return 0;
}
+/*
+ * Group imbalance indicates (and tries to solve) the problem where balancing
+ * groups is inadequate due to tsk_cpus_allowed() constraints.
+ *
+ * Imagine a situation of two groups of 4 cpus each and 4 tasks each with a
+ * cpumask covering 1 cpu of the first group and 3 cpus of the second group.
+ * Something like:
+ *
+ * { 0 1 2 3 } { 4 5 6 7 }
+ * * * * *
+ *
+ * If we were to balance group-wise we'd place two tasks in the first group and
+ * two tasks in the second group. Clearly this is undesired as it will overload
+ * cpu 3 and leave one of the cpus in the second group unused.
+ *
+ * The current solution to this issue is detecting the skew in the first group
+ * by noticing it has a cpu that is overloaded while the remaining cpus are
+ * idle -- or rather, there's a distinct imbalance in the cpus; see
+ * sg_imbalanced().
+ *
+ * When this is so detected; this group becomes a candidate for busiest; see
+ * update_sd_pick_busiest(). And calculcate_imbalance() and
+ * find_busiest_group() avoid some of the usual balance conditional to allow it
+ * to create an effective group imbalance.
+ *
+ * This is a somewhat tricky proposition since the next run might not find the
+ * group imbalance and decide the groups need to be balanced again. A most
+ * subtle and fragile situation.
+ */
+
+struct sg_imb_stats {
+ unsigned long max_nr_running, min_nr_running;
+ unsigned long max_cpu_load, min_cpu_load;
+};
+
+static inline void init_sg_imb_stats(struct sg_imb_stats *sgi)
+{
+ sgi->max_cpu_load = sgi->max_nr_running = 0UL;
+ sgi->min_cpu_load = sgi->min_nr_running = ~0UL;
+}
+
+static inline void
+update_sg_imb_stats(struct sg_imb_stats *sgi,
+ unsigned long load, unsigned long nr_running)
+{
+ if (load > sgi->max_cpu_load)
+ sgi->max_cpu_load = load;
+ if (sgi->min_cpu_load > load)
+ sgi->min_cpu_load = load;
+
+ if (nr_running > sgi->max_nr_running)
+ sgi->max_nr_running = nr_running;
+ if (sgi->min_nr_running > nr_running)
+ sgi->min_nr_running = nr_running;
+}
+
+static inline int
+sg_imbalanced(struct sg_lb_stats *sgs, struct sg_imb_stats *sgi)
+{
+ /*
+ * Consider the group unbalanced when the imbalance is larger
+ * than the average weight of a task.
+ *
+ * APZ: with cgroup the avg task weight can vary wildly and
+ * might not be a suitable number - should we keep a
+ * normalized nr_running number somewhere that negates
+ * the hierarchy?
+ */
+ if ((sgi->max_cpu_load - sgi->min_cpu_load) >= sgs->load_per_task &&
+ (sgi->max_nr_running - sgi->min_nr_running) > 1)
+ return 1;
+
+ return 0;
+}
+
/**
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
* @env: The load balancing environment.
struct sched_group *group, int load_idx,
int local_group, struct sg_lb_stats *sgs)
{
- unsigned long nr_running, max_nr_running, min_nr_running;
- unsigned long load, max_cpu_load, min_cpu_load;
+ struct sg_imb_stats sgi;
+ unsigned long nr_running;
+ unsigned long load;
int i;
- /* Tally up the load of all CPUs in the group */
- max_cpu_load = 0;
- min_cpu_load = ~0UL;
- max_nr_running = 0;
- min_nr_running = ~0UL;
+ init_sg_imb_stats(&sgi);
for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
struct rq *rq = cpu_rq(i);
load = target_load(i, load_idx);
} else {
load = source_load(i, load_idx);
-
- if (load > max_cpu_load)
- max_cpu_load = load;
- if (min_cpu_load > load)
- min_cpu_load = load;
-
- if (nr_running > max_nr_running)
- max_nr_running = nr_running;
- if (min_nr_running > nr_running)
- min_nr_running = nr_running;
+ update_sg_imb_stats(&sgi, load, nr_running);
}
sgs->group_load += load;
sgs->group_power = group->sgp->power;
sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / sgs->group_power;
- /*
- * Consider the group unbalanced when the imbalance is larger
- * than the average weight of a task.
- *
- * APZ: with cgroup the avg task weight can vary wildly and
- * might not be a suitable number - should we keep a
- * normalized nr_running number somewhere that negates
- * the hierarchy?
- */
if (sgs->sum_nr_running)
sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
- if ((max_cpu_load - min_cpu_load) >= sgs->load_per_task &&
- (max_nr_running - min_nr_running) > 1)
- sgs->group_imb = 1;
+ sgs->group_imb = sg_imbalanced(sgs, &sgi);
sgs->group_capacity =
DIV_ROUND_CLOSEST(sgs->group_power, SCHED_POWER_SCALE);
busiest = &sds->busiest_stat;
if (busiest->group_imb) {
+ /*
+ * In the group_imb case we cannot rely on group-wide averages
+ * to ensure cpu-load equilibrium, look at wider averages. XXX
+ */
busiest->load_per_task =
min(busiest->load_per_task, sds->avg_load);
}
if (!busiest->group_imb) {
/*
* Don't want to pull so many tasks that a group would go idle.
+ * Except of course for the group_imb case, since then we might
+ * have to drop below capacity to reach cpu-load equilibrium.
*/
load_above_capacity =
(busiest->sum_nr_running - busiest->group_capacity);
* we also don't want to reduce the group load below the group capacity
* (so that we can implement power-savings policies etc). Thus we look
* for the minimum possible imbalance.
- * Be careful of negative numbers as they'll appear as very large values
- * with unsigned longs.
*/
- max_pull = min(busiest->avg_load - sds->avg_load,
- load_above_capacity);
+ max_pull = min(busiest->avg_load - sds->avg_load, load_above_capacity);
/* How much load to actually move to equalise the imbalance */
env->imbalance = min(
/*
* If the busiest group is imbalanced the below checks don't
- * work because they assumes all things are equal, which typically
+ * work because they assume all things are equal, which typically
* isn't true due to cpus_allowed constraints and the like.
*/
if (busiest->group_imb)
projects / linux.git / commitdiff