summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorMel Gorman <mgorman@suse.de>2013-10-07 11:28:53 +0100
committerIngo Molnar <mingo@kernel.org>2013-10-09 12:40:17 +0200
commitb726b7dfb400c937546fa91cf8523dcb1aa2fc6e (patch)
treeb4a6f741b630bb22568536860f3f46e94c4e8904 /kernel
parent9e645ab6d089f5822479a833c6977c785bcfffe3 (diff)
downloadlinux-stable-b726b7dfb400c937546fa91cf8523dcb1aa2fc6e.tar.gz
linux-stable-b726b7dfb400c937546fa91cf8523dcb1aa2fc6e.tar.bz2
linux-stable-b726b7dfb400c937546fa91cf8523dcb1aa2fc6e.zip
Revert "mm: sched: numa: Delay PTE scanning until a task is scheduled on a new node"
PTE scanning and NUMA hinting fault handling is expensive so commit 5bca2303 ("mm: sched: numa: Delay PTE scanning until a task is scheduled on a new node") deferred the PTE scan until a task had been scheduled on another node. The problem is that in the purely shared memory case that this may never happen and no NUMA hinting fault information will be captured. We are not ruling out the possibility that something better can be done here but for now, this patch needs to be reverted and depend entirely on the scan_delay to avoid punishing short-lived processes. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> 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/1381141781-10992-16-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/fork.c3
-rw-r--r--kernel/sched/fair.c18
-rw-r--r--kernel/sched/features.h4
3 files changed, 1 insertions, 24 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index 086fe73ad6bd..7192d91b5415 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -817,9 +817,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
mm->pmd_huge_pte = NULL;
#endif
-#ifdef CONFIG_NUMA_BALANCING
- mm->first_nid = NUMA_PTE_SCAN_INIT;
-#endif
if (!mm_init(mm, tsk))
goto fail_nomem;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 464207fc9eef..49b11faa2961 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -901,24 +901,6 @@ void task_numa_work(struct callback_head *work)
return;
/*
- * We do not care about task placement until a task runs on a node
- * other than the first one used by the address space. This is
- * largely because migrations are driven by what CPU the task
- * is running on. If it's never scheduled on another node, it'll
- * not migrate so why bother trapping the fault.
- */
- if (mm->first_nid == NUMA_PTE_SCAN_INIT)
- mm->first_nid = numa_node_id();
- if (mm->first_nid != NUMA_PTE_SCAN_ACTIVE) {
- /* Are we running on a new node yet? */
- if (numa_node_id() == mm->first_nid &&
- !sched_feat_numa(NUMA_FORCE))
- return;
-
- mm->first_nid = NUMA_PTE_SCAN_ACTIVE;
- }
-
- /*
* Reset the scan period if enough time has gone by. Objective is that
* scanning will be reduced if pages are properly placed. As tasks
* can enter different phases this needs to be re-examined. Lacking
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 99399f8e4799..cba5c616a157 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -63,10 +63,8 @@ SCHED_FEAT(LB_MIN, false)
/*
* Apply the automatic NUMA scheduling policy. Enabled automatically
* at runtime if running on a NUMA machine. Can be controlled via
- * numa_balancing=. Allow PTE scanning to be forced on UMA machines
- * for debugging the core machinery.
+ * numa_balancing=
*/
#ifdef CONFIG_NUMA_BALANCING
SCHED_FEAT(NUMA, false)
-SCHED_FEAT(NUMA_FORCE, false)
#endif