Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Thu, 08 Feb 2018 15:22:36 -0500 (EST)
Message-Id: <20180208.152236.2148696725742511754.davem@davemloft.net>
To:     dima@arista.com
Cc:     bigeasy@linutronix.de, frederic@kernel.org,
        linux-kernel@vger.kernel.org, alexander.levin@verizon.com,
        peterz@infradead.org, mchehab@s-opensource.com,
        torvalds@linux-foundation.org, hannes@stressinduktion.org,
        paulmck@linux.vnet.ibm.com, wanpeng.li@hotmail.com,
        tglx@linutronix.de, akpm@linux-foundation.org, pabeni@redhat.com,
        rrendec@arista.com, mingo@kernel.org, sgruszka@redhat.com,
        riel@redhat.com, edumazet@google.com
Subject: Re: [RFC PATCH 2/4] softirq: Per vector deferment to workqueue
From:   David Miller <davem@davemloft.net>
In-Reply-To: <1518120895.2849.14.camel@arista.com>
References: <20180208174450.qjvjy752jf4ngt2g@breakpoint.cc>
        <20180208.134506.1374787894560277876.davem@davemloft.net>
        <1518120895.2849.14.camel@arista.com>
Mime-Version: 1.0
Content-Type: Text/Plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Dmitry Safonov <dima@arista.com>
Date: Thu, 08 Feb 2018 20:14:55 +0000

> On Thu, 2018-02-08 at 13:45 -0500, David Miller wrote:
>> From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
>> Date: Thu, 8 Feb 2018 18:44:52 +0100
>> 
>> > May I instead suggest to stick to ksoftirqd? So you run in softirq
>> > context (after return from IRQ) and if takes too long, you offload
>> the
>> > vector to ksoftirqd instead. You may want to play with the metric
>> on
>> > which you decide when you want switch to ksoftirqd / account how
>> long a
>> > vector runs.
>> 
>> Having read over this stuff for the past few weeks this is how I feel
>> as well.  Just make ksofbitrq do what we want (only execute the
>> overloaded softirq vectors).
>> 
>> The more I look at the workqueue stuff, the more complications and
>> weird behavioral artifacts we are getting for questionable gain.
> 
> What about creating several ksoftirqd threads per-cpu?
> Like I did with boot parameter to specify how many threads and which
> softirqs to serve.

Why do we need more than one per cpu?

There is a set of vectors which are "overloaded" and ksoftirqd processes
them one by one.

The only difference with what happens now is that one softirq being
overloaded doesn't defer the processing of all softirqs to ksoftirqd.