mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Chen Yu <yu.c.chen@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: Vincent Guittot <vincent.guittot@linaro.org>,
	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>,
	Libo Chen <libo.chen@oracle.com>,
	Madadi Vineeth Reddy <vineethr@linux.ibm.com>,
	Hillf Danton <hdanton@sina.com>,
	Shrikanth Hegde <sshegde@linux.ibm.com>,
	Jianyong Wu <jianyong.wu@outlook.com>,
	Yangyu Chen <cyy@cyyself.name>,
	Tingyin Duan <tingyin.duan@gmail.com>,
	Vern Hao <vernhao@tencent.com>, Len Brown <len.brown@intel.com>,
	Tim Chen <tim.c.chen@linux.intel.com>,
	Aubrey Li <aubrey.li@intel.com>, Zhao Liu <zhao1.liu@intel.com>,
	Chen Yu <yu.chen.surf@gmail.com>, Chen Yu <yu.c.chen@intel.com>,
	linux-kernel@vger.kernel.org
Subject: [RFC PATCH v4 10/28] sched: Calculate the number of tasks that have LLC preference on a runqueue
Date: Sat,  9 Aug 2025 13:04:04 +0800	[thread overview]
Message-ID: <bd767d696636f233f30f334d41f46ce45c256948.1754712565.git.tim.c.chen@linux.intel.com> (raw)
In-Reply-To: <cover.1754712565.git.tim.c.chen@linux.intel.com>

From: Tim Chen <tim.c.chen@linux.intel.com>

Track for each run queue, the number of tasks that have a LLC preference
and how many of those tasks are running in its preferred LLC.  This is
similar to nr_numa_running and nr_preferred_running for NUMA balance,
and will be used by the cache-aware load balancing in subsequent patches.

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
---
 kernel/sched/core.c  | 12 +++++++++++
 kernel/sched/fair.c  | 51 +++++++++++++++++++++++++++++++++++++++++++-
 kernel/sched/sched.h |  7 ++++++
 3 files changed, 69 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a5fb3057b1c4..a97a8039ce91 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -499,6 +499,18 @@ void __trace_set_current_state(int state_value)
 }
 EXPORT_SYMBOL(__trace_set_current_state);
 
+#ifdef CONFIG_SMP
+int task_llc(const struct task_struct *p)
+{
+	return per_cpu(sd_llc_id, task_cpu(p));
+}
+#else
+int task_llc(const struct task_struct *p)
+{
+	return 0;
+}
+#endif
+
 /*
  * Serialization rules:
  *
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 94ad84ba19e1..f964d5a44fcc 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1195,6 +1195,24 @@ static inline int llc_idx(int cpu)
 	return per_cpu(sd_llc_idx, cpu);
 }
 
+static void account_llc_enqueue(struct rq *rq, struct task_struct *p)
+{
+	if (!sched_feat(SCHED_CACHE))
+		return;
+
+	rq->nr_llc_running += (p->preferred_llc != -1);
+	rq->nr_pref_llc_running += (p->preferred_llc == task_llc(p));
+}
+
+static void account_llc_dequeue(struct rq *rq, struct task_struct *p)
+{
+	if (!sched_feat(SCHED_CACHE))
+		return;
+
+	rq->nr_llc_running -= (p->preferred_llc != -1);
+	rq->nr_pref_llc_running -= (p->preferred_llc == task_llc(p));
+}
+
 void mm_init_sched(struct mm_struct *mm, struct mm_sched __percpu *_pcpu_sched)
 {
 	unsigned long epoch;
@@ -1303,8 +1321,11 @@ void account_mm_sched(struct rq *rq, struct task_struct *p, s64 delta_exec)
 	if (mm->mm_sched_cpu != -1)
 		mm_sched_llc = per_cpu(sd_llc_id, mm->mm_sched_cpu);
 
-	if (p->preferred_llc != mm_sched_llc)
+	if (p->preferred_llc != mm_sched_llc) {
+		account_llc_dequeue(rq, p);
 		p->preferred_llc = mm_sched_llc;
+		account_llc_enqueue(rq, p);
+	}
 }
 
 static void task_tick_cache(struct rq *rq, struct task_struct *p)
@@ -1408,6 +1429,17 @@ void init_sched_mm(struct task_struct *p)
 	work->next = work;
 }
 
