diff options
| author | Peter Zijlstra <a.p.zijlstra@chello.nl> | 2007-09-05 14:32:49 +0200 |
|---|---|---|
| committer | Ingo Molnar <mingo@elte.hu> | 2007-09-05 14:32:49 +0200 |
| commit | 4a55b45036a677fac43fe81ddf7fdcd007aaaee7 (patch) | |
| tree | 86558fa9997e28194d84b997011ed91cde49746c | |
| parent | 7c92e54f6f9601cfa9d8894ee248abcf62ed9a1c (diff) | |
sched: improve prev_sum_exec_runtime setting
Second preparatory patch for fix-ideal runtime:
Mark prev_sum_exec_runtime at the beginning of our run, the same spot
that adds our wait period to wait_runtime. This seems a more natural
location to do this, and it also reduces the code a bit:
text data bss dec hex filename
13397 228 1204 14829 39ed sched.o.before
13391 228 1204 14823 39e7 sched.o.after
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
| -rw-r--r-- | kernel/sched_fair.c | 5 |
1 files changed, 2 insertions, 3 deletions
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index f0dd4be1a3a..2d01bbc2d04 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -684,10 +684,8 @@ __check_preempt_curr_fair(struct cfs_rq *cfs_rq, struct sched_entity *se, * preempt the current task unless the best task has * a larger than sched_granularity fairness advantage: */ - if (__delta > niced_granularity(curr, granularity)) { + if (__delta > niced_granularity(curr, granularity)) resched_task(rq_of(cfs_rq)->curr); - curr->prev_sum_exec_runtime = curr->sum_exec_runtime; - } } static inline void @@ -703,6 +701,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) update_stats_wait_end(cfs_rq, se); update_stats_curr_start(cfs_rq, se); set_cfs_rq_curr(cfs_rq, se); + se->prev_sum_exec_runtime = se->sum_exec_runtime; } static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq) |