linux-kernel - Re: [PATCH 1/3] watchdog/softlockup: low-overhead detection of interrupt storm

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <CAD=FV=UfzLAxbKWUqhbt7iBEZzyuBqCkdaSJFnHGYAw-2mcAYA@mail.gmail.com>
Date: Thu, 25 Jan 2024 07:08:02 -0800
From: Doug Anderson <dianders@...omium.org>
To: Bitao Hu <yaoma@...ux.alibaba.com>
Cc: akpm@...ux-foundation.org, pmladek@...e.com, tglx@...utronix.de, 
	maz@...nel.org, liusong@...ux.alibaba.com, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 1/3] watchdog/softlockup: low-overhead detection of
 interrupt storm

Hi,

On Thu, Jan 25, 2024 at 12:31 AM Bitao Hu <yaoma@...ux.alibaba.com> wrote:
>
> > 2. Sum up all 11 of the stats to get a total. This should still fit
> > into 32-bits.
>
> >
> > 3. Do the math to get the integral percentages and store those in the tail slot.
> >
> I'm a bit confused, why is there a need to sum up all 11 of the stats to
> get a total? I calculate the percentage using sample_period.

Oh, you're right! I saw you looping over NR_STATS in print_cpustat()
and assumed that was because you were totaling them. Yeah, using
sample_period should work.

-Doug