[PATCH][RFC] dirty balancing for cgroups
yamamoto at valinux.co.jp
Thu Jul 10 22:59:26 PDT 2008
> > > - This looks simple but, could you merge this into memory resource controller ?
> > why?
> 3 points.
> 1. Is this useful if used alone ?
it can be. why not?
> 2. memcg requires this kind of feature, basically.
> 3. I wonder I need more work to make this work well under memcg.
i'm not sure if i understand these points. can you explain a bit?
my patch penalizes heavy-writer cgroups as task_dirty_limit does
for heavy-writer tasks. i don't think that it's necessary to be
tied to the memory subsystem because i merely want to group writers.
otoh, if you want to limit the number (or percentage or whatever) of
dirty pages in a memory cgroup, it can't be done independently from
the memory subsystem, of course. it's another story, tho.
> If chasing page->cgroup and memcg make this patch much more complex,
> I think this style of implimentation is a choice.
> About 3.
> Does this works well if I changes get_dirty_limit()'s
> determine_dirtyable_memory() calculation under memcg ?
> But to do this seems not valid if dirty_ratio cgroup and memcg cgroup
> containes different set of tasks.
More information about the Containers