lkml.org 
[lkml]   [2009]   [May]   [27]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    SubjectRe: [PATCH] sched: Support current clocksource handling in fallback sched_clock().
    From
    Date
    On Tue, 2009-05-26 at 16:00 -0700, john stultz wrote:

    > Sure, I guess what I'm trying to pull out here is that should we try to
    > create some OK_FOR_SCHED_CLOCK flag for clocksources, and then we try to
    > make this generic so other arches can add that flag and be done, what is
    > the guidance we want to give to arch maintainers for setting that flag?
    >
    > 1) Has to be very very fast. Can we put a number on this? 50ns to read?

    I'd express it in cpu cycles, but not sure, the very fastest the arch
    has :-) Just tell people this is in their scheduling hot-path and they
    might understand.

    > 2) How long does it have to be monotonic for?

    Forever? (per cpu)

    > Is it ok if it wraps every few seconds?

    No, if it wraps it needs to wrap on u64.



    \
     
     \ /
      Last update: 2009-05-27 09:01    [W:0.018 / U:60.308 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site