diff options
| author | Huang Shijie <shijie@os.amperecomputing.com> | 2024-10-01 09:00:21 +0200 |
|---|---|---|
| committer | Peter Zijlstra <peterz@infradead.org> | 2024-10-07 09:28:41 +0200 |
| commit | 4423af84b29794a9bd2bd07188d8e71083e54c61 (patch) | |
| tree | 67bbb27844d1ee2508dd677cbb49515851af65e9 | |
| parent | sched/fair: remove the DOUBLE_TICK feature (diff) | |
| download | linux-4423af84b29794a9bd2bd07188d8e71083e54c61.tar.xz linux-4423af84b29794a9bd2bd07188d8e71083e54c61.zip | |
sched/fair: optimize the PLACE_LAG when se->vlag is zero
When PLACE_LAG is enabled, from the relationship:
vl_i = (W + w_i)*vl'_i / W
we know that if vl'_i(se->vlag) is zero, the vl_i is zero too.
So if se->vlag is zero, there is no need to waste cycles to
do the calculation.
Signed-off-by: Huang Shijie <shijie@os.amperecomputing.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Christoph Lameter (Ampere) <cl@linux.com>
Link: https://lkml.kernel.org/r/20241001070021.10626-1-shijie@os.amperecomputing.com
| -rw-r--r-- | kernel/sched/fair.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c9e3b8d2a85f..5a621210c9c1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5280,7 +5280,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * * EEVDF: placement strategy #1 / #2 */ - if (sched_feat(PLACE_LAG) && cfs_rq->nr_running) { + if (sched_feat(PLACE_LAG) && cfs_rq->nr_running && se->vlag) { struct sched_entity *curr = cfs_rq->curr; unsigned long load; |