Re: [RFI] Shared accounting for memory resource controller

[KAMEZAWA Hiroyuki]

On Tue, 7 Apr 2009 13:33:55 +0530
Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx> wrote:

> * KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> [2009-04-07 16:33:31]:
> 
> > On Tue, 7 Apr 2009 12:48:25 +0530
> > Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx> wrote:
> > 
> > > * KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> [2009-04-07 16:00:14]:
> > > 
> > > > On Tue, 7 Apr 2009 12:07:22 +0530
> > > > Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx> wrote:
> > > > 
> > > > > Hi, All,
> > > > > 
> > > > > This is a request for input for the design of shared page accounting for
> > > > > the memory resource controller, here is what I have so far
> > > > > 
> > > > 
> > > > In my first impression, I think simple counting is impossible.
> > > > IOW, "usage count" and "shared or not" is very different problem.
> > > > 
> > > > Assume a page and its page_cgroup.
> > > > 
> > > > Case 1)
> > > >   1. a page is mapped by process-X under group-A
> > > >   2. its mapped by process-Y in group-B (now, shared and charged under group-A)
> > > >   3. move process-X to group-B
> > > >   4. now the page is not shared.
> > > > 
> > > 
> > > By shared I don't mean only between cgroups, it could be a page shared
> > > in the same cgroup
> > > 
> > Hmm, is it good information ?
> > 
> > Such kind of information can be calucated by
> > ==
> >    rss = 0;
> >    for_each_process_under_cgroup() {
> >        mm = tsk->mm
> >        rss += mm->anon_rss;
> >    }
> >    some_of_all_rss = rss;
> >    
> >    shared_ratio = mem_cgrou->rss *100 / some_of_all_rss.
> > ==
> >    if 100%, all anon memory are not shared.
> >
> 
> Why only anon? 

no serious intention.
Just because you wrote "expect the user to account all cached pages as shared" ;)

> This seems like a good idea, except when we have a page
> charged to a cgroup and the task that charged it has migrated, in that
> case sum_of_all_rss will be 0.
> 
Yes. But we don't move pages at task-move under expectation that moved
process will call fork() soon.
"task move" has its own problem, so ignoring it for now is a choice.
That kind of troubls can be treated when we fixes "task move".
(or fix "task move" first.)

Thanks,
-Kame

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/