From: Vincent Guittot <vincent.guittot@linaro.org>
To: peterz@infradead.org, mingo@kernel.org, linux-kernel@vger.kernel.org
Cc: valentin.schneider@arm.com, Morten.Rasmussen@arm.com,
Vincent Guittot <vincent.guittot@linaro.org>
Subject: [PATCH v2 1/3] sched/fair: fix rounding issue for asym packing
Date: Fri, 14 Dec 2018 17:01:55 +0100 [thread overview]
Message-ID: <1544803317-7610-2-git-send-email-vincent.guittot@linaro.org> (raw)
In-Reply-To: <1544803317-7610-1-git-send-email-vincent.guittot@linaro.org>
When check_asym_packing() is triggered, the imbalance is set to :
busiest_stat.avg_load * busiest_stat.group_capacity / SCHED_CAPACITY_SCALE
busiest_stat.avg_load also comes from a division and the final rounding
can make imbalance slightly lower than the weighted load of the cfs_rq.
But this is enough to skip the rq in find_busiest_queue and prevents asym
migration to happen.
Add 1 to the avg_load to make sure that the targeted cpu will not be
skipped unexpectidly.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
kernel/sched/fair.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ca46964..c215f7a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8215,6 +8215,12 @@ static inline void update_sg_lb_stats(struct lb_env *env,
/* Adjust by relative CPU capacity of the group */
sgs->group_capacity = group->sgc->capacity;
sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity;
+ /*
+ * Prevent division rounding to make the computation of imbalance
+ * slightly less than original value and to prevent the rq to be then
+ * selected as busiest queue
+ */
+ sgs->avg_load += 1;
if (sgs->sum_nr_running)
sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
--
2.7.4
next prev parent reply other threads:[~2018-12-14 16:02 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-14 16:01 [PATCH v2 0/3] sched/fair: some fixes for asym_packing Vincent Guittot
2018-12-14 16:01 ` Vincent Guittot [this message]
2018-12-18 17:32 ` [PATCH v2 1/3] sched/fair: fix rounding issue for asym packing Valentin Schneider
2018-12-19 8:32 ` Vincent Guittot
2018-12-19 11:58 ` Valentin Schneider
2018-12-19 13:39 ` Vincent Guittot
2018-12-19 14:59 ` Valentin Schneider
2018-12-19 15:05 ` Vincent Guittot
2018-12-19 15:11 ` Valentin Schneider
2018-12-19 15:20 ` Vincent Guittot
2018-12-19 15:30 ` Valentin Schneider
2018-12-19 15:54 ` Vincent Guittot
2018-12-14 16:01 ` [PATCH v2 2/3] sched/fair: trigger asym_packing during idle load balance Vincent Guittot
2018-12-17 16:59 ` Valentin Schneider
2018-12-18 8:17 ` Vincent Guittot
2018-12-18 12:00 ` Valentin Schneider
2018-12-14 16:01 ` [PATCH v2 3/3] sched/fair: fix unnecessary increase of balance interval Vincent Guittot
2018-12-17 16:56 ` Valentin Schneider
2018-12-18 9:32 ` Vincent Guittot
2018-12-18 11:46 ` Valentin Schneider
2018-12-18 13:23 ` Vincent Guittot
2018-12-18 14:09 ` Valentin Schneider
2018-12-19 8:27 ` Vincent Guittot
2018-12-19 11:16 ` Valentin Schneider
2018-12-19 13:29 ` Vincent Guittot
2018-12-19 15:54 ` Valentin Schneider
2018-12-19 16:54 ` 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=1544803317-7610-2-git-send-email-vincent.guittot@linaro.org \
--to=vincent.guittot@linaro.org \
--cc=Morten.Rasmussen@arm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=valentin.schneider@arm.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).