mm: add VM counters for transparent hugepages

I found it difficult to make sense of transparent huge pages without
having any counters for its actions.  Add some counters to vmstat for
allocation of transparent hugepages and fallback to smaller pages.

Optional patch, but useful for development and understanding the system.

Contains improvements from Andrea Arcangeli and Johannes Weiner

[akpm@linux-foundation.org: coding-style fixes]
[hannes@cmpxchg.org: fix vmstat_text[] entries]
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 461c011..2b3831b 100644 (file)
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -58,6 +58,13 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
                UNEVICTABLE_PGCLEARED,  /* on COW, page truncate */
                UNEVICTABLE_PGSTRANDED, /* unable to isolate on unlock */
                UNEVICTABLE_MLOCKFREED,
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+               THP_FAULT_ALLOC,
+               THP_FAULT_FALLBACK,
+               THP_COLLAPSE_ALLOC,
+               THP_COLLAPSE_ALLOC_FAILED,
+               THP_SPLIT,
+#endif
                NR_VM_EVENT_ITEMS
 };
 

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 0a619e0..1722683 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -680,8 +680,11 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
                        return VM_FAULT_OOM;
                page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
                                          vma, haddr, numa_node_id(), 0);
-               if (unlikely(!page))
+               if (unlikely(!page)) {
+                       count_vm_event(THP_FAULT_FALLBACK);
                        goto out;
+               }
+               count_vm_event(THP_FAULT_ALLOC);
                if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
                        put_page(page);
                        goto out;
@@ -909,11 +912,13 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
                new_page = NULL;
 
        if (unlikely(!new_page)) {
+               count_vm_event(THP_FAULT_FALLBACK);
                ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
                                                   pmd, orig_pmd, page, haddr);
                put_page(page);
                goto out;
        }
+       count_vm_event(THP_FAULT_ALLOC);
 
        if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
                put_page(new_page);
@@ -1390,6 +1395,7 @@ int split_huge_page(struct page *page)
 
        BUG_ON(!PageSwapBacked(page));
        __split_huge_page(page, anon_vma);
+       count_vm_event(THP_SPLIT);
 
        BUG_ON(PageCompound(page));
 out_unlock:
@@ -1784,9 +1790,11 @@ static void collapse_huge_page(struct mm_struct *mm,
                                      node, __GFP_OTHER_NODE);
        if (unlikely(!new_page)) {
                up_read(&mm->mmap_sem);
+               count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
                *hpage = ERR_PTR(-ENOMEM);
                return;
        }
+       count_vm_event(THP_COLLAPSE_ALLOC);
        if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
                up_read(&mm->mmap_sem);
                put_page(new_page);
@@ -2151,8 +2159,11 @@ static void khugepaged_do_scan(struct page **hpage)
 #ifndef CONFIG_NUMA
                if (!*hpage) {
                        *hpage = alloc_hugepage(khugepaged_defrag());
-                       if (unlikely(!*hpage))
+                       if (unlikely(!*hpage)) {
+                               count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
                                break;
+                       }
+                       count_vm_event(THP_COLLAPSE_ALLOC);
                }
 #else
                if (IS_ERR(*hpage))
@@ -2192,8 +2203,11 @@ static struct page *khugepaged_alloc_hugepage(void)
 
        do {
                hpage = alloc_hugepage(khugepaged_defrag());
-               if (!hpage)
+               if (!hpage) {
+                       count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
                        khugepaged_alloc_sleep();
+               } else
+                       count_vm_event(THP_COLLAPSE_ALLOC);
        } while (unlikely(!hpage) &&
                 likely(khugepaged_enabled()));
        return hpage;
@@ -2210,8 +2224,11 @@ static void khugepaged_loop(void)
        while (likely(khugepaged_enabled())) {
 #ifndef CONFIG_NUMA
                hpage = khugepaged_alloc_hugepage();
-               if (unlikely(!hpage))
+               if (unlikely(!hpage)) {
+                       count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
                        break;
+               }
+               count_vm_event(THP_COLLAPSE_ALLOC);
 #else
                if (IS_ERR(hpage)) {
                        khugepaged_alloc_sleep();

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 8cb0f0a..897ea9e 100644 (file)
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -948,7 +948,16 @@ static const char * const vmstat_text[] = {
        "unevictable_pgs_cleared",
        "unevictable_pgs_stranded",
        "unevictable_pgs_mlockfreed",
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+       "thp_fault_alloc",
+       "thp_fault_fallback",
+       "thp_collapse_alloc",
+       "thp_collapse_alloc_failed",
+       "thp_split",
 #endif
+
+#endif /* CONFIG_VM_EVENTS_COUNTERS */
 };
 
 static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,