Re: [PATCH v2 3/6] KVM-GST: KVM Steal time accounting

[Jeremy Fitzhardinge <jeremy@goop.org>]

On 01/28/2011 11:52 AM, Glauber Costa wrote:
> This patch accounts steal time time in kernel/sched.
> I kept it from last proposal, because I still see advantages
> in it: Doing it here will give us easier access from scheduler
> variables such as the cpu rq. The next patch shows an example of
> usage for it.

Is this used on the host or guest side?

    J

> Since functions like account_idle_time() can be called from
> multiple places, not only account_process_tick(), steal time
> grabbing is repeated in each account function separatedely.
>
> Signed-off-by: Glauber Costa <glommer@redhat.com>
> CC: Rik van Riel <riel@redhat.com>
> CC: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
> CC: Peter Zijlstra <peterz@infradead.org>
> CC: Avi Kivity <avi@redhat.com>
> ---
>  include/linux/sched.h |    1 +
>  kernel/sched.c        |   41 +++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 42 insertions(+), 0 deletions(-)
>
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index d747f94..77e9297 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -302,6 +302,7 @@ long io_schedule_timeout(long timeout);
>  extern void cpu_init (void);
>  extern void trap_init(void);
>  extern void update_process_times(int user);
> +extern u64 (*hypervisor_steal_time)(void);
>  extern void scheduler_tick(void);
>  
>  extern void sched_show_task(struct task_struct *p);
> diff --git a/kernel/sched.c b/kernel/sched.c
> index ea3e5ef..7765e9d 100644
> --- a/kernel/sched.c
> +++ b/kernel/sched.c
> @@ -3508,6 +3508,39 @@ unsigned long long thread_group_sched_runtime(struct task_struct *p)
>  	return ns;
>  }
>  
> +u64 (*hypervisor_steal_time)(void) = NULL;
> +
> +/*
> + * We have to at flush steal time information every time something else
> + * is accounted. Since the accounting functions are all visible to the rest
> + * of the kernel, it gets tricky to do them in one place. This helper function
> + * helps us.
> + *
> + * When the system is idle, the concept of steal time does not apply. We just
> + * tell the underlying hypervisor that we grabbed the data, but skip steal time
> + * accounting
> + */
> +static int touch_steal_time(int is_idle)
> +{
> +	u64 steal, st;
> +
> +	if (!hypervisor_steal_time)
> +		return 0;
> +
> +	steal = hypervisor_steal_time();
> +
> +	st = usecs_to_cputime(steal / 1000);
> +
> +	if (is_idle)
> +		return 0;
> +
> +	if (st) {
> +		account_steal_time(st);
> +		return 1;
> +	}
> +	return 0;
> +}
> +
>  /*
>   * Account user cpu time to a process.
>   * @p: the process that the cpu time gets accounted to
> @@ -3520,6 +3553,9 @@ void account_user_time(struct task_struct *p, cputime_t cputime,
>  	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
>  	cputime64_t tmp;
>  
> +	if (touch_steal_time(0))
> +		return;
> +
>  	/* Add user time to process. */
>  	p->utime = cputime_add(p->utime, cputime);
>  	p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
> @@ -3580,6 +3616,9 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
>  	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
>  	cputime64_t tmp;
>  
> +	if (touch_steal_time(0))
> +		return;
> +
>  	if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
>  		account_guest_time(p, cputime, cputime_scaled);
>  		return;
> @@ -3627,6 +3666,8 @@ void account_idle_time(cputime_t cputime)
>  	cputime64_t cputime64 = cputime_to_cputime64(cputime);
>  	struct rq *rq = this_rq();
>  
> +	touch_steal_time(1);
> +
>  	if (atomic_read(&rq->nr_iowait) > 0)
>  		cpustat->iowait = cputime64_add(cpustat->iowait, cputime64);
>  	else