+void reset_llc_stats(struct rq *rq)
+{
+	if (!sched_feat(SCHED_CACHE))
+		return;
+
+	if (rq->nr_llc_running)
+		rq->nr_llc_running = 0;
+
+	rq->nr_pref_llc_running = 0;
+}
+
 #else
 
 static inline void account_mm_sched(struct rq *rq, struct task_struct *p,
@@ -1418,6 +1450,17 @@ void init_sched_mm(struct task_struct *p) { }
 
 static void task_tick_cache(struct rq *rq, struct task_struct *p) { }
 
+static void account_llc_enqueue(struct rq *rq, struct task_struct *p)
+{
+}
+
+static void account_llc_dequeue(struct rq *rq, struct task_struct *p)
+{
+}
+
+void reset_llc_stats(struct rq *rq)
+{
+}
 #endif
 
 static inline
@@ -3957,6 +4000,7 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		struct rq *rq = rq_of(cfs_rq);
 
 		account_numa_enqueue(rq, task_of(se));
+		account_llc_enqueue(rq, task_of(se));
 		list_add(&se->group_node, &rq->cfs_tasks);
 	}
 #endif
@@ -3970,10 +4014,15 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 #ifdef CONFIG_SMP
 	if (entity_is_task(se)) {
 		account_numa_dequeue(rq_of(cfs_rq), task_of(se));
+		account_llc_dequeue(rq_of(cfs_rq), task_of(se));
 		list_del_init(&se->group_node);
 	}
 #endif
 	cfs_rq->nr_queued--;
+
+	/* safeguard? */
+	if (!parent_entity(se) && !cfs_rq->nr_queued)
+		reset_llc_stats(rq_of(cfs_rq));
 }
 
 /*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c37c74dfce25..8026e2c66e9f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1106,6 +1106,10 @@ struct rq {
 	unsigned int		nr_preferred_running;
 	unsigned int		numa_migrate_on;
 #endif
+#ifdef CONFIG_SCHED_CACHE
+	unsigned int		nr_pref_llc_running;
+	unsigned int		nr_llc_running;
+#endif
 #ifdef CONFIG_NO_HZ_COMMON
 #ifdef CONFIG_SMP
 	unsigned long		last_blocked_load_update_tick;
@@ -1967,6 +1971,9 @@ init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
 
 #endif /* !CONFIG_NUMA_BALANCING */
 
+void reset_llc_stats(struct rq *rq);
+int task_llc(const struct task_struct *p);
+
 #ifdef CONFIG_SMP
 
