linux-kernel - Re: [PATCH v2 2/5] sched/numa: Replace runnable_load_avg by load

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAKfTPtB04MdaU+C4uSS=qU8O69UFjNsOJw5Ck17WBhxVNHETmg@mail.gmail.com>
Date:   Tue, 18 Feb 2020 16:33:14 +0100
From:   Vincent Guittot <vincent.guittot@...aro.org>
To:     Valentin Schneider <valentin.schneider@....com>
Cc:     Ingo Molnar <mingo@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Juri Lelli <juri.lelli@...hat.com>,
        Dietmar Eggemann <dietmar.eggemann@....com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Ben Segall <bsegall@...gle.com>, Mel Gorman <mgorman@...e.de>,
        linux-kernel <linux-kernel@...r.kernel.org>,
        Phil Auld <pauld@...hat.com>, Parth Shah <parth@...ux.ibm.com>,
        Hillf Danton <hdanton@...a.com>
Subject: Re: [PATCH v2 2/5] sched/numa: Replace runnable_load_avg by load_avg

On Tue, 18 Feb 2020 at 15:54, Valentin Schneider
<valentin.schneider@....com> wrote:
>
> On 2/14/20 3:27 PM, Vincent Guittot wrote:
> > @@ -1473,38 +1473,35 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
> >              group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4;
> >  }
> >
> > -static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
> > -
> > -static unsigned long cpu_runnable_load(struct rq *rq)
> > -{
> > -     return cfs_rq_runnable_load_avg(&rq->cfs);
> > -}
> > +/*
> > + * 'numa_type' describes the node at the moment of load balancing.
> > + */
> > +enum numa_type {
> > +     /* The node has spare capacity that can be used to run more tasks.  */
> > +     node_has_spare = 0,
> > +     /*
> > +      * The node is fully used and the tasks don't compete for more CPU
> > +      * cycles. Nevertheless, some tasks might wait before running.
> > +      */
> > +     node_fully_busy,
> > +     /*
> > +      * The node is overloaded and can't provide expected CPU cycles to all
> > +      * tasks.
> > +      */
> > +     node_overloaded
> > +};
>
> Could we reuse group_type instead? The definitions are the same modulo
> s/group/node/.

Also, imbalance might have but misfit and asym have no meaning at NUMA level

For now I prefer to keep them separate to ease code readability. Also
more changes will come on top of this for NUMA balancing which could
also ends up with numa dedicated states

>
> >
> >  /* Cached statistics for all CPUs within a node */
> >  struct numa_stats {
> >       unsigned long load;
> > -
> > +     unsigned long util;
> >       /* Total compute capacity of CPUs on a node */
> >       unsigned long compute_capacity;
> > +     unsigned int nr_running;
> > +     unsigned int weight;
> > +     enum numa_type node_type;
> >  };
> >
> > -/*
> > - * XXX borrowed from update_sg_lb_stats
> > - */
> > -static void update_numa_stats(struct numa_stats *ns, int nid)
> > -{
> > -     int cpu;
> > -
> > -     memset(ns, 0, sizeof(*ns));
> > -     for_each_cpu(cpu, cpumask_of_node(nid)) {
> > -             struct rq *rq = cpu_rq(cpu);
> > -
> > -             ns->load += cpu_runnable_load(rq);
> > -             ns->compute_capacity += capacity_of(cpu);
> > -     }
> > -
> > -}
> > -
> >  struct task_numa_env {
> >       struct task_struct *p;
> >
> > @@ -1521,6 +1518,47 @@ struct task_numa_env {
> >       int best_cpu;
> >  };
> >
> > +static unsigned long cpu_load(struct rq *rq);
> > +static unsigned long cpu_util(int cpu);
> > +
> > +static inline enum
> > +numa_type numa_classify(unsigned int imbalance_pct,
> > +                      struct numa_stats *ns)
> > +{
> > +     if ((ns->nr_running > ns->weight) &&
> > +         ((ns->compute_capacity * 100) < (ns->util * imbalance_pct)))
> > +             return node_overloaded;
> > +
> > +     if ((ns->nr_running < ns->weight) ||
> > +         ((ns->compute_capacity * 100) > (ns->util * imbalance_pct)))
> > +             return node_has_spare;
> > +
> > +     return node_fully_busy;
> > +}
> > +
>
> As Mel pointed out, this is group_is_overloaded() and group_has_capacity().
> @Mel, you mentioned having a common helper, do you have that laying around?
> I haven't seen it in your reconciliation series.
>
> What I'm naively thinking here is that we could have either move the whole
> thing to just sg_lb_stats (AFAICT the fields of numa_stats are a subset of it),
> or if we really care about the stack we could tweak the ordering to ensure
> we can cast one into the other (not too enticed by that one though).
>
> > +/*
> > + * XXX borrowed from update_sg_lb_stats
> > + */
> > +static void update_numa_stats(struct task_numa_env *env,
> > +                           struct numa_stats *ns, int nid)
> > +{
> > +     int cpu;
> > +
> > +     memset(ns, 0, sizeof(*ns));
> > +     for_each_cpu(cpu, cpumask_of_node(nid)) {
> > +             struct rq *rq = cpu_rq(cpu);
> > +
> > +             ns->load += cpu_load(rq);
> > +             ns->util += cpu_util(cpu);
> > +             ns->nr_running += rq->cfs.h_nr_running;
> > +             ns->compute_capacity += capacity_of(cpu);
> > +     }
> > +
> > +     ns->weight = cpumask_weight(cpumask_of_node(nid));
> > +
> > +     ns->node_type = numa_classify(env->imbalance_pct, ns);
> > +}
> > +
> >  static void task_numa_assign(struct task_numa_env *env,
> >                            struct task_struct *p, long imp)
> >  {