Re: change in sched cpu_power causing regressions with SCHED_MC

[Suresh Siddha]

On Fri, 2010-02-19 at 12:02 -0800, Peter Zijlstra wrote:
> On Fri, 2010-02-19 at 11:50 -0800, Suresh Siddha wrote:
> > On Fri, 2010-02-19 at 11:47 -0800, Peter Zijlstra wrote:
> > > On Fri, 2010-02-19 at 10:36 -0800, Suresh Siddha wrote:
> > > > exec/fork balance is not broken. i.e., during exec/fork we balance the
> > > > load equally among sockets/cores etc. What is broken is:
> > > > 
> > > > a) In SMT case, once we end up in a situation where both the threads of
> > > > the core are busy , with another core completely idle, load balance is
> > > > not moving one of the threads to the idle core. This unbalanced
> > > > situation can happen because of a previous wake-up decision and/or
> > > > threads on other core went to sleep/died etc. Once we end up in this
> > > > unbalanced situation, we continue in that state with out fixing it.
> > > > 
> > > > b) Similar to "a", this is MC case where we end up four cores busy in
> > > > one socket with other 4 cores in another socket completely idle. And
> > > > this is the situation which we are trying to solve in this patch.
> > > > 
> > > > In your above example, we test mostly fork/exec balance but not the
> > > > above sleep/wakeup scenarios. 
> > > 
> > > Ah, indeed. Let me extend my script to cover that.
> > > 
> > > The below script does indeed show a change, but the result still isn't
> > > perfect, when I do ./show-loop 8, it starts 8 loops nicely spread over 2
> > > sockets, the difference is that all 4 remaining would stay on socket 0,
> > > the patched kernel gets 1 over to socket 1.
> > 
> > Peter, Have you applied both my smt patch and mc patch?
> 
> Yes, find_busiest_queue() has the wl fixup in (as per tip/master).

Ok Peter. There is another place that is scaling load_per_task with
cpu_power but later comparing with the difference of max and min of the
actual cpu load. :(

        avg_load_per_task = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
                group->cpu_power;

        if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
                sgs->group_imb = 1;

Fixing this seems to have fixed the problem you mentioned. Can you
please checkout the appended patch? If everything seems ok, then I will
send the patch (against -tip tree) on monday morning with the detailed
changelog.

Signed-off-by: Suresh Siddha <suresh.b.siddha@xxxxxxxxx>
---

diff --git a/kernel/sched.c b/kernel/sched.c
index 3a8fb30..213b445 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3423,6 +3423,7 @@ struct sd_lb_stats {
 	unsigned long max_load;
 	unsigned long busiest_load_per_task;
 	unsigned long busiest_nr_running;
+	unsigned long busiest_group_capacity;
 
 	int group_imb; /* Is there imbalance in this sd */
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
@@ -3742,8 +3743,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	unsigned long load, max_cpu_load, min_cpu_load;
 	int i;
 	unsigned int balance_cpu = -1, first_idle_cpu = 0;
-	unsigned long sum_avg_load_per_task;
-	unsigned long avg_load_per_task;
+	unsigned long avg_load_per_task = 0;
 
 	if (local_group) {
 		balance_cpu = group_first_cpu(group);
@@ -3752,7 +3752,6 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	}
 
 	/* Tally up the load of all CPUs in the group */
-	sum_avg_load_per_task = avg_load_per_task = 0;
 	max_cpu_load = 0;
 	min_cpu_load = ~0UL;
 
@@ -3782,7 +3781,6 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 		sgs->sum_nr_running += rq->nr_running;
 		sgs->sum_weighted_load += weighted_cpuload(i);
 
-		sum_avg_load_per_task += cpu_avg_load_per_task(i);
 	}
 
 	/*
@@ -3801,6 +3799,9 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
 
 
+	if (sgs->sum_nr_running)
+		avg_load_per_task =
+				sgs->sum_weighted_load / sgs->sum_nr_running;
 	/*
 	 * Consider the group unbalanced when the imbalance is larger
 	 * than the average weight of two tasks.
@@ -3810,9 +3811,6 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	 *      normalized nr_running number somewhere that negates
 	 *      the hierarchy?
 	 */
-	avg_load_per_task = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
-		group->cpu_power;
-
 	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
 		sgs->group_imb = 1;
 
