[1/2] hung_task: add detect count for hung tasks

Commit Message

Lance Yang Oct. 22, 2024, 11:47 a.m. UTC

This commit adds a counter, hung_task_detect_count, to track the number of
times hung tasks are detected. This counter provides a straightforward way
to monitor hung task events without manually checking dmesg logs.

With this counter in place, system issues can be spotted quickly, allowing
admins to step in promptly before system load spikes occur, even if the
hung_task_warnings value has been decreased to 0 well before.

Signed-off-by: Mingzhe Yang <[e-mail]>
Signed-off-by: Lance Yang <[e-mail]>
---
 kernel/hung_task.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

Patch

diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 959d99583d1c..229ff3d4e501 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -30,6 +30,11 @@ 
  */
 static int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
 
+/*
+ * Total number of tasks detected as hung since boot:
+ */
+static unsigned long __read_mostly sysctl_hung_task_detect_count;
+
 /*
  * Limit number of tasks checked in a batch.
  *
@@ -115,6 +120,12 @@  static void check_hung_task(struct task_struct *t, unsigned long timeout)
 	if (time_is_after_jiffies(t->last_switch_time + timeout * HZ))
 		return;
 
+	/*
+	 * This counter tracks the total number of tasks detected as hung
+	 * since boot.
+	 */
+	sysctl_hung_task_detect_count++;
+
 	trace_sched_process_hang(t);
 
 	if (sysctl_hung_task_panic) {
@@ -314,6 +325,13 @@  static struct ctl_table hung_task_sysctls[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_NEG_ONE,
 	},
+	{
+		.procname	= "hung_task_detect_count",
+		.data		= &sysctl_hung_task_detect_count,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0444,
+		.proc_handler	= proc_dointvec,
+	},
 };
 
 static void __init hung_task_sysctl_init(void)