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:
> +	/* total= */
> +	for (s = 0; s < NR_PSI_STATES - 1; s++)
> +		group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL));

Just a nit; probably not worth fixing.

This looses the remainder of that division. But since the divisor is
variable it becomes really hard to not loose something at some point.