linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Tim Chen <tim.c.chen@linux.intel.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	K Prateek Nayak <kprateek.nayak@amd.com>,
	"Gautham R . Shenoy" <gautham.shenoy@amd.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>,
	Juri Lelli <juri.lelli@redhat.com>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
	Valentin Schneider <vschneid@redhat.com>,
	Tim Chen <tim.c.chen@intel.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Libo Chen <libo.chen@oracle.com>,
	Abel Wu <wuyun.abel@bytedance.com>,
	Madadi Vineeth Reddy <vineethr@linux.ibm.com>,
	Hillf Danton <hdanton@sina.com>, Len Brown <len.brown@intel.com>,
	linux-kernel@vger.kernel.org, Chen Yu <yu.c.chen@intel.com>
Subject: [RFC patch v3 16/20] sched: Consider LLC locality for active balance
Date: Wed, 18 Jun 2025 11:28:04 -0700	[thread overview]
Message-ID: <1ce821178bf178ce841ea94bb8139fd9a197b86b.1750268218.git.tim.c.chen@linux.intel.com> (raw)
In-Reply-To: <cover.1750268218.git.tim.c.chen@linux.intel.com>

If busiest run queue has only one task, active balance is enlisted
to actually move the task.  However, before moving the task,
we should consider whether we are moving the task from its preferred
LLC.

Don't move the single running task in a run queue to another LLC, if
we are moving it from its desired LLC, or moving it will cause too much
imbalance between the LLCs.

Co-developed-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
---
 kernel/sched/fair.c | 51 ++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 48 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 42222364ad9c..3a8f6fc52055 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -12294,10 +12294,43 @@ imbalanced_active_balance(struct lb_env *env)
 	return 0;
 }
 
+#ifdef CONFIG_SCHED_CACHE
+static inline bool
+break_llc_locality(struct lb_env *env)
+{
+	if (!sched_feat(SCHED_CACHE))
+		return 0;
+
+	if (cpus_share_cache(env->src_cpu, env->dst_cpu))
+		return 0;
+	/*
+	 * All tasks want to stay put. Move only if LLC is
+	 * heavily loaded or don't pull a task from its
+	 * preferred CPU if it is the only one running.
+	 */
+	if (env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable &&
+	    (env->src_rq->nr_running <= 1 ||
+	    _get_migrate_hint(env->src_cpu, env->dst_cpu,
+			      0, false) == mig_forbid))
+		return 1;
+
+	return 0;
+}
+#else
+static inline bool
+break_llc_locality(struct lb_env *env)
+{
+	return 0;
+}
+#endif
+
 static int need_active_balance(struct lb_env *env)
 {
 	struct sched_domain *sd = env->sd;
 
+	if (break_llc_locality(env))
+		return 0;
+
 	if (asym_active_balance(env))
 		return 1;
 
@@ -12317,7 +12350,8 @@ static int need_active_balance(struct lb_env *env)
 			return 1;
 	}
 
-	if (env->migration_type == migrate_misfit)
+	if (env->migration_type == migrate_misfit ||
+	    env->migration_type == migrate_llc_task)
 		return 1;
 
 	return 0;
@@ -12762,9 +12796,20 @@ static int active_load_balance_cpu_stop(void *data)
 		goto out_unlock;
 
 	/* Is there any task to move? */
-	if (busiest_rq->nr_running <= 1)
-		goto out_unlock;
+	if (busiest_rq->nr_running <= 1) {
+#ifdef CONFIG_SCHED_CACHE
+		int llc = llc_idx(target_cpu);
 
+		if (!sched_feat(SCHED_CACHE))
+			goto out_unlock;
+
+		if (llc < 0)
+			goto out_unlock;
+		/* don't migrate if task does not prefer target */
+		if (busiest_rq->nr_pref_llc[llc] < 1)
+#endif
+			goto out_unlock;
+	}
 	/*
 	 * This condition is "impossible", if it occurs
 	 * we need to fix it. Originally reported by
-- 
2.32.0


