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 for Android: free password hash cracker in your pocket

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

Message-Id: <200610021302.k92D23W1003320@turing-police.cc.vt.edu>
Date:	Mon, 02 Oct 2006 09:02:03 -0400
From:	Valdis.Kletnieks@...edu
To:	Thomas Gleixner <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

On Sun, 01 Oct 2006 22:59:01 -0000, Thomas Gleixner said:
> the following patch series is an update in response to your review.

First runtime results - no lockups or other severe badness in a half-hour or so
of running.

-mm2-hrt-dynticks5 shows severe clock drift issues if you run 'cpuspeed'.

Using speedstep-ich as a kernel built-in, and cpuspeed is invoked as:

cpuspeed -d -n -i 10 -p 10 50 -a /proc/acpi/ac_adapter/*/state

If cpuspeed drops the CPU speed from the default 1.6Ghz down to 1.2Ghz (the
only 2 speeds available on this core), the system clock proceeds to lose
about 15 seconds a minute.  I haven't dug further into why yet. (If the system
is busy so cpuspeed keeps the processor at 1.6Ghz, the clock doesn't drift
as much - so it looks like a "when speed is 1.2Ghz" issue...)

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.

Content of type "application/pgp-signature" skipped