sched: Fix missing sched tunable recalculation on cpu add/remove

commit 0bcdcf28c979869f44e05121b96ff2cfb05bd8e6 upstream.

Based on Peter Zijlstras patch suggestion this enables recalculation of
the scheduler tunables in response of a change in the number of cpus. It
also adds a max of eight cpus that are considered in that scaling.

Signed-off-by: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1259579808-11357-2-git-send-email-ehrhardt@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/kernel/sched.c b/kernel/sched.c
index ab15840d3952a6c65ad24f69de16814853f77657..60d74cc721cc8bdb30abc0e7222c5196c2a09afc 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -816,6 +816,7 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32;
  * default: 0.25ms
  */
 unsigned int sysctl_sched_shares_ratelimit = 250000;
+unsigned int normalized_sysctl_sched_shares_ratelimit = 250000;
 
 /*
  * Inject some fuzzyness into changing the per-cpu group shares
@@ -1812,6 +1813,7 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
 #endif
 
 static void calc_load_account_active(struct rq *this_rq);
+static void update_sysctl(void);
 
 #include "sched_stats.h"
 #include "sched_idletask.c"
@@ -7018,22 +7020,23 @@ cpumask_var_t nohz_cpu_mask;
  *
  * This idea comes from the SD scheduler of Con Kolivas:
  */
-static inline void sched_init_granularity(void)
+static void update_sysctl(void)
 {
-       unsigned int factor = 1 + ilog2(num_online_cpus());
-       const unsigned long limit = 200000000;
-
-       sysctl_sched_min_granularity *= factor;
-       if (sysctl_sched_min_granularity > limit)
-               sysctl_sched_min_granularity = limit;
-
-       sysctl_sched_latency *= factor;
-       if (sysctl_sched_latency > limit)
-               sysctl_sched_latency = limit;
+       unsigned int cpus = min(num_online_cpus(), 8U);
+       unsigned int factor = 1 + ilog2(cpus);
 
-       sysctl_sched_wakeup_granularity *= factor;
+#define SET_SYSCTL(name) \
+       (sysctl_##name = (factor) * normalized_sysctl_##name)
+       SET_SYSCTL(sched_min_granularity);
+       SET_SYSCTL(sched_latency);
+       SET_SYSCTL(sched_wakeup_granularity);
+       SET_SYSCTL(sched_shares_ratelimit);
+#undef SET_SYSCTL
+}
 
-       sysctl_sched_shares_ratelimit *= factor;
+static inline void sched_init_granularity(void)
+{
+       update_sysctl();
 }
 
 #ifdef CONFIG_SMP

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 199228b24bbc1b4641d9f2289543ddb9e57344ae..d80812d39d6238378ccac64538056d762128f084 100644 (file)
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -35,12 +35,14 @@
  *  run vmstat and monitor the context-switches (cs) field)
  */
 unsigned int sysctl_sched_latency = 5000000ULL;
+unsigned int normalized_sysctl_sched_latency = 5000000ULL;
 
 /*
  * Minimal preemption granularity for CPU-bound tasks:
  * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
 unsigned int sysctl_sched_min_granularity = 1000000ULL;
+unsigned int normalized_sysctl_sched_min_granularity = 1000000ULL;
 
 /*
  * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
@@ -70,6 +72,7 @@ unsigned int __read_mostly sysctl_sched_compat_yield;
  * have immediate wakeup/sleep latencies.
  */
 unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
+unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
 
@@ -1880,6 +1883,17 @@ move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 
        return 0;
 }
+
+static void rq_online_fair(struct rq *rq)
+{
+       update_sysctl();
+}
+
+static void rq_offline_fair(struct rq *rq)
+{
+       update_sysctl();
+}
+
 #endif /* CONFIG_SMP */
 
 /*
@@ -2027,6 +2041,8 @@ static const struct sched_class fair_sched_class = {
 
        .load_balance           = load_balance_fair,
        .move_one_task          = move_one_task_fair,
+       .rq_online              = rq_online_fair,
+       .rq_offline             = rq_offline_fair,
 #endif
 
        .set_curr_task          = set_curr_task_fair,