From: Valentin Schneider <valentin.schneider@arm.com>
To: bsegall@google.com, Liangyan <liangyan.peng@linux.alibaba.com>
Cc: Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
linux-kernel@vger.kernel.org, shanpeic@linux.alibaba.com,
xlpang@linux.alibaba.com
Subject: Re: [PATCH] sched/fair: don't assign runtime for throttled cfs_rq
Date: Sat, 24 Aug 2019 00:19:02 +0100 [thread overview]
Message-ID: <942ae15c-ffa5-74da-208b-7e82df917e16@arm.com> (raw)
In-Reply-To: <xm26d0gvirdg.fsf@bsegall-linux.svl.corp.google.com>
On 23/08/2019 21:00, bsegall@google.com wrote:
[...]
> Could you mention in the message that this a throttled cfs_rq can have
> account_cfs_rq_runtime called on it because it is throttled before
> idle_balance, and the idle_balance calls update_rq_clock to add time
> that is accounted to the task.
>
Mayhaps even a comment for the extra condition.
> I think this solution is less risky than unthrottling
> in this area, so other than that:
>
> Reviewed-by: Ben Segall <bsegall@google.com>
>
If you don't mind squashing this in:
-----8<-----
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b1d9cec9b1ed..b47b0bcf56bc 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4630,6 +4630,10 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining)
if (!cfs_rq_throttled(cfs_rq))
goto next;
+ /* By the above check, this should never be true */
+ WARN_ON(cfs_rq->runtime_remaining > 0);
+
+ /* Pick the minimum amount to return to a positive quota state */
runtime = -cfs_rq->runtime_remaining + 1;
if (runtime > remaining)
runtime = remaining;
----->8-----
I'm not adamant about the extra comment, but the WARN_ON would be nice IMO.
@Ben, do you reckon we want to strap
Cc: <stable@vger.kernel.org>
Fixes: ec12cb7f31e2 ("sched: Accumulate per-cfs_rq cpu usage and charge against bandwidth")
to the thing? AFAICT the pick_next_task_fair() + idle_balance() dance you
described should still be possible on that commit.
Other than that,
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
[...]
next prev parent reply other threads:[~2019-08-23 23:19 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-14 18:00 [PATCH] sched/fair: don't assign runtime for throttled cfs_rq Liangyan
2019-08-15 16:36 ` Valentin Schneider
[not found] ` <7C1833A8-27A4-4755-9B1E-335C20207A66@linux.alibaba.com>
2019-08-16 14:02 ` Valentin Schneider
2019-08-16 14:31 ` Valentin Schneider
[not found] ` <02BC41EE-6653-4473-91D4-CDEE53D8703D@linux.alibaba.com>
2019-08-16 17:19 ` Valentin Schneider
2019-08-19 17:34 ` Valentin Schneider
2019-08-20 10:54 ` [PATCH] sched/fair: Add missing unthrottle_cfs_rq() Valentin Schneider
2019-08-22 9:21 ` Peter Zijlstra
2019-08-22 17:43 ` bsegall
2019-08-22 18:48 ` bsegall
2019-08-22 20:40 ` Valentin Schneider
2019-08-22 21:10 ` Valentin Schneider
2019-08-23 7:22 ` Liangyan
2019-08-23 20:00 ` [PATCH] sched/fair: don't assign runtime for throttled cfs_rq bsegall
2019-08-23 23:19 ` Valentin Schneider [this message]
2019-08-26 17:38 ` bsegall
2019-08-27 2:45 ` Liangyan
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=942ae15c-ffa5-74da-208b-7e82df917e16@arm.com \
--to=valentin.schneider@arm.com \
--cc=bsegall@google.com \
--cc=liangyan.peng@linux.alibaba.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=shanpeic@linux.alibaba.com \
--cc=xlpang@linux.alibaba.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).