hc
2024-02-20 102a0743326a03cd1a1202ceda21e175b7d3575c
kernel/Documentation/admin-guide/cgroup-v1/memory.rst
....@@ -82,6 +82,8 @@
8282 memory.swappiness set/show swappiness parameter of vmscan
8383 (See sysctl's vm.swappiness)
8484 memory.move_charge_at_immigrate set/show controls of moving charges
85
+ This knob is deprecated and shouldn't be
86
+ used.
8587 memory.oom_control set/show oom controls.
8688 memory.numa_stat show the number of memory usage per numa
8789 node
....@@ -740,8 +742,15 @@
740742 It is recommended to set the soft limit always below the hard limit,
741743 otherwise the hard limit will take precedence.
742744
743
-8. Move charges at task migration
744
-=================================
745
+8. Move charges at task migration (DEPRECATED!)
746
+===============================================
747
+
748
+THIS IS DEPRECATED!
749
+
750
+It's expensive and unreliable! It's better practice to launch workload
751
+tasks directly from inside their target cgroup. Use dedicated workload
752
+cgroups to allow fine-grained policy adjustments without having to
753
+move physical pages between control domains.
745754
746755 Users can move charges associated with a task along with task migration, that
747756 is, uncharge task's pages from the old cgroup and charge them to the new cgroup.