Messages in this thread Patch in this message | | | From | Andrew Theurer <> | Subject | CAN_MIGRATE seems screwed up | Date | Wed, 27 Aug 2003 10:07:59 -0500 |
| |
OK, not sure how long this has been this way, but:
#define CAN_MIGRATE_TASK(p,rq,this_cpu) \ ((!idle || (jiffies - (p)->last_run > cache_decay_ticks)) && \ !task_running(rq, p) && \ cpu_isset(this_cpu, (p)->cpus_allowed))
Is broken. Having !idle make no sense. It should be just the opposite; an idle cpu should be able to have a more aggressive steal, and a busy cpu should not.
diff -Naurp linux-2.6.0-test4/kernel/sched.c linux-2.6.0-test4-can_migrate/kernel/sched.c --- linux-2.6.0-test4/kernel/sched.c Fri Aug 22 18:58:43 2003 +++ linux-2.6.0-test4-can_migrate/kernel/sched.c Wed Aug 27 11:32:46 2003 @@ -1064,7 +1064,7 @@ skip_queue: */ #define CAN_MIGRATE_TASK(p,rq,this_cpu) \ - ((!idle || (jiffies - (p)->last_run > cache_decay_ticks)) && \ + ((idle || (jiffies - (p)->last_run > cache_decay_ticks)) && \ !task_running(rq, p) && \ cpu_isset(this_cpu, (p)->cpus_allowed)) - 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/
| |