Re: [PATCH 09/10] provide a version of cpuusage statistics insidecpu cgroup

[Glauber Costa]

On 10/05/2011 01:46 PM, Peter Zijlstra wrote:
> On Sun, 2011-10-02 at 23:21 +0400, Glauber Costa wrote:
> > +/*
> > + * charge this task's execution time to its accounting group.
> > + *
> > + * called with rq->lock held.
> > + */
> > +static void cpuusage_charge(struct task_struct *tsk, u64 cputime)
> > +{
> > +       int cpu;
> > +
> > +#ifdef CONFIG_CGROUP_CPUACCT
> > +       struct cpuacct *ca;
> > +#endif
> > +#ifdef CONFIG_CGROUP_SCHED
> > +       struct task_group *tg;
> > +#endif
> > +       cpu = task_cpu(tsk);
> > +
> > +       rcu_read_lock();
> > +
> > +#ifdef CONFIG_CGROUP_CPUACCT
> > +       ca = task_ca(tsk);
> > +
> > +       if (unlikely(!cpuacct_subsys.active))
> > +               goto no_cpuacct;
> > +
> > +       for (; ca; ca = ca->parent) {
> > +               u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
> > +               *cpuusage += cputime;
> > +       }
> > +no_cpuacct:
> > +#endif
> > +
> > +#ifdef CONFIG_CGROUP_SCHED
> > +       tg = task_group(tsk);
> > +       for (; tg; tg = tg->parent) {
> > +               u64 *cpuusage = per_cpu_ptr(tg->cpuusage, cpu);
> > +               *cpuusage += cputime;
> > +       }
> > +#endif
> > +       rcu_read_unlock();
> > +}
>
> I don't actually think we need to do this. tg->se[cpu]->sum_exec_runtime
> should contain the same information.

Well,

We should at least sum up se and rt_se, right?
Otherwise... I will re-read the code, but from a first sight, I think 
you are right.



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/