[PATCH 14/17] sched/eevdf: Better handle mixed slice length

[Peter Zijlstra <peterz@infradead.org>]

In the case where (due to latency-nice) there are different request
sizes in the tree, the smaller requests tend to be dominated by the
larger. Also note how the EEVDF lag limits are based on r_max.

Therefore; add a heuristic that for the mixed request size case, moves
smaller requests to placement strategy #2 which ensures they're
immidiately eligible and and due to their smaller (virtual) deadline
will cause preemption.

NOTE: this relies on update_entity_lag() to impose lag limits above
a single slice.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/sched/fair.c     |   14 ++++++++++++++
 kernel/sched/features.h |    1 +
 kernel/sched/sched.h    |    1 +
 3 files changed, 16 insertions(+)

--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -616,6 +616,7 @@ avg_vruntime_add(struct cfs_rq *cfs_rq,
 	s64 key = entity_key(cfs_rq, se);
 
 	cfs_rq->avg_vruntime += key * weight;
+	cfs_rq->avg_slice += se->slice * weight;
 	cfs_rq->avg_load += weight;
 }
 
@@ -626,6 +627,7 @@ avg_vruntime_sub(struct cfs_rq *cfs_rq,
 	s64 key = entity_key(cfs_rq, se);
 
 	cfs_rq->avg_vruntime -= key * weight;
+	cfs_rq->avg_slice -= se->slice * weight;
 	cfs_rq->avg_load -= weight;
 }
 
@@ -4832,6 +4834,18 @@ place_entity(struct cfs_rq *cfs_rq, stru
 		lag = se->vlag;
 
 		/*
+		 * For latency sensitive tasks; those that have a shorter than
+		 * average slice and do not fully consume the slice, transition
+		 * to EEVDF placement strategy #2.
+		 */
+		if (sched_feat(PLACE_FUDGE) &&
+		    cfs_rq->avg_slice > se->slice * cfs_rq->avg_load) {
+			lag += vslice;
+			if (lag > 0)
+				lag = 0;
+		}
+
+		/*
 		 * If we want to place a task and preserve lag, we have to
 		 * consider the effect of the new entity on the weighted
 		 * average and compensate for this, otherwise lag can quickly
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -5,6 +5,7 @@
  * sleep+wake cycles. EEVDF placement strategy #1, #2 if disabled.
  */
 SCHED_FEAT(PLACE_LAG, true)
+SCHED_FEAT(PLACE_FUDGE, true)
 SCHED_FEAT(PLACE_DEADLINE_INITIAL, true)
 
 /*
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -559,6 +559,7 @@ struct cfs_rq {
 	unsigned int		idle_h_nr_running; /* SCHED_IDLE */
 
 	s64			avg_vruntime;
+	u64			avg_slice;
 	u64			avg_load;
 
 	u64			exec_clock;