On 3 June 2014 15:43, Srivatsa S. Bhat <[email protected]> wrote: > diff --git a/drivers/cpufreq/cpufreq_governor.c > b/drivers/cpufreq/cpufreq_governor.c > index e1c6433..2597bbe 100644 > --- a/drivers/cpufreq/cpufreq_governor.c > +++ b/drivers/cpufreq/cpufreq_governor.c > @@ -36,14 +36,29 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu) > struct od_dbs_tuners *od_tuners = dbs_data->tuners; > struct cs_dbs_tuners *cs_tuners = dbs_data->tuners; > struct cpufreq_policy *policy; > + unsigned int sampling_rate; > unsigned int max_load = 0; > unsigned int ignore_nice; > unsigned int j; > > - if (dbs_data->cdata->governor == GOV_ONDEMAND) > + if (dbs_data->cdata->governor == GOV_ONDEMAND) { > + struct od_cpu_dbs_info_s *od_dbs_info = > + dbs_data->cdata->get_cpu_dbs_info_s(cpu); > + > + /* > + * Sometimes, the ondemand governor uses an additional > + * multiplier to give long delays. So apply this multiplier to > + * the 'sampling_rate', so as to keep the wake-up-from-idle > + * detection logic a bit conservative. > + */ > + sampling_rate = od_tuners->sampling_rate; > + sampling_rate *= od_dbs_info->rate_mult; > + > ignore_nice = od_tuners->ignore_nice_load; > - else > + } else { > + sampling_rate = cs_tuners->sampling_rate; > ignore_nice = cs_tuners->ignore_nice_load; > + } > > policy = cdbs->cur_policy; > > @@ -96,7 +111,29 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu) > if (unlikely(!wall_time || wall_time < idle_time)) > continue; > > - load = 100 * (wall_time - idle_time) / wall_time; > + /* > + * If the CPU had gone completely idle, and a task just woke > up > + * on this CPU now, it would be unfair to calculate 'load' the > + * usual way for this elapsed time-window, because it will > show > + * near-zero load, irrespective of how CPU intensive the new > + * task is. This is undesirable for latency-sensitive bursty > + * workloads. > + * > + * To avoid this, we reuse the 'load' from the previous > + * time-window and give this task a chance to start with a > + * reasonably high CPU frequency. > + * > + * Detecting this situation is easy: the governor's deferrable > + * timer would not have fired during CPU-idle periods. Hence > + * an unusually large 'wall_time' (as compared to the sampling > + * rate) indicates this scenario. > + */ > + if (unlikely(wall_time > (2 * sampling_rate))) { > + load = j_cdbs->prev_load; > + } else { > + load = 100 * (wall_time - idle_time) / wall_time; > + j_cdbs->prev_load = load; > + } > > if (load > max_load) > max_load = load; > @@ -323,6 +360,10 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy, > j_cdbs->cur_policy = policy; > j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, > &j_cdbs->prev_cpu_wall, > io_busy); > + j_cdbs->prev_load = 100 * (j_cdbs->prev_cpu_wall - > + j_cdbs->prev_cpu_idle) / > + j_cdbs->prev_cpu_wall; > + > if (ignore_nice) > j_cdbs->prev_cpu_nice = > kcpustat_cpu(j).cpustat[CPUTIME_NICE]; > diff --git a/drivers/cpufreq/cpufreq_governor.h > b/drivers/cpufreq/cpufreq_governor.h > index bfb9ae1..b56552b 100644 > --- a/drivers/cpufreq/cpufreq_governor.h > +++ b/drivers/cpufreq/cpufreq_governor.h > @@ -134,6 +134,7 @@ struct cpu_dbs_common_info { > u64 prev_cpu_idle; > u64 prev_cpu_wall; > u64 prev_cpu_nice; > + unsigned int prev_load; > struct cpufreq_policy *cur_policy; > struct delayed_work work; > /*
Acked-by: Viresh Kumar <[email protected]> -- 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/
