10-04 13:23 ` Paolo Bonzini
2012-10-05 5:43 ` Rusty Russell
[not found] ` <87391t1nkq.fsf__40391.6521034718$1349505001$gmane$org@rustcorp.com.au>
2012-10-06 12:54 ` Paolo Bonzini
2012-10-09 4:59 ` Rusty Russell
2012-10-09 7:27 ` Paolo Bonzini
2012-10-11 0:03 ` Rusty Russell
2012-10-11 11:04 ` Michael S. Tsirkin
2012-10-11 22:37 ` Rusty Russell
2012-10-12 7:38 ` Paolo Bonzini
2012-10-12 11:52 ` Cornelia Huck
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=87wqz6kgg4.fsf@codemonkey.ws \
--to=anthony@codemonkey$(echo .)ws \
--cc=avi@redhat$(echo .)com \
--cc=kvm@vger$(echo .)kernel.org \
--cc=levinsasha928@gmail$(echo .)com \
--cc=linux-kernel@vger$(echo .)kernel.org \
--cc=mst@redhat$(echo .)com \
--cc=netdev@vger$(echo .)kernel.org \
--cc=rusty@rustcorp$(echo .)com.au \
--cc=tahm@linux$(echo .)vnet.ibm.com \
--cc=virtualization@lists$(echo .)linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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