Re: [patch] lockless, scalable get_pid(), for_each_process()

Ingo Molnar (mingo@elte.hu)
Wed, 18 Sep 2002 19:36:00 +0200 (CEST)


On Wed, 18 Sep 2002, William Lee Irwin III wrote:

> > i agree that this is okay, as an added mechanism. Nevertheless this does
> > not eliminate the 'box locks up for seconds' (or even minutes) situation.
>
> The lockups I see range from hours to "it spun over the weekend, time to
> pull the plug".

this can happen if there's a genuine PID space squeeze wrt. nr_threads -
that is solved by adding Linus' suggestion to the PID allocator. I believe
you saw that problem, not any inherent get_pid() algorithmic inefficiency.

nevertheless we do lock up for 32 seconds if there are 32K PIDs allocated
in a row and last_pid hits that range - regardless of pid_max. (Depending
on the cache architecture it could take significantly more.)

Ingo

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