From: "Michael S. Tsirkin" <mst@redhat.com>
To: Parav Pandit <parav@nvidia.com>
Cc: Jason Wang <jasowang@redhat.com>,
Si-Wei Liu <si-wei.liu@oracle.com>, Gavin Li <gavinl@nvidia.com>,
"Hemminger, Stephen" <stephen@networkplumber.org>,
davem <davem@davemloft.net>,
virtualization <virtualization@lists.linux-foundation.org>,
Virtio-Dev <virtio-dev@lists.oasis-open.org>,
"jesse.brandeburg@intel.com" <jesse.brandeburg@intel.com>,
"alexander.h.duyck@intel.com" <alexander.h.duyck@intel.com>,
"kubakici@wp.pl" <kubakici@wp.pl>,
"sridhar.samudrala@intel.com" <sridhar.samudrala@intel.com>,
"loseweigh@gmail.com" <loseweigh@gmail.com>,
Gavi Teitz <gavi@nvidia.com>
Subject: Re: [virtio-dev] [PATCH] virtio-net: use mtu size as buffer length for big packets
Date: Wed, 10 Aug 2022 12:05:18 -0400 [thread overview]
Message-ID: <20220810120440-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <PH0PR12MB54819E083F0DEBF30403C380DC659@PH0PR12MB5481.namprd12.prod.outlook.com>
On Wed, Aug 10, 2022 at 04:00:08PM +0000, Parav Pandit wrote:
>
> > From: Michael S. Tsirkin <mst@redhat.com>
> > Sent: Wednesday, August 10, 2022 5:03 AM
> > > >
> > > > Should we make this depend on the vq reset ability maybe?
> > >
> > > The advantage of this is to keep TX working. Or we can use device
> > > reset as a fallback if there's no vq reset.
> > >
> > > Thanks
> >
> > Device reset is really annoying in that it loses all the state:
> > rx filters etc etc.
>
> The elegant solution is let driver tell the new mtu to the device.
> One way to do so is by using existing ctrl vq.
That will need a new feature bit.
> If merged buffer is done, and new mtu is > minimum posting size, no need to undergo vq reset.
> If merged buffer is not done, and buffer posted are smaller than new mtu, undergo vq reset optionally.
This can be done with or without sending mtu to device.
--
MST
---------------------------------------------------------------------
To unsubscribe, e-mail: virtio-dev-unsubscribe@lists.oasis-open.org
For additional commands, e-mail: virtio-dev-help@lists.oasis-open.org
WARNING: multiple messages have this Message-ID (diff)
From: "Michael S. Tsirkin" <mst@redhat.com>
To: Parav Pandit <parav@nvidia.com>
Cc: "alexander.h.duyck@intel.com" <alexander.h.duyck@intel.com>,
Virtio-Dev <virtio-dev@lists.oasis-open.org>,
"kubakici@wp.pl" <kubakici@wp.pl>,
"sridhar.samudrala@intel.com" <sridhar.samudrala@intel.com>,
"jesse.brandeburg@intel.com" <jesse.brandeburg@intel.com>,
Gavi Teitz <gavi@nvidia.com>,
virtualization <virtualization@lists.linux-foundation.org>,
"Hemminger, Stephen" <stephen@networkplumber.org>,
"loseweigh@gmail.com" <loseweigh@gmail.com>,
davem <davem@davemloft.net>, Gavin Li <gavinl@nvidia.com>
Subject: Re: [virtio-dev] [PATCH] virtio-net: use mtu size as buffer length for big packets
Date: Wed, 10 Aug 2022 12:05:18 -0400 [thread overview]
Message-ID: <20220810120440-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <PH0PR12MB54819E083F0DEBF30403C380DC659@PH0PR12MB5481.namprd12.prod.outlook.com>
On Wed, Aug 10, 2022 at 04:00:08PM +0000, Parav Pandit wrote:
>
> > From: Michael S. Tsirkin <mst@redhat.com>
> > Sent: Wednesday, August 10, 2022 5:03 AM
> > > >
> > > > Should we make this depend on the vq reset ability maybe?
> > >
> > > The advantage of this is to keep TX working. Or we can use device
> > > reset as a fallback if there's no vq reset.
> > >
> > > Thanks
> >
> > Device reset is really annoying in that it loses all the state:
> > rx filters etc etc.
>
> The elegant solution is let driver tell the new mtu to the device.
> One way to do so is by using existing ctrl vq.
That will need a new feature bit.
> If merged buffer is done, and new mtu is > minimum posting size, no need to undergo vq reset.
> If merged buffer is not done, and buffer posted are smaller than new mtu, undergo vq reset optionally.
This can be done with or without sending mtu to device.