 static inline void
-- 
2.25.1


  parent reply	other threads:[~2025-08-09  5:10 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-08-09  4:57 [RFC PATCH v4 00/28] Cache aware load-balancing Chen Yu
2025-08-09  5:00 ` [RFC PATCH v4 01/28] sched: " Chen Yu
2025-08-12  1:30   ` kernel test robot
2025-08-12  3:26     ` Chen, Yu C
2025-08-09  5:01 ` [RFC PATCH v4 02/28] sched: Several fixes for cache aware scheduling Chen Yu
2025-08-09  5:01 ` [RFC PATCH v4 03/28] sched: Avoid task migration within its preferred LLC Chen Yu
2025-08-09  5:02 ` [RFC PATCH v4 04/28] sched: Avoid calculating the cpumask if the system is overloaded Chen Yu
2025-08-09  5:02 ` [RFC PATCH v4 05/28] sched: Add hysteresis to switch a task's preferred LLC Chen Yu
2025-09-29 13:44   ` Peter Zijlstra
2025-09-30  4:31     ` Chen, Yu C
2025-08-09  5:02 ` [RFC PATCH v4 06/28] sched: Save the per LLC utilization for better cache aware scheduling Chen Yu
2025-09-29 14:09   ` Peter Zijlstra
2025-09-30  4:34     ` Chen, Yu C
2025-08-09  5:03 ` [RFC PATCH v4 07/28] sched: Add helper function to decide whether to allow " Chen Yu
2025-10-01 13:17   ` Peter Zijlstra
2025-10-02 11:31     ` Chen, Yu C
2025-10-02 11:50       ` Peter Zijlstra
2025-10-02 12:51         ` Chen, Yu C
2025-10-02 17:46         ` Tim Chen
2025-08-09  5:03 ` [RFC PATCH v4 08/28] sched: Set up LLC indexing Chen Yu
2025-09-26  6:14   ` Adam Li
2025-09-26 13:51     ` Chen, Yu C
2025-09-29 10:43       ` Adam Li
2025-09-30  2:54         ` Chen, Yu C
2025-08-09  5:03 ` [RFC PATCH v4 09/28] sched: Introduce task preferred LLC field Chen Yu
2025-08-09  5:04 ` Chen Yu [this message]
2025-08-09  5:04 ` [RFC PATCH v4 11/28] sched: Introduce per runqueue task LLC preference counter Chen Yu
2025-08-09  5:04 ` [RFC PATCH v4 12/28] sched: Calculate the total number of preferred LLC tasks during load balance Chen Yu
2025-08-09  5:05 ` [RFC PATCH v4 13/28] sched: Tag the sched group as llc_balance if it has tasks prefer other LLC Chen Yu
2025-08-09  5:05 ` [RFC PATCH v4 14/28] sched: Introduce update_llc_busiest() to deal with groups having preferred LLC tasks Chen Yu
2025-08-09  5:06 ` [RFC PATCH v4 15/28] sched: Introduce a new migration_type to track the preferred LLC load balance Chen Yu
2025-08-09  5:06 ` [RFC PATCH v4 16/28] sched: Consider LLC locality for active balance Chen Yu
2025-08-09  5:06 ` [RFC PATCH v4 17/28] sched: Consider LLC preference when picking tasks from busiest queue Chen Yu
2025-08-09  5:07 ` [RFC PATCH v4 18/28] sched: Do not migrate task if it is moving out of its preferred LLC Chen Yu
2025-08-09  5:07 ` [RFC PATCH v4 19/28] sched: Introduce SCHED_CACHE_LB to control cache aware load balance Chen Yu
2025-08-09  5:07 ` [RFC PATCH v4 20/28] sched: Introduce SCHED_CACHE_WAKE to control LLC aggregation on wake up Chen Yu
2025-08-09  5:07 ` [RFC PATCH v4 21/28] sched: Introduce a static key to enable cache aware only for multi LLCs Chen Yu
2025-08-09  5:07 ` [RFC PATCH v4 22/28] sched: Turn EPOCH_PERIOD and EPOCH_OLD into tunnable debugfs Chen Yu
2025-08-09  5:08 ` [RFC PATCH v4 23/28] sched: Scan a task's preferred node for preferred LLC Chen Yu
2025-08-12  1:59   ` kernel test robot
2025-08-12  3:36     ` Chen, Yu C
2025-08-09  5:08 ` [RFC PATCH v4 24/28] sched: Record average number of runninhg tasks per process Chen Yu
2025-08-09  5:08 ` [RFC PATCH v4 25/28] sched: Skip cache aware scheduling if the process has many active threads Chen Yu
2025-09-02  3:52   ` Tingyin Duan
2025-09-02  5:16   ` Tingyin Duan
2025-09-02  6:14     ` Chen, Yu C
2025-09-02  7:56       ` Duan Tingyin
2025-08-09  5:08 ` [RFC PATCH v4 26/28] sched: Do not enable cache aware scheduling for process with large RSS Chen Yu
2025-09-26  8:48   ` Adam Li
2025-09-26 14:30     ` Chen, Yu C
2025-08-09  5:09 ` [RFC PATCH v4 27/28] sched: Allow the user space to tune the scale factor for RSS comparison Chen Yu
2025-08-09  5:09 ` [RFC PATCH v4 28/28] sched: Add ftrace to track cache aware load balance and hottest CPU changes Chen Yu

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=bd767d696636f233f30f334d41f46ce45c256948.1754712565.git.tim.c.chen@linux.intel.com \
    --to=yu.c.chen@intel.com \
    --cc=aubrey.li@intel.com \
    --cc=bsegall@google.com \
    --cc=cyy@cyyself.name \
    --cc=dietmar.eggemann@arm.com \
    --cc=gautham.shenoy@amd.com \
    --cc=hdanton@sina.com \
    --cc=jianyong.wu@outlook.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=sshegde@linux.ibm.com \
    --cc=tim.c.chen@linux.intel.com \
    --cc=tingyin.duan@gmail.com \
    --cc=vernhao@tencent.com \
    --cc=vincent.guittot@linaro.org \
    --cc=vineethr@linux.ibm.com \
    --cc=vschneid@redhat.com \
    --cc=yu.chen.surf@gmail.com \
    --cc=zhao1.liu@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

all inboxes | Powered by JetHome®