Currently, multiple tasks can wakeup on same cpu from
select_idle_sibiling() path in case they wakeup simulatenously
and last ran on the same llc. This happens because an idle cpu
is not updated until idle task is scheduled out. Any task waking
during that period may potentially select that cpu for a wakeup
candidate.
Introduce a per cpu variable that is set as soon as a cpu is
selected for wakeup for any task. This prevents from other tasks
to select the same cpu again. Note: This does not close the race
window but minimizes it to accessing the per-cpu variable. If two
wakee tasks access the per cpu variable at the same time, they may
select the same cpu again. But it minimizes the race window
considerably.
Here are some performance numbers:
Hardware config: 20 core (40 hyperthreaded cpus) x86 box.
uperf config:ping pong test on loopback interface with message size = 8k
Baseline (4.14) Baseline +pcpu
Mean stdev Mean stdev Improvement(%)
1 9.056 0.02 8.966 0.083 -0.993
2 17.664 0.13 17.448 0.303 -1.222
4 32.03 0.22 31.972 0.129 -0.181
8 58.198 0.31 58.588 0.198 0.670
16 101.018 0.67 100.056 0.455 -0.952
32 148.1 15.41 164.494 2.312 11.069
64 203.66 1.16 203.042 1.348 -0.3073
128 197.12 1.04 194.722 1.174 -1.2165
schbench config: message threads = 2; time = 180s, worker thread = 19
Baseline(4.14) Base+pcpu
Max Latency
Mean stdev Mean stdev Improvement(%)
16457 2046.51 12985.4 48.46 21.0949747828
Latency in usec(lower is better)
Mean stdev Mean stdev Improvement(%)
50% 63 4.774 58 4 7.936
75% 81.6 1.2 79.4 0.8 2.696
90% 92.8 0.979 90.6 0.489 2.370
95% 102.6 1.624 99 0.894 3.508
99% 126.25 4.573 120.4 3.872 4.63
99.5% 2712.2 4772.883 133.6 5.571 95.074
Reported by Joel:
Jackbench(Android)
count 16304 (@60 fps, 4.5 minutes)
Without patch With patch
mean 5.196633 4.429641 (+14.75%)
std 2.030054 2.310025
25% 5.606810 1.991017 (+64.48%)
50% 5.824013 5.716631 (+1.84%)
75% 5.987102 5.932751 (+0.90%)
95% 6.461230 6.301318 (+2.47%)
99% 9.828959 9.697076 (+1.34%)
The details are at:
https://lkml.org/lkml/2017/11/22/5
Suggested-by: Peter Zijlstra <[email protected]>
Tested-by: Joel Fernandes <[email protected]>
Signed-off-by: Atish Patra <[email protected]>
---
kernel/sched/core.c | 4 ++++
kernel/sched/fair.c | 12 +++++++++---
kernel/sched/idle_task.c | 1 +
kernel/sched/sched.h | 1 +
4 files changed, 15 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2288a14..d9d501c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3896,6 +3896,7 @@ int task_prio(const struct task_struct *p)
return p->prio - MAX_RT_PRIO;
}
+DEFINE_PER_CPU(int, claim_wakeup);
/**
* idle_cpu - is a given CPU idle currently?
* @cpu: the processor in question.
@@ -3917,6 +3918,9 @@ int idle_cpu(int cpu)
return 0;
#endif
+ if (per_cpu(claim_wakeup, cpu))
+ return 0;
+
return 1;
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 13393bb..885023a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6077,8 +6077,10 @@ static int select_idle_core(struct task_struct *p,
struct sched_domain *sd, int
idle = false;
}
- if (idle)
+ if (idle) {
+ per_cpu(claim_wakeup, core) = 1;
return core;
+ }
}
/*
@@ -6102,8 +6104,10 @@ static int select_idle_smt(struct task_struct *p, struct
sched_domain *sd, int t
for_each_cpu(cpu, cpu_smt_mask(target)) {
if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
continue;
- if (idle_cpu(cpu))
+ if (idle_cpu(cpu)) {
+ per_cpu(claim_wakeup, cpu) = 1;
return cpu;
+ }
}
return -1;
@@ -6165,8 +6169,10 @@ static int select_idle_cpu(struct task_struct *p, struct
sched_domain *sd, int t
return -1;
if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
continue;
- if (idle_cpu(cpu))
+ if (idle_cpu(cpu)) {
+ per_cpu(claim_wakeup, cpu) = 1;
break;
+ }
}
time = local_clock() - time;
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 0c00172..64d6495 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -28,6 +28,7 @@ pick_next_task_idle(struct rq *rq, struct task_struct *prev,
struct rq_flags *rf
{
put_prev_task(rq, prev);
update_idle_core(rq);
+ this_cpu_write(claim_wakeup, 0);
schedstat_inc(rq->sched_goidle);
return rq->idle;
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 8aa24b4..5f70b98 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1068,6 +1068,7 @@ DECLARE_PER_CPU(int, sd_llc_id);
DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
DECLARE_PER_CPU(struct sched_domain *, sd_numa);
DECLARE_PER_CPU(struct sched_domain *, sd_asym);
+DECLARE_PER_CPU(int, claim_wakeup);
struct sched_group_capacity {
atomic_t ref;
--
2.7.4
