summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2012-05-23 18:00:43 +0200
committerIngo Molnar <mingo@kernel.org>2012-05-30 14:02:24 +0200
commit74a5ce20e6eeeb3751340b390e7ac1d1d07bbf55 (patch)
treeebbef56666aa11303eafbfb6adbfce56e7a4c605
parent2ea45800d8e1c3c51c45a233d6bd6289a297a386 (diff)
downloadop-kernel-dev-74a5ce20e6eeeb3751340b390e7ac1d1d07bbf55.zip
op-kernel-dev-74a5ce20e6eeeb3751340b390e7ac1d1d07bbf55.tar.gz
sched: Fix SD_OVERLAP
SD_OVERLAP exists to allow overlapping groups, overlapping groups appear in NUMA topologies that aren't fully connected. The typical result of not fully connected NUMA is that each cpu (or rather node) will have different spans for a particular distance. However due to how sched domains are traversed -- only the first cpu in the mask goes one level up -- the next level only cares about the spans of the cpus that went up. Due to this two things were observed to be broken: - build_overlap_sched_groups() -- since its possible the cpu we're building the groups for exists in multiple (or all) groups, the selection criteria of the first group didn't ensure there was a cpu for which is was true that cpumask_first(span) == cpu. Thus load- balancing would terminate. - update_group_power() -- assumed that the cpu span of the first group of the domain was covered by all groups of the child domain. The above explains why this isn't true, so deal with it. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: David Rientjes <rientjes@google.com> Link: http://lkml.kernel.org/r/1337788843.9783.14.camel@laptop Signed-off-by: Ingo Molnar <mingo@kernel.org>
-rw-r--r--kernel/sched/core.c7
-rw-r--r--kernel/sched/fair.c25
2 files changed, 25 insertions, 7 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5573361..3a69374 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6030,11 +6030,14 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
cpumask_or(covered, covered, sg_span);
- sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span));
+ sg->sgp = *per_cpu_ptr(sdd->sgp, i);
atomic_inc(&sg->sgp->ref);
- if (cpumask_test_cpu(cpu, sg_span))
+ if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
+ cpumask_first(sg_span) == cpu) {
+ WARN_ON_ONCE(!cpumask_test_cpu(cpu, sg_span));
groups = sg;
+ }
if (!first)
first = sg;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 940e6d1..f0380d4 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3574,11 +3574,26 @@ void update_group_power(struct sched_domain *sd, int cpu)
power = 0;
- group = child->groups;
- do {
- power += group->sgp->power;
- group = group->next;
- } while (group != child->groups);
+ if (child->flags & SD_OVERLAP) {
+ /*
+ * SD_OVERLAP domains cannot assume that child groups
+ * span the current group.
+ */
+
+ for_each_cpu(cpu, sched_group_cpus(sdg))
+ power += power_of(cpu);
+ } else {
+ /*
+ * !SD_OVERLAP domains can assume that child groups
+ * span the current group.
+ */
+
+ group = child->groups;
+ do {
+ power += group->sgp->power;
+ group = group->next;
+ } while (group != child->groups);
+ }
sdg->sgp->power = power;
}
OpenPOWER on IntegriCloud