[RFC PATCH v2 4/5] sched: small imbalance corrections

[Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>]

Add functions to bump up the imbalance to eventually initiate
a task move to balance across groups.

Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
---

 kernel/sched.c |   74 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 74 insertions(+), 0 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index c99b5bd..cf1aae1 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3229,6 +3229,80 @@ void update_sd_loads(struct sd_loads *sdl, struct group_loads *gl)
 	}
 }
 
+/* Bump up imbalance to one task so that some task movement can happen */
+
+int small_imbalance_one_task(struct sd_loads *sdl, unsigned long *imbalance)
+{
+	unsigned int imbn;
+	imbn = 2;
+	if (sdl->local.nr_running) {
+		if (sdl->busiest.avg_load_per_task >
+			sdl->local.avg_load_per_task)
+			imbn = 1;
+	}
+
+	if (sdl->busiest.load_per_cpu - sdl->local.load_per_cpu +
+		2*sdl->busiest.avg_load_per_task >=
+				sdl->busiest.avg_load_per_task * imbn) {
+		*imbalance = sdl->busiest.avg_load_per_task;
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * Adjust imbalance to move task if the result of the move will
+ * yield better use of cpu power
+ */
+
+void small_imbalance_optimize_cpu_power(struct sd_loads *sdl,
+					unsigned long *imbalance)
+{
+	unsigned long tmp, pwr_now, pwr_move;
+	pwr_move = pwr_now = 0;
+
+	/*
+	 * OK, we don't have enough imbalance to justify moving tasks,
+	 * however we may be able to increase total CPU power used by
+	 * moving them.
+	 */
+
+	pwr_now += sdl->busiest.group->__cpu_power *
+			min(sdl->busiest.avg_load_per_task,
+			sdl->busiest.load_per_cpu);
+	pwr_now += sdl->local.group->__cpu_power *
+			min(sdl->local.avg_load_per_task,
+			sdl->local.load_per_cpu);
+	pwr_now /= SCHED_LOAD_SCALE;
+
+	/* Amount of load we'd subtract */
+	tmp = sg_div_cpu_power(sdl->busiest.group,
+			sdl->busiest.avg_load_per_task * SCHED_LOAD_SCALE);
+	if (sdl->busiest.load_per_cpu > tmp)
+		pwr_move += sdl->busiest.group->__cpu_power *
+			min(sdl->busiest.avg_load_per_task,
+			    sdl->busiest.load_per_cpu - tmp);
+
+	/* Amount of load we'd add */
+	if (sdl->busiest.load_per_cpu * sdl->busiest.group->__cpu_power <
+			sdl->busiest.avg_load_per_task * SCHED_LOAD_SCALE)
+		tmp = sg_div_cpu_power(sdl->local.group,
+				sdl->busiest.load_per_cpu *
+				sdl->busiest.group->__cpu_power);
+	else
+		tmp = sg_div_cpu_power(sdl->local.group,
+			sdl->busiest.avg_load_per_task * SCHED_LOAD_SCALE);
+	pwr_move += sdl->local.group->__cpu_power *
+			min(sdl->local.avg_load_per_task,
+			sdl->local.load + tmp);
+	pwr_move /= SCHED_LOAD_SCALE;
+
+	/* Move if we gain throughput */
+	if (pwr_move > pwr_now)
+		*imbalance = sdl->busiest.avg_load_per_task;
+
+}
+
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
 void update_powersavings_group_loads(struct sd_loads *sdl,
 				     struct group_loads *gl,