From: Yang Yang <yang.yang29@xxxxxxxxxx>
Users may use ksm by calling madvise(, , MADV_MERGEABLE) when they want
to save memory, it's a tradeoff by suffering delay on ksm cow. Users can
get to know how much memory ksm saved by reading
/sys/kernel/mm/ksm/pages_sharing, but they don't know what's the costs
of ksm cow, and this is important of some delay sensitive tasks.
So add ksm cow events to help users evaluate whether or how to use ksm.
Signed-off-by: Yang Yang <yang.yang29@xxxxxxxxxx>
Reviewed-by: David Hildenbrand <david@xxxxxxxxxx>
Reviewed-by: xu xin <xu.xin16@xxxxxxxxxx>
Reviewed-by: Ran Xiaokai <ran.xiaokai@xxxxxxxxxx>
---
v2:
- fix compile error when CONFIG_KSM is not set
v3:
- delete KSM_COW_FAIL event
---
include/linux/vm_event_item.h | 1 +
mm/memory.c | 4 ++++
mm/vmstat.c | 1 +
3 files changed, 6 insertions(+)
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 16a0a4fd000b..d817ba541851 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -131,6 +131,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
SWAP_RA_HIT,
#ifdef CONFIG_KSM
KSM_SWPIN_COPY,
+ COW_KSM,
#endif
#endif
#ifdef CONFIG_X86
diff --git a/mm/memory.c b/mm/memory.c
index 4111f97c91a0..12925ceaf745 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3339,6 +3339,10 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
get_page(vmf->page);
pte_unmap_unlock(vmf->pte, vmf->ptl);
+#ifdef CONFIG_KSM
+ if (PageKsm(vmf->page))
+ count_vm_event(COW_KSM);
+#endif
return wp_page_copy(vmf);
}
diff --git a/mm/vmstat.c b/mm/vmstat.c
index d5cc8d739fac..710d71af2285 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1390,6 +1390,7 @@ const char * const vmstat_text[] = {
"swap_ra_hit",
#ifdef CONFIG_KSM
"ksm_swpin_copy",
+ "cow_ksm",
#endif
#endif
#ifdef CONFIG_X86
--
2.25.1
