Re: [PATCH] kernel/watchdog: Prevent false hardlockup on overloaded system

2016-12-19 Thread Andrew Morton
On Tue, 6 Dec 2016 11:17:13 -0500 Don Zickus wrote: > On an overloaded system, it is possible that a change in the watchdog > threshold > can be delayed long enough to trigger a false positive. > > This can easily be achieved by having a cpu spinning indefinitely on a task, > while another cpu

Re: [PATCH] kernel/watchdog: Prevent false hardlockup on overloaded system

2016-12-15 Thread Aaron Tomlin
On Tue 2016-12-06 11:17 -0500, Don Zickus wrote: > On an overloaded system, it is possible that a change in the watchdog > threshold > can be delayed long enough to trigger a false positive. > > This can easily be achieved by having a cpu spinning indefinitely on a task, > while another cpu updat

[PATCH] kernel/watchdog: Prevent false hardlockup on overloaded system

2016-12-06 Thread Don Zickus
On an overloaded system, it is possible that a change in the watchdog threshold can be delayed long enough to trigger a false positive. This can easily be achieved by having a cpu spinning indefinitely on a task, while another cpu updates watchdog threshold. What happens is while trying to park t