Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <e7a5e964-6113-f54d-1477-5eb561f843e3@bytedance.com>
Date:   Tue, 1 Nov 2022 17:14:26 +0800
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:102.0)
 Gecko/20100101 Thunderbird/102.4.1
Subject: Re: [PATCH] sched/fair: favor non-idle group in tick preemption
To:     Josh Don <joshdon@google.com>, Chuyi Zhou <zhouchuyi@bytedance.com>
Cc:     peterz@infradead.org, juri.lelli@redhat.com, mingo@redhat.com,
        vincent.guittot@linaro.org, linux-kernel@vger.kernel.org
References: <20221027081630.34081-1-zhouchuyi@bytedance.com>
 <CABk29NtDny9qKZbZZ_i8Brwjtqs5GA0G4_SffzK4HzG3RrXVhQ@mail.gmail.com>
 <64d963b6-2d9c-3f93-d427-a1ff705fb65a@bytedance.com>
 <CABk29NsbGuMPcA8NJagMfPyHij3864F3DVQ6wpCj3UAo8tbFNQ@mail.gmail.com>
 <5af26ac9-3bdb-32d2-77a7-6cd8feca97aa@bytedance.com>
 <CABk29Nt38d31LnazbcSVB036jUYemC1KRpR2Dn7YgLmXkp-QBQ@mail.gmail.com>
Content-Language: en-US
From:   Abel Wu <wuyun.abel@bytedance.com>
In-Reply-To: <CABk29Nt38d31LnazbcSVB036jUYemC1KRpR2Dn7YgLmXkp-QBQ@mail.gmail.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk

Hi Josh,

On 11/1/22 6:44 AM, Josh Don wrote:
> ...nit...
> Some weirdness about this change though, is that if there is a
> non-idle current entity, and the two next entities on the cfs_rq are
> idle and non-idle respectively, we'll now take longer to preempt the
> on-cpu non-idle entity, because the non-idle entity on the cfs_rq is
> 'hidden' by the idle 'first' entity. Wakeup preemption is different
> because we're always directly comparing the current entity with the
> newly woken entity.

Indeed. The hidden non-idle entity might run longer at the cost of
delayed preemption. This behavior is not compliant to the SCHED_NORMAL
semantics. But we also can't tell from here that the non-idle entity
contains SCHED_NORMAL tasks or not. As long as the entities do not
aware of the schedule policies, this ambiguity exists.

Best,
Abel