From: Darren Hart <darren@dvhart.com>
To: Peter Williams <pwil3058@bigpond.net.au>
Cc: linux-kernel@vger.kernel.org, Ingo Molnar <mingo@elte.hu>,
Thomas Gleixner <tglx@linutronix.de>,
"Stultz, John" <johnstul@us.ibm.com>,
"Siddha, Suresh B" <suresh.b.siddha@intel.com>,
Nick Piggin <nickpiggin@yahoo.com.au>
Subject: Re: RT task scheduling
Date: Thu, 6 Apr 2006 10:24:34 -0700 [thread overview]
Message-ID: <200604061024.35300.darren@dvhart.com> (raw)
In-Reply-To: <443496CA.6050905@bigpond.net.au>
On Wednesday 05 April 2006 21:19, Peter Williams wrote:
> Darren Hart wrote:
> > My last mail specifically addresses preempt-rt, but I'd like to know
> > people's thoughts regarding this issue in the mainline kernel. Please
> > see my previous post "realtime-preempt scheduling - rt_overload behavior"
> > for a testcase that produces unpredictable scheduling results.
> >
> > Part of the issue here is to define what we consider "correct behavior"
> > for SCHED_FIFO realtime tasks. Do we (A) need to strive for "strict
> > realtime priority scheduling" where the NR_CPUS highest priority runnable
> > SCHED_FIFO tasks are _always_ running? Or do we (B) take the best effort
> > approach with an upper limit RT priority imbalances, where an imbalance
> > may occur (say at wakeup or exit) but will be remedied within 1 tick.
> > The smpnice patches improve load balancing, but don't provide (A).
> >
> > More details in the previous mail...
>
> I'm currently researching some ideas to improve smpnice that may help in
> this situation. The basic idea is that as well as trying to equally
> distribute the weighted load among the groups/queues we should also try
> to achieve equal "average load per task" for each group/queue. (As well
> as helping with problems such as yours, this will help to restore the
> "equal distribution of nr_running" amongst groups/queues aim that is
> implicit without smpnice due to the fact that load is just a smoothed
> version of nr_running.)
Can you elaborate on what you mean by "average load per task" ?
Also, since smpnice is (correct me if I am wrong) load_balancing, I don't
think it will prevent the problem from happening, but rather fix it when it
does. If we want to prevent it from happening, I think we need to do
something like the rt_overload code from the RT patchset.
>
> In find_busiest_group(), I think that load balancing in the case where
> *imbalance is greater than busiest_load_per_task will tend towards this
> result and also when *imbalance is less than busiest_load_per_task AND
> busiest_load_per_task is less than this_load_per_task. However, in the
> case where *imbalance is less than busiest_load_per_task AND
> busiest_load_per_task is greater than this_load_per_task this will not
> be the case as the amount of load moved from "busiest" to "this" will be
> less than or equal to busiest_load_per_task and this will actually
> increase the value of busiest_load_per_task. So, although it will
> achieve the aim of equally distributing the weighted load, it won't help
> the second aim of equal "average load per task" values for groups/queues.
>
> The obvious way to fix this problem is to alter the code so that more
> than busiest_load_per_task is moved from "busiest" to "this" in these
> cases while at the same time ensuring that the imbalance between their
> loads doesn't get any bigger. I'm working on a patch along these lines.
>
> Changes to find_idlest_group() and try_to_wake_up() taking into account
> the "average load per task" on the candidate queues/groups as well as
> their weighted loads may also help and I'll be looking at them as well.
> It's not immediately obvious to me how this can be done so any ideas
> would be welcome. It will likely involve taking the load weight of the
> waking task into account as well.
>
> Peter
next prev parent reply other threads:[~2006-04-06 17:24 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-04-06 3:25 RT task scheduling Darren Hart
2006-04-06 4:19 ` Peter Williams
2006-04-06 17:24 ` Darren Hart [this message]
2006-04-06 23:02 ` Peter Williams
2006-04-06 7:37 ` Ingo Molnar
2006-04-06 14:55 ` Darren Hart
2006-04-06 18:16 ` Darren Hart
2006-04-06 22:35 ` Darren Hart
2006-04-07 22:58 ` Vernon Mauery
2006-04-06 23:06 ` Peter Williams
2006-04-07 3:07 ` Bill Huey
2006-04-07 7:11 ` Ingo Molnar
2006-04-07 8:39 ` Bill Huey
2006-04-07 9:11 ` Bill Huey
2006-04-07 9:19 ` Ingo Molnar
2006-04-07 10:39 ` Bill Huey
2006-04-07 10:51 ` Ingo Molnar
2006-04-07 11:14 ` Bill Huey
2006-04-07 11:29 ` Ingo Molnar
2006-04-07 22:18 ` Bill Huey
2006-04-07 14:56 ` Darren Hart
2006-04-07 21:06 ` Bill Huey
2006-04-07 22:37 ` Darren Hart
2006-04-07 23:36 ` Bill Huey
2006-04-08 3:01 ` Steven Rostedt
2006-04-08 4:28 ` Vernon Mauery
2006-04-08 4:45 ` Steven Rostedt
2006-04-08 7:16 ` Ingo Molnar
2006-04-08 7:25 ` Ingo Molnar
2006-04-08 7:54 ` Bill Huey
2006-04-08 8:03 ` Ingo Molnar
2006-04-08 10:02 ` Bill Huey
2006-04-08 0:11 ` Peter Williams
2006-04-07 9:23 ` Bill Huey
2006-04-09 13:16 ` Ingo Molnar
2006-04-09 17:25 ` Darren Hart
2006-04-09 18:31 ` Ingo Molnar
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=200604061024.35300.darren@dvhart.com \
--to=darren@dvhart.com \
--cc=johnstul@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=nickpiggin@yahoo.com.au \
--cc=pwil3058@bigpond.net.au \
--cc=suresh.b.siddha@intel.com \
--cc=tglx@linutronix.de \
/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).