Messages in this thread | | | Date | Sun, 2 Dec 2007 23:20:40 +0100 | From | Ingo Molnar <> | Subject | Re: [feature] automatically detect hung TASK_UNINTERRUPTIBLE tasks |
| |
* Andi Kleen <andi@firstfloor.org> wrote:
> > Until now users had little direct recourse to get such problems > > fixed. (we had sysrq-t, but that included no real metric of how long > > a task was > > Actually task delay accounting can measure this now. iirc someone had > a latencytop based on it already.
Delay accounting (or the /proc/<PID>/sched fields that i added recently) only get updated once a task has finished its unreasonably long delay and has scheduled. So lockups or extremely long delays _wont be detected_ this way. This is a debugging facility that clearly belongs into the kernel. Your arguments just make no objective sense.
Ingo
| |