--
MST
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
next prev parent reply other threads:[~2022-08-10 16:05 UTC|newest]
Thread overview: 102+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-02 4:45 [virtio-dev] [PATCH] virtio-net: use mtu size as buffer length for big packets Gavin Li
2022-08-04 5:00 ` Jason Wang
2022-08-04 5:00 ` Jason Wang
2022-08-04 7:10 ` Michael S. Tsirkin
2022-08-04 7:10 ` Michael S. Tsirkin
2022-08-04 7:23 ` Jason Wang
2022-08-04 7:23 ` Jason Wang
2022-08-04 7:24 ` Jason Wang
2022-08-04 7:24 ` Jason Wang
2022-08-08 6:54 ` Gavin Li
2022-08-08 6:24 ` Gavin Li
2022-08-05 22:11 ` Si-Wei Liu
2022-08-05 22:11 ` Si-Wei Liu
2022-08-05 23:26 ` Si-Wei Liu
2022-08-05 23:26 ` Si-Wei Liu
2022-08-08 7:34 ` Gavin Li
2022-08-08 7:31 ` Gavin Li
2022-08-08 23:56 ` Si-Wei Liu
2022-08-08 23:56 ` Si-Wei Liu
2022-08-09 7:06 ` Gavin Li
2022-08-09 7:44 ` Jason Wang
2022-08-09 7:44 ` Jason Wang
2022-08-09 9:22 ` Michael S. Tsirkin
2022-08-09 9:22 ` Michael S. Tsirkin
2022-08-09 9:28 ` Jason Wang
2022-08-09 9:28 ` Jason Wang
2022-08-09 9:25 ` Michael S. Tsirkin
2022-08-09 9:25 ` Michael S. Tsirkin
2022-08-09 9:40 ` Jason Wang
2022-08-09 9:40 ` Jason Wang
2022-08-09 18:38 ` Si-Wei Liu
2022-08-09 18:38 ` Si-Wei Liu
2022-08-09 18:42 ` Parav Pandit
2022-08-09 18:42 ` Parav Pandit via Virtualization
2022-08-09 19:08 ` Si-Wei Liu
2022-08-09 19:08 ` Si-Wei Liu
2022-08-09 19:18 ` Parav Pandit
2022-08-09 19:18 ` Parav Pandit via Virtualization
2022-08-09 20:32 ` Si-Wei Liu
2022-08-09 20:32 ` Si-Wei Liu
2022-08-09 21:13 ` Parav Pandit
2022-08-09 21:13 ` Parav Pandit via Virtualization
2022-08-09 21:32 ` Michael S. Tsirkin
2022-08-09 21:32 ` Michael S. Tsirkin
2022-08-09 21:37 ` Michael S. Tsirkin
2022-08-09 21:37 ` Michael S. Tsirkin
2022-08-09 21:49 ` Parav Pandit
2022-08-09 21:49 ` Parav Pandit via Virtualization
2022-08-09 22:25 ` Michael S. Tsirkin
2022-08-09 22:25 ` Michael S. Tsirkin
2022-08-09 22:49 ` Parav Pandit
2022-08-09 22:49 ` Parav Pandit via Virtualization
2022-08-09 22:59 ` Michael S. Tsirkin
2022-08-09 22:59 ` Michael S. Tsirkin
2022-08-09 23:04 ` Michael S. Tsirkin
2022-08-09 23:04 ` Michael S. Tsirkin
2022-08-09 23:24 ` Si-Wei Liu
2022-08-09 23:24 ` Si-Wei Liu
2022-08-10 6:14 ` Michael S. Tsirkin
2022-08-10 6:14 ` Michael S. Tsirkin
2022-08-10 6:15 ` Michael S. Tsirkin
2022-08-10 6:15 ` Michael S. Tsirkin
2022-08-10 6:59 ` Jason Wang
2022-08-10 6:59 ` Jason Wang
2022-08-10 9:03 ` Michael S. Tsirkin
2022-08-10 9:03 ` Michael S. Tsirkin
2022-08-10 16:00 ` Parav Pandit
2022-08-10 16:00 ` Parav Pandit via Virtualization
2022-08-10 16:05 ` Michael S. Tsirkin [this message]
2022-08-10 16:05 ` Michael S. Tsirkin
2022-08-10 16:22 ` Parav Pandit
2022-08-10 16:22 ` Parav Pandit via Virtualization
2022-08-10 16:58 ` Michael S. Tsirkin
2022-08-10 16:58 ` Michael S. Tsirkin
2022-08-10 17:02 ` Michael S. Tsirkin
2022-08-10 17:02 ` Michael S. Tsirkin
2022-08-10 17:06 ` Parav Pandit
2022-08-10 17:06 ` Parav Pandit via Virtualization
2022-08-10 17:12 ` Michael S. Tsirkin
2022-08-10 17:12 ` Michael S. Tsirkin
2022-08-11 0:26 ` Si-Wei Liu
2022-08-11 0:26 ` Si-Wei Liu
2022-08-09 22:32 ` Si-Wei Liu
2022-08-09 22:32 ` Si-Wei Liu
2022-08-09 22:37 ` Michael S. Tsirkin
2022-08-09 22:37 ` Michael S. Tsirkin
2022-08-09 22:54 ` Si-Wei Liu
2022-08-09 22:54 ` Si-Wei Liu
2022-08-09 23:03 ` Michael S. Tsirkin
2022-08-09 23:03 ` Michael S. Tsirkin
2022-08-10 1:24 ` Jason Wang
2022-08-10 1:24 ` Jason Wang
2022-08-09 21:34 ` Michael S. Tsirkin
2022-08-09 21:34 ` Michael S. Tsirkin
2022-08-09 21:39 ` Si-Wei Liu
2022-08-09 21:39 ` Si-Wei Liu
2022-08-09 22:27 ` Michael S. Tsirkin
2022-08-09 22:27 ` Michael S. Tsirkin
2022-08-10 1:15 ` Jason Wang
2022-08-10 1:15 ` Jason Wang
2022-08-09 18:06 ` Si-Wei Liu
2022-08-09 18:06 ` Si-Wei Liu
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=20220810120440-mutt-send-email-mst@kernel.org \
--to=mst@redhat.com \
--cc=alexander.h.duyck@intel.com \
--cc=davem@davemloft.net \
--cc=gavi@nvidia.com \
--cc=gavinl@nvidia.com \
--cc=jasowang@redhat.com \
--cc=jesse.brandeburg@intel.com \
--cc=kubakici@wp.pl \
--cc=loseweigh@gmail.com \
--cc=parav@nvidia.com \
--cc=si-wei.liu@oracle.com \
--cc=sridhar.samudrala@intel.com \
--cc=stephen@networkplumber.org \
--cc=virtio-dev@lists.oasis-open.org \
--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.