The following commit has been merged into the sched/core branch of tip:
Commit-ID: a9723389cc759c891d481de271ac73eeaa123bcb
Gitweb: https://git.kernel.org/tip/a9723389cc759c891d481de271ac73eeaa123bcb
Author: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
AuthorDate: Tue, 12 Nov 2019 15:50:43 +01:00
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitterDate: Mon, 18 Nov 2019 14:33:12 +01:00
sched/fair: Add comments for group_type and balancing at SD_NUMA level
Add comments to describe each state of goup_type and to add some details
about the load balance at NUMA level.
[ Valentin Schneider: Updates to the comments. ]
[ mingo: Other updates to the comments. ]
Reported-by: Mel Gorman <mgorman@xxxxxxx>
Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Acked-by: Valentin Schneider <valentin.schneider@xxxxxxx>
Cc: Ben Segall <bsegall@xxxxxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Mike Galbraith <efault@xxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/1573570243-1903-1-git-send-email-vincent.guittot@xxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
kernel/sched/fair.c | 35 +++++++++++++++++++++++++++++++----
1 file changed, 31 insertions(+), 4 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2fc08e7..1f93d96 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6980,17 +6980,40 @@ static unsigned long __read_mostly max_load_balance_interval = HZ/10;
enum fbq_type { regular, remote, all };
/*
- * group_type describes the group of CPUs at the moment of the load balance.
+ * 'group_type' describes the group of CPUs at the moment of load balancing.
+ *
* The enum is ordered by pulling priority, with the group with lowest priority
- * first so the groupe_type can be simply compared when selecting the busiest
- * group. see update_sd_pick_busiest().
+ * first so the group_type can simply be compared when selecting the busiest
+ * group. See update_sd_pick_busiest().
*/
enum group_type {
+ /* The group has spare capacity that can be used to run more tasks. */
group_has_spare = 0,
+ /*
+ * The group is fully used and the tasks don't compete for more CPU
+ * cycles. Nevertheless, some tasks might wait before running.
+ */
group_fully_busy,
+ /*
+ * SD_ASYM_CPUCAPACITY only: One task doesn't fit with CPU's capacity
+ * and must be migrated to a more powerful CPU.
+ */
group_misfit_task,
+ /*
+ * SD_ASYM_PACKING only: One local CPU with higher capacity is available,
+ * and the task should be migrated to it instead of running on the
+ * current CPU.
+ */
group_asym_packing,
+ /*
+ * The tasks' affinity constraints previously prevented the scheduler
+ * from balancing the load across the system.
+ */
group_imbalanced,
+ /*
+ * The CPU is overloaded and can't provide expected CPU cycles to all
+ * tasks.
+ */
group_overloaded
};
@@ -8589,7 +8612,11 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
/*
* Try to use spare capacity of local group without overloading it or
- * emptying busiest
+ * emptying busiest.
+ * XXX Spreading tasks across NUMA nodes is not always the best policy
+ * and special care should be taken for SD_NUMA domain level before
+ * spreading the tasks. For now, load_balance() fully relies on
+ * NUMA_BALANCING and fbq_classify_group/rq to override the decision.
*/
if (local->group_type == group_has_spare) {
if (busiest->group_type > group_fully_busy) {
|