sched: Track the runnable average on a per-task entity basis

Instead of tracking averaging the load parented by a cfs_rq, we can track
entity load directly. With the load for a given cfs_rq then being the sum
of its children.

To do this we represent the historical contribution to runnable average
within each trailing 1024us of execution as the coefficients of a
geometric series.

We can express this for a given task t as:

  runnable_sum(t) = \Sum u_i * y^i, runnable_avg_period(t) = \Sum 1024 * y^i
  load(t) = weight_t * runnable_sum(t) / runnable_avg_period(t)

Where: u_i is the usage in the last i`th 1024us period (approximately 1ms)
~ms and y is chosen such that y^k = 1/2.  We currently choose k to be 32 which
roughly translates to about a sched period.

Signed-off-by: Paul Turner <pjt@google.com>
Reviewed-by: Ben Segall <bsegall@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20120823141506.372695337@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 13 insertions, 0 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0dd42a02df2e..418fc6d8a4da 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1095,6 +1095,16 @@ struct load_weight {
         unsigned long weight, inv_weight;
 };
 
+struct sched_avg {
+        /*
+         * These sums represent an infinite geometric series and so are bound
+         * above by 1024/(1-y).  Thus we only need a u32 to store them for for all
+         * choices of y < 1-2^(-32)*1024.
+         */
+        u32 runnable_avg_sum, runnable_avg_period;
+        u64 last_runnable_update;
+};
+
 #ifdef CONFIG_SCHEDSTATS
 struct sched_statistics {
         u64                     wait_start;
@@ -1155,6 +1165,9 @@ struct sched_entity {
         /* rq "owned" by this entity/group: */
         struct cfs_rq           *my_q;
 #endif
+#ifdef CONFIG_SMP
+        struct sched_avg        avg;
+#endif
 };
 
 struct sched_rt_entity {