Commit 70652f6e authored by Ebru Akagunduz's avatar Ebru Akagunduz Committed by Linus Torvalds

mm: make optimistic check for swapin readahead

Introduce a new sysfs integer knob
/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_swap which makes
optimistic check for swapin readahead to increase thp collapse rate.
Before getting swapped out pages to memory, checks them and allows up to a
certain number.  It also prints out using tracepoints amount of unmapped
ptes.

[vdavydov@parallels.com: fix scan not aborted on SCAN_EXCEED_SWAP_PTE]
[sfr@canb.auug.org.au: build fix]
  Link: http://lkml.kernel.org/r/20160616154503.65806e12@canb.auug.org.auSigned-off-by: default avatarEbru Akagunduz <ebru.akagunduz@gmail.com>
Acked-by: default avatarRik van Riel <riel@redhat.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Xie XiuQi <xiexiuqi@huawei.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: David Rientjes <rientjes@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: default avatarStephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent ef3cc4db
......@@ -28,7 +28,8 @@
EM( SCAN_SWAP_CACHE_PAGE, "page_swap_cache") \
EM( SCAN_DEL_PAGE_LRU, "could_not_delete_page_from_lru")\
EM( SCAN_ALLOC_HUGE_PAGE_FAIL, "alloc_huge_page_failed") \
EMe( SCAN_CGROUP_CHARGE_FAIL, "ccgroup_charge_failed")
EM( SCAN_CGROUP_CHARGE_FAIL, "ccgroup_charge_failed") \
EMe( SCAN_EXCEED_SWAP_PTE, "exceed_swap_pte")
#undef EM
#undef EMe
......@@ -45,9 +46,9 @@ SCAN_STATUS
TRACE_EVENT(mm_khugepaged_scan_pmd,
TP_PROTO(struct mm_struct *mm, struct page *page, bool writable,
bool referenced, int none_or_zero, int status),
bool referenced, int none_or_zero, int status, int unmapped),
TP_ARGS(mm, page, writable, referenced, none_or_zero, status),
TP_ARGS(mm, page, writable, referenced, none_or_zero, status, unmapped),
TP_STRUCT__entry(
__field(struct mm_struct *, mm)
......@@ -56,6 +57,7 @@ TRACE_EVENT(mm_khugepaged_scan_pmd,
__field(bool, referenced)
__field(int, none_or_zero)
__field(int, status)
__field(int, unmapped)
),
TP_fast_assign(
......@@ -65,15 +67,17 @@ TRACE_EVENT(mm_khugepaged_scan_pmd,
__entry->referenced = referenced;
__entry->none_or_zero = none_or_zero;
__entry->status = status;
__entry->unmapped = unmapped;
),
TP_printk("mm=%p, scan_pfn=0x%lx, writable=%d, referenced=%d, none_or_zero=%d, status=%s",
TP_printk("mm=%p, scan_pfn=0x%lx, writable=%d, referenced=%d, none_or_zero=%d, status=%s, unmapped=%d",
__entry->mm,
__entry->pfn,
__entry->writable,
__entry->referenced,
__entry->none_or_zero,
__print_symbolic(__entry->status, SCAN_STATUS))
__print_symbolic(__entry->status, SCAN_STATUS),
__entry->unmapped)
);
TRACE_EVENT(mm_collapse_huge_page,
......
......@@ -57,7 +57,8 @@ enum scan_result {
SCAN_SWAP_CACHE_PAGE,
SCAN_DEL_PAGE_LRU,
SCAN_ALLOC_HUGE_PAGE_FAIL,
SCAN_CGROUP_CHARGE_FAIL
SCAN_CGROUP_CHARGE_FAIL,
SCAN_EXCEED_SWAP_PTE
};
#define CREATE_TRACE_POINTS
......@@ -100,6 +101,7 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
* fault.
*/
static unsigned int khugepaged_max_ptes_none __read_mostly;
static unsigned int khugepaged_max_ptes_swap __read_mostly;
static int khugepaged(void *none);
static int khugepaged_slab_init(void);
......@@ -598,6 +600,33 @@ static struct kobj_attribute khugepaged_max_ptes_none_attr =
__ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show,
khugepaged_max_ptes_none_store);
static ssize_t khugepaged_max_ptes_swap_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
{
return sprintf(buf, "%u\n", khugepaged_max_ptes_swap);
}
static ssize_t khugepaged_max_ptes_swap_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
int err;
unsigned long max_ptes_swap;
err = kstrtoul(buf, 10, &max_ptes_swap);
if (err || max_ptes_swap > HPAGE_PMD_NR-1)
return -EINVAL;
khugepaged_max_ptes_swap = max_ptes_swap;
return count;
}
static struct kobj_attribute khugepaged_max_ptes_swap_attr =
__ATTR(max_ptes_swap, 0644, khugepaged_max_ptes_swap_show,
khugepaged_max_ptes_swap_store);
static struct attribute *khugepaged_attr[] = {
&khugepaged_defrag_attr.attr,
&khugepaged_max_ptes_none_attr.attr,
......@@ -606,6 +635,7 @@ static struct attribute *khugepaged_attr[] = {
&full_scans_attr.attr,
&scan_sleep_millisecs_attr.attr,
&alloc_sleep_millisecs_attr.attr,
&khugepaged_max_ptes_swap_attr.attr,
NULL,
};
......@@ -674,6 +704,7 @@ static int __init hugepage_init(void)
khugepaged_pages_to_scan = HPAGE_PMD_NR * 8;
khugepaged_max_ptes_none = HPAGE_PMD_NR - 1;
khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8;
/*
* hugepages can't be allocated by the buddy allocator
*/
......@@ -2507,7 +2538,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
struct page *page = NULL;
unsigned long _address;
spinlock_t *ptl;
int node = NUMA_NO_NODE;
int node = NUMA_NO_NODE, unmapped = 0;
bool writable = false, referenced = false;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
......@@ -2523,6 +2554,14 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR;
_pte++, _address += PAGE_SIZE) {
pte_t pteval = *_pte;
if (is_swap_pte(pteval)) {
if (++unmapped <= khugepaged_max_ptes_swap) {
continue;
} else {
result = SCAN_EXCEED_SWAP_PTE;
goto out_unmap;
}
}
if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
if (!userfaultfd_armed(vma) &&
++none_or_zero <= khugepaged_max_ptes_none) {
......@@ -2609,7 +2648,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
}
out:
trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,
none_or_zero, result);
none_or_zero, result, unmapped);
return ret;
}
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment