It would be better to try to check other siblings first if
SD_PREFER_SIBLING is flaged when pushing tasks - migration.
Suggested-by: Peter Zijlstra <pet...@infradead.org>
Signed-off-by: Byungchul Park <byungchul.p...@lge.com>
Reviewed-by: Steven Rostedt (VMware) <rost...@goodmis.org>
---
kernel/sched/rt.c | 80 ++++++++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 77 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 979b734..a32e36d 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1618,12 +1618,35 @@ static struct task_struct
*pick_highest_pushable_task(struct rq *rq, int cpu)
static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
+/*
+ * Find the first cpu in: mask & sd & ~prefer
+ */
+static int find_cpu(const struct cpumask *mask,
+ const struct sched_domain *sd,
+ const struct sched_domain *prefer)
+{
+ const struct cpumask *sds = sched_domain_span(sd);
+ const struct cpumask *ps = prefer ? sched_domain_span(prefer) : NULL;
+ int cpu;
+
+ for_each_cpu(cpu, mask) {
+ if (!cpumask_test_cpu(cpu, sds))
+ continue;
+ if (ps && cpumask_test_cpu(cpu, ps))
+ continue;
+ break;
+ }
+
+ return cpu;
+}
+
static int find_lowest_rq(struct task_struct *task)
{
- struct sched_domain *sd;
+ struct sched_domain *sd, *prefer = NULL;
struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask);
int this_cpu = smp_processor_id();
int cpu = task_cpu(task);
+ int fallback_cpu = -1;
/* Make sure the mask is initialized first */
if (unlikely(!lowest_mask))
@@ -1668,9 +1691,37 @@ static int find_lowest_rq(struct task_struct *task)
return this_cpu;
}
- best_cpu = cpumask_first_and(lowest_mask,
- sched_domain_span(sd));
+ /*
+ * If a cpu exists that is in the lowest_mask and
+ * the current sd span, but not in the prefer sd
+ * span, then that becomes our choice.
+ *
+ * Of course, the lowest possible cpu is already
+ * under consideration through lowest_mask.
+ */
+ best_cpu = find_cpu(lowest_mask, sd, prefer);
+
if (best_cpu < nr_cpu_ids) {
+ /*
+ * If current domain is SD_PREFER_SIBLING
+ * flaged, we have to try to check other
+ * siblings first.
+ */
+ if (sd->flags & SD_PREFER_SIBLING) {
+ prefer = sd;
+
+ /*
+ * fallback_cpu should be one
+ * in the closest domain among
+ * SD_PREFER_SIBLING domains,
+ * in case that more than one
+ * SD_PREFER_SIBLING domains
+ * exist in the hierachy.
+ */
+ if (fallback_cpu == -1)
+ fallback_cpu = best_cpu;
+ continue;
+ }
rcu_read_unlock();
return best_cpu;
}
@@ -1679,6 +1730,29 @@ static int find_lowest_rq(struct task_struct *task)
rcu_read_unlock();
/*
+ * If fallback_cpu is valid, all our guesses failed *except* for
+ * SD_PREFER_SIBLING domain. Now, we can return the fallback cpu.
+ *
+ * XXX: Consider the following example, 4 cores SMT2 system:
+ *
+ * LLC [0 - 7]
+ * SMT [0 1][2 3][4 5][6 7]
+ * o x o x x x x x
+ *
+ * where 'o': occupied and 'x': empty.
+ *
+ * A wakeup on cpu0 will exclude cpu1 and choose cpu3, since
+ * cpu1 is in a SD_PREFER_SIBLING sd and cpu3 is not. However,
+ * in this case, cpu4 would have been a better choice, since
+ * cpu3 is a (SMT) thread of an already loaded core.
+ *
+ * Doing it 'right' is difficult and expensive. The current
+ * solution is an acceptable approximation.
+ */
+ if (fallback_cpu != -1)
+ return fallback_cpu;
+
+ /*
* And finally, if there were no matches within the domains
* just give the caller *something* to work with from the compatible
* locations.
--
1.9.1
