[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20201214170017.877557652@infradead.org>
Date: Mon, 14 Dec 2020 17:48:23 +0100
From: Peter Zijlstra <peterz@...radead.org>
To: mgorman@...hsingularity.net, vincent.guittot@...aro.org
Cc: peterz@...radead.org, linux-kernel@...r.kernel.org,
aubrey.li@...ux.intel.com, mingo@...hat.com, juri.lelli@...hat.com,
valentin.schneider@....com, qais.yousef@....com,
dietmar.eggemann@....com, rostedt@...dmis.org, bsegall@...gle.com,
tim.c.chen@...ux.intel.com, benbjiang@...il.com
Subject: [RFC][PATCH 1/5] sched/fair: Fix select_idle_cpu()s cost accounting
We compute the average cost of the total scan, but then use it as a
per-cpu scan cost when computing the scan proportion. Fix this by
properly computing a per-cpu scan cost.
This also fixes a bug where we would terminate early (!--nr, case) and
not account that cost at all.
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
---
kernel/sched/fair.c | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6144,10 +6144,10 @@ static inline int select_idle_smt(struct
static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
{
struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
+ int cpu, loops = 1, nr = INT_MAX;
+ int this = smp_processor_id();
struct sched_domain *this_sd;
u64 time;
- int this = smp_processor_id();
- int cpu, nr = INT_MAX;
this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
if (!this_sd)
@@ -6175,14 +6175,19 @@ static int select_idle_cpu(struct task_s
}
for_each_cpu_wrap(cpu, cpus, target) {
- if (!--nr)
- return -1;
if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
break;
+
+ if (loops >= nr) {
+ cpu = -1;
+ break;
+ }
+ loops++;
}
if (sched_feat(SIS_PROP)) {
time = cpu_clock(this) - time;
+ time = div_u64(time, loops);
update_avg(&this_sd->avg_scan_cost, time);
}
Powered by blists - more mailing lists