Commit f9bcf1e0 authored Aug 11, 2016 by Wanpeng Li Committed by Ingo Molnar Aug 11, 2016

sched/cputime: Fix steal time accounting



Commit:

  57430218 ("sched/cputime: Count actually elapsed irq & softirq time")

... didn't take steal time into consideration with passing the noirqtime
kernel parameter.

As Paolo pointed out before:

| Why not? If idle=poll, for example, any time the guest is suspended (and
| thus cannot poll) does count as stolen time.

This patch fixes it by reducing steal time from idle time accounting when
the noirqtime parameter is true. The average idle time drops from 56.8%
to 54.75% for nohz idle kvm guest(noirqtime, idle=poll, four vCPUs running
on one pCPU).

Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Radim <rkrcmar@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1470893795-3527-1-git-send-email-wanpeng.li@hotmail.com


Signed-off-by: Ingo Molnar <mingo@kernel.org>

parent c0c8c9fa

kernel/sched/cputime.c

+9 −2

Original line number	Diff line number	Diff line
		@@ -508,13 +508,20 @@ void account_process_tick(struct task_struct *p, int user_tick)
		*/
		void account_idle_ticks(unsigned long ticks)
		{

		cputime_t cputime, steal;
		if (sched_clock_irqtime) {
		irqtime_account_idle_ticks(ticks);
		return;
		}

		account_idle_time(jiffies_to_cputime(ticks));
		cputime = cputime_one_jiffy;
		steal = steal_account_process_time(cputime);

		if (steal >= cputime)
		return;

		cputime -= steal;
		account_idle_time(cputime);
		}

		/*

Admin message