There is a 90% regression observed with a large Oracle performance test
on a 4 node system. Profiles indicated that the overhead was due to
contention on sp_lock when looking up shared memory policies. These
policies do not have the appropriate flags to allow them to be
automatically balanced so trapping faults on them is pointless. This
patch skips VMAs that do not have MPOL_F_MOF set.

[[email protected]: Initial patch]
Reviewed-by: Rik van Riel <[email protected]>
Reported-and-tested-by: Joe Mario <[email protected]>
Signed-off-by: Mel Gorman <[email protected]>
---
 include/linux/mempolicy.h |  1 +
 kernel/sched/fair.c       |  2 +-
 mm/mempolicy.c            | 24 ++++++++++++++++++++++++
 3 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 0d7df39..f6b2c4d 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -136,6 +136,7 @@ struct mempolicy *mpol_shared_policy_lookup(struct 
shared_policy *sp,
 
 struct mempolicy *get_vma_policy(struct task_struct *tsk,
                struct vm_area_struct *vma, unsigned long addr);
+bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma);
 
 extern void numa_default_policy(void);
 extern void numa_policy_init(void);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f136057..f9329d5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1130,7 +1130,7 @@ void task_numa_work(struct callback_head *work)
                vma = mm->mmap;
        }
        for (; vma; vma = vma->vm_next) {
-               if (!vma_migratable(vma))
+               if (!vma_migratable(vma) || !vma_policy_mof(p, vma))
                        continue;
 
                do {
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index adc93b2..54004a8 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1633,6 +1633,30 @@ struct mempolicy *get_vma_policy(struct task_struct 
*task,
        return pol;
 }
 
+bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma)
+{
+       struct mempolicy *pol = get_task_policy(task);
+       if (vma) {
+               if (vma->vm_ops && vma->vm_ops->get_policy) {
+                       bool ret = false;
+
+                       pol = vma->vm_ops->get_policy(vma, vma->vm_start);
+                       if (pol && (pol->flags & MPOL_F_MOF))
+                               ret = true;
+                       mpol_cond_put(pol);
+
+                       return ret;
+               } else if (vma->vm_policy) {
+                       pol = vma->vm_policy;
+               }
+       }
+
+       if (!pol)
+               return default_policy.flags & MPOL_F_MOF;
+
+       return pol->flags & MPOL_F_MOF;
+}
+
 static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone)
 {
        enum zone_type dynamic_policy_zone = policy_zone;
-- 
1.8.1.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to