Messages in this thread | | | Subject | Re: [patch 2/3] sched: fix minimum power returned by update_cpu_power() | From | Suresh Siddha <> | Date | Mon, 16 Aug 2010 10:37:59 -0700 |
| |
On Mon, 2010-08-16 at 00:50 -0700, Peter Zijlstra wrote: > On Fri, 2010-08-13 at 12:45 -0700, Suresh Siddha wrote: > > plain text document attachment (fix_update_cpu_power.patch) > > Default cpu_power needs to be multiples of SCHED_LOAD_SCALE and not '1'. > > Fix it. > > > > Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> > > --- > > kernel/sched_fair.c | 2 +- > > 1 file changed, 1 insertion(+), 1 deletion(-) > > > > Index: tree/kernel/sched_fair.c > > =================================================================== > > --- tree.orig/kernel/sched_fair.c > > +++ tree/kernel/sched_fair.c > > @@ -2309,7 +2309,7 @@ static void update_cpu_power(struct sche > > power >>= SCHED_LOAD_SHIFT; > > > > if (!power) > > - power = 1; > > + power = SCHED_LOAD_SCALE; > > > > smt_power freq_power rt_power > power = SCHED_LOAD_SCALE * ---------- * ---------- * ---------- > LOAD_SCALE LOAD_SCALE LOAD_SCALE > > Which, in the above case ends up being 0, so how does resetting it back > to LOAD_SCALE make sense?
hmm, true, but I thought I saw some load balancing code which was depending on SCHED_LOAD_SCALE value. Ignore this for now. Will get back to you if this indeed is a problem.
thanks, suresh
| |