Re: lowlatency-2.2.14-B1 + 2.2.14aa7 fixes crash, but...

From: Manfred Spraul (manfreds@colorfullife.com)
Date: Fri Feb 11 2000 - 17:00:21 EST


Andrea Arcangeli wrote:
>
> On Fri, 11 Feb 2000, William Montgomery wrote:
>
> >looking at the IKD docs I couldnt find a "stuck-process-oopser" feature.
>
> semaphore deadlock detector.
>
He wrote that the process is stuck in __wait_on_buffer(), I'm not sure
if the semaphore deadlock detector will detect this.

What about writing a generic module that walks through the task array
and dumps the complete (8kB) kernel stack? The big advantage is that we
could load it at runtime, and it has zero impact on the normal kernel
operations. Perhaps even a user space program could do that through
kcore/kmem.

(The typical stuck process report: "My uptime is 40 days, and now I have
10 stuck processes. What should I do?")

--
	Manfred

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Tue Feb 15 2000 - 21:00:21 EST