Re: Process Aggregates: module based support for jobs

From: Rik van Riel (
Date: Thu Jun 22 2000 - 08:42:29 EST

On Thu, 22 Jun 2000, Andrey Savochkin wrote:
> On Wed, Jun 21, 2000 at 12:28:57PM -0300, Marcelo Tosatti wrote:
> > On Tue, 20 Jun 2000, Andrey Savochkin wrote:
> [snip]
> > > policy. Contrary to upper limits, guaranteed minimal amount of resources
> > > provides you quality of service for "well-behaved" subjects independently of
> > > (mis-)behavior of others. That's how I'm approaching to memory management.
> >
> > This is really nice.
> > How do you plan to make this with current 2.4 VM active/inactive/scanvenge
> > lists?
> I'm making experiments at this moment.

I have a plan on how to make this work. A (very rough) draft
of the idea is on:

Basically we want to:
1) try and make an educated guess as to how big the actual
   working set of each process is

2) normalise the rss guarantees / limits to make sure that:
     - the sum of all rss guarantees never exceeds physmem/N
     - no rss limit is above ulimit.rss
     - a user does not exceed his/her rss quota
     - a user does not get below his/her rss guarantee



The Internet is not a network of computers. It is a network
of people. That is its real strength.

Wanna talk about the kernel? / #kernelnewbies

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to Please read the FAQ at

This archive was generated by hypermail 2b29 : Fri Jun 23 2000 - 21:00:24 EST