On Tue, 30 Mar 2010 10:33:01 +0900 Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx> wrote: > On Mon, 29 Mar 2010 13:36:45 +0900, KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> wrote: > > Hmm...then, a shmem page is moved even if the task doesn't do page-fault. > > Could you clarify > > "All pages in the range mapped by a task will be moved to the new group > > even if the task doesn't do page fault, i.e. not tasks' RSS." > > ? > I see. > > This is the updated version. > > === > From: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx> > > This patch adds support for moving charge of shmem and swap of it. It's enabled > by setting bit 2 of <target cgroup>/memory.move_charge_at_immigrate. > > Signed-off-by: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> BTW, I'm glad if I can see some clean up around migrations. Total clean up after all necessary functions will be good. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxxx For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>