Documentation/vm/transhuge.txt: add information about max_ptes_swap
max_ptes_swap specifies how many pages can be brought in from swap when
collapsing a group of pages into a transparent huge page.
/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_swap
A higher value can cause excessive swap IO and waste memory. A lower
value can prevent THPs from being collapsed, resulting fewer pages being
collapsed into THPs, and lower memory access performance.
Signed-off-by: Ebru Akagunduz <[email protected]>
Acked-by: Rik van Riel <[email protected]>
Acked-by: David Rientjes <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Cc: Kirill A. Shutemov <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt
index 8143b9e..8a28268 100644
--- a/Documentation/vm/transhuge.txt
+++ b/Documentation/vm/transhuge.txt
@@ -170,6 +170,16 @@
max_ptes_none can waste cpu time very little, you can
ignore it.
+max_ptes_swap specifies how many pages can be brought in from
+swap when collapsing a group of pages into a transparent huge page.
+
+/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_swap
+
+A higher value can cause excessive swap IO and waste
+memory. A lower value can prevent THPs from being
+collapsed, resulting fewer pages being collapsed into
+THPs, and lower memory access performance.
+
== Boot parameter ==
You can change the sysfs boot time defaults of Transparent Hugepage