linux-kernel - Re: [PATCH v4] genirq: Machine-parsable version of /proc/interrupts

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]

Date:   Sat, 10 Sep 2016 01:19:11 +0200 (CEST)
From:   Thomas Gleixner <tglx@...utronix.de>
To:     Craig Gallek <kraigatgoog@...il.com>
cc:     David Decotigny <decot@...gle.com>, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v4] genirq: Machine-parsable version of
 /proc/interrupts

On Fri, 9 Sep 2016, Craig Gallek wrote:
> +What:		/sys/kernel/irq/<irq>/per_cpu_count
> +Date:		September 2016
> +KernelVersion:	4.9
> +Contact:	Craig Gallek <kraig@...gle.com>
> +Description:	The number of times the interrupt has fired since boot.  This
> +		is a comma-separated list of counters; one per online CPU in
> +		CPU id order.  NOTE: If the set of online CPUs changes, the
> +		counter positions in this list will also change and counters
> +		for offline CPUs will not be available.

More thoughts:

We could easily print all possible cpus here instead of restricting it to
online cpus. The per cpu counters are still available.

That way you can even observe the affinity change after a online or offline
and a tool which is interrested in more than the sum wouldn't have to cope
with changing positions.

Thanks,

	tglx