linux-kernel - Re: [patch 00/21] high resolution timers / dynamic ticks

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:	Mon, 02 Oct 2006 14:25:28 -0400
From:	Valdis.Kletnieks@...edu
To:	tglx@...utronix.de
Cc:	Andrew Morton <akpm@...l.org>, LKML <linux-kernel@...r.kernel.org>,
	Ingo Molnar <mingo@...e.hu>, Jim Gettys <jg@...top.org>,
	John Stultz <johnstul@...ibm.com>,
	David Woodhouse <dwmw2@...radead.org>,
	Arjan van de Ven <arjan@...radead.org>,
	Dave Jones <davej@...hat.com>
Subject: Re: [patch 00/21] high resolution timers / dynamic ticks - V2

(Sorry for the size of the note, there's some 50K of logs attached)

On Mon, 02 Oct 2006 15:43:02 +0200, Thomas Gleixner said:
> Can you please send me the bootlog and further dmesg output (especially
> when related to timers / cpufreq).

I booted the box to single-user both times, and then started cpuspeed.
I then did a cat of /proc/interrupts, /proc/uptime, and a date command,
waited 60 seconds according to my watch, and repeated.  I then dumped
the dmesg.  The -dyntick kernel moved 'uptime' almost exactly 45 seconds
(almost certainly a by-product of running at 1.2Ghz rather than 1.6Ghz).
Does the dyntick code make any unwritten assumptions about a jiffie or
bogomips remaining constant?

Attached - config diff, date and /proc dumps from both -mm2 and -mm2-dyntick,
and the dmesg's from both boots.

Yell if you have any other questions/suggestions/etc..

> > I'm also seeing gkrellm reporting about 25% CPU use when "near-idle" (X is up
> > but not much is going on) when that's usually down around 5-6%.  I need to
> > collect some oprofile numbers and investigate that as well.
>
> I look into the accounting fixups again.
I still need to get oprofile runs of this and see what's going on.

View attachment "config.diff" of type "text/plain " (962 bytes)

View attachment "date.mm2" of type "text/plain " (1354 bytes)

View attachment "date.mm2-dyntick" of type "text/plain " (1352 bytes)

View attachment "dmesg.mm2" of type "text/plain " (26855 bytes)

View attachment "dmesg.mm2-dyntick" of type "text/plain " (26946 bytes)

Content of type "application/pgp-signature" skipped