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.au
Signed-off-by: Ebru Akagunduz <ebru.akagunduz@gmail.com>
Acked-by: Rik 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: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
index 551ba4a..fad6539 100644
--- a/include/trace/events/huge_memory.h
+++ b/include/trace/events/huge_memory.h
@@ -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 @@
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 @@
__field(bool, referenced)
__field(int, none_or_zero)
__field(int, status)
+ __field(int, unmapped)
),
TP_fast_assign(
@@ -65,15 +67,17 @@
__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,