sched/numa: Adjust scan rate in task_numa_placement

Adjust numa_scan_period in task_numa_placement, depending on how much
useful work the numa code can do. The more local faults there are in a
given scan window the longer the period (and hence the slower the scan rate)
during the next window. If there are excessive shared faults then the scan
period will decrease with the amount of scaling depending on whether the
ratio of shared/private faults. If the preferred node changes then the
scan rate is reset to recheck if the task is properly placed.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-59-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 9 insertions, 0 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 59f953b2e413..2292f6c1596f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1365,6 +1365,14 @@ struct task_struct {
          */
         unsigned long *numa_faults_buffer;
 
+        /*
+         * numa_faults_locality tracks if faults recorded during the last
+         * scan window were remote/local. The task scan period is adapted
+         * based on the locality of the faults with different weights
+         * depending on whether they were shared or private faults
+         */
+        unsigned long numa_faults_locality[2];
+
         int numa_preferred_nid;
         unsigned long numa_pages_migrated;
 #endif /* CONFIG_NUMA_BALANCING */
@@ -1455,6 +1463,7 @@ struct task_struct {
 #define TNF_MIGRATED    0x01
 #define TNF_NO_GROUP    0x02
 #define TNF_SHARED      0x04
+#define TNF_FAULT_LOCAL 0x08
 
 #ifdef CONFIG_NUMA_BALANCING
 extern void task_numa_fault(int last_node, int node, int pages, int flags);