watchdog, hung_task_timeout: Add Kconfig configurable default

This patch allows the default value for sysctl_hung_task_timeout_secs
to be set at build time. The feature carries virtually no overhead,
so it makes sense to keep it enabled. On heavily loaded systems, though,
it can end up triggering stack traces when there is no bug other than
the system being underprovisioned. We use this patch to keep the hung task
facility available but disabled at boot-time.

The default of 120 seconds is preserved. As a note, commit e162b39a may
have accidentally reverted commit fb822db4, which raised the default from
120 seconds to 480 seconds.

Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Acked-by: Mandeep Singh Baines <msb@google.com>
Link: http://lkml.kernel.org/r/4DB8600C.8080000@suse.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 53ead174da2f0a7c7849df4ef81b60a96fe7c4f6..ea640120ab8606195e8fcddabe5c81180598b4cb 100644 (file)
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -33,7 +33,7 @@ unsigned long __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
 /*
  * Zero means infinite timeout - no checking done:
  */
-unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120;
+unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT;
 
 unsigned long __read_mostly sysctl_hung_task_warnings = 10;
 

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index c768bcdda1b700331a991cad681c5c2d6862c419..debbb0580bf066f9a832e3786e72dc3d9c3c5c71 100644 (file)
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -238,6 +238,21 @@ config DETECT_HUNG_TASK
          enabled then all held locks will also be reported. This
          feature has negligible overhead.
 
+config DEFAULT_HUNG_TASK_TIMEOUT
+       int "Default timeout for hung task detection (in seconds)"
+       depends on DETECT_HUNG_TASK
+       default 120
+       help
+         This option controls the default timeout (in seconds) used
+         to determine when a task has become non-responsive and should
+         be considered hung.
+
+         It can be adjusted at runtime via the kernel.hung_task_timeout
+         sysctl or by writing a value to /proc/sys/kernel/hung_task_timeout.
+
+         A timeout of 0 disables the check.  The default is two minutes.
+         Keeping the default should be fine in most cases.
+
 config BOOTPARAM_HUNG_TASK_PANIC
        bool "Panic (Reboot) On Hung Tasks"
        depends on DETECT_HUNG_TASK