Messages in this thread | | | Date | Sun, 13 Jun 1999 02:38:03 +0200 (CEST) | From | Andrea Arcangeli <> | Subject | Re: New schedule() and semaphore implementation ... |
| |
On Sat, 12 Jun 1999, Davide Libenzi wrote:
>But sure that if my goodness loop in __sem_wake_up() don't release the best >task neither LIFO & FIFO will do.
With the difference that FIFO will work in O(1) while your sem_wake_up() will work in O(nr_task_in_waitqueue). Your way the cost for every wakeup would be `goodness_cost * nr_tasks_in_waitqueue'.
>Anyway is better a FIFO politics then give all tasks the free way.
Agreed.
Andrea Arcangeli
- 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/
| |