[lkml]   [2013]   [Oct]   [16]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH 4/5] sched: Guarantee new group-entities always have weight
On Wed, Oct 16, 2013 at 03:16:44PM -0700, Paul Turner wrote:
> > Hurm.. this gives new groups a massive weight; nr_cpus * NICE_0. ISTR
> > there being some issues with this; or was that on the wakeup path where
> > a task woke on a cpu who's group entity had '0' load because it used to
> > run on another cpu -- I can't remember.
> This could also arbitrarily be MIN_WEIGHT.
> I don't think it actually matters, in practice the set of conditions
> for this weight to ever see use are very specific (e.g. the race
> described above). Otherwise it's always going to be re-initialized (on
> first actual enqueue) to the right value. (NICE_0_LOAD seemed to make
> sense since this is what you'd "expect" for a new, single thread,
> autogroup/group.)

Fair enough. Thanks!

 \ /
  Last update: 2013-10-17 00:41    [W:0.061 / U:2.064 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site