This patch improves throughput with the smp nice balancing code. Many thanks to Martin Bligh for the usage of his regression testing bed to confirm the effectiveness of various patches. Con ---
The intermittent scheduling of the migration thread at ultra high priority makes the smp nice handling see that runqueue as being heavily loaded. The migration thread itself actually handles the balancing so its influence on priority balancing should be ignored. Signed-off-by: Con Kolivas <[email protected]> Index: linux-2.6.12-mm1/kernel/sched.c =================================================================== --- linux-2.6.12-mm1.orig/kernel/sched.c 2005-06-26 17:59:10.000000000 +1000 +++ linux-2.6.12-mm1/kernel/sched.c 2005-06-26 18:02:01.000000000 +1000 @@ -669,6 +669,31 @@ static inline void dec_prio_bias(runqueu { rq->prio_bias -= MAX_PRIO - prio; } + +static inline void inc_nr_running(task_t *p, runqueue_t *rq) +{ + rq->nr_running++; + if (rt_task(p)) { + if (p != rq->migration_thread) + /* + * The migration thread does the actual balancing. Do + * not bias by its priority as the ultra high priority + * will skew balancing adversely. + */ + inc_prio_bias(rq, p->prio); + } else + inc_prio_bias(rq, p->static_prio); +} + +static inline void dec_nr_running(task_t *p, runqueue_t *rq) +{ + rq->nr_running--; + if (rt_task(p)) { + if (p != rq->migration_thread) + dec_prio_bias(rq, p->prio); + } else + dec_prio_bias(rq, p->static_prio); +} #else static inline void inc_prio_bias(runqueue_t *rq, int prio) { @@ -677,25 +702,17 @@ static inline void inc_prio_bias(runqueu static inline void dec_prio_bias(runqueue_t *rq, int prio) { } -#endif static inline void inc_nr_running(task_t *p, runqueue_t *rq) { rq->nr_running++; - if (rt_task(p)) - inc_prio_bias(rq, p->prio); - else - inc_prio_bias(rq, p->static_prio); } static inline void dec_nr_running(task_t *p, runqueue_t *rq) { rq->nr_running--; - if (rt_task(p)) - dec_prio_bias(rq, p->prio); - else - dec_prio_bias(rq, p->static_prio); } +#endif /* * __activate_task - move a task to the runqueue.
Attachment:
pgp1L3logKrBY.pgp
Description: PGP signature
- Follow-Ups:
- Re: [PATCH] sched: consider migration thread with smp nice
- From: Peter Williams <[email protected]>
- Re: [PATCH] sched: consider migration thread with smp nice
- Prev by Date: Re: [PATCH] xtensa: Architecture support for Tensilica Xtensa Part 1
- Next by Date: Re: reiser4 plugins
- Previous by thread: Re: [PATCH] xtensa: Architecture support for Tensilica Xtensa Part 1
- Next by thread: Re: [PATCH] sched: consider migration thread with smp nice
- Index(es):