sched: Introduce temporary FAIR_GROUP_SCHED dependency for load-tracking

While per-entity load-tracking is generally useful, beyond computing shares
distribution, e.g. runnable based load-balance (in progress), governors,
power-management, etc.

These facilities are not yet consumers of this data.  This may be trivially
reverted when the information is required; but avoid paying the overhead for
calculations we will not use until then.

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/20120823141507.422162369@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index e483ccb08ce635e3db1d25fe81cc9c34180aba98..e1581a029e3d3187ae125b8effd15d0a94d68730 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1168,7 +1168,13 @@ struct sched_entity {
        /* rq "owned" by this entity/group: */
        struct cfs_rq           *my_q;
 #endif
-#ifdef CONFIG_SMP
+/*
+ * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
+ * removed when useful for applications beyond shares distribution (e.g.
+ * load-balance).
+ */
+#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
+       /* Per-entity load-tracking */
        struct sched_avg        avg;
 #endif
 };

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f26860074ef2ba59062370cf9c908c684b53534b..5dae0d252ff7728f4a0a7e8e30ac2c089f8a3ec7 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1526,7 +1526,12 @@ static void __sched_fork(struct task_struct *p)
        p->se.vruntime                  = 0;
        INIT_LIST_HEAD(&p->se.group_node);
 
-#ifdef CONFIG_SMP
+/*
+ * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
+ * removed when useful for applications beyond shares distribution (e.g.
+ * load-balance).
+ */
+#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
        p->se.avg.runnable_avg_period = 0;
        p->se.avg.runnable_avg_sum = 0;
 #endif

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6ecf455fd95bd214708831fbda34a92f5ece2c57..3e6a3531fa90222216f2e431cd7c2481d797f0ef 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -882,7 +882,8 @@ static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
 }
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
-#ifdef CONFIG_SMP
+/* Only depends on SMP, FAIR_GROUP_SCHED may be removed when useful in lb */
+#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
 /*
  * We choose a half-life close to 1 scheduling period.
  * Note: The tables below are dependent on this value.
@@ -3173,6 +3174,12 @@ unlock:
        return new_cpu;
 }
 
+/*
+ * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
+ * removed when useful for applications beyond shares distribution (e.g.
+ * load-balance).
+ */
+#ifdef CONFIG_FAIR_GROUP_SCHED
 /*
  * Called immediately before a task is migrated to a new cpu; task_cpu(p) and
  * cfs_rq_of(p) references at time of call are still valid and identify the
@@ -3196,6 +3203,7 @@ migrate_task_rq_fair(struct task_struct *p, int next_cpu)
                atomic64_add(se->avg.load_avg_contrib, &cfs_rq->removed_load);
        }
 }
+#endif
 #endif /* CONFIG_SMP */
 
 static unsigned long
@@ -5773,8 +5781,9 @@ const struct sched_class fair_sched_class = {
 
 #ifdef CONFIG_SMP
        .select_task_rq         = select_task_rq_fair,
+#ifdef CONFIG_FAIR_GROUP_SCHED
        .migrate_task_rq        = migrate_task_rq_fair,
-
+#endif
        .rq_online              = rq_online_fair,
        .rq_offline             = rq_offline_fair,
 

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0a75a430ca778c4b09b360a419a27b14cf3c42a7..5eca173b563f2663b16a0a6637b9a9f901b27c3e 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -225,6 +225,12 @@ struct cfs_rq {
 #endif
 
 #ifdef CONFIG_SMP
+/*
+ * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
+ * removed when useful for applications beyond shares distribution (e.g.
+ * load-balance).
+ */
+#ifdef CONFIG_FAIR_GROUP_SCHED
        /*
         * CFS Load tracking
         * Under CFS, load is tracked on a per-entity basis and aggregated up.
@@ -234,7 +240,8 @@ struct cfs_rq {
        u64 runnable_load_avg, blocked_load_avg;
        atomic64_t decay_counter, removed_load;
        u64 last_decay;
-
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+/* These always depend on CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_FAIR_GROUP_SCHED
        u32 tg_runnable_contrib;
        u64 tg_load_contrib;