From: Jonathan Greenwood II (gwood83@gmail.com)
Date: Sun Dec 07 2008 - 03:44:52 ARST
Hey Pavel that's some hardcore testing you've done there. Very interesting
results, I'm more clear on your standpoint with "max-reserved-bandwidth" it
was very unclear with the previous threads on what the argument was based
upon. Very good post...
Jonathan
On Sat, Dec 6, 2008 at 9:07 PM, Pavel Bykov <slidersv@gmail.com> wrote:
> Hi all.
> I spent quite some time doing tests as part of another CBWFQ thread, and I
> want to post this to everyone.
> Although it's around 25 pages long, a lot of it are pictures and tables. It
> should really shed light on how QoS works, and what we are actually QoSing.
> Some points there:
> - you can really see why we need QoS on LAN
> - you can see how max-reserved-bandwidth command does not have any
> influence
> on queueing
> - a glimpse of internal CBWFQ operation
> - class-default starvation, where even with a tiny reservation to another
> class will not let any traffic in class-default through (in older IOS)
>
> Here is the link:
> http://www.boxoid.org/cisco/MAX-RESERVED-BANDWIDTH-AND-CBWFQ.pdf
>
>
> --
> Pavel Bykov
>
>
> Blogs and organic groups at http://www.ccie.net
>
> _______________________________________________________________________
> Subscription information may be found at:
> http://www.groupstudy.com/list/CCIELab.html
Blogs and organic groups at http://www.ccie.net
This archive was generated by hypermail 2.1.4 : Thu Jan 01 2009 - 12:53:07 ARST