[PATCH 3/3] docs/admin-guide/cgroup-v2: add cpuset.mems.migration

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Add docs for new interface cpuset.mems.migration, most of which
are stolen from cpuset(7) manpages.

Signed-off-by: Abel Wu <wuyun.abel@xxxxxxxxxxxxx>
---
 Documentation/admin-guide/cgroup-v2.rst | 36 +++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index b1e81aa8598a..abf6589a390d 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -2079,6 +2079,42 @@ Cpuset Interface Files
 	Changing the partition state of an invalid partition root to
 	"member" is always allowed even if child cpusets are present.
 
+  cpuset.mems.migration
+	A read-write single value file which exists on non-root
+	cpuset-enabled cgroups.
+
+	Only the following migration modes are defined.
+
+	  ========	==========================================
+	  "none"	migration disabled [default]
+	  "sync"	move pages to cpuset nodes synchronously
+	  "lazy"	move pages to cpuset nodes on second touch
+	  ========	==========================================
+
+	By default, "none" mode is enabled. In this mode, once a page
+	is allocated (given a physical page of main memory) then that
+	page stays on whatever node it was allocated, so long as it
+	remains allocated, even if the cpusets memory placement policy
+	'cpuset.mems' subsequently changes.
+
+	If "sync" mode is enabled in a cpuset, when the 'cpuset.mems'
+	setting is changed, any memory page in use by any process in
+	the cpuset that is on a memory node that is no longer allowed
+	will be migrated to a memory node that is allowed synchronously.
+	The relative placement of a migrated page within the cpuset is
+	preserved during these migration operations if possible.
+
+	The "lazy" mode is almost the same as "sync" mode, except that
+	it doesn't move the pages right away. Instead it sets these
+	pages to protnone, and numa faults triggered by second touching
+	these pages will handle the movement.
+
+	Furthermore, if a process is moved into a cpuset with migration
+	enabled ("sync" or "lazy" enabled), any memory pages it uses
+	that on memory nodes allowed in its previous cpuset, but which
+	are not allowed in its new cpuset, will be migrated to a memory
+	node allowed in the new cpuset.
+
 
 Device controller
 -----------------
-- 
2.31.1




[Index of Archives]     [Kernel Newbies]     [Security]     [Netfilter]     [Bugtraq]     [Linux FS]     [Yosemite Forum]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Samba]     [Video 4 Linux]     [Device Mapper]     [Linux Resources]

  Powered by Linux