[PATCH v2 17/23] sched/cache: Record the number of active threads per process for cache-aware scheduling

[Tim Chen]

From: Chen Yu <yu.c.chen@xxxxxxxxx>

A performance regression was observed by Prateek when running hackbench
with many threads per process (high fd count). To avoid this, processes
with a large number of active threads are excluded from cache-aware
scheduling.

With sched_cache enabled, record the number of active threads in each
process during the periodic task_cache_work(). While iterating over
CPUs, if the currently running task belongs to the same process as the
task that launched task_cache_work(), increment the active thread count.

This number will be used by subsequent patch to inhibit cache aware
load balance.

Suggested-by: K Prateek Nayak <kprateek.nayak@xxxxxxx>
Signed-off-by: Chen Yu <yu.c.chen@xxxxxxxxx>
Signed-off-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
---

Notes:
    v1->v2: No change.

 include/linux/mm_types.h |  1 +
 kernel/sched/fair.c      | 11 +++++++++--
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 1ea16ef90566..04743983de4d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1043,6 +1043,7 @@ struct mm_struct {
 		raw_spinlock_t mm_sched_lock;
 		unsigned long mm_sched_epoch;
 		int mm_sched_cpu;
+		u64 nr_running_avg ____cacheline_aligned_in_smp;
 #endif
 
 #ifdef CONFIG_MMU
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 580a967efdac..2f38ad82688f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1421,11 +1421,11 @@ static void task_tick_cache(struct rq *rq, struct task_struct *p)
 
 static void __no_profile task_cache_work(struct callback_head *work)
 {
-	struct task_struct *p = current;
+	struct task_struct *p = current, *cur;
 	struct mm_struct *mm = p->mm;
 	unsigned long m_a_occ = 0;
 	unsigned long curr_m_a_occ = 0;
-	int cpu, m_a_cpu = -1;
+	int cpu, m_a_cpu = -1, nr_running = 0;
 	cpumask_var_t cpus;
 
 	WARN_ON_ONCE(work != &p->cache_work);
@@ -1458,6 +1458,12 @@ static void __no_profile task_cache_work(struct callback_head *work)
 					m_occ = occ;
 					m_cpu = i;
 				}
+				rcu_read_lock();
+				cur = rcu_dereference(cpu_rq(i)->curr);
+				if (cur && !(cur->flags & (PF_EXITING | PF_KTHREAD)) &&
+				    cur->mm == mm)
+					nr_running++;
+				rcu_read_unlock();
 			}
 
 			/*
@@ -1501,6 +1507,7 @@ static void __no_profile task_cache_work(struct callback_head *work)
 		mm->mm_sched_cpu = m_a_cpu;
 	}
 
+	update_avg(&mm->nr_running_avg, nr_running);
 	free_cpumask_var(cpus);
 }
 
-- 
2.32.0