summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorRik van Riel <riel@redhat.com>2013-10-07 11:29:39 +0100
committerIngo Molnar <mingo@kernel.org>2013-10-09 14:48:21 +0200
commitde1c9ce6f07fec0381a39a9d0b379ea35aa1167f (patch)
treed96bf1a2b25dfa84d3fe5f6fe00fb780800e3ef3 /kernel
parent1e3646ffc64b232cb14a5ef01d7b98997c1b73f9 (diff)
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 'kernel')
-rw-r--r--kernel/sched/fair.c8
-rw-r--r--kernel/sysctl.c7
2 files changed, 15 insertions, 0 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8454c38b1b12..e7884dc3416d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -833,6 +833,14 @@ unsigned int sysctl_numa_balancing_scan_size = 256;
/* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
unsigned int sysctl_numa_balancing_scan_delay = 1000;
+/*
+ * After skipping a page migration on a shared page, skip N more numa page
+ * migrations unconditionally. This reduces the number of NUMA migrations
+ * in shared memory workloads, and has the effect of pulling tasks towards
+ * where their memory lives, over pulling the memory towards the task.
+ */
+unsigned int sysctl_numa_balancing_migrate_deferred = 16;
+
static unsigned int task_nr_scan_windows(struct task_struct *p)
{
unsigned long rss = 0;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index e509b90a8002..a159e1fd2013 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -391,6 +391,13 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "numa_balancing_migrate_deferred",
+ .data = &sysctl_numa_balancing_migrate_deferred,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_SCHED_DEBUG */
{