From: Vincent Guittot <vincent.guittot@linaro.org>
To: mingo@redhat.com, peterz@infradead.org, juri.lelli@redhat.com,
dietmar.eggemann@arm.com, rostedt@goodmis.org,
bsegall@google.com, mgorman@suse.de, bristot@redhat.com,
linux-kernel@vger.kernel.org, tim.c.chen@linux.intel.com
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Subject: [PATCH v2 3/4] sched/fair: Wait before decaying max_newidle_lb_cost
Date: Fri, 15 Oct 2021 14:46:53 +0200 [thread overview]
Message-ID: <20211015124654.18093-4-vincent.guittot@linaro.org> (raw)
In-Reply-To: <20211015124654.18093-1-vincent.guittot@linaro.org>
Decay max_newidle_lb_cost only when it has not been updated for a while
and ensure to not decay a recently changed value.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
include/linux/sched/topology.h | 2 +-
kernel/sched/fair.c | 8 +++++---
kernel/sched/topology.c | 2 +-
3 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 8f0f778b7c91..9c8878f201ab 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -98,7 +98,7 @@ struct sched_domain {
/* idle_balance() stats */
u64 max_newidle_lb_cost;
- unsigned long next_decay_max_lb_cost;
+ unsigned long last_decay_max_lb_cost;
u64 avg_scan_cost; /* select_idle_sibling */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6b8065b72847..2967d13737b7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10265,10 +10265,10 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
* Decay the newidle max times here because this is a regular
* visit to all the domains. Decay ~1% per second.
*/
- if (time_after(jiffies, sd->next_decay_max_lb_cost)) {
+ if (time_after(jiffies, sd->last_decay_max_lb_cost + HZ)) {
sd->max_newidle_lb_cost =
(sd->max_newidle_lb_cost * 253) / 256;
- sd->next_decay_max_lb_cost = jiffies + HZ;
+ sd->last_decay_max_lb_cost = jiffies;
need_decay = 1;
}
max_cost += sd->max_newidle_lb_cost;
@@ -10912,8 +10912,10 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
t1 = sched_clock_cpu(this_cpu);
domain_cost = t1 - t0;
- if (domain_cost > sd->max_newidle_lb_cost)
+ if (domain_cost > sd->max_newidle_lb_cost) {
sd->max_newidle_lb_cost = domain_cost;
+ sd->last_decay_max_lb_cost = jiffies;
+ }
curr_cost += domain_cost;
t0 = t1;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index c56faae461d9..edd71649d579 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1572,7 +1572,7 @@ sd_init(struct sched_domain_topology_level *tl,
.last_balance = jiffies,
.balance_interval = sd_weight,
.max_newidle_lb_cost = 0,
- .next_decay_max_lb_cost = jiffies,
+ .last_decay_max_lb_cost = jiffies,
.child = child,
#ifdef CONFIG_SCHED_DEBUG
.name = tl->name,
--
2.17.1
next prev parent reply other threads:[~2021-10-15 12:50 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-10-15 12:46 [PATCH v2 0/4] Improve newidle lb cost tracking and early abort Vincent Guittot
2021-10-15 12:46 ` [PATCH v2 1/4] sched/fair: Account update_blocked_averages in newidle_balance cost Vincent Guittot
2021-10-15 12:46 ` [PATCH v2 2/4] sched/fair: Skip update_blocked_averages if we are defering load balance Vincent Guittot
2021-10-15 12:46 ` Vincent Guittot [this message]
2021-10-15 17:40 ` [PATCH v2 3/4] sched/fair: Wait before decaying max_newidle_lb_cost Peter Zijlstra
2021-10-15 18:02 ` Vincent Guittot
2021-10-15 18:29 ` Peter Zijlstra
2021-10-15 12:46 ` [PATCH v2 4/4] sched/fair: Remove sysctl_sched_migration_cost condition Vincent Guittot
2021-10-15 17:42 ` Peter Zijlstra
2021-10-15 17:57 ` 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=20211015124654.18093-4-vincent.guittot@linaro.org \
--to=vincent.guittot@linaro.org \
--cc=bristot@redhat.com \
--cc=bsegall@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tim.c.chen@linux.intel.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).