[PATCH 1/4] sched,time: remove non-power-of-two divides from __acct_update_integrals

[riel]

From: Rik van Riel <riel@xxxxxxxxxx>

When running a microbenchmark calling an invalid syscall number
in a loop, on a nohz_full CPU, we spend a full 9% of our CPU
time in __acct_update_integrals.

This function converts cputime_t to jiffies, to a timeval, only to
convert the timeval back to microseconds before discarding it.

This patch leaves __acct_update_integrals functionally equivalent,
but speeds things up by about 12%, with 10 million calls to an
invalid syscall number dropping from 3.7 to 3.25 seconds.

Signed-off-by: Rik van Riel <riel@xxxxxxxxxx>
---
 kernel/tsacct.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 975cb49e32bf..41667b23dbd0 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -93,9 +93,9 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
 {
 	struct mm_struct *mm;
 
-	/* convert pages-usec to Mbyte-usec */
-	stats->coremem = p->acct_rss_mem1 * PAGE_SIZE / MB;
-	stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE / MB;
+	/* convert pages-nsec/KB to Mbyte-usec, see __acct_update_integrals */
+	stats->coremem = p->acct_rss_mem1 * PAGE_SIZE / (1000 * KB);
+	stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE / (1000 * KB);
 	mm = get_task_mm(p);
 	if (mm) {
 		/* adjust to KB unit */
@@ -125,22 +125,21 @@ static void __acct_update_integrals(struct task_struct *tsk,
 {
 	if (likely(tsk->mm)) {
 		cputime_t time, dtime;
-		struct timeval value;
 		unsigned long flags;
 		u64 delta;
 
 		local_irq_save(flags);
 		time = stime + utime;
 		dtime = time - tsk->acct_timexpd;
-		jiffies_to_timeval(cputime_to_jiffies(dtime), &value);
-		delta = value.tv_sec;
-		delta = delta * USEC_PER_SEC + value.tv_usec;
+		delta = cputime_to_nsecs(dtime);
 
-		if (delta == 0)
+		if (delta < TICK_NSEC)
 			goto out;
+
 		tsk->acct_timexpd = time;
-		tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
-		tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
+		/* The final unit will be Mbyte-usecs, see xacct_add_tsk */
+		tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm) / 1024;
+		tsk->acct_vm_mem1 += delta * tsk->mm->total_vm / 1024;
 	out:
 		local_irq_restore(flags);
 	}
-- 
2.5.0