linux-kernel - Re: [RESEND PATCH V5 0/8] remove cpu

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:	Tue, 6 May 2014 13:39:36 +0200
From:	Peter Zijlstra <peterz@...radead.org>
To:	Preeti Murthy <preeti.lkml@...il.com>
Cc:	Alex Shi <alex.shi@...aro.org>,
	Morten Rasmussen <Morten.Rasmussen@....com>, mingo@...hat.com,
	Vincent Guittot <vincent.guittot@...aro.org>,
	Daniel Lezcano <daniel.lezcano@...aro.org>,
	Mike Galbraith <efault@....de>, wangyun@...ux.vnet.ibm.com,
	LKML <linux-kernel@...r.kernel.org>,
	Mel Gorman <mgorman@...e.de>,
	Preeti U Murthy <preeti@...ux.vnet.ibm.com>
Subject: Re: [RESEND PATCH V5 0/8] remove cpu_load idx

On Tue, May 06, 2014 at 03:24:13PM +0530, Preeti Murthy wrote:
> Hi Morten, Peter, Alex,
> 
> In a similar context, I noticed that /proc/loadavg makes use of
> avenrun[] array which keeps track of the history of the global
> load average. This however makes use of the sum of
> nr_running + nr_uninterruptible per cpu. Why are we not
> using the cpu_load[] array here which also keeps track
> of the history of per-cpu load and then return a sum of it?

Entirely different kind of 'load'. Note that you cannot use
->nr_uninterruptible per-cpu, also note that sched/proc.c doesn't.

> Using nr_running to show the global load average would
> be misleading when entire load balancing is being done on the
> basis of the history of cfs_rq->runnable_load_avg/cpu_load[]
> right? IOW, to the best of my understanding we do not use
> nr_running anywhere to directly determine cpu load in the kernel.
> 
> My idea was that the global/per_cpu load that we reflect via
> proc/sys interfaces must be consistent. I haven't really
> looked at what /proc/schedstat, /proc/stat, top are all reading
> from. But /proc/loadavg is reading out global nr_running +
> waiting tasks when this will not give us the accurate picture
> of the system load especially when there are many short running
> tasks.

Nobody said /proc/loadavg is a sane number, but its what it is and since
its a global number its entirely unsuited for balancing -- not to
mention all other reasons its crap.


Content of type "application/pgp-signature" skipped