RIFT -- Motivation, Additional Requirements and Use Cases in User Access Networks

Document Type Expired Internet-Draft (individual)
Last updated 2018-12-15 (latest revision 2018-06-13)
Stream (None)
Intended RFC status (None)
Expired & archived
plain text pdf html 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This Internet-Draft is no longer active.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


RIFT is a new specialized dynamic routing protocol originally designed for Clos and Fat Tree Data Center networks. It is designed to work on multilevel network topologies in which nodes in certain level will only connect to nodes in one upper or lower level with optional and non-contiguous intra-level connectivity. While the protocol was originally designed to meet the needs of Massively Scalable Data Centers, its ability to automatically prune the information distribution from higher levels to lower levels, as well as provide optimal routing for intra and inter-level traffic makes it a good match for user access networks, or any network that combines end user access and various compute enabling various network service for these end users. Current directions in distributed computing seek to blur even that distinction. Large distributed networks can be created, where virtual compute units can be in all tiers, combining and crossing many requirements for DC or User Access design. This draft seeks to analyze these requirements.


Yan Filyurin (yfilyurin@bloomberg.net)

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