lkml.org 
[lkml]   [2010]   [Oct]   [21]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    From
    Date
    SubjectRe: [RFC tg_shares_up improvements - v1 01/12] sched: rewrite tg_shares_up
    On Thu, Oct 21, 2010 at 1:08 AM, Bharata B Rao
    <bharata@linux.vnet.ibm.com> wrote:
    > On Fri, Oct 15, 2010 at 09:43:50PM -0700, pjt@google.com wrote:
    >> From: Peter Zijlstra <a.p.zijlstra@chello.nl>
    >> --- kernel/sched_fair.c.orig
    >> +++ kernel/sched_fair.c
    >> @@ -417,7 +417,6 @@ int sched_proc_update_handler(struct ctl
    >>       WRT_SYSCTL(sched_min_granularity);
    >>       WRT_SYSCTL(sched_latency);
    >>       WRT_SYSCTL(sched_wakeup_granularity);
    >> -     WRT_SYSCTL(sched_shares_ratelimit);
    >>  #undef WRT_SYSCTL
    >>
    >>       return 0;
    >> @@ -633,7 +632,6 @@ account_entity_enqueue(struct cfs_rq *cf
    >>               list_add(&se->group_node, &cfs_rq->tasks);
    >>       }
    >>       cfs_rq->nr_running++;
    >> -     se->on_rq = 1;
    >>  }
    >>
    >>  static void
    >> @@ -647,9 +645,89 @@ account_entity_dequeue(struct cfs_rq *cf
    >>               list_del_init(&se->group_node);
    >>       }
    >>       cfs_rq->nr_running--;
    >> -     se->on_rq = 0;
    >>  }
    >>
    > <snip>
    >> @@ -771,7 +849,9 @@ enqueue_entity(struct cfs_rq *cfs_rq, st
    >>        * Update run-time statistics of the 'current'.
    >>        */
    >>       update_curr(cfs_rq);
    >> +     update_cfs_load(cfs_rq);
    >>       account_entity_enqueue(cfs_rq, se);
    >> +     update_cfs_shares(cfs_rq_of(se));
    >>
    >>       if (flags & ENQUEUE_WAKEUP) {
    >>               place_entity(cfs_rq, se, 0);
    >> @@ -782,6 +862,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, st
    >>       check_spread(cfs_rq, se);
    >>       if (se != cfs_rq->curr)
    >>               __enqueue_entity(cfs_rq, se);
    >> +     se->on_rq = 1;
    >>  }
    >>
    >>  static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
    >> @@ -825,8 +906,11 @@ dequeue_entity(struct cfs_rq *cfs_rq, st
    >>
    >>       if (se != cfs_rq->curr)
    >>               __dequeue_entity(cfs_rq, se);
    >> +     se->on_rq = 0;
    >
    > Since setting and un-setting of se->on_rq is completely handled within
    > sched_fair.c, we can remove the redundant setting and un-setting of
    > se->on_rq from sched.c:[en]dequeue_task. Even w/o this patch, they were
    > redundant I suppose.

    Mmmm I think SCHED_RT (currently) depends on this, it could probably
    cleaned up in a separate patch.

    >
    > Regards,
    > Bharata.
    >
    --
    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: 2010-10-21 10:41    [W:0.035 / U:90.140 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site