[lkml]   [2015]   [Apr]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH 1/3] cpuidle: Store the idle start time stamp
On Wed, Apr 15, 2015 at 02:50:33PM +0200, Daniel Lezcano wrote:
> I was thinking about converting to nanosecond the cpuidle framework but it
> is not worth to do that as the resolution is too high for the idle states.

The question is if saving those 4 bytes (unsigned int vs u64) on
next_timer_us is worth having to do that /1000 all the time.

The one spot where its used:

new_factor += RESOLUTION * measured_us / data->next_timer_us;

Could be fixed with a few shifts, all that matters is that measured_us
and next_timer_us are in the same metric, it doesn't need to be us, it
could be ns/1024 for instance.

 \ /
  Last update: 2015-04-15 15:41    [W:0.065 / U:0.012 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site