This patch makes swapin readahead to improve thp collapse rate.
When khugepaged scanned pages, there can be a few of the pages
in swap area.
With the patch THP can collapse 4kB pages into a THP when
there are up to max_ptes_swap swap ptes in a 2MB range.
The patch was tested with a test program that allocates
800MB of memory, writes to it, and then sleeps. I force
the system to swap out all. Afterwards, the test program
touches the area by writing, it skips a page in each
20 pages of the area.
Without the patch, system did not swap in readahead.
THP rate was %47 of the program of the memory, it
did not change over time.
With this patch, after 10 minutes of waiting khugepaged had
collapsed %99 of the program's memory.
Signed-off-by: Ebru Akagunduz <ebru.akagun...@gmail.com>
Acked-by: Rik van Riel <r...@redhat.com>
---
Changes in v2:
- Use FAULT_FLAG_ALLOW_RETRY|FAULT_FLAG_RETRY_NOWAIT flag
instead of 0x0 when called do_swap_page from
__collapse_huge_page_swapin (Rik van Riel)
Changes in v3:
- Catch VM_FAULT_HWPOISON and VM_FAULT_OOM return cases
in __collapse_huge_page_swapin (Kirill A. Shutemov)
Test results:
After swapped out
-------------------------------------------------------------------
| Anonymous | AnonHugePages | Swap | Fraction |
-------------------------------------------------------------------
With patch | 267128 kB | 266240 kB | 532876 kB | %99 |
-------------------------------------------------------------------
Without patch | 238160 kB | 235520 kB | 561844 kB | %98 |
-------------------------------------------------------------------
After swapped in
-------------------------------------------------------------------
| Anonymous | AnonHugePages | Swap | Fraction |
-------------------------------------------------------------------
With patch | 533876 kB | 530432 kB | 266128 kB | %99 |
-------------------------------------------------------------------
Without patch | 499956 kB | 235520 kB | 300048 kB | %47 |
-------------------------------------------------------------------
include/linux/mm.h | 4 ++++
include/trace/events/huge_memory.h | 24 ++++++++++++++++++++++
mm/huge_memory.c | 41 ++++++++++++++++++++++++++++++++++++++
mm/memory.c | 2 +-
4 files changed, 70 insertions(+), 1 deletion(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index eacf348..603f3ba 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -40,6 +40,10 @@
#define MM_COLLAPSE_ISOLATE_FAIL 5
#define MM_EXCEED_SWAP_PTE 2
+extern int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pte_t *page_table, pmd_t *pmd,
+ unsigned int flags, pte_t orig_pte);
+
struct mempolicy;
struct anon_vma;
struct anon_vma_chain;
diff --git a/include/trace/events/huge_memory.h
b/include/trace/events/huge_memory.h
index b6bdcc4..8d34086 100644
--- a/include/trace/events/huge_memory.h
+++ b/include/trace/events/huge_memory.h
@@ -98,6 +98,30 @@ TRACE_EVENT(mm_collapse_huge_page_isolate,
__entry->ret)
);
+TRACE_EVENT(mm_collapse_huge_page_swapin,
+
+ TP_PROTO(struct mm_struct *mm, int swap_pte, int ret),
+
+ TP_ARGS(mm, swap_pte, ret),
+
+ TP_STRUCT__entry(
+ __field(struct mm_struct *, mm)
+ __field(int, swap_pte)
+ __field(int, ret)
+ ),
+
+ TP_fast_assign(
+ __entry->mm = mm;
+ __entry->swap_pte = swap_pte;
+ __entry->ret = ret;
+ ),
+
+ TP_printk("mm=%p, swap_pte=%d, ret=%d",
+ __entry->mm,
+ __entry->swap_pte,
+ __entry->ret)
+);
+
#endif /* __HUGE_MEMORY_H */
#include <trace/define_trace.h>
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b4cef9d..b372b40 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2511,6 +2511,45 @@ static bool hugepage_vma_check(struct vm_area_struct
*vma)
return true;
}
+/*
+ * Bring missing pages in from swap, to complete THP collapse.
+ * Only done if khugepaged_scan_pmd believes it is worthwhile.
+ *
+ * Called and returns without pte mapped or spinlocks held,
+ * but with mmap_sem held to protect against vma changes.
+ */
+
+static void __collapse_huge_page_swapin(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmd,
+ pte_t *pte)
+{
+ unsigned long _address;
+ pte_t pteval = *pte;
+ int swap_pte = 0, ret = 0;
+
+ pte = pte_offset_map(pmd, address);
+ for (_address = address; _address < address + HPAGE_PMD_NR*PAGE_SIZE;
+ pte++, _address += PAGE_SIZE) {
+ pteval = *pte;
+ if (is_swap_pte(pteval)) {
+ swap_pte++;
+ ret = do_swap_page(mm, vma, _address, pte, pmd,
+ FAULT_FLAG_ALLOW_RETRY|FAULT_FLAG_RETRY_NOWAIT,
+ pteval);
+ if (ret == VM_FAULT_HWPOISON || ret == VM_FAULT_OOM) {
+ trace_mm_collapse_huge_page_swapin(mm,
vma->vm_start, swap_pte, 0);
+ return;
+ }
+ /* pte is unmapped now, we need to map it */
+ pte = pte_offset_map(pmd, _address);
+ }
+ }
+ pte--;
+ pte_unmap(pte);
+ trace_mm_collapse_huge_page_swapin(mm, swap_pte, 1);
+}
+
static void collapse_huge_page(struct mm_struct *mm,
unsigned long address,
struct page **hpage,
@@ -2584,6 +2623,8 @@ static void collapse_huge_page(struct mm_struct *mm,
anon_vma_lock_write(vma->anon_vma);
+ __collapse_huge_page_swapin(mm, vma, address, pmd, pte);
+
pte = pte_offset_map(pmd, address);
pte_ptl = pte_lockptr(mm, pmd);
diff --git a/mm/memory.c b/mm/memory.c
index 67afe75..eec23a2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2443,7 +2443,7 @@ EXPORT_SYMBOL(unmap_mapping_range);
* We return with the mmap_sem locked or unlocked in the same cases
* as does filemap_fault().
*/
-static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
+int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
unsigned int flags, pte_t orig_pte)
{
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
