From: Wei Wang <wei.w.wang@intel.com>
To: Jason Wang <jasowang@redhat.com>, "Michael S. Tsirkin" <mst@redhat.com>
Cc: "virtio-dev@lists.oasis-open.org"
<virtio-dev@lists.oasis-open.org>,
"stefanha@gmail.com" <stefanha@gmail.com>,
"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>,
"jan.scheurich@ericsson.com" <jan.scheurich@ericsson.com>,
"armbru@redhat.com" <armbru@redhat.com>,
"marcandre.lureau@gmail.com" <marcandre.lureau@gmail.com>,
"pbonzini@redhat.com" <pbonzini@redhat.com>
Subject: Re: [Qemu-devel] [virtio-dev] Re: [virtio-dev] Re: [PATCH v1] virtio-net: enable configurable tx queue size
Date: Tue, 13 Jun 2017 15:17:27 +0800 [thread overview]
Message-ID: <593F9187.6040800@intel.com> (raw)
In-Reply-To: <f8a64b2c-e769-4e9c-1cc6-ad31ea266010@redhat.com>
On 06/13/2017 02:29 PM, Jason Wang wrote:
> The issue is what if there's a mismatch of max #sgs between qemu and
>>>> When the vhost backend is used, QEMU is not involved in the data path.
>>>> The vhost backend
>>>> directly gets what is offered by the guest from the vq. Why would
>>>> there be a mismatch of
>>>> max #sgs between QEMU and vhost, and what is the QEMU side max #sgs
>>>> used for? Thanks.
>>> You need query the backend max #sgs in this case at least. no? If not
>>> how do you know the value is supported by the backend?
>>>
>>> Thanks
>>>
>> Here is my thought: vhost backend has already been supporting 1024 sgs,
>> so I think it might not be necessary to query the max sgs that the vhost
>> backend supports. In the setup phase, when QEMU detects the backend is
>> vhost, it assumes 1024 max sgs is supported, instead of giving an extra
>> call to query.
>
> We can probably assume vhost kernel supports up to 1024 sgs. But how
> about for other vhost-user backends?
>
So far, I haven't seen any vhost backend implementation supporting less
than 1024 sgs.
> And what you said here makes me ask one of my questions in the past:
>
> Do we have plan to extend 1024 to a larger value or 1024 looks good
> for the future years? If we only care about 1024, there's even no need
> for a new config filed, a feature flag is more than enough. If we want
> to extend it to e.g 2048, we definitely need to query vhost backend's
> limit (even for vhost-kernel).
>
According to virtio spec (e.g. 2.4.4), unreasonably large descriptors are
not encouraged to be used by the guest. If possible, I would suggest to use
1024 as the largest number of descriptors that the guest can chain, even
when
we have larger queue size in the future. That is,
if (backend == QEMU backend)
config.max_chain_size = 1023 (defined by the qemu backend
implementation);
else if (backend == vhost)
config.max_chain_size = 1024;
It is transparent to the guest. From the guest's point of view, all it
knows is a value
given to him via reading config.max_chain_size.
Best,
Wei
next prev parent reply other threads:[~2017-06-13 7:16 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-06-05 8:57 [Qemu-devel] [PATCH v1] virtio-net: enable configurable tx queue size Wei Wang
2017-06-05 15:38 ` Michael S. Tsirkin
2017-06-05 15:41 ` Eric Blake
2017-06-05 15:45 ` Michael S. Tsirkin
2017-06-06 3:32 ` Wei Wang
2017-06-07 1:04 ` Wei Wang
2017-06-08 19:01 ` Michael S. Tsirkin
2017-06-09 3:00 ` Wei Wang
2017-06-12 9:30 ` [Qemu-devel] [virtio-dev] " Wei Wang
2017-06-12 20:43 ` Michael S. Tsirkin
2017-06-13 3:10 ` Wei Wang
2017-06-13 3:19 ` Jason Wang
2017-06-13 3:51 ` Wei Wang
2017-06-13 3:55 ` Jason Wang
2017-06-13 3:59 ` Jason Wang
2017-06-13 6:13 ` Wei Wang
2017-06-13 6:31 ` Jason Wang
2017-06-13 7:49 ` [Qemu-devel] [virtio-dev] " Wei Wang
2017-06-13 6:08 ` [Qemu-devel] " Wei Wang
2017-06-13 6:29 ` [Qemu-devel] [virtio-dev] " Jason Wang
2017-06-13 7:17 ` Wei Wang [this message]
2017-06-13 9:04 ` Jason Wang
2017-06-13 9:50 ` Wei Wang
2017-06-13 10:46 ` Jason Wang
2017-06-14 11:26 ` Jason Wang
2017-06-14 15:22 ` Michael S. Tsirkin
2017-06-15 4:16 ` Jason Wang
2017-06-15 6:52 ` [Qemu-devel] [virtio-dev] " Wei Wang
2017-06-16 3:22 ` Michael S. Tsirkin
2017-06-16 8:57 ` Jason Wang
2017-06-16 10:10 ` Wei Wang
2017-06-16 15:15 ` Michael S. Tsirkin
2017-06-17 8:37 ` Wei Wang
2017-06-18 19:46 ` Michael S. Tsirkin
2017-06-19 7:40 ` Wei Wang
2017-06-16 15:19 ` Michael S. Tsirkin
2017-06-16 17:04 ` Maxime Coquelin
2017-06-16 20:33 ` Michael S. Tsirkin
2017-06-05 15:47 ` [Qemu-devel] " 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=593F9187.6040800@intel.com \
--to=wei.w.wang@intel.com \
--cc=armbru@redhat.com \
--cc=jan.scheurich@ericsson.com \
--cc=jasowang@redhat.com \
--cc=marcandre.lureau@gmail.com \
--cc=mst@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=stefanha@gmail.com \
--cc=virtio-dev@lists.oasis-open.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).