Revert "cfq: Make use of service count to estimate the rb_key offset"

This reverts commit 3586e917f2.

Corrado Zoccolo <czoccolo@gmail.com> correctly points out, that we need
consistency of rb_key offset across groups. This means we cannot properly
use the per-service_tree service count. Revert this change.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
This commit is contained in:
Jens Axboe 2009-11-30 09:38:13 +01:00
parent 8e550632cc
commit 464191c65b

View file

@ -609,14 +609,10 @@ cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
struct cfq_queue *cfqq)
{
struct cfq_rb_root *service_tree;
service_tree = service_tree_for(cfqq_prio(cfqq), cfqq_type(cfqq), cfqd);
/*
* just an approximation, should be ok.
*/
return service_tree->count * (cfq_prio_slice(cfqd, 1, 0) -
return (cfqd->busy_queues - 1) * (cfq_prio_slice(cfqd, 1, 0) -
cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio));
}