summaryrefslogtreecommitdiffstats
path: root/kernel/tsacct.c
diff options
context:
space:
mode:
authorRik van Riel <riel@redhat.com>2016-02-10 20:08:24 -0500
committerIngo Molnar <mingo@kernel.org>2016-02-29 09:53:08 +0100
commit382c2fe994321d503647ce8ee329b9420dc7c1f9 (patch)
treeed44c0f4af5476fa268e0e2811be51e8caab7456 /kernel/tsacct.c
parentc3a990dc9fab590fb88608410f1cc2bc866bdf30 (diff)
downloadlinux-382c2fe994321d503647ce8ee329b9420dc7c1f9.tar.bz2
sched, time: Remove non-power-of-two divides from __acct_update_integrals()
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@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: clark@redhat.com Cc: eric.dumazet@gmail.com Cc: fweisbec@gmail.com Cc: luto@amacapital.net Link: http://lkml.kernel.org/r/1455152907-18495-2-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/tsacct.c')
-rw-r--r--kernel/tsacct.c26
1 files changed, 16 insertions, 10 deletions
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 975cb49e32bf..460ee2bbfef3 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -93,9 +93,11 @@ 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/1024 to Mbyte-usec, see __acct_update_integrals */
+ stats->coremem = p->acct_rss_mem1 * PAGE_SIZE;
+ do_div(stats->coremem, 1000 * KB);
+ stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE;
+ do_div(stats->virtmem, 1000 * KB);
mm = get_task_mm(p);
if (mm) {
/* adjust to KB unit */
@@ -125,22 +127,26 @@ 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;
+ /* Avoid division: cputime_t is often in nanoseconds already. */
+ 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;
+ /*
+ * Divide by 1024 to avoid overflow, and to avoid division.
+ * The final unit reported to userspace is Mbyte-usecs,
+ * the rest of the math is done in xacct_add_tsk.
+ */
+ tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm) >> 10;
+ tsk->acct_vm_mem1 += delta * tsk->mm->total_vm >> 10;
out:
local_irq_restore(flags);
}