linux-kernel - Re: Cryogenic: Enabling Power-Aware Applications on Linux

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]

Message-ID: <53487FE7.2040604@grothoff.org>
Date:	Sat, 12 Apr 2014 01:51:03 +0200
From:	Christian Grothoff <christian@...thoff.org>
To:	Pavel Machek <pavel@....cz>
CC:	Alejandra Morales <alejandra.morales@....de>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Re: Cryogenic: Enabling Power-Aware Applications on Linux

On 04/12/2014 12:05 AM, Pavel Machek wrote:
> Hi!
> 
>>>> Cryogenic is the result of my Master's Thesis, completed at the Technical University
>>>> of Munich under the supervision of Christian Grothoff. You can find more information
>>>> about Cryogenic at https://gnunet.org/cryogenic
>>>
>>> Do you have any measurements how much power it actually saves?
>>
>> Yes, it depends on the device, but we have demonstrated power
>> savings for two different types of devices using two different
>> measurement setups performed by two independent groups.  Some
>> of the measurements are available on the website, the second
>> set should become available "soon" (but we can already say that
>> for the scenario we measured, the savings are in the same range
>> as before).
> 
> The video I seen.... AFAICT the savings are in <10% range?

For the scenario we scripted, yes. But note that we only
allowed 50% of the packets transmitted to be delayed (a bit).
If you were to increase the allowed delay or allowed a larger
fraction of packets to be delayed, you should see larger savings.

> I seen demo on UDP packets... delayed TCP socket write is probably
> easy, but would API allow delayed TCP connect?

Yes.

> Hmm, but the API needs redoing, anyway, fcntl()?

Depends --- while I like the idea, I did not hear enough to be
certain that having this feature embedded in such a non-modular
way was already the consensus (and I do not see a reasonable
way to change the API this way while maintaining the modularity
of the current code).

Download attachment "0x48426C7E.asc" of type "application/pgp-keys" (7099 bytes)