From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
To: Vincent Guittot <vincent.guittot@linaro.org>
Cc: peterz@infradead.org, mingo@redhat.com, linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH 3/4] sched/topology: remove smt_gain
Date: Tue, 4 Sep 2018 03:37:42 -0700 [thread overview]
Message-ID: <20180904103742.GC61288@linux.vnet.ibm.com> (raw)
In-Reply-To: <20180904093626.GA23936@linaro.org>
* Vincent Guittot <vincent.guittot@linaro.org> [2018-09-04 11:36:26]:
> Hi Srikar,
>
> Le Tuesday 04 Sep 2018 à 01:24:24 (-0700), Srikar Dronamraju a écrit :
> > However after this change, capacity_orig of each SMT thread would be
> > 1024. For example SMT 8 core capacity_orig would now be 8192.
> >
> > smt_gain was suppose to make a multi threaded core was slightly more
> > powerful than a single threaded core. I suspect if that sometimes hurt
>
> Is there system with both single threaded and multi threaded core ?
> That was the main open point for me (and for Qais too)
>
I dont know of any systems that have come with single threaded and
multithreaded. However some user can still offline few threads in a core
while leaving other cores untouched. I dont really know why somebody
would want to do it. For example, some customer was toying with SMT 3
mode in a SMT 8 power8 box.
>
> > us when doing load balance between 2 cores i.e at MC or DIE sched
> > domain. Even with 2 threads running on a core, the core might look
> > lightly loaded 2048/8192. Hence might dissuade movement to a idle core.
>
> Then, there is the sibling flag at SMT level that normally ensures 1 task per
> core for such UC
>
Agree.
> >
> > I always wonder why arch_scale_cpu_capacity() is called with NULL
> > sched_domain, in scale_rt_capacity(). This way capacity might actually
>
> Probably because until this v4.19-rcxx version, the rt scaling was done
> relatively to local cpu capacity:
> capacity = arch_scale_cpu() * scale_rt_capacity / SCHED_CAPACITY_SCALE
>
> Whereas now, it directly returns the remaining capacity
>
> > be more than the capacity_orig. I am always under an impression that
> > capacity_orig > capacity. Or am I misunderstanding that?
>
> You are right, there is a bug for SMT and the patch below should fix it.
> Nevertheless, we still have the problem in some other places in the code.
>
> Subject: [PATCH] sched/fair: fix scale_rt_capacity() for SMT
>
> Since commit:
> commit 523e979d3164 ("sched/core: Use PELT for scale_rt_capacity()")
> scale_rt_capacity() returns the remaining capacity and not a scale factor
> to apply on cpu_capacity_orig. arch_scale_cpu() is directly called by
> scale_rt_capacity() so we must take the sched_domain argument
>
> Fixes: 523e979d3164 ("sched/core: Use PELT for scale_rt_capacity()")
> Reported-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
> Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
--
Thanks and Regards
Srikar Dronamraju
next prev parent reply other threads:[~2018-09-04 10:38 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-08-29 13:19 [PATCH 0/4] sched/numa: remove unused code Vincent Guittot
2018-08-29 13:19 ` [PATCH 1/4] sched/numa: remove unused code from update_numa_stats() Vincent Guittot
2018-09-04 6:39 ` Srikar Dronamraju
2018-09-10 10:19 ` [tip:sched/core] sched/numa: Remove " tip-bot for Vincent Guittot
2018-08-29 13:19 ` [PATCH 2/4] sched/numa: remove unused nr_running field Vincent Guittot
2018-09-04 6:40 ` Srikar Dronamraju
2018-09-10 10:20 ` [tip:sched/core] sched/numa: Remove unused numa_stats::nr_running field tip-bot for Vincent Guittot
2018-08-29 13:19 ` [RFC PATCH 3/4] sched/topology: remove smt_gain Vincent Guittot
2018-08-29 14:08 ` Qais Yousef
2018-08-29 14:42 ` Vincent Guittot
2018-09-07 12:42 ` Peter Zijlstra
2018-09-10 11:23 ` Qais Yousef
2018-09-04 8:24 ` Srikar Dronamraju
2018-09-04 9:36 ` Vincent Guittot
2018-09-04 10:37 ` Srikar Dronamraju [this message]
2018-09-05 7:36 ` Vincent Guittot
2018-09-05 8:50 ` Srikar Dronamraju
2018-09-05 9:11 ` Vincent Guittot
2018-09-05 11:14 ` Srikar Dronamraju
2018-09-06 9:21 ` Vincent Guittot
2018-09-10 11:05 ` Qais Yousef
2018-09-10 10:07 ` [tip:sched/core] sched/fair: Fix scale_rt_capacity() for SMT tip-bot for Vincent Guittot
2018-12-11 15:31 ` [tip:sched/core] sched/topology: Remove the ::smt_gain field from 'struct sched_domain' tip-bot for Vincent Guittot
2018-08-29 13:19 ` [RFC PATCH 4/4] sched/topology: remove unused sd param from arch_scale_cpu_capacity() Vincent Guittot
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=20180904103742.GC61288@linux.vnet.ibm.com \
--to=srikar@linux.vnet.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=vincent.guittot@linaro.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).