summaryrefslogtreecommitdiff
path: root/include/linux/sched.h
diff options
context:
space:
mode:
authorRik van Riel <riel@redhat.com>2013-10-07 14:29:39 +0400
committerIngo Molnar <mingo@kernel.org>2013-10-09 16:48:21 +0400
commitde1c9ce6f07fec0381a39a9d0b379ea35aa1167f (patch)
treed96bf1a2b25dfa84d3fe5f6fe00fb780800e3ef3 /include/linux/sched.h
parent1e3646ffc64b232cb14a5ef01d7b98997c1b73f9 (diff)
downloadlinux-de1c9ce6f07fec0381a39a9d0b379ea35aa1167f.tar.xz
sched/numa: Skip some page migrations after a shared fault
Shared faults can lead to lots of unnecessary page migrations, slowing down the system, and causing private faults to hit the per-pgdat migration ratelimit. This patch adds sysctl numa_balancing_migrate_deferred, which specifies how many shared page migrations to skip unconditionally, after each page migration that is skipped because it is a shared fault. This reduces the number of page migrations back and forth in shared fault situations. It also gives a strong preference to the tasks that are already running where most of the memory is, and to moving the other tasks to near the memory. Testing this with a much higher scan rate than the default still seems to result in fewer page migrations than before. Memory seems to be somewhat better consolidated than previously, with multi-instance specjbb runs on a 4 node system. 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/1381141781-10992-62-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'include/linux/sched.h')
-rw-r--r--include/linux/sched.h5
1 files changed, 4 insertions, 1 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d24f70ffddee..833eed55cf43 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1342,6 +1342,8 @@ struct task_struct {
int numa_scan_seq;
unsigned int numa_scan_period;
unsigned int numa_scan_period_max;
+ int numa_preferred_nid;
+ int numa_migrate_deferred;
unsigned long numa_migrate_retry;
u64 node_stamp; /* migration stamp */
struct callback_head numa_work;
@@ -1372,7 +1374,6 @@ struct task_struct {
*/
unsigned long numa_faults_locality[2];
- int numa_preferred_nid;
unsigned long numa_pages_migrated;
#endif /* CONFIG_NUMA_BALANCING */
@@ -1469,6 +1470,8 @@ extern void task_numa_fault(int last_node, int node, int pages, int flags);
extern pid_t task_numa_group_id(struct task_struct *p);
extern void set_numabalancing_state(bool enabled);
extern void task_numa_free(struct task_struct *p);
+
+extern unsigned int sysctl_numa_balancing_migrate_deferred;
#else
static inline void task_numa_fault(int last_node, int node, int pages,
int flags)