Re: [PATCH 8/9] psi: pressure stall information for CPU, memory, and IO

[Peter Zijlstra]

On Wed, Aug 01, 2018 at 11:19:57AM -0400, Johannes Weiner wrote:
> +static bool test_state(unsigned int *tasks, int cpu, enum psi_states state)
> +{
> +	switch (state) {
> +	case PSI_IO_SOME:
> +		return tasks[NR_IOWAIT];
> +	case PSI_IO_FULL:
> +		return tasks[NR_IOWAIT] && !tasks[NR_RUNNING];
> +	case PSI_MEM_SOME:
> +		return tasks[NR_MEMSTALL];
> +	case PSI_MEM_FULL:
> +		/*
> +		 * Since we care about lost potential, things are
> +		 * fully blocked on memory when there are no other
> +		 * working tasks, but also when the CPU is actively
> +		 * being used by a reclaimer and nothing productive
> +		 * could run even if it were runnable.
> +		 */
> +		return tasks[NR_MEMSTALL] &&
> +			(!tasks[NR_RUNNING] ||
> +			 cpu_curr(cpu)->flags & PF_MEMSTALL);

I don't think you can do this, there is nothing that guarantees
cpu_curr() still exists.

> +	case PSI_CPU_SOME:
> +		return tasks[NR_RUNNING] > 1;
> +	case PSI_NONIDLE:
> +		return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] ||
> +			tasks[NR_RUNNING];
> +	default:
> +		return false;
> +	}
> +}
> +
> +static bool psi_update_stats(struct psi_group *group)
> +{
> +	u64 deltas[NR_PSI_STATES - 1] = { 0, };
> +	unsigned long missed_periods = 0;
> +	unsigned long nonidle_total = 0;
> +	u64 now, expires, period;
> +	int cpu;
> +	int s;
> +
> +	mutex_lock(&group->stat_lock);
> +
> +	/*
> +	 * Collect the per-cpu time buckets and average them into a
> +	 * single time sample that is normalized to wallclock time.
> +	 *
> +	 * For averaging, each CPU is weighted by its non-idle time in
> +	 * the sampling period. This eliminates artifacts from uneven
> +	 * loading, or even entirely idle CPUs.
> +	 *
> +	 * We don't need to synchronize against CPU hotplugging. If we
> +	 * see a CPU that's online and has samples, we incorporate it.
> +	 */
> +	for_each_online_cpu(cpu) {
> +		struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu);
> +		u32 uninitialized_var(nonidle);

urgh.. I can see why the compiler got confused. Dodgy :-)

> +
> +		BUILD_BUG_ON(PSI_NONIDLE != NR_PSI_STATES - 1);
> +
> +		for (s = PSI_NONIDLE; s >= 0; s--) {
> +			u32 time, delta;
> +
> +			time = READ_ONCE(groupc->times[s]);
> +			/*
> +			 * In addition to already concluded states, we
> +			 * also incorporate currently active states on
> +			 * the CPU, since states may last for many
> +			 * sampling periods.
> +			 *
> +			 * This way we keep our delta sampling buckets
> +			 * small (u32) and our reported pressure close
> +			 * to what's actually happening.
> +			 */
> +			if (test_state(groupc->tasks, cpu, s)) {
> +				/*
> +				 * We can race with a state change and
> +				 * need to make sure the state_start
> +				 * update is ordered against the
> +				 * updates to the live state and the
> +				 * time buckets (groupc->times).
> +				 *
> +				 * 1. If we observe task state that
> +				 * needs to be recorded, make sure we
> +				 * see state_start from when that
> +				 * state went into effect or we'll
> +				 * count time from the previous state.
> +				 *
> +				 * 2. If the time delta has already
> +				 * been added to the bucket, make sure
> +				 * we don't see it in state_start or
> +				 * we'll count it twice.
> +				 *
> +				 * If the time delta is out of
> +				 * state_start but not in the time
> +				 * bucket yet, we'll miss it entirely
> +				 * and handle it in the next period.
> +				 */
> +				smp_rmb();
> +				time += cpu_clock(cpu) - groupc->state_start;
> +			}

The alternative is adding an update to scheduler_tick(), that would
ensure you're never more than nr_cpu_ids * TICK_NSEC behind.

> +			delta = time - groupc->times_prev[s];
> +			groupc->times_prev[s] = time;
> +
> +			if (s == PSI_NONIDLE) {
> +				nonidle = nsecs_to_jiffies(delta);
> +				nonidle_total += nonidle;
> +			} else {
> +				deltas[s] += (u64)delta * nonidle;
> +			}
> +		}
> +	}