From: Paolo Bonzini <pbonzini@redhat.com>
To: Stefan Priebe - Profihost AG <s.priebe@profihost.ag>
Cc: Stefan Hajnoczi <stefanha@gmail.com>, qemu-devel <qemu-devel@nongnu.org>
Subject: Re: [Qemu-devel] virtio-scsi vs. virtio-blk
Date: Thu, 09 Aug 2012 14:19:04 +0200 [thread overview]
Message-ID: <5023AAB8.1090703@redhat.com> (raw)
In-Reply-To: <5023A83D.9070509@profihost.ag>
Il 09/08/2012 14:08, Stefan Priebe - Profihost AG ha scritto:
>
> virtio-scsi:
> rand 4k:
> write: io=822448KB, bw=82228KB/s, iops=20557, runt= 10002msec
> read : io=950920KB, bw=94694KB/s, iops=23673, runt= 10042msec
> seq:
> write: io=2436MB, bw=231312KB/s, iops=56, runt= 10784msec
> read : io=3248MB, bw=313799KB/s, iops=76, runt= 10599msec
>
> virtio-blk:
> rand 4k:
> write: io=896472KB, bw=89051KB/s, iops=22262, runt= 10067msec
> read : io=1710MB, bw=175073KB/s, iops=43768, runt= 10002msec
> seq:
> write: io=4008MB, bw=391285KB/s, iops=95, runt= 10489msec
> read : io=5748MB, bw=570178KB/s, iops=139, runt= 10323msec
Thanks; some overhead is expected, but not this much. Especially the
sequential case is bad, what disk is this?
Things to test include:
- using the deadline I/O scheduler on at least the host, and possibly
the guest too
- running perf on the guest and the host (separately) to get profiles
Paolo
next prev parent reply other threads:[~2012-08-09 12:19 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-08-08 15:21 [Qemu-devel] virtio-scsi vs. virtio-blk Stefan Priebe
2012-08-08 16:17 ` Paolo Bonzini
2012-08-08 17:12 ` Stefan Priebe
2012-08-08 17:37 ` Paolo Bonzini
2012-08-09 6:13 ` Stefan Priebe
2012-08-09 7:01 ` Paolo Bonzini
2012-08-09 7:07 ` Stefan Priebe
2012-08-09 7:19 ` Paolo Bonzini
2012-08-09 7:41 ` Stefan Priebe
2012-08-09 7:53 ` Paolo Bonzini
2012-08-09 8:00 ` Stefan Priebe
2012-08-09 8:03 ` Paolo Bonzini
2012-08-09 9:18 ` Stefan Hajnoczi
2012-08-09 10:17 ` Stefan Priebe - Profihost AG
2012-08-09 11:04 ` Stefan Hajnoczi
2012-08-09 11:10 ` Paolo Bonzini
2012-08-09 11:24 ` Stefan Priebe - Profihost AG
2012-08-09 12:08 ` Stefan Priebe - Profihost AG
2012-08-09 12:19 ` Paolo Bonzini [this message]
2012-08-09 12:31 ` Stefan Priebe - Profihost AG
2012-08-09 12:44 ` Paolo Bonzini
2012-08-09 15:41 ` Stefan Priebe - Profihost AG
2012-08-09 12:52 ` ronnie sahlberg
2012-08-09 13:15 ` Paolo Bonzini
2012-08-09 13:39 ` Stefan Priebe - Profihost AG
2012-08-09 13:42 ` Paolo Bonzini
2012-08-09 13:52 ` Stefan Priebe - Profihost AG
2012-08-09 14:35 ` Paolo Bonzini
2012-08-09 14:25 ` Stefan Priebe - Profihost AG
2012-08-10 9:22 ` Stefan Priebe - Profihost AG
2012-08-10 10:20 ` Paolo Bonzini
2012-08-10 10:28 ` Stefan Priebe - Profihost AG
2012-08-10 10:30 ` Paolo Bonzini
2012-08-10 11:12 ` ronnie sahlberg
2012-08-10 11:57 ` Stefan Priebe - Profihost AG
2012-08-10 12:04 ` ronnie sahlberg
2012-08-10 12:14 ` Stefan Priebe - Profihost AG
2012-08-10 12:24 ` ronnie sahlberg
2012-08-10 12:35 ` Stefan Priebe - Profihost AG
2012-08-10 12:39 ` Paolo Bonzini
2012-08-10 12:43 ` Stefan Priebe - Profihost AG
2012-08-10 11:20 ` ronnie sahlberg
2012-08-10 11:54 ` Stefan Priebe - Profihost AG
2012-08-10 11:58 ` ronnie sahlberg
2012-08-10 12:38 ` Stefan Priebe - Profihost AG
2012-08-10 11:49 ` Stefan Priebe - Profihost AG
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=5023AAB8.1090703@redhat.com \
--to=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=s.priebe@profihost.ag \
--cc=stefanha@gmail.com \
/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.