From: Shannon Zhao <zhaoshenglong@huawei.com>
To: <linux-kernel@vger.kernel.org>
Cc: <mst@redhat.com>, <peter.maydell@linaro.org>,
<john.liuli@huawei.com>, <joel.schopp@amd.com>,
<remy.gauguey@cea.fr>, <qemu-devel@nongnu.org>,
<n.nikolaev@virtualopensystems.com>,
<virtualization@lists.linux-foundation.org>,
<peter.huangpeng@huawei.com>, <hangaohuai@huawei.com>
Subject: Re: [RFC PATCH] virtio-mmio: support for multiple irqs
Date: Wed, 5 Nov 2014 15:59:36 +0800 [thread overview]
Message-ID: <5459D8E8.6060709@huawei.com> (raw)
In-Reply-To: <1415093712-15156-1-git-send-email-zhaoshenglong@huawei.com>
On 2014/11/4 17:35, Shannon Zhao wrote:
> As the current virtio-mmio only support single irq,
> so some advanced features such as vhost-net with irqfd
> are not supported. And the net performance is not
> the best without vhost-net and irqfd supporting.
>
Hi Joel, Peter, Mst,
Some virtio-net with virtio-mmio performance data on ARM added as followed:
Type of backend bandwith(GBytes/sec)
virtio-net 0.66
vhost-net 1.49
vhost-net with irqfd 2.01
Test cmd: ./iperf -c 192.168.0.2 -P 1 -i 10 -p 5001 -f G -t 60
>From this test data, irqfd has great improvement (about 30%) on performance.
So maybe it's necessary to enable multiple irq support to make vhost-net
with virtio-mmio on ARM be able to use irqfd.
How do you guys think? Look forward for your feedback.
Thanks,
Shannon
> This patch support virtio-mmio to request multiple
> irqs like virtio-pci. With this patch and qemu assigning
> multiple irqs for virtio-mmio device, it's ok to use
> vhost-net with irqfd on arm/arm64.
>
WARNING: multiple messages have this Message-ID (diff)
From: Shannon Zhao <zhaoshenglong@huawei.com>
To: linux-kernel@vger.kernel.org
Cc: peter.maydell@linaro.org, hangaohuai@huawei.com,
joel.schopp@amd.com, john.liuli@huawei.com, remy.gauguey@cea.fr,
mst@redhat.com, qemu-devel@nongnu.org,
n.nikolaev@virtualopensystems.com,
virtualization@lists.linux-foundation.org,
peter.huangpeng@huawei.com
Subject: Re: [Qemu-devel] [RFC PATCH] virtio-mmio: support for multiple irqs
Date: Wed, 5 Nov 2014 15:59:36 +0800 [thread overview]
Message-ID: <5459D8E8.6060709@huawei.com> (raw)
In-Reply-To: <1415093712-15156-1-git-send-email-zhaoshenglong@huawei.com>
On 2014/11/4 17:35, Shannon Zhao wrote:
> As the current virtio-mmio only support single irq,
> so some advanced features such as vhost-net with irqfd
> are not supported. And the net performance is not
> the best without vhost-net and irqfd supporting.
>
Hi Joel, Peter, Mst,
Some virtio-net with virtio-mmio performance data on ARM added as followed:
Type of backend bandwith(GBytes/sec)
virtio-net 0.66
vhost-net 1.49
vhost-net with irqfd 2.01
Test cmd: ./iperf -c 192.168.0.2 -P 1 -i 10 -p 5001 -f G -t 60
>From this test data, irqfd has great improvement (about 30%) on performance.
So maybe it's necessary to enable multiple irq support to make vhost-net
with virtio-mmio on ARM be able to use irqfd.
How do you guys think? Look forward for your feedback.
Thanks,
Shannon
> This patch support virtio-mmio to request multiple
> irqs like virtio-pci. With this patch and qemu assigning
> multiple irqs for virtio-mmio device, it's ok to use
> vhost-net with irqfd on arm/arm64.
>
next prev parent reply other threads:[~2014-11-05 8:00 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-11-04 9:35 [RFC PATCH] virtio-mmio: support for multiple irqs Shannon Zhao
2014-11-04 9:35 ` [Qemu-devel] " Shannon Zhao
2014-11-05 7:59 ` Shannon Zhao
2014-11-05 7:59 ` Shannon Zhao [this message]
2014-11-05 7:59 ` [Qemu-devel] " Shannon Zhao
2014-11-05 8:26 ` GAUGUEY Rémy 228890
2014-11-05 8:26 ` [Qemu-devel] " GAUGUEY Rémy 228890
2014-11-05 9:12 ` Shannon Zhao
2014-11-05 9:12 ` [Qemu-devel] " Shannon Zhao
2014-11-05 15:27 ` Joel Schopp
2014-11-05 15:27 ` Joel Schopp
2014-11-05 15:27 ` Joel Schopp
2014-11-06 3:26 ` Shannon Zhao
2014-11-06 3:26 ` Shannon Zhao
2014-11-06 3:26 ` Shannon Zhao
2014-11-05 9:12 ` Shannon Zhao
2014-11-05 8:26 ` GAUGUEY Rémy 228890
2014-11-06 9:34 ` Michael S. Tsirkin
2014-11-06 9:34 ` [Qemu-devel] " Michael S. Tsirkin
2014-11-06 9:34 ` Michael S. Tsirkin
2014-11-06 9:54 ` Shannon Zhao
2014-11-06 9:54 ` Shannon Zhao
2014-11-06 9:54 ` [Qemu-devel] " Shannon Zhao
2014-11-06 11:09 ` Michael S. Tsirkin
2014-11-06 11:09 ` [Qemu-devel] " Michael S. Tsirkin
2014-11-06 11:09 ` Michael S. Tsirkin
2014-11-07 2:36 ` Shannon Zhao
2014-11-07 2:36 ` Shannon Zhao
2014-11-07 2:36 ` [Qemu-devel] " Shannon Zhao
2014-11-11 15:11 ` Pawel Moll
2014-11-11 15:11 ` [Qemu-devel] " Pawel Moll
2014-11-11 15:11 ` Pawel Moll
2014-11-12 8:32 ` Shannon Zhao
2014-11-12 8:32 ` [Qemu-devel] " Shannon Zhao
2014-11-12 8:32 ` Shannon Zhao
2014-11-12 18:33 ` Pawel Moll
2014-11-12 18:33 ` [Qemu-devel] " Pawel Moll
2014-11-12 18:33 ` Pawel Moll
2014-11-13 9:39 ` Shannon Zhao
2014-11-13 9:39 ` [Qemu-devel] " Shannon Zhao
2014-11-13 9:39 ` Shannon Zhao
2014-11-14 17:54 ` Pawel Moll
2014-11-14 17:54 ` [Qemu-devel] " Pawel Moll
2014-11-14 17:54 ` Pawel Moll
-- strict thread matches above, loose matches on Subject: below --
2014-11-04 9:35 Shannon Zhao
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=5459D8E8.6060709@huawei.com \
--to=zhaoshenglong@huawei.com \
--cc=hangaohuai@huawei.com \
--cc=joel.schopp@amd.com \
--cc=john.liuli@huawei.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mst@redhat.com \
--cc=n.nikolaev@virtualopensystems.com \
--cc=peter.huangpeng@huawei.com \
--cc=peter.maydell@linaro.org \
--cc=qemu-devel@nongnu.org \
--cc=remy.gauguey@cea.fr \
--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.