lkml.org 
[lkml]   [2014]   [Aug]   [4]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 2/2] softlockup: make detector be aware of task switch of processes hogging cpu
Date

For now, soft lockup detector warns once for each case of process softlockup.
But the thread 'watchdog/n' may can not always get cpu at the time slot between
the task switch of two processes hogging that cpu.
This case is a false negative of "warn only once for a process", as there may be
a different process that is going to hog the cpu. Is is better for detector to
be aware of it.

Signed-off-by: chai wen <chaiw.fnst@cn.fujitsu.com>
---
kernel/watchdog.c | 18 ++++++++++++++++--
1 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 4c2e11c..908050c 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -42,6 +42,7 @@ static DEFINE_PER_CPU(bool, softlockup_touch_sync);
static DEFINE_PER_CPU(bool, soft_watchdog_warn);
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt);
+static DEFINE_PER_CPU(pid_t, softlockup_warn_pid_saved);
#ifdef CONFIG_HARDLOCKUP_DETECTOR
static DEFINE_PER_CPU(bool, hard_watchdog_warn);
static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
@@ -317,6 +318,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
*/
duration = is_softlockup(touch_ts);
if (unlikely(duration)) {
+ pid_t pid = task_pid_nr(current);
+
/*
* If a virtual machine is stopped by the host it can look to
* the watchdog like a soft lockup, check to see if the host
@@ -326,8 +329,18 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
return HRTIMER_RESTART;

/* only warn once */
- if (__this_cpu_read(soft_watchdog_warn) == true)
+ if (__this_cpu_read(soft_watchdog_warn) == true) {
+ /*
+ * soft lockup detector should be aware of that there
+ * may be a task-swicth of two different processes
+ * hogging the cpu continously
+ */
+ if (__this_cpu_read(softlockup_warn_pid_saved) != pid) {
+ __this_cpu_write(soft_watchdog_warn, false);
+ __touch_watchdog();
+ }
return HRTIMER_RESTART;
+ }

if (softlockup_all_cpu_backtrace) {
/* Prevent multiple soft-lockup reports if one cpu is already
@@ -342,7 +355,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)

printk(KERN_EMERG "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
smp_processor_id(), duration,
- current->comm, task_pid_nr(current));
+ current->comm, pid);
+ __this_cpu_write(softlockup_warn_pid_saved, pid);
print_modules();
print_irqtrace_events(current);
if (regs)
--
1.7.1


\
 
 \ /
  Last update: 2014-08-04 10:21    [W:0.068 / U:2.732 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site