Messages in this thread | | | Date | Fri, 20 Aug 2004 10:14:58 +0200 | From | Ingo Molnar <> | Subject | Re: 2.6.8.1-mm2 |
| |
* Rusty Russell <rusty@rustcorp.com.au> wrote:
> + /* Delayed cleanup on death of task with uncaring parent. */ > + struct list_head death;
> +/* Keventd handles tasks whose parent won't ever release_task them. */ > +static DEFINE_PER_CPU(struct list_head, unreleased_tasks); > +static DEFINE_PER_CPU(struct work_struct, release_task_work);
no! this removes the whole performance optimization of self-reaping and re-introduces the context-switches. Just measure the creation/destruction performance of threads. Strong NACK.
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/
| |