linux-kernel - [RFC PATCH 14/08] [DEBUG] sched/fair: Add more lb_stats around lb

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]

Message-ID: <20250316102916.10614-6-kprateek.nayak@amd.com>
Date: Sun, 16 Mar 2025 10:29:15 +0000
From: K Prateek Nayak <kprateek.nayak@....com>
To: Ingo Molnar <mingo@...hat.com>, Peter Zijlstra <peterz@...radead.org>,
	Juri Lelli <juri.lelli@...hat.com>, Vincent Guittot
	<vincent.guittot@...aro.org>, Chen Yu <yu.c.chen@...el.com>,
	<linux-kernel@...r.kernel.org>
CC: Dietmar Eggemann <dietmar.eggemann@....com>, Steven Rostedt
	<rostedt@...dmis.org>, Ben Segall <bsegall@...gle.com>, Mel Gorman
	<mgorman@...e.de>, Valentin Schneider <vschneid@...hat.com>, David Vernet
	<void@...ifault.com>, "Gautham R. Shenoy" <gautham.shenoy@....com>, "Swapnil
 Sapkal" <swapnil.sapkal@....com>, Shrikanth Hegde <sshegde@...ux.ibm.com>, "K
 Prateek Nayak" <kprateek.nayak@....com>
Subject: [RFC PATCH 14/08] [DEBUG] sched/fair: Add more lb_stats around lb_time and stats reuse

Add stats for load balancing time and stats reuse efficiency.

Signed-off-by: K Prateek Nayak <kprateek.nayak@....com>
---
 include/linux/sched/topology.h |  5 +++++
 kernel/sched/fair.c            | 21 ++++++++++++++++++++-
 kernel/sched/stats.c           |  9 +++++++--
 3 files changed, 32 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index a16d7d9dd9d3..dea65eb263c6 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -123,6 +123,11 @@ struct sched_domain {
 	unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_min_time[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_max_time[CPU_MAX_IDLE_TYPES];
+	unsigned long lb_total_time[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_stats_reused[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_stats_recomputed[CPU_MAX_IDLE_TYPES];
 
 	/* Active load balancing */
 	unsigned int alb_count;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 31501b933d45..bb7b21421415 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10491,10 +10491,13 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 	 * group_smt_balance is not possible under busy load balancing.
 	 */
 	if (can_retrieve_stats(env->sd, env->idle) &&
-	    retrieve_cached_stats(group, sgs))
+	    retrieve_cached_stats(group, sgs)) {
+		schedstat_inc(env->sd->lb_stats_reused[env->idle]);
 		goto group_classify;
+	}
 
 	memset(sgs, 0, sizeof(*sgs));
+	schedstat_inc(env->sd->lb_stats_recomputed[env->idle]);
 
 	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
 		struct rq *rq = cpu_rq(i);
@@ -11901,6 +11904,7 @@ static int sched_balance_rq(int this_cpu, struct rq *this_rq,
 {
 	int ld_moved, cur_ld_moved, active_balance = 0;
 	struct sched_domain *sd_parent = sd->parent;
+	u64 lb_start = sched_clock_cpu(this_cpu);
 	struct sched_group *group;
 	struct rq *busiest;
 	struct rq_flags rf;
@@ -12174,6 +12178,21 @@ static int sched_balance_rq(int this_cpu, struct rq *this_rq,
 	    sd->balance_interval < sd->max_interval)
 		sd->balance_interval *= 2;
 out:
+	if (schedstat_enabled()) {
+		u64 now = sched_clock_cpu(this_cpu);
+		u64 elapsed = now - lb_start;
+
+		if (!schedstat_val(sd->lb_min_time[idle]) ||
+		    elapsed < schedstat_val(sd->lb_min_time[idle]))
+			__schedstat_set(sd->lb_min_time[idle], elapsed);
+
+		if (!schedstat_val(sd->lb_max_time[idle]) ||
+		    elapsed > schedstat_val(sd->lb_max_time[idle]))
+			__schedstat_set(sd->lb_max_time[idle], elapsed);
+
+		__schedstat_add(sd->lb_total_time[idle], elapsed);
+	}
+
 	return ld_moved;
 }
 
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index 4346fd81c31f..b2ace3c51062 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -141,7 +141,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
 			seq_printf(seq, "domain%d %s %*pb", dcount++, sd->name,
 				   cpumask_pr_args(sched_domain_span(sd)));
 			for (itype = 0; itype < CPU_MAX_IDLE_TYPES; itype++) {
-				seq_printf(seq, " %u %u %u %u %u %u %u %u %u %u %u",
+				seq_printf(seq, " %u %u %u %u %u %u %u %u %u %u %u %u %u %lu %u %u",
 				    sd->lb_count[itype],
 				    sd->lb_balanced[itype],
 				    sd->lb_failed[itype],
@@ -152,7 +152,12 @@ static int show_schedstat(struct seq_file *seq, void *v)
 				    sd->lb_gained[itype],
 				    sd->lb_hot_gained[itype],
 				    sd->lb_nobusyq[itype],
-				    sd->lb_nobusyg[itype]);
+				    sd->lb_nobusyg[itype],
+				    sd->lb_min_time[itype],
+				    sd->lb_max_time[itype],
+				    sd->lb_total_time[itype],
+				    sd->lb_stats_reused[itype],
+				    sd->lb_stats_recomputed[itype]);
 			}
 			seq_printf(seq,
 				   " %u %u %u %u %u %u %u %u %u %u %u %u\n",
-- 
2.43.0