linux-kernel - [PATCH 11/15] sched/eevdf: Better handle mixed slice length

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Wed, 31 May 2023 13:58:50 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     mingo@...nel.org, vincent.guittot@...aro.org
Cc:     linux-kernel@...r.kernel.org, peterz@...radead.org,
        juri.lelli@...hat.com, dietmar.eggemann@....com,
        rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de,
        bristot@...hat.com, corbet@....net, qyousef@...alina.io,
        chris.hyser@...cle.com, patrick.bellasi@...bug.net, pjt@...gle.com,
        pavel@....cz, qperret@...gle.com, tim.c.chen@...ux.intel.com,
        joshdon@...gle.com, timj@....org, kprateek.nayak@....com,
        yu.c.chen@...el.com, youssefesmat@...omium.org,
        joel@...lfernandes.org, efault@....de, tglx@...utronix.de
Subject: [PATCH 11/15] sched/eevdf: Better handle mixed slice length

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@...radead.org>
---
 kernel/sched/fair.c     |   30 ++++++++++++++++++++++++++++++
 kernel/sched/features.h |    1 +
 kernel/sched/sched.h    |    1 +
 3 files changed, 32 insertions(+)

--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -642,6 +642,7 @@ 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;
 }
 
@@ -652,6 +653,7 @@ 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;
 }
 
@@ -4908,6 +4910,21 @@ static inline void update_misfit_status(
 
 #endif /* CONFIG_SMP */
 
+static inline bool
+entity_has_slept(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+{
+	u64 now;
+
+	if (!(flags & ENQUEUE_WAKEUP))
+		return false;
+
+	if (flags & ENQUEUE_MIGRATED)
+		return true;
+
+	now = rq_clock_task(rq_of(cfs_rq));
+	return (s64)(se->exec_start - now) >= se->slice;
+}
+
 static void
 place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
@@ -4930,6 +4947,19 @@ 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) &&
+		    entity_has_slept(cfs_rq, se, flags)) {
+			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
@@ -555,6 +555,7 @@ struct cfs_rq {
 	unsigned int		idle_h_nr_running; /* SCHED_IDLE */
 
 	s64			avg_vruntime;
+	u64			avg_slice;
 	u64			avg_load;
 
 	u64			exec_clock;