sched/numa: Stay on the same node if CLONE_VM

A newly spawned thread inside a process should stay on the same
NUMA node as its parent. This prevents processes from being "torn"
across multiple NUMA nodes every time they spawn a new thread.

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/1381141781-10992-49-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index ff54385..8563e3d 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2021,7 +2021,7 @@ extern void wake_up_new_task(struct task_struct *tsk);
 #else
  static inline void kick_process(struct task_struct *tsk) { }
 #endif
-extern void sched_fork(struct task_struct *p);
+extern void sched_fork(unsigned long clone_flags, struct task_struct *p);
 extern void sched_dead(struct task_struct *p);
 
 extern void proc_caches_init(void);

diff --git a/kernel/fork.c b/kernel/fork.c
index 7192d91..c93be06 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1310,7 +1310,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 
        /* Perform scheduler related setup. Assign this task to a CPU. */
-       sched_fork(p);
+       sched_fork(clone_flags, p);
 
        retval = perf_event_init_task(p);
        if (retval)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 51092d5..3e2c893 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1696,7 +1696,7 @@ int wake_up_state(struct task_struct *p, unsigned int state)
  *
  * __sched_fork() is basic setup used by init_idle() too:
  */
-static void __sched_fork(struct task_struct *p)
+static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
        p->on_rq                        = 0;
 
@@ -1725,11 +1725,15 @@ static void __sched_fork(struct task_struct *p)
                p->mm->numa_scan_seq = 0;
        }
 
+       if (clone_flags & CLONE_VM)
+               p->numa_preferred_nid = current->numa_preferred_nid;
+       else
+               p->numa_preferred_nid = -1;
+
        p->node_stamp = 0ULL;
        p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
        p->numa_migrate_seq = 1;
        p->numa_scan_period = sysctl_numa_balancing_scan_delay;
-       p->numa_preferred_nid = -1;
        p->numa_work.next = &p->numa_work;
        p->numa_faults = NULL;
        p->numa_faults_buffer = NULL;
@@ -1761,12 +1765,12 @@ void set_numabalancing_state(bool enabled)
 /*
  * fork()/clone()-time setup:
  */
-void sched_fork(struct task_struct *p)
+void sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
        unsigned long flags;
        int cpu = get_cpu();
 
-       __sched_fork(p);
+       __sched_fork(clone_flags, p);
        /*
         * We mark the process as running here. This guarantees that
         * nobody will actually run it, and a signal or other external
@@ -4287,7 +4291,7 @@ void init_idle(struct task_struct *idle, int cpu)
 
        raw_spin_lock_irqsave(&rq->lock, flags);
 
-       __sched_fork(idle);
+       __sched_fork(0, idle);
        idle->state = TASK_RUNNING;
        idle->se.exec_start = sched_clock();