From: Peter Zijlstra <peterz@infradead.org>
To: Yihao Wu <wuyihao@linux.alibaba.com>
Cc: "Ingo Molnar" <mingo@redhat.com>,
"Vincent Guittot" <vincent.guittot@linaro.org>,
"Dietmar Eggemann" <dietmar.eggemann@arm.com>,
"Shanpei Chen" <shanpeic@linux.alibaba.com>,
王贇 <yun.wang@linux.alibaba.com>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH] sched/fair: Again ignore percpu threads for imbalance pulls
Date: Sat, 11 Dec 2021 12:12:15 +0100 [thread overview]
Message-ID: <20211211111215.GW16608@worktop.programming.kicks-ass.net> (raw)
In-Reply-To: <20211211094808.109295-1-wuyihao@linux.alibaba.com>
On Sat, Dec 11, 2021 at 05:48:08PM +0800, Yihao Wu wrote:
> commit 2f5f4cce496e ("sched/fair: Ignore percpu threads for imbalance
> pulls") was meant to fix a performance issue, when load balance tries to
> migrate pinned kernel threads at MC domain level. This was destined to
> fail. After it fails, it further makes wakeup balance at NUMA domain level
> messed up. The most severe case that I noticed and frequently occurs:
> |sum_nr_running(node1) - sum_nr_running(node2)| > 100
>
> However the original bugfix failed, because it covers only case 1) below.
> 1) Created by create_kthread
> 2) Created by kernel_thread
> No kthread is assigned to task_struct in case 2 (Please refer to comments
> in free_kthread_struct) so it simply won't work.
>
> The easist way to cover both cases is to check nr_cpus_allowed, just as
> discussed in the mailing list of the v1 version of the original fix.
>
> * lmbench3.lat_proc -P 104 fork (2 NUMA, and 26 cores, 2 threads)
>
> w/out patch w/ patch
> fork+exit latency 1660 ms 1520 ms ( 8.4%)
>
> Fixes: 2f5f4cce496e ("sched/fair: Ignore percpu threads for imbalance pulls")
> Signed-off-by: Yihao Wu <wuyihao@linux.alibaba.com>
> ---
> kernel/kthread.c | 6 +-----
> 1 file changed, 1 insertion(+), 5 deletions(-)
>
> diff --git a/kernel/kthread.c b/kernel/kthread.c
> index 4a4d7092a2d8..cb05d3ff2de4 100644
> --- a/kernel/kthread.c
> +++ b/kernel/kthread.c
> @@ -543,11 +543,7 @@ void kthread_set_per_cpu(struct task_struct *k, int cpu)
>
> bool kthread_is_per_cpu(struct task_struct *p)
> {
> - struct kthread *kthread = __to_kthread(p);
> - if (!kthread)
> - return false;
> -
> - return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
> + return (p->flags & PF_KTHREAD) && p->nr_cpus_allowed == 1;
> }
NAK, this will break lots of things.
next prev parent reply other threads:[~2021-12-11 11:12 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-12-11 9:48 [PATCH] sched/fair: Again ignore percpu threads for imbalance pulls Yihao Wu
2021-12-11 11:12 ` Peter Zijlstra [this message]
2021-12-16 18:26 ` Valentin Schneider
2022-01-17 14:50 ` Yihao Wu
2022-01-17 17:16 ` Valentin Schneider
2022-01-18 8:11 ` Yihao Wu
2022-01-18 17:10 ` Valentin Schneider
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20211211111215.GW16608@worktop.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=dietmar.eggemann@arm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=shanpeic@linux.alibaba.com \
--cc=vincent.guittot@linaro.org \
--cc=wuyihao@linux.alibaba.com \
--cc=yun.wang@linux.alibaba.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).