lkml.org 
[lkml]   [2012]   [Feb]   [17]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
Date
SubjectRe: [RFC PATCH 01/14] sched: track the runnable average on a per-task entitiy basis
On Thu, Feb 16, 2012 at 5:27 AM, Peter Zijlstra <a.p.zijlstra@chello.nl> wrote:
> On Wed, 2012-02-01 at 17:38 -0800, Paul Turner wrote:
>> +static __always_inline u64 decay_load(u64 val, int n)
>> +{
>> +       for (;n && val;n--) {
>> +               val *= 4008;
>> +               val >>= 12;
>> +       }
>> +
>> +       return val;
>> +}
>
>> +                       sa->runnable_avg_sum =
>> +                               decay_load(sa->runnable_avg_sum, 1);
>> +                       sa->runnable_avg_period =
>> +                               decay_load(sa->runnable_avg_period, 1);
>
> Since all you ever seem to do is:
>
>  x = decay(x, n);
>
> and frequently run over the line limits it might make sense to either
> introduce a CPP helper or make the first argument a pointer and ditch
> the return value so we end up with something like:
>
>  decay(&x, n);

Ah-ha, good idea. I had done some other fiddles to try and make
things fit better, but this will work.

Thanks!
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2012-02-17 12:47    [W:0.096 / U:31.844 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site