qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Zhang Haoyu" <zhanghy@sangfor.com>
To: Amit Shah <amit.shah@redhat.com>
Cc: qemu-devel <qemu-devel@nongnu.org>, kvm <kvm@vger.kernel.org>
Subject: Re: [Qemu-devel] [question] virtio-blk performancedegradationhappened with virito-serial
Date: Thu, 4 Sep 2014 10:20:53 +0800	[thread overview]
Message-ID: <201409041020508649585@sangfor.com> (raw)
In-Reply-To: 20140902063637.GG14171@grmbl.mre

>> >>> Hi, all
>> >>> 
>> >>> I start a VM with virtio-serial (default ports number: 31), and found that virtio-blk performance degradation happened, about 25%, this problem can be reproduced 100%.
>> >>> without virtio-serial:
>> >>> 4k-read-random 1186 IOPS
>> >>> with virtio-serial:
>> >>> 4k-read-random 871 IOPS
>> >>> 
>> >>> but if use max_ports=2 option to limit the max number of virio-serial ports, then the IO performance degradation is not so serious, about 5%.
>> >>> 
>> >>> And, ide performance degradation does not happen with virtio-serial.
>> >>
>> >>Pretty sure it's related to MSI vectors in use.  It's possible that
>> >>the virtio-serial device takes up all the avl vectors in the guests,
>> >>leaving old-style irqs for the virtio-blk device.
>> >>
>> >I don't think so,
>> >I use iometer to test 64k-read(or write)-sequence case, if I disable the virtio-serial dynamically via device manager->virtio-serial => disable,
>> >then the performance get promotion about 25% immediately, then I re-enable the virtio-serial via device manager->virtio-serial => enable,
>> >the performance got back again, very obvious.
>> add comments:
>> Although the virtio-serial is enabled, I don't use it at all, the degradation still happened.
>
>Using the vectors= option as mentioned below, you can restrict the
>number of MSI vectors the virtio-serial device gets.  You can then
>confirm whether it's MSI that's related to these issues.
>
I use "-device virtio-serial,vectors=4" instead of "-device virtio-serial", but the degradation still happened, nothing changed.
with virtio-serial enabled:
64k-write-sequence: 4200 IOPS
with virtio-serial disabled:
64k-write-sequence: 5300 IOPS

How to confirm whether it's MSI in windows?

Thanks,
Zhang Haoyu

>> >So, I think it has no business with legacy interrupt mode, right?
>> >
>> >I am going to observe the difference of perf top data on qemu and perf kvm stat data when disable/enable virtio-serial in guest,
>> >and the difference of perf top data on guest when disable/enable virtio-serial in guest,
>> >any ideas?
>> >
>> >Thanks,
>> >Zhang Haoyu
>> >>If you restrict the number of vectors the virtio-serial device gets
>> >>(using the -device virtio-serial-pci,vectors= param), does that make
>> >>things better for you?

  parent reply	other threads:[~2014-09-04  3:43 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-08-29  7:45 [Qemu-devel] [question] virtio-blk performance degradation happened with virito-serial Zhang Haoyu
2014-08-29 14:38 ` Amit Shah
2014-09-01 12:38   ` [Qemu-devel] [question] virtio-blk performance degradationhappened " Zhang Haoyu
2014-09-01 12:46     ` Amit Shah
2014-09-01 12:57       ` [Qemu-devel] [question] virtio-blk performancedegradationhappened " Zhang Haoyu
2014-09-01 12:52     ` [Qemu-devel] [question] virtio-blk performance degradationhappened " Zhang Haoyu
2014-09-01 13:09       ` Christian Borntraeger
2014-09-01 13:12         ` Paolo Bonzini
2014-09-01 13:22           ` Christian Borntraeger
2014-09-01 13:29             ` Paolo Bonzini
2014-09-01 14:03               ` Christian Borntraeger
2014-09-01 14:15                 ` Christian Borntraeger
2014-09-04  7:56             ` [Qemu-devel] [question] virtio-blk performance degradationhappenedwith virito-serial Zhang Haoyu
2014-09-07  9:46               ` Zhang Haoyu
2014-09-11  6:11                 ` Amit Shah
2014-09-12  3:21                   ` [Qemu-devel] [question] virtio-blk performance degradation happened with virito-serial Zhang Haoyu
2014-09-12 12:38                     ` Stefan Hajnoczi
2014-09-13 17:22                       ` Max Reitz
2014-09-16 14:59                     ` Zhang Haoyu
2014-09-02  6:36       ` [Qemu-devel] [question] virtio-blk performance degradationhappened " Amit Shah
2014-09-02 18:05         ` Andrey Korolyov
2014-09-02 18:11           ` Amit Shah
2014-09-02 18:27             ` Andrey Korolyov
2014-09-04  2:20         ` Zhang Haoyu [this message]
2014-09-19  5:53         ` Fam Zheng
2014-09-19 13:35           ` Paolo Bonzini
2014-09-22 13:23           ` [Qemu-devel] [question] virtio-blk performancedegradationhappened " Zhang Haoyu
2014-09-23  1:29             ` Fam Zheng

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=201409041020508649585@sangfor.com \
    --to=zhanghy@sangfor.com \
    --cc=amit.shah@redhat.com \
    --cc=kvm@vger.kernel.org \
    --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).