Received-SPF: pass (google.com: domain of linux-kernel+bounces-59489-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
Date: Fri, 9 Feb 2024 15:48:31 +0100
From: Petr Mladek <pmladek@suse.com>
To: Bitao Hu <yaoma@linux.alibaba.com>
Cc: dianders@chromium.org, akpm@linux-foundation.org, kernelfans@gmail.com,
	liusong@linux.alibaba.com, linux-kernel@vger.kernel.org
Subject: Re: [PATCHv6 0/2] *** Detect interrupt storm in softlockup ***
Message-ID: <ZcY7P7KLDt90XqYE@alley>
References: <20240208125426.70511-1-yaoma@linux.alibaba.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20240208125426.70511-1-yaoma@linux.alibaba.com>

On Thu 2024-02-08 20:54:24, Bitao Hu wrote:
> Hi, guys.
> I have implemented a low-overhead method for detecting interrupt
> storm in softlockup. Please review it, all comments are welcome.

I like this work.

I wonder if you might be interested also in reporting problems
when soft IRQs are offloaded to the "ksoftirqd/X" kthreads
for too long.

The kthreads are processes with normal priority. As a result,
offloading soft IRQs to kthreads might cause huge difference
on loaded systems.

I have seen several problems when a flood of softIRQs triggered
offloading them. And it caused several second delays on networking
interfaces.

Best Regards,
Petr