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 05/28] sched: Add hysteresis to switch a task's preferred LLC
Date: Sat,  9 Aug 2025 13:02:18 +0800	[thread overview]
Message-ID: <e51f8a6e172606d520c91c94c0c14b045639217e.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>

Switching a process's preferred LLC generates lots of task
migrations across LLCs. To avoid frequent switches
of home LLC, implement the following policy:

1. Require a 2x occ change threshold to switch preferred LLC
2. Don't discard preferred LLC for a task

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
---
 kernel/sched/fair.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a7be5c5ecba3..9e3c6f0eb934 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1175,6 +1175,14 @@ static s64 update_curr_se(struct rq *rq, struct sched_entity *curr)
 #define EPOCH_PERIOD	(HZ/100)	/* 10 ms */
 #define EPOCH_OLD	5		/* 50 ms */
 
+static int llc_id(int cpu)
+{
+	if (cpu < 0)
+		return -1;
+
+	return per_cpu(sd_llc_id, cpu);
+}
+
 void mm_init_sched(struct mm_struct *mm, struct mm_sched __percpu *_pcpu_sched)
 {
 	unsigned long epoch;
@@ -1307,6 +1315,7 @@ static void __no_profile task_cache_work(struct callback_head *work)
 	struct task_struct *p = current;
 	struct mm_struct *mm = p->mm;
 	unsigned long m_a_occ = 0;
+	unsigned long last_m_a_occ = 0;
 	int cpu, m_a_cpu = -1;
 	cpumask_var_t cpus;
 
@@ -1345,11 +1354,13 @@ static void __no_profile task_cache_work(struct callback_head *work)
 					     per_cpu(sd_llc_id, i), occ, m_occ, m_cpu, nr);
 			}
 
-			a_occ /= nr;
+			// a_occ /= nr;
 			if (a_occ > m_a_occ) {
 				m_a_occ = a_occ;
 				m_a_cpu = m_cpu;
 			}
+			if (llc_id(cpu) == llc_id(mm->mm_sched_cpu))
+				last_m_a_occ = a_occ;
 
 			trace_printk("(%d) a_occ: %ld m_a_occ: %ld\n",
 				     per_cpu(sd_llc_id, cpu), a_occ, m_a_occ);
@@ -1363,13 +1374,10 @@ static void __no_profile task_cache_work(struct callback_head *work)
 		}
 	}
 
-	/*
-	 * If the max average cache occupancy is 'small' we don't care.
-	 */
-	if (m_a_occ < (NICE_0_LOAD >> EPOCH_OLD))
-		m_a_cpu = -1;
-
-	mm->mm_sched_cpu = m_a_cpu;
+	if (m_a_occ > (2 * last_m_a_occ)) {
+		/* avoid the bouncing of mm_sched_cpu */
+		mm->mm_sched_cpu = m_a_cpu;
+	}
 
 	free_cpumask_var(cpus);
 }
-- 
2.25.1


  parent reply	other threads:[~2025-08-09  5:08 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 ` Chen Yu [this message]
2025-09-29 13:44   ` [RFC PATCH v4 05/28] sched: Add hysteresis to switch a task's preferred LLC 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 ` [RFC PATCH v4 10/28] sched: Calculate the number of tasks that have LLC preference on a runqueue Chen Yu
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=e51f8a6e172606d520c91c94c0c14b045639217e.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®