Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 2ed513e7 authored by Patrick Bellasi's avatar Patrick Bellasi Committed by Dmitry Shmidt
Browse files

ANDROID: FIXUP: sched/tune: fix payoff calculation for boost region 



The definition of the acceptance regions as well as the translation of
these regions into a payoff value was both wrong which turned out in:
a) a wrong definition of payoff for the performance boost region
b) a correct "by chance" definition of the payoff for the performance
   constraint region (i.e. two sign errors together fixing the formula)

This patch provides a better description of the cut regions as well as
a fixed version of the payoff computations, which are now reduced to a
single formula usable for both cases.

Reported-by: default avatarLeo Yan <leo.yan@linaro.org>
Reviewed-by: default avatarLeo Yan <leo.yan@linaro.org>
Signed-off-by: default avatarLeo Yan <leo.yan@linaro.org>
Signed-off-by: default avatarPatrick Bellasi <patrick.bellasi@arm.com>
Signed-off-by: default avatarAndres Oportus <andresoportus@google.com>
parent e71c4255

kernel/sched/tune.c

+39 −38
Original line number Diff line number Diff line
@@ -51,50 +51,51 @@ __schedtune_accept_deltas(int nrg_delta, int cap_delta, 
			  int perf_boost_idx, int perf_constrain_idx)

{

	int payoff = -INT_MAX;

	int gain_idx = -1;



	/* Performance Boost (B) region */

	if (nrg_delta > 0 && cap_delta > 0) {

		/*

		 * Evaluate "Performance Boost" vs "Energy Increase"

		 * payoff criteria:

		 *    cap_delta / nrg_delta < cap_gain / nrg_gain

		 * which is:

		 *    nrg_delta * cap_gain > cap_delta * nrg_gain

		 */

		payoff  = nrg_delta * threshold_gains[perf_boost_idx].cap_gain;

		payoff -= cap_delta * threshold_gains[perf_boost_idx].nrg_gain;



		trace_sched_tune_filter(

				nrg_delta, cap_delta,

				threshold_gains[perf_boost_idx].nrg_gain,

				threshold_gains[perf_boost_idx].cap_gain,

				payoff, 8);

	if (nrg_delta >= 0 && cap_delta > 0)

		gain_idx = perf_boost_idx;

	/* Performance Constraint (C) region */

	else if (nrg_delta < 0 && cap_delta <= 0)

		gain_idx = perf_constrain_idx;



	/* Default: reject schedule candidate */

	if (gain_idx == -1)

		return payoff;

	}



	/* Performance Constraint (C) region */

	if (nrg_delta < 0 && cap_delta < 0) {

	/*

	 * Evaluate "Performance Boost" vs "Energy Increase"

	 *

	 * - Performance Boost (B) region

	 *

	 *   Condition: nrg_delta > 0 && cap_delta > 0

	 *   Payoff criteria:

	 *     cap_gain / nrg_gain  < cap_delta / nrg_delta =

	 *     cap_gain * nrg_delta < cap_delta * nrg_gain

	 *   Note that since both nrg_gain and nrg_delta are positive, the

	 *   inequality does not change. Thus:

	 *

	 *     payoff = (cap_delta * nrg_gain) - (cap_gain * nrg_delta)

	 *

	 * - Performance Constraint (C) region

	 *

	 *   Condition: nrg_delta < 0 && cap_delta < 0

	 *   payoff criteria:

		 *    cap_delta / nrg_delta > cap_gain / nrg_gain

		 * which is:

		 *    cap_delta * nrg_gain > nrg_delta * cap_gain

	 *     cap_gain / nrg_gain  > cap_delta / nrg_delta =

	 *     cap_gain * nrg_delta < cap_delta * nrg_gain

	 *   Note that since nrg_gain > 0 while nrg_delta < 0, the

	 *   inequality change. Thus:

	 *

	 *     payoff = (cap_delta * nrg_gain) - (cap_gain * nrg_delta)

	 *

	 * This means that, in case of same positive defined {cap,nrg}_gain

	 * for both the B and C regions, we can use the same payoff formula

	 * where a positive value represents the accept condition.

	 */

		payoff  = cap_delta * threshold_gains[perf_constrain_idx].nrg_gain;

		payoff -= nrg_delta * threshold_gains[perf_constrain_idx].cap_gain;

	payoff  = cap_delta * threshold_gains[gain_idx].nrg_gain;

	payoff -= nrg_delta * threshold_gains[gain_idx].cap_gain;



		trace_sched_tune_filter(

				nrg_delta, cap_delta,

				threshold_gains[perf_constrain_idx].nrg_gain,

				threshold_gains[perf_constrain_idx].cap_gain,

				payoff, 6);



		return payoff;

	}



	/* Default: reject schedule candidate */

	return payoff;

}