[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20181019183057.GA31016@hirez.programming.kicks-ass.net>
Date: Fri, 19 Oct 2018 20:30:57 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Peng Hao <penghao122@...a.com.cn>
Cc: mingo@...hat.com, linux-kernel@...r.kernel.org,
Peng Hao <peng.hao2@....com.cn>
Subject: Re: [PATCH] sched/fair : modify comment of fbq_type description
On Fri, Oct 19, 2018 at 12:44:54PM -0400, Peng Hao wrote:
>
> From: Peng Hao <peng.hao2@....com.cn>
>
> for type 'all', the comment 'there is no distinction' is vague.
> make it clearer.
>
> Signed-off-by: Peng Hao <peng.hao2@....com.cn>
> ---
> kernel/sched/fair.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index f808ddf..3a0543f 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -8304,7 +8304,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
> * We classify groups/runqueues into three groups:
> * - regular: there are !numa tasks
> * - remote: there are numa tasks that run on the 'wrong' node
> - * - all: there is no distinction
> + * - all: there are numa tasks that run on the 'right' node
No, that is actively wrong. Both the previous cases inlcude that.
If anything, it should be: all tasks are numa tasks and run on the
'right' node.
Powered by blists - more mailing lists