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;
Date:   Thu, 13 Jul 2023 19:27:19 -0400
From:   Phil Auld <pauld@redhat.com>
To:     Benjamin Segall <bsegall@google.com>
Cc:     linux-kernel@vger.kernel.org, Juri Lelli <juri.lelli@redhat.com>,
        Ingo Molnar <mingo@redhat.com>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Valentin Schneider <vschneid@redhat.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Mel Gorman <mgorman@suse.de>,
        Frederic Weisbecker <frederic@kernel.org>,
        Tejun Heo <tj@kernel.org>
Subject: Re: [PATCH v2 1/2] sched, cgroup: Restore meaning to
 hierarchical_quota
Message-ID: <20230713232719.GA32912@lorien.usersys.redhat.com>
References: <20230712133357.381137-1-pauld@redhat.com>
 <20230712133357.381137-2-pauld@redhat.com>
 <xm268rbkg4tg.fsf@google.com>
 <20230713132306.GA13342@lorien.usersys.redhat.com>
 <xm26zg3zefl7.fsf@google.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <xm26zg3zefl7.fsf@google.com>
Precedence: bulk

On Thu, Jul 13, 2023 at 01:12:04PM -0700 Benjamin Segall wrote:
> Phil Auld <pauld@redhat.com> writes:
> 
> > On Wed, Jul 12, 2023 at 03:09:31PM -0700 Benjamin Segall wrote:
> >> Phil Auld <pauld@redhat.com> writes:
> >> 
> >> > In cgroupv2 cfs_b->hierarchical_quota is set to -1 for all task
> >> > groups due to the previous fix simply taking the min.  It should
> >> > reflect a limit imposed at that level or by an ancestor. Even
> >> > though cgroupv2 does not require child quota to be less than or
> >> > equal to that of its ancestors the task group will still be
> >> > constrained by such a quota so this should be shown here. Cgroupv1
> >> > continues to set this correctly.
> >> >
> >> > In both cases, add initialization when a new task group is created
> >> > based on the current parent's value (or RUNTIME_INF in the case of
> >> > root_task_group). Otherwise, the field is wrong until a quota is
> >> > changed after creation and __cfs_schedulable() is called.
> >> >
> >> > Fixes: c53593e5cb69 ("sched, cgroup: Don't reject lower cpu.max on ancestors")
> >> > Signed-off-by: Phil Auld <pauld@redhat.com>
> >> > Reviewed-by: Ben Segall <bsegall@google.com>
> >> > Cc: Ingo Molnar <mingo@redhat.com>
> >> > Cc: Peter Zijlstra <peterz@infradead.org>
> >> > Cc: Vincent Guittot <vincent.guittot@linaro.org>
> >> > Cc: Juri Lelli <juri.lelli@redhat.com>
> >> > Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
> >> > Cc: Valentin Schneider <vschneid@redhat.com>
> >> > Cc: Ben Segall <bsegall@google.com>
> >> > Cc: Frederic Weisbecker <frederic@kernel.org>
> >> > Cc: Tejun Heo <tj@kernel.org>
> >> > ---
> >> >
> >> > v2: Improve comment about how setting hierarchical_quota correctly
> >> >
> >> > helps the scheduler. Remove extra parens.
> >> >  kernel/sched/core.c  | 13 +++++++++----
> >> >  kernel/sched/fair.c  |  7 ++++---
> >> >  kernel/sched/sched.h |  2 +-
> >> >  3 files changed, 14 insertions(+), 8 deletions(-)
> >> >
> >> > diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> >> > index a68d1276bab0..f80697a79baf 100644
> >> > --- a/kernel/sched/core.c
> >> > +++ b/kernel/sched/core.c
> >> > @@ -9904,7 +9904,7 @@ void __init sched_init(void)
> >> >  		ptr += nr_cpu_ids * sizeof(void **);
> >> >  
> >> >  		root_task_group.shares = ROOT_TASK_GROUP_LOAD;
> >> > -		init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
> >> > +		init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
> >> >  #endif /* CONFIG_FAIR_GROUP_SCHED */
> >> >  #ifdef CONFIG_RT_GROUP_SCHED
> >> >  		root_task_group.rt_se = (struct sched_rt_entity **)ptr;
> >> > @@ -11038,11 +11038,16 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
> >> >  
> >> >  		/*
> >> >  		 * Ensure max(child_quota) <= parent_quota.  On cgroup2,
> >> > -		 * always take the min.  On cgroup1, only inherit when no
> >> > -		 * limit is set:
> >> > +		 * always take the non-RUNTIME_INF min.  On cgroup1, only
> >> > +		 * inherit when no limit is set. In cgroup2 this is used
> >> > +		 * by the scheduler to determine if a given CFS task has a
> >> > +		 * bandwidth constraint at some higher level.
> >> >  		 */
> >> 
> >> It's still used for determining this on cgroup1 (and the cgroup1 code
> >> still works for that), right?
> >>
> >
> > It would, except that the enforcement of child quota <= parent quota
> > means that cfs_rq->runtime_enabled will be set and we'll hit that first
> > on cgroup1.  So we don't really use it for this determination in
> > cgroup1.
> 
> cgroup1 tg_cfs_schedulable_down only constricts child quota when it's
> set. You can set quota=RUNTIME_INF on any cgroup, no matter what its
> parent is. (The schedulable constraint is a little silly)
> 

Aargh :)   I had "In both cases this ..." there before I talked myself out
of it.

I'll update this one.


Cheers,
Phil


--