sched/numa: Fix numa balancing stats in /proc/pid/sched

Commit 44dba3d5d6a1 ("sched: Refactor task_struct to use
numa_faults instead of numa_* pointers") modified the way
tsk->numa_faults stats are accounted.

However that commit never touched show_numa_stats() that is displayed
in /proc/pid/sched and thus the numbers displayed in /proc/pid/sched
don't match the actual numbers.

Fix it by making sure that /proc/pid/sched reflects the task
fault numbers. Also add group fault stats too.

Also couple of more modifications are added here:

1. Format changes:

  - Previously we would list two entries per node, one for private
    and one for shared. Also the home node info was listed in each entry.

  - Now preferred node, total_faults and current node are
    displayed separately.

  - Now there is one entry per node, that lists private,shared task and
    group faults.

2. Unit changes:

  - p->numa_pages_migrated was getting reset after every read of
    /proc/pid/sched. It's more useful to have absolute numbers since
    differential migrations between two accesses can be more easily
    calculated.

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Iulia Manda <iulia.manda21@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1435252903-1081-4-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 17 insertions, 21 deletions

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index f1dcd1d390c1..4222ec50ab88 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -517,11 +517,21 @@ __initcall(init_sched_debug_procfs);
         SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
 
 
+#ifdef CONFIG_NUMA_BALANCING
+void print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
+                unsigned long tpf, unsigned long gsf, unsigned long gpf)
+{
+        SEQ_printf(m, "numa_faults node=%d ", node);
+        SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf);
+        SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf);
+}
+#endif
+
+
 static void sched_show_numa(struct task_struct *p, struct seq_file *m)
 {
 #ifdef CONFIG_NUMA_BALANCING
         struct mempolicy *pol;
-        int node, i;
 
         if (p->mm)
                 P(mm->numa_scan_seq);
@@ -533,26 +543,12 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m)
         mpol_get(pol);
         task_unlock(p);
 
-        SEQ_printf(m, "numa_migrations, %ld\n", xchg(&p->numa_pages_migrated, 0));
-
-        for_each_online_node(node) {
-                for (i = 0; i < 2; i++) {
-                        unsigned long nr_faults = -1;
-                        int cpu_current, home_node;
-
-                        if (p->numa_faults)
-                                nr_faults = p->numa_faults[2*node + i];
-
-                        cpu_current = !i ? (task_node(p) == node) :
-                                (pol && node_isset(node, pol->v.nodes));
-
-                        home_node = (p->numa_preferred_nid == node);
-
-                        SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n",
-                                i, node, cpu_current, home_node, nr_faults);
-                }
-        }
-
+        P(numa_pages_migrated);
+        P(numa_preferred_nid);
+        P(total_numa_faults);
+        SEQ_printf(m, "current_node=%d, numa_group_id=%d\n",
+                        task_node(p), task_numa_group_id(p));
+        show_numa_stats(p, m);
         mpol_put(pol);
 #endif
 }