linux-kernel - [RFC PATCH v0 2/3] sched/numa: Add cumulative history of per-process fault stats

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: <20220128052851.17162-3-bharata@amd.com>
Date:   Fri, 28 Jan 2022 10:58:50 +0530
From:   Bharata B Rao <bharata@....com>
To:     <linux-kernel@...r.kernel.org>
CC:     <mingo@...hat.com>, <peterz@...radead.org>,
        <juri.lelli@...hat.com>, <vincent.guittot@...aro.org>,
        <dietmar.eggemann@....com>, <rostedt@...dmis.org>,
        <bsegall@...gle.com>, <mgorman@...e.de>, <bristot@...hat.com>,
        <dishaa.talreja@....com>, Wei Huang <wei.huang2@....com>,
        Bharata B Rao <bharata@....com>
Subject: [RFC PATCH v0 2/3] sched/numa: Add cumulative history of per-process fault stats

From: Disha Talreja <dishaa.talreja@....com>

The cumulative history of local/remote (lr) and private/shared (ps)
will be used for calculating adaptive scan period.

Co-developed-by: Wei Huang <wei.huang2@....com>
Signed-off-by: Wei Huang <wei.huang2@....com>
Signed-off-by: Disha Talreja <dishaa.talreja@....com>
Signed-off-by: Bharata B Rao <bharata@....com>
---
 include/linux/mm_types.h |  2 ++
 kernel/sched/fair.c      | 49 +++++++++++++++++++++++++++++++++++++++-
 2 files changed, 50 insertions(+), 1 deletion(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 4f978c09d3db..2c6f119b947f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -614,6 +614,8 @@ struct mm_struct {
 		/* Process-based Adaptive NUMA */
 		atomic_long_t faults_locality[2];
 		atomic_long_t faults_shared[2];
+		unsigned long faults_locality_history[2];
+		unsigned long faults_shared_history[2];
 
 		spinlock_t pan_numa_lock;
 		unsigned int numa_scan_period;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1d6404b2d42e..4911b3841d00 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2102,14 +2102,56 @@ static void numa_group_count_active_nodes(struct numa_group *numa_group)
 /**********************************************/
 /*  Process-based Adaptive NUMA (PAN) Design  */
 /**********************************************/
+/*
+ * Update the cumulative history of local/remote and private/shared
+ * statistics. If the numbers are too small worthy of updating,
+ * return FALSE, otherwise return TRUE.
+ */
+static bool pan_update_history(struct task_struct *p)
+{
+	unsigned long local, remote, shared, private;
+	long diff;
+	int i;
+
+	remote = atomic_long_read(&p->mm->faults_locality[0]);
+	local = atomic_long_read(&p->mm->faults_locality[1]);
+	shared = atomic_long_read(&p->mm->faults_shared[0]);
+	private = atomic_long_read(&p->mm->faults_shared[1]);
+
+	/* skip if the activities in this window are too small */
+	if (local + remote < 100)
+		return false;
+
+	/* decay over the time window by 1/4 */
+	diff = local - (long)(p->mm->faults_locality_history[1] / 4);
+	p->mm->faults_locality_history[1] += diff;
+	diff = remote - (long)(p->mm->faults_locality_history[0] / 4);
+	p->mm->faults_locality_history[0] += diff;
+
+	/* decay over the time window by 1/2 */
+	diff = shared - (long)(p->mm->faults_shared_history[0] / 2);
+	p->mm->faults_shared_history[0] += diff;
+	diff = private - (long)(p->mm->faults_shared_history[1] / 2);
+	p->mm->faults_shared_history[1] += diff;
+
+	/* clear the statistics for the next window */
+	for (i = 0; i < 2; i++) {
+		atomic_long_set(&(p->mm->faults_locality[i]), 0);
+		atomic_long_set(&(p->mm->faults_shared[i]), 0);
+	}
+
+	return true;
+}
+
 /*
  * Updates mm->numa_scan_period under mm->pan_numa_lock.
- *
  * Returns p->numa_scan_period now but updated to return
  * p->mm->numa_scan_period in a later patch.
  */
 static unsigned long pan_get_scan_period(struct task_struct *p)
 {
+	pan_update_history(p);
+
 	return p->numa_scan_period;
 }
 
@@ -2836,10 +2878,15 @@ static void task_numa_work(struct callback_head *work)
 static void pan_init_numa(struct task_struct *p)
 {
 	struct mm_struct *mm = p->mm;
+	int i;
 
 	spin_lock_init(&mm->pan_numa_lock);
 	mm->numa_scan_period = sysctl_numa_balancing_scan_delay;
 
+	for (i = 0; i < 2; i++) {
+		mm->faults_locality_history[i] = 0;
+		mm->faults_shared_history[i] = 0;
+	}
 }
 
 void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
-- 
2.25.1