If we run in full dynticks mode, we currently have no way to correctly update the secondary decaying indexes of the CPU load stats as it is typically maintained by update_cpu_load_active() at each tick.
We have an available infrastructure that handles tickless loads (cf: decay_load_missed) but it seems to only work for idle tickless loads, which only applies if the CPU hasn't run any real task but idle on the tickless timeslice. Until we can provide a sane mathematical solution to handle full dynticks loads, lets simply deactivate the LB_BIAS sched feature if CONFIG_NO_HZ_FULL as it is currently the only user of the decayed load records. The first load index that represents the current runqueue load weight is still maintained and usable. Signed-off-by: Frederic Weisbecker <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Li Zhong <[email protected]> Cc: Paul E. McKenney <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Steven Rostedt <[email protected]> Cc: Thomas Gleixner <[email protected]> Cc: Borislav Petkov <[email protected]> Cc: Alex Shi <[email protected]> Cc: Paul Turner <[email protected]> Cc: Mike Galbraith <[email protected]> Cc: Vincent Guittot <[email protected]> --- kernel/sched/fair.c | 13 +++++++++++-- kernel/sched/features.h | 3 +++ 2 files changed, 14 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c0ac2c3..2e8df6f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2937,6 +2937,15 @@ static unsigned long weighted_cpuload(const int cpu) return cpu_rq(cpu)->load.weight; } +static inline int sched_lb_bias(void) +{ +#ifndef CONFIG_NO_HZ_FULL + return sched_feat(LB_BIAS); +#else + return 0; +#endif +} + /* * Return a low guess at the load of a migration-source cpu weighted * according to the scheduling class and "nice" value. @@ -2949,7 +2958,7 @@ static unsigned long source_load(int cpu, int type) struct rq *rq = cpu_rq(cpu); unsigned long total = weighted_cpuload(cpu); - if (type == 0 || !sched_feat(LB_BIAS)) + if (type == 0 || !sched_lb_bias()) return total; return min(rq->cpu_load[type-1], total); @@ -2964,7 +2973,7 @@ static unsigned long target_load(int cpu, int type) struct rq *rq = cpu_rq(cpu); unsigned long total = weighted_cpuload(cpu); - if (type == 0 || !sched_feat(LB_BIAS)) + if (type == 0 || !sched_lb_bias()) return total; return max(rq->cpu_load[type-1], total); diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 99399f8..635f902 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -43,7 +43,10 @@ SCHED_FEAT(ARCH_POWER, true) SCHED_FEAT(HRTICK, false) SCHED_FEAT(DOUBLE_TICK, false) + +#ifndef CONFIG_NO_HZ_FULL SCHED_FEAT(LB_BIAS, true) +#endif /* * Decrement CPU power based on time not spent running tasks -- 1.7.5.4 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
