[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <150367598066.27971.13705066235932844708@mail.alporthouse.com>
Date: Fri, 25 Aug 2017 16:46:20 +0100
From: Chris Wilson <chris@...is-wilson.co.uk>
To: Peter Zijlstra <peterz@...radead.org>,
"Josef Bacik" <josef@...icpanda.com>
Cc: "Rik van Riel" <riel@...hat.com>, linux-kernel@...r.kernel.org,
jhladky@...hat.com, mingo@...nel.org, mgorman@...e.de
Subject: Re: [PATCH] sched/fair: Fix wake_affine() for !NUMA_BALANCING
Quoting Peter Zijlstra (2017-08-01 22:43:07)
> @@ -5356,20 +5295,115 @@ static int wake_wide(struct task_struct
> return 1;
> }
>
> +struct llc_stats {
> + unsigned long nr_running;
> + unsigned long load;
> + unsigned long capacity;
> + int has_capacity;
> +};
> +
> +static void get_llc_stats(struct llc_stats *stats, int cpu)
> +{
> + struct sched_domain_shared *sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
> +
> + if (!sds) {
> + memset(&stats, 0, sizeof(*stats));
^
Just in case, stray & before stats.
-Chris
Powered by blists - more mailing lists