On Wed 23-11-16 15:36:51, Balbir Singh wrote: > In the absence of hotplug we use extra memory proportional to > (possible_nodes - online_nodes) * number_of_cgroups. PPC64 has a patch > to disable large consumption with large number of cgroups. This patch > adds hotplug support to memory cgroups and reverts the commit that > limited possible nodes to online nodes.
Balbir, I have asked this in the previous version but there still seems to be a lack of information of _why_ do we want this, _how_ much do we save on the memory overhead on most systems and _why_ the additional complexity is really worth it. Please make sure to add all this in the cover letter. I still didn't get to look into those patches because I am swamped with other things but to be honest I do not really see a strong justification to make it high priority for me. > Cc: Tejun Heo <t...@kernel.org> > Cc: Andrew Morton <a...@linux-foundation.org> > Cc: Johannes Weiner <han...@cmpxchg.org> > Cc: Michal Hocko <mho...@kernel.org> > Cc: Vladimir Davydov <vdavydov....@gmail.com> > > I've tested this patches under a VM with two nodes and movable > nodes enabled. I've offlined nodes and checked that the system > and cgroups with tasks deep in the hierarchy continue to work > fine. > > These patches are on top of linux-next (20161117) > > Changelog v2: > Add get/put_online_mems() around node iteration > Use MEM_OFFLINE/MEM_ONLINE instead of MEM_GOING_OFFLINE/ONLINE > > Balbir Singh (3): > mm: Add basic infrastructure for memcg hotplug support > mm: Move operations to hotplug callbacks > powerpc/mm: fix node_possible_map limitations > > arch/powerpc/mm/numa.c | 7 ---- > mm/memcontrol.c | 107 > +++++++++++++++++++++++++++++++++++++++++++------ > 2 files changed, 94 insertions(+), 20 deletions(-) > > -- > 2.5.5 -- Michal Hocko SUSE Labs
