sched: reduce schedstat variable overhead a bit

schedstat is useful in investigating CPU scheduler behavior.  Ideally,
I think it is beneficial to have it on all the time.  However, the
cost of turning it on in production system is quite high, largely due
to number of events it collects and also due to its large memory
footprint.

Most of the fields probably don't need to be full 64-bit on 64-bit
arch.  Rolling over 4 billion events will most like take a long time
and user space tool can be made to accommodate that.  I'm proposing
kernel to cut back most of variable width on 64-bit system.  (note,
the following patch doesn't affect 32-bit system).

Signed-off-by: Ken Chen <kenchen@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 14 insertions, 16 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index b19cc5b..b60f8a5 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -332,22 +332,22 @@ struct rq {
 	struct sched_info rq_sched_info;
 
 	/* sys_sched_yield() stats */
-	unsigned long yld_exp_empty;
-	unsigned long yld_act_empty;
-	unsigned long yld_both_empty;
-	unsigned long yld_count;
+	unsigned int yld_exp_empty;
+	unsigned int yld_act_empty;
+	unsigned int yld_both_empty;
+	unsigned int yld_count;
 
 	/* schedule() stats */
-	unsigned long sched_switch;
-	unsigned long sched_count;
-	unsigned long sched_goidle;
+	unsigned int sched_switch;
+	unsigned int sched_count;
+	unsigned int sched_goidle;
 
 	/* try_to_wake_up() stats */
-	unsigned long ttwu_count;
-	unsigned long ttwu_local;
+	unsigned int ttwu_count;
+	unsigned int ttwu_local;
 
 	/* BKL stats */
-	unsigned long bkl_count;
+	unsigned int bkl_count;
 #endif
 	struct lock_class_key rq_lock_key;
 };
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index a5e517e..e6fb392 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -137,7 +137,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "  .%-30s: %ld\n", "nr_running", cfs_rq->nr_running);
 	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
 #ifdef CONFIG_SCHEDSTATS
-	SEQ_printf(m, "  .%-30s: %ld\n", "bkl_count",
+	SEQ_printf(m, "  .%-30s: %d\n", "bkl_count",
 			rq->bkl_count);
 #endif
 	SEQ_printf(m, "  .%-30s: %ld\n", "nr_spread_over",
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 1c08484..ef1a7df 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -21,7 +21,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
 
 		/* runqueue-specific stats */
 		seq_printf(seq,
-		    "cpu%d %lu %lu %lu %lu %lu %lu %lu %lu %lu %llu %llu %lu",
+		    "cpu%d %u %u %u %u %u %u %u %u %u %llu %llu %lu",
 		    cpu, rq->yld_both_empty,
 		    rq->yld_act_empty, rq->yld_exp_empty, rq->yld_count,
 		    rq->sched_switch, rq->sched_count, rq->sched_goidle,
@@ -42,8 +42,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
 			seq_printf(seq, "domain%d %s", dcount++, mask_str);
 			for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES;
 					itype++) {
-				seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu "
-						"%lu",
+				seq_printf(seq, " %u %u %u %u %u %u %u %u",
 				    sd->lb_count[itype],
 				    sd->lb_balanced[itype],
 				    sd->lb_failed[itype],
@@ -53,8 +52,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
 				    sd->lb_nobusyq[itype],
 				    sd->lb_nobusyg[itype]);
 			}
-			seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu %lu"
-			    " %lu %lu %lu\n",
+			seq_printf(seq, " %u %u %u %u %u %u %u %u %u %u %u %u\n",
 			    sd->alb_count, sd->alb_failed, sd->alb_pushed,
 			    sd->sbe_count, sd->sbe_balanced, sd->sbe_pushed,
 			    sd->sbf_count, sd->sbf_balanced, sd->sbf_pushed,