  parent reply	other threads:[~2025-06-18 18:22 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-18 18:27 [RFC patch v3 00/20] Cache aware scheduling Tim Chen
2025-06-18 18:27 ` [RFC patch v3 01/20] sched: Cache aware load-balancing Tim Chen
2025-06-26 12:23   ` Jianyong Wu
2025-06-26 13:32     ` Chen, Yu C
2025-06-27  0:10       ` Tim Chen
2025-06-27  2:13         ` Jianyong Wu
2025-07-03 19:29   ` Shrikanth Hegde
2025-07-04  8:40     ` Chen, Yu C
2025-07-04  8:45       ` Peter Zijlstra
2025-07-04  8:54         ` Shrikanth Hegde
2025-07-07 19:57     ` Tim Chen
2025-06-18 18:27 ` [RFC patch v3 02/20] sched: Several fixes for cache aware scheduling Tim Chen
2025-07-03 19:33   ` Shrikanth Hegde
2025-07-07 21:02     ` Tim Chen
2025-07-08  1:15   ` Libo Chen
2025-07-08  7:54     ` Chen, Yu C
2025-07-08 15:47       ` Libo Chen
2025-06-18 18:27 ` [RFC patch v3 03/20] sched: Avoid task migration within its preferred LLC Tim Chen
2025-06-18 18:27 ` [RFC patch v3 04/20] sched: Avoid calculating the cpumask if the system is overloaded Tim Chen
2025-07-03 19:39   ` Shrikanth Hegde
2025-07-07 14:57     ` Tim Chen
2025-06-18 18:27 ` [RFC patch v3 05/20] sched: Add hysteresis to switch a task's preferred LLC Tim Chen
2025-07-02  6:47   ` Madadi Vineeth Reddy
2025-07-02 21:47     ` Tim Chen
2025-06-18 18:27 ` [RFC patch v3 06/20] sched: Save the per LLC utilization for better cache aware scheduling Tim Chen
2025-06-18 18:27 ` [RFC patch v3 07/20] sched: Add helper function to decide whether to allow " Tim Chen
2025-07-08  0:41   ` Libo Chen
2025-07-08  8:29     ` Chen, Yu C
2025-07-08 17:22       ` Libo Chen
2025-07-09 14:41         ` Chen, Yu C
2025-07-09 21:31           ` Libo Chen
2025-07-08 21:59     ` Tim Chen
2025-07-09 21:22       ` Libo Chen
2025-06-18 18:27 ` [RFC patch v3 08/20] sched: Set up LLC indexing Tim Chen
2025-07-03 19:44   ` Shrikanth Hegde
2025-07-04  9:36     ` Chen, Yu C
2025-06-18 18:27 ` [RFC patch v3 09/20] sched: Introduce task preferred LLC field Tim Chen
2025-06-18 18:27 ` [RFC patch v3 10/20] sched: Calculate the number of tasks that have LLC preference on a runqueue Tim Chen
2025-07-03 19:45   ` Shrikanth Hegde
2025-07-04 15:00     ` Chen, Yu C
2025-06-18 18:27 ` [RFC patch v3 11/20] sched: Introduce per runqueue task LLC preference counter Tim Chen
2025-06-18 18:28 ` [RFC patch v3 12/20] sched: Calculate the total number of preferred LLC tasks during load balance Tim Chen
2025-06-18 18:28 ` [RFC patch v3 13/20] sched: Tag the sched group as llc_balance if it has tasks prefer other LLC Tim Chen
2025-06-18 18:28 ` [RFC patch v3 14/20] sched: Introduce update_llc_busiest() to deal with groups having preferred LLC tasks Tim Chen
2025-07-03 19:52   ` Shrikanth Hegde
2025-07-05  2:26     ` Chen, Yu C
2025-06-18 18:28 ` [RFC patch v3 15/20] sched: Introduce a new migration_type to track the preferred LLC load balance Tim Chen
2025-06-18 18:28 ` Tim Chen [this message]
2025-06-18 18:28 ` [RFC patch v3 17/20] sched: Consider LLC preference when picking tasks from busiest queue Tim Chen
2025-06-18 18:28 ` [RFC patch v3 18/20] sched: Do not migrate task if it is moving out of its preferred LLC Tim Chen
2025-06-18 18:28 ` [RFC patch v3 19/20] sched: Introduce SCHED_CACHE_LB to control cache aware load balance Tim Chen
2025-06-18 18:28 ` [RFC patch v3 20/20] sched: Introduce SCHED_CACHE_WAKE to control LLC aggregation on wake up Tim Chen
2025-06-19  6:39 ` [RFC patch v3 00/20] Cache aware scheduling Yangyu Chen
2025-06-19 13:21   ` Chen, Yu C
2025-06-19 14:12     ` Yangyu Chen
2025-06-20 19:25 ` Madadi Vineeth Reddy
2025-06-22  0:39   ` Chen, Yu C
2025-06-24 17:47     ` Madadi Vineeth Reddy
2025-06-23 16:45   ` Tim Chen
2025-06-24  5:00 ` K Prateek Nayak
2025-06-24 12:16   ` Chen, Yu C
2025-06-25  4:19     ` K Prateek Nayak
2025-06-25  0:30   ` Tim Chen
2025-06-25  4:30     ` K Prateek Nayak
2025-07-03 20:00   ` Shrikanth Hegde
2025-07-04 10:09     ` Chen, Yu C
2025-07-09 19:39 ` Madadi Vineeth Reddy
2025-07-10  3:33   ` Chen, Yu C

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1ce821178bf178ce841ea94bb8139fd9a197b86b.1750268218.git.tim.c.chen@linux.intel.com \
    --to=tim.c.chen@linux.intel.com \
    --cc=bsegall@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=gautham.shenoy@amd.com \
    --cc=hdanton@sina.com \
    --cc=juri.lelli@redhat.com \
    --cc=kprateek.nayak@amd.com \
    --cc=len.brown@intel.com \
    --cc=libo.chen@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=tim.c.chen@intel.com \
    --cc=vincent.guittot@linaro.org \
    --cc=vineethr@linux.ibm.com \
    --cc=vschneid@redhat.com \
    --cc=wuyun.abel@bytedance.com \
    --cc=yu.c.chen@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).