linux-kernel - Re: [PATCH] raise tsc clocksource rating

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: <47266276.4030000@goop.org>
Date:	Mon, 29 Oct 2007 15:45:10 -0700
From:	Jeremy Fitzhardinge <jeremy@...p.org>
To:	Zachary Amsden <zach@...are.com>
CC:	Glauber de Oliveira Costa <gcosta@...hat.com>,
	linux-kernel@...r.kernel.org, tglx@...utronix.de,
	rusty@...tcorp.com.au, --cc@...hat.com, mingo@...e.hu,
	avi@...amnet.com, kvm-devel@...ts.sourceforge.net,
	Glauber de Oliveira Costa <glauber@....localdomain>,
	Dan Hecht <dhecht@...are.com>,
	Garrett Smith <garrett@...are.com>
Subject: Re: [PATCH] raise tsc clocksource rating

Zachary Amsden wrote:
> On Mon, 2007-10-29 at 20:10 -0300, Glauber de Oliveira Costa wrote:
>   
>> From: Glauber de Oliveira Costa <glauber@....localdomain>
>>
>> tsc is very good time source (when it does not have drifts, does not
>> change it's frequency, i.e. when it works), so it should have its rating
>> raised to a value greater than, or equal 400.
>>
>> Since it's being a tendency among paravirt clocksources to use values
>> around 400, we should declare tsc as even better: So we use 500.
>>     
>
> Why is the TSC better than a paravirt clocksource?  In our case this is
> definitely inaccurate.  Paravirt clocksources should be preferred to
> TSC, and both must be made available in hardware for platforms which do
> not support paravirt.
>
> Also, please cc all the paravirt developers on things related to
> paravirt, especially things with such broad effect.  I think 400 is a
> good value for a perfect native clocksource.  >400 should be reserved
> for super-real (i.e. paravirt) sources that should always be chosen over
> a hardware realistic implementation in a virtual environment.
>   

Yes, agreed.  The tsc is never the right thing to use if there's a
paravirt clocksource available.

What's wrong with rating it 300?  What inferior clocksource does it lose
out to?  Shouldn't that clocksource be lowered?  (Why don't we just use
1 to 10?)

    J
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/