RDMA over the Internet Protocol Suite (roi) Concluded WG

Note: The data for concluded WGs is occasionally incorrect.

WG Name RDMA over the Internet Protocol Suite
Acronym roi
Area Transport Area (tsv)
State Concluded
Charter charter-ietf-roi-01 Approved
Dependencies Document dependency graph (SVG)
Personnel Chairs Allyn Romanow
Stephen Bailey
Mailing list Address rdma@yahoogroups.com
To subscribe rdma-subscribe@yahoogroups.com
Archive http://groups.yahoo.com/group/rdma

Charter for Working Group


Much of today's usage of the Internet and IP networks is for
buffer-to-buffer data transfers, often in the form of bulk data and
inter-process communications, using a variety of Internet protocols,
including HTTP, FTP, NFS, CIFS, and soon, iSCSI. Gigabit and faster
network transfers incur heavy system resource costs, including both
CPU use and system bus bandwidth, particularly on the receiving side.
Overhead is dominated by the costs of processing and copying incoming
data in order to place it at its ultimate destination.

A solution to this problem that has been widely used in both research
and industry is direct data placement, which can be enabled by a
remote direct memory access (RDMA) protocol. An RDMA protocol makes it
possible for a network interface to place data from an incoming packet
directly into the memory where the application wants the data. This
has significant savings in the receive side overhead and is needed for
efficient support of multi-gigabit networks.

The industry's need for high efficiency, high bandwidth communications
in the data center has led to both proprietary and standards-based
RDMA technologies, such as the Virtual Interface Architecture (VIA),
and Infiniband. However, these protocols are incompatible with the
Internet Protocol framework. The purpose of this WG is to develop the
requirements for an RDMA architecture and protocol for use with the
Internet Protocol suite.

It is envisioned that the RDMA protocol developed will be cleanly
layered above existing Internet transport protocols such as SCTP and
TCP, and rely on them for reliable delivery and congestion management.

The working group will develop several documents. These are:
* A problem statement, which describes what the problems are, the
motivation for making RDMA service available in the Internet
and IP networks, and provides a basic explanation of generic
RDMA technology. Informational RFC.
* A requirements document that describes the technical
requirements of an RDMA protocol for use in the Internet and
IP networks. Informational RFC.
* A document that sets out the case for RDMA in a detailed
discussion of the technology, including what the problem is,
alternative methods of solving it, and why an RDMA technology
is a sound approach. Informational RFC.


Date Milestone