About this list Date view Thread view Subject view Author view Attachment view

From: Jacques Gelinas (jack_at_solucorp.qc.ca)
Date: Tue 23 Oct 2001 - 22:06:23 BST


On Tue, 23 Oct 2001 17:32:11 -0500, Rik van Riel wrote
> On Tue, 23 Oct 2001, Jacques Gelinas wrote:
>
> > + sched
> >
> > This changes the way priority is calculated for processes in a
> > vserver. The priority is kind of aglomerated. A vserver running 50
> > active processes will have a same impact on the server as if it was
> > running a single process (roughly).
>
> Arghhhhh, this changes the scheduler's _fast path_, not fun.
>
> Should I port my fairsched patch to a newer 2.4 kernel and
> add vserver support for it ? My approach only changes the
> priority recalculation in the scheduler and achieves pretty
> much the same effect _without_ needing to change goodness().

I am open to that. The effect we want to achieve is to have on vserver not taking
all the machine for itself. So it does not have to be 100% fair.

What is the impact of this goodness change btw ? Does the division is causing
some evil effect ?

---------------------------------------------------------
Jacques Gelinas <jack_at_solucorp.qc.ca>
vserver: run general purpose virtual servers on one box, full speed!
http://www.solucorp.qc.ca/miscprj/s_context.hc


About this list Date view Thread view Subject view Author view Attachment view
[Next/Previous Months] [Main vserver Project Homepage] [Howto Subscribe/Unsubscribe] [Paul Sladen's vserver stuff]
Generated on Wed 06 Nov 2002 - 07:03:38 GMT by hypermail 2.1.3