revert "sched: fix fair sleepers" (e22ecef1d2658ba54ed7d3fdb5d60829fb434c23), because it is causing audio skipping, see: http://bugzilla.kernel.org/show_bug.cgi?id=10428 the patch is correct and the real cause of the skipping is not understood (tracing makes it go away), but time has run out so we'll revert it and re-try in 2.6.26.
Unified · Split
| @@ -510,10 +510,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) · 509 unmodified lines | |||
| 510 | 510 | ||
| 511 | if (!initial) { | 511 | if (!initial) { |
| 512 | /* sleeps upto a single latency don't count. */ | 512 | /* sleeps upto a single latency don't count. */ |
| 513 | if (sched_feat(NEW_FAIR_SLEEPERS)) { | 513 | if (sched_feat(NEW_FAIR_SLEEPERS)) |
| 514 | vruntime -= calc_delta_fair(sysctl_sched_latency, | 514 | vruntime -= sysctl_sched_latency; |
| 515 | &cfs_rq->load); | ||
| 516 | } | ||
| 517 | 515 | ||
| 518 | /* ensure we never gain time by being placed backwards. */ | 516 | /* ensure we never gain time by being placed backwards. */ |
| 519 | vruntime = max_vruntime(se->vruntime, vruntime); | 517 | vruntime = max_vruntime(se->vruntime, vruntime); |