@@ -718,6 +718,8 @@ do { \
P(sis_domain_search);
P(sis_scanned);
P(sis_failed);
+ P(sis_recent_hit);
+ P(sis_recent_miss);
}
#undef P
@@ -6291,16 +6291,19 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
recent_used_cpu = p->recent_used_cpu;
if (recent_used_cpu != prev &&
recent_used_cpu != target &&
- cpus_share_cache(recent_used_cpu, target) &&
- (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
- cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
- asym_fits_capacity(task_util, recent_used_cpu)) {
- /*
- * Replace recent_used_cpu with prev as it is a potential
- * candidate for the next wake:
- */
- p->recent_used_cpu = prev;
- return recent_used_cpu;
+ cpus_share_cache(recent_used_cpu, target)) {
+ if ((available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
+ cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
+ asym_fits_capacity(task_util, recent_used_cpu)) {
+ /*
+ * Replace recent_used_cpu with prev as it is a potential
+ * candidate for the next wake:
+ */
+ p->recent_used_cpu = prev;
+ schedstat_inc(this_rq()->sis_recent_hit);
+ return recent_used_cpu;
+ }
+ schedstat_inc(this_rq()->sis_recent_miss);
}
/*
@@ -1055,6 +1055,8 @@ struct rq {
unsigned int sis_domain_search;
unsigned int sis_scanned;
unsigned int sis_failed;
+ unsigned int sis_recent_hit;
+ unsigned int sis_recent_miss;
#endif
#ifdef CONFIG_CPU_IDLE
@@ -10,7 +10,7 @@
* Bump this up when changing the output format or the meaning of an existing
* format, so that tools can adapt (or abort)
*/
-#define SCHEDSTAT_VERSION 16
+#define SCHEDSTAT_VERSION 17
static int show_schedstat(struct seq_file *seq, void *v)
{
@@ -30,14 +30,15 @@ static int show_schedstat(struct seq_file *seq, void *v)
/* runqueue-specific stats */
seq_printf(seq,
- "cpu%d %u 0 %u %u %u %u %llu %llu %lu %u %u %u %u",
+ "cpu%d %u 0 %u %u %u %u %llu %llu %lu %u %u %u %u %u %u",
cpu, rq->yld_count,
rq->sched_count, rq->sched_goidle,
rq->ttwu_count, rq->ttwu_local,
rq->rq_cpu_time,
rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount,
rq->sis_search, rq->sis_domain_search,
- rq->sis_scanned, rq->sis_failed);
+ rq->sis_scanned, rq->sis_failed,
+ rq->sis_recent_hit, rq->sis_recent_miss);
seq_printf(seq, "\n");
This simply tracks the efficiency of the recent_used_cpu. The hit rate of this matters as it can avoid a domain search. Similarly, the miss rate matters because each miss is a penalty to the fast path. It is not required that this patch be merged with the series but if we are looking at the usefulness of p->recent_used_cpu, the stats generate hard data on what the hit rate is. MMTests uses this to generate additional metrics. SIS Recent Used Hit: A recent CPU was eligible and used. Each hit is a domain search avoided. SIS Recent Used Miss: A recent CPU was eligible but unavailable. Each time this is miss, there was a small penalty to the fast path before a domain search happened. SIS Recent Success Rate: A percentage of the number of hits versus the total attempts to use the recent CPU. SIS Recent Attempts: The total number of times the recent CPU was examined. A high number of Recent Attempts with a low Success Rate implies the fast path is being punished severely. This could have been presented as a weighting of hits and misses but calculating an appropriate weight for misses is problematic. Signed-off-by: Mel Gorman <mgorman@techsingularity.net> --- kernel/sched/debug.c | 2 ++ kernel/sched/fair.c | 23 +++++++++++++---------- kernel/sched/sched.h | 2 ++ kernel/sched/stats.c | 7 ++++--- 4 files changed, 21 insertions(+), 13 deletions(-)