From: Juan Quintela <quintela@redhat.com>
To: Felipe Franciosi <felipe@nutanix.com>
Cc: Peter Xu <peterx@redhat.com>,
"Jason J. Herne" <jjherne@linux.vnet.ibm.com>,
amit Shah <amit.shah@redhat.com>,
"Dr. David Alan Gilbert" <dgilbert@redhat.com>,
Malcolm Crossley <malcolm@nutanix.com>,
"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>
Subject: Re: [Qemu-devel] [PATCH 4/4] migration: use dirty_rate_high_cnt more aggressively
Date: Tue, 30 May 2017 18:17:09 +0200 [thread overview]
Message-ID: <874lw2e2uy.fsf@secure.mitica> (raw)
In-Reply-To: <1495642203-12702-5-git-send-email-felipe@nutanix.com> (Felipe Franciosi's message of "Wed, 24 May 2017 17:10:03 +0100")
Felipe Franciosi <felipe@nutanix.com> wrote:
> The commit message from 070afca25 suggests that dirty_rate_high_cnt
> should be used more aggressively to start throttling after two
> iterations instead of four. The code, however, only changes the auto
> convergence behaviour to throttle after three iterations. This makes the
> behaviour more aggressive by kicking off throttling after two iterations
> as originally intended.
>
> Signed-off-by: Felipe Franciosi <felipe@nutanix.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
First, Felipe is doing performance testing with the changes.
Second, if you want autoconverge slower, you can use smaller increments.
So, I think that this is ok.
It is more, if you want you can send numbers of your workloads with
current parameter and removing it altogether to convince me that it is a
good idea just to drop it.
Thanks, Juan.
prev parent reply other threads:[~2017-05-30 16:17 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-05-24 16:09 [Qemu-devel] [PATCH 0/4] migration: autoconverge counter fixes Felipe Franciosi
2017-05-24 16:10 ` [Qemu-devel] [PATCH 1/4] migration: keep bytes_xfer_prev init'd to zero Felipe Franciosi
2017-05-25 0:50 ` Peter Xu
2017-05-30 16:14 ` Juan Quintela
2017-05-24 16:10 ` [Qemu-devel] [PATCH 2/4] migration: set dirty_pages_rate before autoconverge logic Felipe Franciosi
2017-05-25 0:40 ` Peter Xu
2017-05-25 10:52 ` Felipe Franciosi
2017-05-25 11:10 ` Peter Xu
2017-05-30 16:14 ` Juan Quintela
2017-05-24 16:10 ` [Qemu-devel] [PATCH 3/4] migration: set bytes_xfer_* outside of " Felipe Franciosi
2017-05-25 0:40 ` Peter Xu
2017-05-30 16:14 ` Juan Quintela
2017-05-24 16:10 ` [Qemu-devel] [PATCH 4/4] migration: use dirty_rate_high_cnt more aggressively Felipe Franciosi
2017-05-24 16:25 ` Daniel P. Berrange
2017-05-24 16:36 ` Felipe Franciosi
2017-05-25 1:03 ` Peter Xu
2017-05-25 11:20 ` Felipe Franciosi
2017-05-26 2:45 ` Peter Xu
2017-05-30 16:17 ` Juan Quintela [this message]
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=874lw2e2uy.fsf@secure.mitica \
--to=quintela@redhat.com \
--cc=amit.shah@redhat.com \
--cc=dgilbert@redhat.com \
--cc=felipe@nutanix.com \
--cc=jjherne@linux.vnet.ibm.com \
--cc=malcolm@nutanix.com \
--cc=peterx@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).