[Devel] Re: [PATCH 9/9] ext3: do not throttle metadata and journal IO

[Balbir Singh]

* Theodore Tso <tytso at mit.edu> [2009-04-21 15:14:01]:

> On Tue, Apr 21, 2009 at 11:44:29PM +0530, Balbir Singh wrote:
> > 
> > That would be true in general, but only the process writing to the
> > file will dirty it. So dirty already accounts for the read/write
> > split. I'd assume that the cost is only for the dirty page, since we
> > do IO only on write in this case, unless I am missing something very
> > obvious.
> 
> Maybe I'm missing something, but the (in development) patches I saw
> seemed to use the existing infrastructure designed for RSS cost
> tracking (which is also not yet in mainline, unless I'm mistaken ---
> but I didn't see page_get_page_cgroup() in the mainline tree yet).
> 
> Right?  So if process A in cgroup A reads touches the file first by
> reading from it, then the pages read by process A will be assigned as
> being "owned" by cgroup A.   Then when the patch described at
> 
>       http://lkml.org/lkml/2008/9/9/245

That is correct, but on reclaim (hitting the limit) a page that is frequently
used by B and not A, can get reclaimed from A and move to B if B is
heavily using it.

> 
> ... tries to charge a write done by process B in cgroup B, the code
> will call page_get_page_cgroup(), see that it is "owned" by cgroup A,
> and charge the dirty page to cgroup A.  If process A and all of the
> other processes in cgroup A only access this file read-only, and
> process B is updating this file very heavily --- and it is a large
> file --- then cgroup B will get a completely free pass as far as
> dirtying pages to this file, since it will be all charged 100% to
> cgroup A, incorrectly.
> 
> So what am I missing?

You are right. As long as A is not exceeding its limit, B will get a
free pass at the page. The page will be inactive on A's LRU and active
on the global LRU though from the memory controller perspective. We'll
need to find a way to fix this, if this is a very common scenario for
the IO controller.

-- 
	Balbir
_______________________________________________
Containers mailing list
Containers at lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/containers