LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: 王擎 <firstname.lastname@example.org>
To: Thomas Gleixner <email@example.com>
Cc: Peter Zijlstra <firstname.lastname@example.org>,
Ingo Molnar <email@example.com>,
Frederic Weisbecker <firstname.lastname@example.org>,
Michal Hocko <email@example.com>,
Davidlohr Bueso <firstname.lastname@example.org>,
Will Deacon <email@example.com>,
"Paul E. McKenney" <firstname.lastname@example.org>,
Dirk Behme <email@example.com>,
Subject: Re:Re: [PATCH,RESEND] softirq: Introduce SOFTIRQ_FORCED_THREADING
Date: Sat, 28 Aug 2021 10:18:17 +0800 (GMT+08:00) [thread overview]
Message-ID: <AJ*AdQAQD9tzCOr4iYm-E4pL.3.1630117097688.Hmail.firstname.lastname@example.org> (raw)
>On Mon, Aug 23 2021 at 11:33, Wang Qing wrote:
>> At present, whether the softirq is executed when the interrupt exits
>> is controlled by IRQ_FORCED_THREADING. This is unreasonable. It should
>> be split and allowed to take effect separately.
>There is nothing unreasonable about it. When interrupt force threading
>is in effect then it obviously requires that soft interrupt processing
>goes into threaded mode as well. But the threaded execution still takes
>place when the force threaded interrupt handler completes. Only softirqs
>which are raised from hard interrupt context (e.g. timer interrupt) are
>forced off to ksoftirqd.
>What you are proposing here is completly different as you enforce
>softirq execution in context of ksoftirqd only.
Thank you for reply and explanation, I just provide a choice to balance
the execution of softirq according to their own business scenarios.
>> At the same time, we should increase the priority of ksoftirqd when
>> forbidden to execute in interrupt exits. I refer to the implementation
>> of PREEMPT_RT and think it is reasonable.
>What are you referring to? PREEMPT_RT does not modify the priority of
>ksoftirqd. If system designers want to do that, then they can do so from
I refer to the kernel-3.14 RT Patches. I used it at that time and achieved
very good results.
I remember where I saw that softirqd was split into the original process
and the RT process. This can partially solve my problem.
>And doing so can be problematic depending on the workload as this
>effectively breaks the softirq overload mitigation mechanism which
>depends on deferring to ksoftirqd so that e.g. the consumers of received
>network packets can be scheduled and the system can make progress.
>Just because it does not break on your system with your particular
>workload and configuration does not make it suitable for general
>> +#ifdef CONFIG_SOFTIRQ_FORCED_THREADING
>> +static inline void invoke_softirq(void)
>> + wakeup_softirqd();
>Depending on the configuration and timing this breaks any early boot
>mechanism which depends on softirqs being handled before ksoftirqd is
>available. This was clearly never tested with full RCU debugging
>Aside of that the changelog lacks any form of technical analysis and
>justification for this. Just claiming that things are [un]reasonable and
>making uninformed statements about PREEMPT_RT does not qualify. Quite
>the contrary it's definitely unreasonable.
Thank you for your patient guidance, if necessary, I will add it in the next version.
next prev parent reply other threads:[~2021-08-28 2:18 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-23 3:33 Wang Qing
2021-08-23 4:22 ` Mike Galbraith
2021-08-23 6:33 ` 王擎
2021-08-23 7:43 ` Mike Galbraith
2021-08-27 22:27 ` Thomas Gleixner
2021-08-28 2:18 ` 王擎 [this message]
2021-08-28 14:07 ` Thomas Gleixner
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:
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--subject='Re:Re: [PATCH,RESEND] softirq: Introduce SOFTIRQ_FORCED_THREADING' \
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
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).