From: yue <kvmluck@163.com>
To: jasowang@redhat.com, qemu-devel <qemu-devel@nongnu.org>
Subject: [Qemu-devel] is there a way to optimize vhost of virtio-net
Date: Mon, 17 Oct 2016 23:39:40 +0800 (CST) [thread overview]
Message-ID: <4d81f2a6.eb4d.157d34c5f61.Coremail.kvmluck@163.com> (raw)
hi, jasowang:
according to my test , the vm's network performance is just 20% of physical ethernet, the thread of vhost easily eat up 100% cpu when under pressure.
when using multi queue(two queues) the performance goes up by 50%, but it uses more threads.
if we can come to a conclusion that vhost is bottomneck? or do you have any idea to improve , first we do not need to care how violent the idea is.
thanks
next reply other threads:[~2016-10-17 15:55 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-10-17 15:39 yue [this message]
-- strict thread matches above, loose matches on Subject: below --
2016-10-18 9:24 [Qemu-devel] is there a way to optimize vhost of virtio-net yue
2016-10-17 10:39 yue
2016-10-21 1:55 ` Jason Wang
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=4d81f2a6.eb4d.157d34c5f61.Coremail.kvmluck@163.com \
--to=kvmluck@163.com \
--cc=jasowang@redhat.com \
--cc=qemu-devel@nongnu.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).