lkml.org 
[lkml]   [2011]   [Feb]   [21]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [CFS Bandwidth Control v4 5/7] sched: add exports tracking cfs bandwidth control statistics
On Tue, Feb 22, 2011 at 08:44:20AM +0530, Balbir Singh wrote:
> * Paul Turner <pjt@google.com> [2011-02-15 19:18:36]:
>
> > From: Nikhil Rao <ncrao@google.com>
> >
> > This change introduces statistics exports for the cpu sub-system, these are
> > added through the use of a stat file similar to that exported by other
> > subsystems.
> >
> > The following exports are included:
> >
> > nr_periods: number of periods in which execution occurred
> > nr_throttled: the number of periods above in which execution was throttle
> > throttled_time: cumulative wall-time that any cpus have been throttled for
> > this group
> >
> > Signed-off-by: Paul Turner <pjt@google.com>
> > Signed-off-by: Nikhil Rao <ncrao@google.com>
> > Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
> > ---
> > kernel/sched.c | 26 ++++++++++++++++++++++++++
> > kernel/sched_fair.c | 16 +++++++++++++++-
> > 2 files changed, 41 insertions(+), 1 deletion(-)
> >
> > Index: tip/kernel/sched.c
> > ===================================================================
> > --- tip.orig/kernel/sched.c
> > +++ tip/kernel/sched.c
> > @@ -254,6 +254,11 @@ struct cfs_bandwidth {
> > ktime_t period;
> > u64 runtime, quota;
> > struct hrtimer period_timer;
> > +
> > + /* throttle statistics */
> > + u64 nr_periods;
> > + u64 nr_throttled;
> > + u64 throttled_time;
> > };
> > #endif
> >
> > @@ -389,6 +394,7 @@ struct cfs_rq {
> > #ifdef CONFIG_CFS_BANDWIDTH
> > u64 quota_assigned, quota_used;
> > int throttled;
> > + u64 throttled_timestamp;
> > #endif
> > #endif
> > };
> > @@ -426,6 +432,10 @@ void init_cfs_bandwidth(struct cfs_bandw
> >
> > hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
> > cfs_b->period_timer.function = sched_cfs_period_timer;
> > +
> > + cfs_b->nr_periods = 0;
> > + cfs_b->nr_throttled = 0;
> > + cfs_b->throttled_time = 0;
> > }
> >
> > static
> > @@ -9332,6 +9342,18 @@ static int cpu_cfs_period_write_u64(stru
> > return tg_set_cfs_period(cgroup_tg(cgrp), cfs_period_us);
> > }
> >
> > +static int cpu_stats_show(struct cgroup *cgrp, struct cftype *cft,
> > + struct cgroup_map_cb *cb)
> > +{
> > + struct task_group *tg = cgroup_tg(cgrp);
> > + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
> > +
> > + cb->fill(cb, "nr_periods", cfs_b->nr_periods);
> > + cb->fill(cb, "nr_throttled", cfs_b->nr_throttled);
> > + cb->fill(cb, "throttled_time", cfs_b->throttled_time);
> > +
> > + return 0;
> > +}
> > #endif /* CONFIG_CFS_BANDWIDTH */
> > #endif /* CONFIG_FAIR_GROUP_SCHED */
> >
> > @@ -9378,6 +9400,10 @@ static struct cftype cpu_files[] = {
> > .read_u64 = cpu_cfs_period_read_u64,
> > .write_u64 = cpu_cfs_period_write_u64,
> > },
> > + {
> > + .name = "stat",
> > + .read_map = cpu_stats_show,
> > + },
> > #endif
> > #ifdef CONFIG_RT_GROUP_SCHED
> > {
> > Index: tip/kernel/sched_fair.c
> > ===================================================================
> > --- tip.orig/kernel/sched_fair.c
> > +++ tip/kernel/sched_fair.c
> > @@ -1519,17 +1519,25 @@ static void throttle_cfs_rq(struct cfs_r
> >
> > out_throttled:
> > cfs_rq->throttled = 1;
> > + cfs_rq->throttled_timestamp = rq_of(cfs_rq)->clock;
> > update_cfs_rq_load_contribution(cfs_rq, 1);
> > }
> >
> > static void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
> > {
> > struct rq *rq = rq_of(cfs_rq);
> > + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
> > struct sched_entity *se;
> >
> > se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
> >
> > update_rq_clock(rq);
> > + /* update stats */
> > + raw_spin_lock(&cfs_b->lock);
> > + cfs_b->throttled_time += (rq->clock - cfs_rq->throttled_timestamp);
> > + raw_spin_unlock(&cfs_b->lock);
> > + cfs_rq->throttled_timestamp = 0;
> > +
> > /* (Try to) avoid maintaining share statistics for idle time */
> > cfs_rq->load_stamp = cfs_rq->load_last = rq->clock_task;
> >
> > @@ -1571,7 +1579,7 @@ static void account_cfs_rq_quota(struct
> >
> > static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
> > {
> > - int i, idle = 1;
> > + int i, idle = 1, num_throttled = 0;
> > u64 delta;
> > const struct cpumask *span;
> >
> > @@ -1593,6 +1601,7 @@ static int do_sched_cfs_period_timer(str
> >
> > if (!cfs_rq_throttled(cfs_rq))
> > continue;
> > + num_throttled++;
> >
> > delta = tg_request_cfs_quota(cfs_rq->tg);
> >
> > @@ -1608,6 +1617,11 @@ static int do_sched_cfs_period_timer(str
> > }
> > }
> >
> > + /* update throttled stats */
> > + cfs_b->nr_periods++;
> > + if (num_throttled)
> > + cfs_b->nr_throttled++;
> > +
> > return idle;
> > }
> >
>
> Should we consider integrating this in cpuacct, it would be difficult
> if we spill over stats between controllers.

Given that cpuacct controller can be mounted independently, I am not sure
if we should integrate these stats. These stats come from cpu controller.

I initially had similar stats as part of /proc/sched_debug since there
are a bunch of other group specific stats (including rt throttle stats)
in /proc/sched_debug.

Regards,
Bharata.


\
 
 \ /
  Last update: 2011-02-22 05:15    [from the cache]
©2003-2011 Jasper Spaans