linux-kernel - Re: [PATCH 2/3] sched/numa: Allow a floating imbalance between NUMA nodes

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: <CAKfTPtBj1nJhQrsAoH0mBrc9Md+_icNJuWx7P=yQbqM2fYCAwg@mail.gmail.com>
Date:   Tue, 17 Nov 2020 15:24:56 +0100
From:   Vincent Guittot <vincent.guittot@...aro.org>
To:     Mel Gorman <mgorman@...hsingularity.net>
Cc:     LKML <linux-kernel@...r.kernel.org>,
        Ingo Molnar <mingo@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Valentin Schneider <valentin.schneider@....com>,
        Juri Lelli <juri.lelli@...hat.com>
Subject: Re: [PATCH 2/3] sched/numa: Allow a floating imbalance between NUMA nodes

On Tue, 17 Nov 2020 at 14:42, Mel Gorman <mgorman@...hsingularity.net> wrote:
>
> Currently, an imbalance is only allowed when a destination node
> is almost completely idle. This solved one basic class of problems
> and was the cautious approach.
>
> This patch revisits the possibility that NUMA nodes can be imbalanced
> until 25% of the CPUs are occupied. The reasoning behind 25% is somewhat
> superficial -- it's half the cores when HT is enabled.  At higher
> utilisations, balancing should continue as normal and keep things even
> until scheduler domains are fully busy or over utilised.

This reminds me previous discussions on the same topic: how much
imbalance is allowed that will not screw up the bandwidth of the node
I'm worried that there is no topology insight in the decision like
hyperthreading, or number of cpus in the LLC

>
> Note that this is not expected to be a universal win. Any benchmark
> that prefers spreading as wide as possible with limited communication
> will favour the old behaviour as there is more memory bandwidth.
> Workloads that communicate heavily in pairs such as netperf or tbench
> benefit. For the tests I ran, the vast majority of workloads saw
> a benefit so it seems to be a worthwhile tradeoff.
>
> Signed-off-by: Mel Gorman <mgorman@...hsingularity.net>
> ---
>  kernel/sched/fair.c | 22 ++++++++++++----------
>  1 file changed, 12 insertions(+), 10 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 5fbed29e4001..33709dfac24d 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -1550,7 +1550,8 @@ struct task_numa_env {
>  static unsigned long cpu_load(struct rq *rq);
>  static unsigned long cpu_runnable(struct rq *rq);
>  static unsigned long cpu_util(int cpu);
> -static inline long adjust_numa_imbalance(int imbalance, int dst_running);
> +static inline long adjust_numa_imbalance(int imbalance,
> +                                       int dst_running, int dst_weight);
>
>  static inline enum
>  numa_type numa_classify(unsigned int imbalance_pct,
> @@ -1930,7 +1931,8 @@ static void task_numa_find_cpu(struct task_numa_env *env,
>                 src_running = env->src_stats.nr_running - 1;
>                 dst_running = env->dst_stats.nr_running + 1;
>                 imbalance = max(0, dst_running - src_running);
> -               imbalance = adjust_numa_imbalance(imbalance, dst_running);
> +               imbalance = adjust_numa_imbalance(imbalance, dst_running,
> +                                                       env->dst_stats.weight);
>
>                 /* Use idle CPU if there is no imbalance */
>                 if (!imbalance) {
> @@ -8993,16 +8995,15 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
>
>  #define NUMA_IMBALANCE_MIN 2
>
> -static inline long adjust_numa_imbalance(int imbalance, int dst_running)
> +static inline long adjust_numa_imbalance(int imbalance,
> +                               int dst_running, int dst_weight)
>  {
> -       unsigned int imbalance_min;
> -
>         /*
>          * Allow a small imbalance based on a simple pair of communicating
> -        * tasks that remain local when the source domain is almost idle.
> +        * when the destination is lightly loaded so that pairs of
> +        * communicating tasks may remain local.
>          */
> -       imbalance_min = NUMA_IMBALANCE_MIN;
> -       if (dst_running <= imbalance_min)
> +       if (dst_running < (dst_weight >> 2) && imbalance <= NUMA_IMBALANCE_MIN)
>                 return 0;
>
>         return imbalance;
> @@ -9105,9 +9106,10 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
>                 }
>
>                 /* Consider allowing a small imbalance between NUMA groups */
> -               if (env->sd->flags & SD_NUMA)
> +               if (env->sd->flags & SD_NUMA) {
>                         env->imbalance = adjust_numa_imbalance(env->imbalance,
> -                                               busiest->sum_nr_running);
> +                               busiest->sum_nr_running, busiest->group_weight);
> +               }
>
>                 return;
>         }
> --
> 2.26.2
>