lkml.org 
[lkml]   [2020]   [Jul]   [5]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH v2] hung_task:add detecting task in D state milliseconds timeout
Date
current hung_task_check_interval_secs and hung_task_timeout_secs
only supports seconds. In some cases,the TASK_UNINTERRUPTIBLE state
takes less than 1 second,may need to hung task trigger panic
get ramdump or print all cpu task.

modify hung_task_check_interval_secs to hung_task_check_interval_millisecs,
check interval use milliseconds. Add hung_task_timeout_millisecs file to
set milliseconds.
task timeout = hung_task_timeout_secs * 1000 + hung_task_timeout_millisecs.
(timeout * HZ / 1000) calculate how many are generated jiffies
in timeout milliseconds.

Signed-off-by: yang che <chey84736@gmail.com>
---

v1->v2:
add hung_task_check_interval_millisecs,hung_task_timeout_millisecs.
fix writing to the millisecond file silently overrides the setting in
the seconds file.

[1]https://lore.kernel.org/lkml/CAN_w4MWMfoDGfpON-bYHrU=KuJG2vpFj01ZbN4r-iwM4AyyuGw@mail.gmail.com

include/linux/sched/sysctl.h | 3 ++-
kernel/hung_task.c | 25 ++++++++++++++++++-------
kernel/sysctl.c | 12 ++++++++++--
3 files changed, 30 insertions(+), 10 deletions(-)

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 660ac49..179c331 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -16,8 +16,9 @@ extern unsigned int sysctl_hung_task_all_cpu_backtrace;

extern int sysctl_hung_task_check_count;
extern unsigned int sysctl_hung_task_panic;
+extern unsigned long sysctl_hung_task_timeout_millisecs;
extern unsigned long sysctl_hung_task_timeout_secs;
-extern unsigned long sysctl_hung_task_check_interval_secs;
+extern unsigned long sysctl_hung_task_check_interval_millisecs;
extern int sysctl_hung_task_warnings;
int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos);
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index ce76f49..809c999 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -37,6 +37,7 @@ int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
* the RCU grace period. So it needs to be upper-bound.
*/
#define HUNG_TASK_LOCK_BREAK (HZ / 10)
+#define SECONDS 1000

/*
* Zero means infinite timeout - no checking done:
@@ -44,9 +45,14 @@ int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT;

/*
+ * Zero means only use sysctl_hung_task_timeout_secs
+ */
+unsigned long __read_mostly sysctl_hung_task_timeout_millisecs;
+
+/*
* Zero (default value) means use sysctl_hung_task_timeout_secs:
*/
-unsigned long __read_mostly sysctl_hung_task_check_interval_secs;
+unsigned long __read_mostly sysctl_hung_task_check_interval_millisecs;

int __read_mostly sysctl_hung_task_warnings = 10;

@@ -108,7 +114,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
t->last_switch_time = jiffies;
return;
}
- if (time_is_after_jiffies(t->last_switch_time + timeout * HZ))
+
+ if (time_is_after_jiffies(t->last_switch_time + (timeout * HZ) / SECONDS))
return;

trace_sched_process_hang(t);
@@ -126,13 +133,16 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
if (sysctl_hung_task_warnings) {
if (sysctl_hung_task_warnings > 0)
sysctl_hung_task_warnings--;
- pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n",
- t->comm, t->pid, (jiffies - t->last_switch_time) / HZ);
+
+ pr_err("INFO: task %s:%d blocked for more than %ld seconds %ld milliseconds.\n",
+ t->comm, t->pid, (jiffies - t->last_switch_time) / HZ,
+ (jiffies - t->last_switch_time) % HZ * (SECONDS / HZ));
pr_err(" %s %s %.*s\n",
print_tainted(), init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
init_utsname()->version);
pr_err("\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
+ "\"echo 0 > /proc/sys/kernel/hung_task_timeout_millisecs\""
" disables this message.\n");
sched_show_task(t);
hung_task_show_lock = true;
@@ -217,7 +227,7 @@ static long hung_timeout_jiffies(unsigned long last_checked,
unsigned long timeout)
{
/* timeout of 0 will disable the watchdog */
- return timeout ? last_checked - jiffies + timeout * HZ :
+ return timeout ? last_checked - jiffies + (timeout * HZ) / SECONDS :
MAX_SCHEDULE_TIMEOUT;
}

@@ -281,8 +291,9 @@ static int watchdog(void *dummy)
set_user_nice(current, 0);

for ( ; ; ) {
- unsigned long timeout = sysctl_hung_task_timeout_secs;
- unsigned long interval = sysctl_hung_task_check_interval_secs;
+ unsigned long timeout = sysctl_hung_task_timeout_secs * SECONDS +
+ sysctl_hung_task_timeout_millisecs;
+ unsigned long interval = sysctl_hung_task_check_interval_millisecs;
long t;

if (interval == 0)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index db1ce7a..8f7ac33 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2476,6 +2476,14 @@ static struct ctl_table kern_table[] = {
.extra1 = SYSCTL_ZERO,
},
{
+ .procname = "hung_task_timeout_millisecs",
+ .data = &sysctl_hung_task_timeout_millisecs,
+ .maxlen = sizeof(unsigned long),
+ .mode = 0644,
+ .proc_handler = proc_dohung_task_timeout_secs,
+ .extra2 = &hung_task_timeout_max,
+ },
+ {
.procname = "hung_task_timeout_secs",
.data = &sysctl_hung_task_timeout_secs,
.maxlen = sizeof(unsigned long),
@@ -2484,8 +2492,8 @@ static struct ctl_table kern_table[] = {
.extra2 = &hung_task_timeout_max,
},
{
- .procname = "hung_task_check_interval_secs",
- .data = &sysctl_hung_task_check_interval_secs,
+ .procname = "hung_task_check_interval_millisecs",
+ .data = &sysctl_hung_task_check_interval_millisecs,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_dohung_task_timeout_secs,
--
2.7.4
\
 
 \ /
  Last update: 2020-07-05 14:50    [W:0.052 / U:0.300 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site