sched: reintroduce the sched_min_granularity tunable

we lost the sched_min_granularity tunable to a clever optimization
that uses the sched_latency/min_granularity ratio - but the ratio
is quite unintuitive to users and can also crash the kernel if the
ratio is set to 0. So reintroduce the min_granularity tunable,
while keeping the ratio maintained internally.

no functionality changed.

[ mingo@elte.hu: some fixlets. ]

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 28 insertions, 7 deletions

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 8763bee6b661..c495dcf7031b 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -35,16 +35,21 @@
 const_debug unsigned int sysctl_sched_latency = 20000000ULL;
 
 /*
- * After fork, child runs first. (default) If set to 0 then
- * parent will (try to) run first.
+ * Minimal preemption granularity for CPU-bound tasks:
+ * (default: 1 msec, units: nanoseconds)
  */
-const_debug unsigned int sysctl_sched_child_runs_first = 1;
+const_debug unsigned int sysctl_sched_min_granularity = 1000000ULL;
 
 /*
- * Minimal preemption granularity for CPU-bound tasks:
- * (default: 2 msec, units: nanoseconds)
+ * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
  */
-const_debug unsigned int sysctl_sched_nr_latency = 20;
+const_debug unsigned int sched_nr_latency = 20;
+
+/*
+ * After fork, child runs first. (default) If set to 0 then
+ * parent will (try to) run first.
+ */
+const_debug unsigned int sysctl_sched_child_runs_first = 1;
 
 /*
  * sys_sched_yield() compat mode
@@ -212,6 +217,22 @@ static inline struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
  * Scheduling class statistics methods:
  */
 
+#ifdef CONFIG_SCHED_DEBUG
+int sched_nr_latency_handler(struct ctl_table *table, int write,
+                struct file *filp, void __user *buffer, size_t *lenp,
+                loff_t *ppos)
+{
+        int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+
+        if (ret || !write)
+                return ret;
+
+        sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency,
+                                        sysctl_sched_min_granularity);
+
+        return 0;
+}
+#endif
 
 /*
  * The idea is to set a period in which each task runs once.
@@ -224,7 +245,7 @@ static inline struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 static u64 __sched_period(unsigned long nr_running)
 {
         u64 period = sysctl_sched_latency;
-        unsigned long nr_latency = sysctl_sched_nr_latency;
+        unsigned long nr_latency = sched_nr_latency;
 
         if (unlikely(nr_running > nr_latency)) {
                 period *= nr_running;