From: George Dunlap <george.dunlap@citrix.com>
To: Dario Faggioli <dario.faggioli@citrix.com>,
George Dunlap <George.Dunlap@eu.citrix.com>
Cc: Tianyang Chen <tiche@seas.upenn.edu>,
Meng Xu <xumengpanda@gmail.com>,
"xen-devel@lists.xen.org" <xen-devel@lists.xen.org>
Subject: Load calculation refresh in credit2 (was in Re: Questions about the use of idle_vcpu[])
Date: Mon, 18 Jan 2016 14:12:08 +0000 [thread overview]
Message-ID: <569CF2B8.9020406@citrix.com> (raw)
In-Reply-To: <1453121249.11427.83.camel@citrix.com>
[Changing the title to align with the current topic]
On 18/01/16 12:47, Dario Faggioli wrote:
> On Mon, 2016-01-18 at 12:37 +0000, George Dunlap wrote:
>> On Mon, Jan 18, 2016 at 11:00 AM, Dario Faggioli
>> <dario.faggioli@citrix.com> wrote:
>>>>
>>> Credit2, AFAICR, could also avoid _always_ re-setting the timer,
>>> but it
>>> does need to do that at least a few times, even when idle is
>>> selected,
>>> because of the dynamic load tracking mechanism it includes. In
>>> fact,
>>> that is based on a 'decaying average', which in turns relies on
>>> csched2_schedule() to run and update the statistics, even when the
>>> cpu
>>> is idle. If we don't do that, the load tracking mechanism will
>>> never
>>> see that the cpu (well, it's actually the runqueue) is idle, and
>>> the
>>> load will never go down! :-/
>>
>> I don't think that's true -- it looks like balance_load() will call
>> __update_runq_load() on the "other" runqueue before considering it,
>> and will also call __update_svc_load() on each vcpu before
>> considering
>> it. Shouldn't that suffice?
>>
> Mm... It looks like it should.
>
> And yet, I observed that 'load not going down' behavior while doing
> development for the patch I mentioned, both on Credit2 and Credit (with
> patches for extending the load tracking to Credit applied).
>
> I was, in the same series, also trying to optimize the Credit2's load
> balancer a little bit, though, so what I saw may be the effect of some
> other change of mine...
Hmm... Did you see it when the system was under load, or mostly idle?
Load balancing only happens on a reset event; and the frequency of reset
events will be CREDIT_INIT / (% utilization); so for a system at 1%
utilization that would be once every second. Is that the kind of number
you were seeing? Or were you actually seeing idle runqueues not having
anything pushed to them *during* a balance for some reason?
-George
next prev parent reply other threads:[~2016-01-18 14:12 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-01-15 1:04 Questions about the use of idle_vcpu[] Tianyang Chen
2016-01-18 10:47 ` George Dunlap
2016-01-18 11:00 ` Dario Faggioli
2016-01-18 12:37 ` George Dunlap
2016-01-18 12:47 ` Dario Faggioli
2016-01-18 14:12 ` George Dunlap [this message]
2016-01-19 9:23 ` Load calculation refresh in credit2 (was in Re: Questions about the use of idle_vcpu[]) Dario Faggioli
2016-01-18 16:07 ` Questions about the use of idle_vcpu[] Meng Xu
2016-01-18 16:32 ` Dario Faggioli
2016-01-18 16:41 ` Meng Xu
2016-01-19 22:59 ` Tianyang Chen
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=569CF2B8.9020406@citrix.com \
--to=george.dunlap@citrix.com \
--cc=George.Dunlap@eu.citrix.com \
--cc=dario.faggioli@citrix.com \
--cc=tiche@seas.upenn.edu \
--cc=xen-devel@lists.xen.org \
--cc=xumengpanda@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 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).