watchdog: Change the default timeout and configure nmi watchdog period based on watch...

Before the conversion of the NMI watchdog to perf event, the
watchdog timeout was 5 seconds. Now it is 60 seconds. For my
particular application, netbooks, 5 seconds was a better
timeout. With a short timeout, we catch faults earlier and are
able to send back a panic. With a 60 second timeout, the user is
unlikely to wait and will instead hit the power button, causing
us to lose the panic info.

This change configures the NMI period to watchdog_thresh and
sets the softlockup_thresh to watchdog_thresh * 2. In addition,
watchdog_thresh was reduced to 10 seconds as suggested by Ingo
Molnar.

Signed-off-by: Mandeep Singh Baines <msb@chromium.org>
Cc: Marcin Slusarz <marcin.slusarz@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/1306127423-3347-4-git-send-email-msb@chromium.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
LKML-Reference: <20110517071642.GF22305@elte.hu>

diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 5260fe91bcb66301aeb2eb97ad833ab855212494..d5e57db0f7beaa82a60c1c341bcc7a85a5e5d847 100644 (file)
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -19,9 +19,9 @@
 #include <linux/delay.h>
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
-u64 hw_nmi_get_sample_period(void)
+u64 hw_nmi_get_sample_period(int watchdog_thresh)
 {
-       return (u64)(cpu_khz) * 1000 * 60;
+       return (u64)(cpu_khz) * 1000 * watchdog_thresh;
 }
 #endif
 

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 5317b8b2198f71f2d59ec239a153f25b865e67c1..2d304efc89dfc442fe76607a940371618d7700f0 100644 (file)
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -45,7 +45,7 @@ static inline bool trigger_all_cpu_backtrace(void)
 
 #ifdef CONFIG_LOCKUP_DETECTOR
 int hw_nmi_is_cpu_stuck(struct pt_regs *);
-u64 hw_nmi_get_sample_period(void);
+u64 hw_nmi_get_sample_period(int watchdog_thresh);
 extern int watchdog_enabled;
 extern int watchdog_thresh;
 struct ctl_table;

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 60301916f62eb868662156655d186dae35cb2f7d..6e63097fa73a8082ebe189b35f367e837ee21bef 100644 (file)
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -28,7 +28,7 @@
 #include <linux/perf_event.h>
 
 int watchdog_enabled = 1;
-int __read_mostly watchdog_thresh = 60;
+int __read_mostly watchdog_thresh = 10;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
 static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
@@ -91,6 +91,17 @@ static int __init nosoftlockup_setup(char *str)
 __setup("nosoftlockup", nosoftlockup_setup);
 /*  */
 
+/*
+ * Hard-lockup warnings should be triggered after just a few seconds. Soft-
+ * lockups can have false positives under extreme conditions. So we generally
+ * want a higher threshold for soft lockups than for hard lockups. So we couple
+ * the thresholds with a factor: we make the soft threshold twice the amount of
+ * time the hard threshold is.
+ */
+static int get_softlockup_thresh()
+{
+       return watchdog_thresh * 2;
+}
 
 /*
  * Returns seconds, approximately.  We don't need nanosecond
@@ -110,7 +121,7 @@ static unsigned long get_sample_period(void)
         * increment before the hardlockup detector generates
         * a warning
         */
-       return watchdog_thresh * (NSEC_PER_SEC / 5);
+       return get_softlockup_thresh() * (NSEC_PER_SEC / 5);
 }
 
 /* Commands for resetting the watchdog */
@@ -182,7 +193,7 @@ static int is_softlockup(unsigned long touch_ts)
        unsigned long now = get_timestamp(smp_processor_id());
 
        /* Warn about unreasonable delays: */
-       if (time_after(now, touch_ts + watchdog_thresh))
+       if (time_after(now, touch_ts + get_softlockup_thresh()))
                return now - touch_ts;
 
        return 0;
@@ -359,7 +370,7 @@ static int watchdog_nmi_enable(int cpu)
 
        /* Try to register using hardware perf events */
        wd_attr = &wd_hw_attr;
-       wd_attr->sample_period = hw_nmi_get_sample_period();
+       wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh);
        event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback);
        if (!IS_ERR(event)) {
                printk(KERN_INFO "NMI watchdog enabled, takes one hw-pmu counter.\n");