netdev - Re: Network latency regressions from 2.6.22 to 2.6.29

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: <Pine.LNX.4.64.0904172354160.2522@wrl-59.cs.helsinki.fi>
Date:	Sat, 18 Apr 2009 00:43:09 +0300 (EEST)
From:	"Ilpo Järvinen" <ilpo.jarvinen@...sinki.fi>
To:	Christoph Lameter <cl@...ux.com>
cc:	David Miller <davem@...emloft.net>, dada1@...mosbay.com,
	rick.jones2@...com, Netdev <netdev@...r.kernel.org>
Subject: Re: Network latency regressions from 2.6.22 to 2.6.29

On Fri, 17 Apr 2009, Christoph Lameter wrote:

> On Thu, 16 Apr 2009, David Miller wrote:
> 
> > More seriously, it's going to be hard to isolate anything
> > unless you concern yourself with changes to one thing
> > on one system at a time.
> 
> Only the kernel version was changed on both systems. Changing only a
> single system would have meant considering complex interactions between
> the network layers of varying versions which would make
> the problem even more difficult to track down.
> 
> I changed one thing: The kernel version.

No we're not talking about n^2 results here but claiming that changing 
only a single network endpoint makes things _more complex_ is quite bogus? 
Like it or not, those network layers you mention are still separated by 
pretty standadized medium whose encoding and timing is certainly quite 
independent of the kernel version :-).

I'd suggest you take the latest and v2.6.22 and run the remaining two 
mixed setups (I hope your scripts are not too fixed with identical 
versions... :-)).

-- 
 i.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html