@@ -3880,6 +3878,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 			sds->max_load = sgs.avg_load;
 			sds->busiest = group;
 			sds->busiest_nr_running = sgs.sum_nr_running;
+			sds->busiest_group_capacity = sgs.group_capacity;
 			sds->busiest_load_per_task = sgs.sum_weighted_load;
 			sds->group_imb = sgs.group_imb;
 		}
@@ -3902,6 +3901,7 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 {
 	unsigned long tmp, pwr_now = 0, pwr_move = 0;
 	unsigned int imbn = 2;
+	unsigned long scaled_busy_load_per_task;
 
 	if (sds->this_nr_running) {
 		sds->this_load_per_task /= sds->this_nr_running;
@@ -3912,8 +3912,12 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 		sds->this_load_per_task =
 			cpu_avg_load_per_task(this_cpu);
 
-	if (sds->max_load - sds->this_load + sds->busiest_load_per_task >=
-			sds->busiest_load_per_task * imbn) {
+	scaled_busy_load_per_task = sds->busiest_load_per_task
+						 * SCHED_LOAD_SCALE;
+	scaled_busy_load_per_task /= sds->busiest->cpu_power;
+
+	if (sds->max_load - sds->this_load + scaled_busy_load_per_task >=
+			(scaled_busy_load_per_task * imbn)) {
 		*imbalance = sds->busiest_load_per_task;
 		return;
 	}
@@ -3964,7 +3968,7 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
 		unsigned long *imbalance)
 {
-	unsigned long max_pull;
+	unsigned long max_pull, load_above_capacity = ~0UL;
 	/*
 	 * In the presence of smp nice balancing, certain scenarios can have
 	 * max load less than avg load(as we skip the groups at or below
@@ -3975,9 +3979,30 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
 		return fix_small_imbalance(sds, this_cpu, imbalance);
 	}
 
-	/* Don't want to pull so many tasks that a group would go idle */
-	max_pull = min(sds->max_load - sds->avg_load,
-			sds->max_load - sds->busiest_load_per_task);
+	if (!sds->group_imb) {
+		/*
+ 	 	 * Don't want to pull so many tasks that a group would go idle.
+	 	 */
+		load_above_capacity = (sds->busiest_nr_running - 
+						sds->busiest_group_capacity);
+
+		load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_LOAD_SCALE);
+	
+		load_above_capacity /= sds->busiest->cpu_power;
+	}
+
+	/*
+	 * We're trying to get all the cpus to the average_load, so we don't
+	 * want to push ourselves above the average load, nor do we wish to
+	 * reduce the max loaded cpu below the average load, as either of these
+	 * actions would just result in more rebalancing later, and ping-pong
+	 * tasks around. Thus we look for the minimum possible imbalance.
+	 * Negative imbalances (*we* are more loaded than anyone else) will
+	 * be counted as no imbalance for these purposes -- we can't fix that
+	 * by pulling tasks to us. Be careful of negative numbers as they'll
+	 * appear as very large values with unsigned longs.
+	 */
+	max_pull = min(sds->max_load - sds->avg_load, load_above_capacity);
 
 	/* How much load to actually move to equalise the imbalance */
 	*imbalance = min(max_pull * sds->busiest->cpu_power,
@@ -4069,19 +4094,6 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 		sds.busiest_load_per_task =
 			min(sds.busiest_load_per_task, sds.avg_load);
 
-	/*
-	 * We're trying to get all the cpus to the average_load, so we don't
-	 * want to push ourselves above the average load, nor do we wish to
-	 * reduce the max loaded cpu below the average load, as either of these
-	 * actions would just result in more rebalancing later, and ping-pong
-	 * tasks around. Thus we look for the minimum possible imbalance.
-	 * Negative imbalances (*we* are more loaded than anyone else) will
-	 * be counted as no imbalance for these purposes -- we can't fix that
-	 * by pulling tasks to us. Be careful of negative numbers as they'll
-	 * appear as very large values with unsigned longs.
-	 */
-	if (sds.max_load <= sds.busiest_load_per_task)
-		goto out_balanced;
 
 	/* Looks like there is an imbalance. Compute it */
 	calculate_imbalance(&sds, this_cpu, imbalance);

 


--
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/