[nsp] ip load-sharing per-packet - cef accelerated ?

[Jared Mauch]

On Mon, Mar 10, 2003 at 03:29:11PM -0700, Cisco Geek Rotation wrote:
> At 05:26 PM 3/10/2003 -0500, Jared Mauch wrote:
> >On Mon, Mar 10, 2003 at 02:22:12PM -0800, Dan Hollis wrote:
> >> My understanding is that 'ip load-sharing per-packet' is CEF accelerated,
> >> yes?
> >>
> >> Just trying to understand why some providers won't support per-packet 
> >CEF.
> >
> >        A good reason they tend to avoid it is it causes
> >out of order packets which result in lower end-to-end throughput.
> >
> >        What you want is a srcIP/dstIP/srcPT/dstPT based balancing
> >to be perfectly honest.  This will keep the same flows on the same
> >circuit.
> >
> >        - Jared
> 
> 
> 
> Is this what ip cef per-destination does?

	I believe that takes only the dstIP into account.

	By including the ports in the analysis, you could
(for example), have 2 t1s and two different people sucking
down from a remote system (ftp.freebsd.org) at 170k each.

	- jared

-- 
Jared Mauch  | pgp key available via finger from jared at puck.nether.net
clue++;      | http://puck.nether.net/~jared/  My statements are only mine.