Re: inlines in kernel/sched.c

[Andrew Morton]

Ingo Molnar wrote:
> 
> On Sun, 28 Jul 2002, Andrew Morton wrote:
> 
> > Ingo, could you please review the use of inlines in the
> > scheduler sometime?  They seem to be excessive.
> >
> > For example, this patch reduces the sched.d icache footprint
> > by 1.5 kilobytes.
> 
> the patch also hurts context-switch latencies - it went
> from 1.35 usecs to 1.42 usecs - a 5% drop.
> 

It will hurt with benchmarks, because with benchmarks
all of the scheuler is in L1 all the time.

This stuff's hard.  I don't know what the right answer
is, really.

To optimise for scheduler-intensive workloads we should
optimise for the all-in-cache case.  To optimise for
other workloads we should aim to reduce the cache footprint.

Perhaps.  Dunno.

-