A consideration on memory controller.

KAMEZAWA Hiroyuki kamezawa.hiroyu at jp.fujitsu.com
Mon Jan 21 02:22:59 PST 2008


On Mon, 21 Jan 2008 15:20:36 +0530
Balbir Singh <balbir at linux.vnet.ibm.com> wrote:

> > > This topic needs more discussion, we have some form of page-cache
> > > control built into the memory controller.
> > > 
> > Hmm. ok. I'looking forward to see.
> > 
> 
> Could you elaborate on what sort of page-cache control you need, is it
> global page-cache control?
> 
What I mentioned to in my mail was global page cache. 

But, my purpose is isolate workload between applications and guarantee
stable performance/latency and memory controller's limiting page usage
feature will do half of work.
So, per-cgroup page-cache control is (maybe) good enough for making applications
stable by keeping room for immediate use of anon and by avoiding unnecessary swapout.

but above can be archieved by
 - reserve/guarantee amount of free memory by some technique, bacground 
   kthread, throttling,
 - do good design of swappiness.
 - etc...

So, the word "limiting page cache" itself is not important. Above will
limit amount of page-cache as a result.
Ways to reach my goal is not one, maybe. I should find the best one :)

Thanks,
-Kame



More information about the Containers mailing list