Re: [RFC][PATCH 2/7] RSS controller core

[Balbir Singh]

On 3/11/07, Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> wrote:
> > On Sun, 11 Mar 2007 15:26:41 +0300 Kirill Korotaev <dev@xxxxx> wrote:
> > Andrew Morton wrote:
> > > On Tue, 06 Mar 2007 17:55:29 +0300
> > > Pavel Emelianov <xemul@xxxxx> wrote:
> > >
> > >
> > >>+struct rss_container {
> > >>+   struct res_counter res;
> > >>+   struct list_head page_list;
> > >>+   struct container_subsys_state css;
> > >>+};
> > >>+
> > >>+struct page_container {
> > >>+   struct page *page;
> > >>+   struct rss_container *cnt;
> > >>+   struct list_head list;
> > >>+};
> > >
> > >
> > > ah.  This looks good.  I'll find a hunk of time to go through this work
> > > and through Paul's patches.  It'd be good to get both patchsets lined
> > > up in -mm within a couple of weeks.  But..
> > >
> > > We need to decide whether we want to do per-container memory limitation via
> > > these data structures, or whether we do it via a physical scan of some
> > > software zone, possibly based on Mel's patches.
> > i.e. a separate memzone for each container?
>
> Yep.  Straightforward machine partitioning.  An attractive thing is that it
> 100% reuses existing page reclaim, unaltered.

We discussed zones for resource control and some of the disadvantages at
             http://lkml.org/lkml/2006/10/30/222

I need to look at Mel's patches to determine if they are suitable for
control. But in a thread of discussion on those patches, it was agreed
that memory fragmentation and resource control are independent issues.


> > imho memzone approach is inconvinient for pages sharing and shares accounting.
> > it also makes memory management more strict, forbids overcommiting
> > per-container etc.
>
> umm, who said they were requirements?

We discussed some of the requirements in the RFC: Memory Controller
requirements thread
                                http://lkml.org/lkml/2006/10/30/51

> > Maybe you have some ideas how we can decide on this?
>
> We need to work out what the requirements are before we can settle on an
> implementation.
>
> Sigh.  Who is running this show?   Anyone?

All the stake holders involved in the RFC discussion :-) We've been
talking and building on top of each others patches. I hope that was a
good answer ;)

> You can actually do a form of overcommittment by allowing multiple
> containers to share one or more of the zones.  Whether that is sufficient
> or suitable I don't know.  That depends on the requirements, and we haven't
> even discussed those, let alone agreed to them.

There are other things like resizing a zone, finding the right size,
etc. I'll look
at Mel's patches to see what is supported.

Warm Regards,
Balbir Singh
-
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/