MPLS-Based Hierarchical SDN for Hyper-Scale DC/Cloud

Document Type Expired Internet-Draft (individual)
Authors Luyuan Fang  , Deepak Bansal  , Fabio Chiussi  , Chandrasekar R  , Ebben Aries  , Shahram Davari  , Barak Gafni  , Dan Voyer  , Nabil Bitar 
Last updated 2016-07-26 (latest revision 2016-01-23)
Stream (None)
Intended RFC status (None)
Expired & archived
pdf htmlized bibtex
Stream Stream state (No stream defined)
Consensus Boilerplate Unknown
RFC Editor Note (None)
IESG IESG state Expired
Telechat date
Responsible AD (None)
Send notices to (None)

This Internet-Draft is no longer active. A copy of the expired Internet-Draft can be found at


This document describes Hierarchical SDN (HSDN), an architectural solution to scale the Data Center (DC) and Data Center Interconnect (DCI) networks to support tens of millions of physical underlay endpoints, while efficiently handling both Equal Cost Multi Path (ECMP) load-balanced traffic and any-to-any end-to-end Traffic Engineered (TE) traffic. HSDN achieves massive scale using surprisingly small forwarding tables in the network nodes. HSDN introduces a new paradigm for both forwarding and control planes, in that all paths in the network are pre-established in the forwarding tables and the labels can identify entire paths rather than simply destinations. The HSDN forwarding architecture is based on four main concepts: 1. Dividing the DC and DCI in a hierarchically-partitioned structure; 2. Assigning groups of Underlay Border Nodes in charge of forwarding within each partition; 3. Constructing HSDN MPLS label stacks to identify endpoints and paths according to the HSDN structure; and 4. Forwarding using the HSDN MPLS labels.


Luyuan Fang (
Deepak Bansal (
Fabio Chiussi (
Chandrasekar R (
Ebben Aries (
Shahram Davari (
Barak Gafni (
Dan Voyer (
Nabil Bitar (

(Note: The e-mail addresses provided for the authors of this Internet-Draft may no longer be valid.)