提交 464191c6 编写于 作者: J Jens Axboe

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

This reverts commit 3586e917.

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: NJens Axboe <jens.axboe@oracle.com>
上级 8e550632
......@@ -609,15 +609,11 @@ 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) -
cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio));
return (cfqd->busy_queues - 1) * (cfq_prio_slice(cfqd, 1, 0) -
cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio));
}
/*
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册