From mboxrd@z Thu Jan 1 00:00:00 1970 From: vincent.guittot@linaro.org (Vincent Guittot) Date: Thu, 11 Sep 2014 13:20:54 +0200 Subject: [PATCH v5 08/12] sched: move cfs task on a CPU with higher capacity In-Reply-To: <20140911100721.GT3190@worktop.ger.corp.intel.com> References: <1409051215-16788-1-git-send-email-vincent.guittot@linaro.org> <1409051215-16788-9-git-send-email-vincent.guittot@linaro.org> <20140911100721.GT3190@worktop.ger.corp.intel.com> Message-ID: To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On 11 September 2014 12:07, Peter Zijlstra wrote: > On Tue, Aug 26, 2014 at 01:06:51PM +0200, Vincent Guittot wrote: > >> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c >> index 18db43e..60ae1ce 100644 >> --- a/kernel/sched/fair.c >> +++ b/kernel/sched/fair.c >> @@ -6049,6 +6049,14 @@ static bool update_sd_pick_busiest(struct lb_env *env, >> return true; >> } >> >> + /* >> + * The group capacity is reduced probably because of activity from other >> + * sched class or interrupts which use part of the available capacity >> + */ >> + if ((sg->sgc->capacity_orig * 100) > (sgs->group_capacity * >> + env->sd->imbalance_pct)) >> + return true; >> + >> return false; >> } > > This is unlikely to have worked as intended. You will never reach this, > except on PowerPC >= 7. All other machines will have bailed at the > !ASYM_PACKING check above this. Ah yes, i miss that change while rebasing on rik patches. My use case fall in this wider test now that we always select a busiest group