The MPLS WG Archive

["David Allan" <dallan@nortelnetworks.com>]

Title: RE: AW: your mail

Tissa:

I think we need to be a bit stricter. Define mis-ordering...at what granularity ;-). Similarly any path test tool (e.g. ICMP) must follow the same path as the traffic.

cheers
Dave

> -----Original Message-----
> From: Tissa Senevirathne [mailto:tsenevir@hotmail.com]
> Sent: Tuesday, July 02, 2002 1:48 PM
> To: Heinrich.Hummel@icn.siemens.de; erosen@cisco.com;
> Shahram_Davari@pmc-sierra.com
> Cc: eosborne@cisco.com; george_s97@hotmail.com; scullptor@yahoo.com;
> mpls@UU.NET
> Subject: Re: AW: your mail
>
>
> Why are we saying ECMP hash is to pick a number between 1 and
> 6 ? Why not 64
> ?
>
> In my opinion ECMP is entirely a local implementation issue.
> And at WG
> requirement level one sentence to say
> " Any load balancing policies implemented MUST not mis order packets"
> is adequate
>
>
> >From: Hummel Heinrich <Heinrich.Hummel@icn.siemens.de>
> >To: "'erosen@cisco.com'" <erosen@cisco.com>,        Shahram Davari
> ><Shahram_Davari@pmc-sierra.com>
> >CC: "'Eric Osborne'" <eosborne@cisco.com>,        George Sheng
> ><george_s97@hotmail.com>, scullptor@yahoo.com,        mpls@UU.NET
> >Subject: AW: your mail Date: Tue, 2 Jul 2002 16:25:37 +0200
> >
> >It  gets weirder  and weirder: The MPLS WG invents a label
> stack, but does
> >not care at all that any of the
> >deeper nested labels may ever be signalled/carried by means of a
> >Label-TLV/object (no public comments to my
> >Hierarchical LSPs, draft-hummel-mpls-hierarchical-lsp-01.txt).
> >
> >However it is ok, to "steal" the deepest nested label and call it
> >"VC-label" for indexing
> >some VRF at some remote PE. Furthermore it is ok, to "steal"
> the very same
> >label for hashing.
> >
> >Independent from what is clean and what is quick&dirty, I
> cannot detect any
> >sense in giving a hash-meaning to the bottom label at all.
> >
> >
> >
> >Heinrich Hummel
> >Siemens
> >
> >-----Ursprüngliche Nachricht-----
> >Von: Eric Rosen [mailto:erosen@cisco.com]
> >Gesendet: Dienstag, 2. Juli 2002 16:06
> >An: Shahram Davari
> >Cc: 'Eric Osborne'; George Sheng; scullptor@yahoo.com; mpls@UU.NET
> >Betreff: Re: your mail
> >
> >
> >Shahram> To do ECMP, you need to  assign hashed values to
> egress ports.
> >This
> >Shahram> assignment is the hash state that I said you need.
> >
> >A hash is  a function that maps  some sequence of octets
> into  a sequence
> >of
> >integers.  If you want to split  traffic over six paths,
> while ensuring
> >that
> >all packets  with the  same bottom label  travel the  same
> path, you  need
> >a
> >function that maps  a 20 bit quantity  into a number from
> 1-6.   There is
> >no
> >need to maintain state of any kind.
>
>
>
>
> _________________________________________________________________
> Chat with friends online, try MSN Messenger: http://messenger.msn.com
>
>