sched: Print sched_group::__cpu_power in sched_domain_debug

Impact: extend debug info /proc/sched_debug

If the user changes the value of the sched_mc/smt_power_savings sysfs
tunable, it'll trigger a rebuilding of the whole sched_domain tree,
with the SD_POWERSAVINGS_BALANCE flag set at certain levels.

As a result, there would be a change in the __cpu_power of sched_groups
in the sched_domain hierarchy.

Print the __cpu_power values for each sched_group in sched_domain_debug
to help verify this change and correlate it with the change in the
load-balancing behavior.

Signed-off-by: Gautham R Shenoy <ego@in.ibm.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20090330045520.2869.24777.stgit@sofia.in.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/sched.c b/kernel/sched.c
index 8d1bdbe..6234d10 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -6963,7 +6963,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
                cpumask_or(groupmask, groupmask, sched_group_cpus(group));
 
                cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
                cpumask_or(groupmask, groupmask, sched_group_cpus(group));
 
                cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));

-               printk(KERN_CONT " %s", str);
+               printk(KERN_CONT " %s (__cpu_power = %d)", str,
+                                               group->__cpu_power);

 
                group = group->next;
        } while (group != sd->groups);
 
                group = group->next;
        } while (group != sd->groups);