From: Glauber Costa <glommer@redhat.com>
To: Dietmar Maurer <dietmar@proxmox.com>
Cc: Anthony Liguori <anthony@codemonkey.ws>, kvm <kvm@vger.kernel.org>
Subject: Re: migrate_set_downtime bug
Date: Wed, 30 Sep 2009 01:48:32 -0300 [thread overview]
Message-ID: <20090930044832.GA5149@mothafucka.localdomain> (raw)
In-Reply-To: <90D306BE6EBC8D428A824FBBA7A3113DFDCDF17D@ronja.maurer-it.com>
On Tue, Sep 29, 2009 at 06:36:57PM +0200, Dietmar Maurer wrote:
> > Also, if this is really the case (buffered), then the bandwidth capping
> > part
> > of migration is also wrong.
> >
> > Have you compared the reported bandwidth to your actual bandwith ? I
> > suspect
> > the source of the problem can be that we're currently ignoring the time
> > we take
> > to transfer the state of the devices, and maybe it is not negligible.
> >
>
> I have a 1GB network (e1000 card), and get values like bwidth=0.98 - which is much too high.
The main reason for not using the whole migration time is that it can lead to values
that are not very helpful in situation where the network load changes too much.
Since the problem you pinpointed do exist, I would suggest measuring the average load of the last,
say, 10 iterations. How would that work for you?
next prev parent reply other threads:[~2009-09-30 4:48 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-09-29 13:00 migrate_set_downtime bug Dietmar Maurer
2009-09-29 14:36 ` Dietmar Maurer
2009-09-29 15:09 ` Dietmar Maurer
2009-09-29 15:39 ` Anthony Liguori
2009-09-29 16:23 ` Glauber Costa
2009-09-29 16:36 ` Dietmar Maurer
2009-09-30 4:48 ` Glauber Costa [this message]
2009-09-30 6:58 ` Dietmar Maurer
2009-09-30 8:55 ` Dietmar Maurer
2009-09-30 11:23 ` Glauber Costa
2009-09-30 14:11 ` Dietmar Maurer
2009-09-30 16:39 ` Glauber Costa
2009-09-30 18:41 ` Dietmar Maurer
2009-10-05 12:17 ` Avi Kivity
2009-10-05 13:04 ` Glauber Costa
2009-10-05 13:17 ` Avi Kivity
2009-10-05 14:09 ` Dietmar Maurer
2009-10-05 15:32 ` Glauber Costa
2009-10-06 8:30 ` Dietmar Maurer
2009-10-06 17:33 ` Glauber Costa
2009-10-07 4:42 ` Dietmar Maurer
2009-10-07 12:32 ` Glauber Costa
2009-10-07 19:40 ` Dietmar Maurer
2009-10-05 14:01 ` Dietmar Maurer
2009-10-05 14:06 ` Avi Kivity
2009-10-05 14:08 ` Dietmar Maurer
2009-10-05 14:15 ` Avi Kivity
2009-10-05 14:11 ` Dietmar Maurer
2009-10-05 14:18 ` Dietmar Maurer
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=20090930044832.GA5149@mothafucka.localdomain \
--to=glommer@redhat.com \
--cc=anthony@codemonkey.ws \
--cc=dietmar@proxmox.com \
--cc=kvm@vger.kernel.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