Re: [PATCH 11/11] blkcg: implement per-blkg request allocation

[Vivek Goyal <vgoyal-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>]

On Fri, Apr 27, 2012 at 11:56:12AM -0400, Vivek Goyal wrote:
> On Fri, Apr 27, 2012 at 08:51:40AM -0700, Tejun Heo wrote:
> > On Fri, Apr 27, 2012 at 11:48:41AM -0400, Vivek Goyal wrote:
> > > Not an unpriviliged malicious application. In typical cgroup scenario, we
> > > can allow unpriviliged users to create child cgroups so that it can
> > > further subdivide its resources to its children group. (ex. put firefox
> > > in one cgroup, open office in another group etc.).
> > > 
> > > So it is not same as jack up nr_requests.
> > 
> > I find allowing unpriv users creating cgroups dumb.  cgroup consumes
> > kernel memory.  Sans using kmemcg, what prevents them from creating
> > gazillion cgroups and consuming all memories?  The idea of allowing
> > cgroups to !priv users is just broken from the get go.
> 
> Well creating a task consumes memory too but we allow unpriv users to
> create tasks. :-)

Well, kernel can kill tasks and reclaim that memory so this is not an
appropriate example. 

A more suitable example probably is AIO where kernel pins down some
memory and we limit that amount by upper limit on number of aio requests.

Thanks
Vivek