Greg Watson

User-space protocols deliver high performance to applications on a low-cost Gb/s LAN

Two important questions in high-speed networking are firstly, how to provide Gbit/s networking at low cost and secondly, how to provide a flexible low-level network interface so that applications can control their data from the instant it arrives. We describe some work that addresses both of these questions. The Jetstream Gbit/s LAN is an experimental, low-cost network interface that provides the services required by delay-sensitive traffic as well as meeting the performance needs of current applications. Jetstream is a combination of traditional shared-medium LAN technology and more recent ATM cell- and switch-based technology. Jetstream frames contain a channel identifier so that the network driver can immediately associate an incoming frame with its application. We have developed such a driver that enables applications to control how their data should be managed without the need to first move the data into the applications address space. Consequently, applications can elect to read just a part of a frame and then instruct the driver to move the remainder directly to its destination. Individual channels can elect to receive frames that have failed their CRC, while applications can specify frame-drop policies on a per-channel basis. Measured results show that both kernel- and user-space protocols can achieve very good throughput: applications using both TCP and our own reliable byte-stream protocol have demonstrated throughputs in excess of 200 Mbit/s. The benefits of running protocols in user-space are well known- the drawback has often been a severe penalty in the performance achieved. In this paper we show that it is possible to have the best of both worlds.

Afterburner (network-independent card for protocols)

Many current implementations of protocols such as the Transmission Control Protocol/Internet Protocol (TCP/IP) are inefficient because data are often accessed more frequently than necessary. Three techniques that reduce the need for memory bandwidth are proposed. The techniques are copy-on-write, page remapping, and single-copy. Afterburner, a network-independent card that provides the services that are necessary for a single-copy protocol stack, is described. The card has 1 MByte of local buffers and provides a simple interface to a variety of network link adapters, including HIPPI and asynchronous transfer mode (ATM). Afterburner can support transfers to and from the link adapter card at rates up to 1 Gbit/s. An implementation of TCP/IP that uses the features provided by Afterburner to reduce the movement of data to a single copy is discussed. Measurements of the end-to-end performance of Afterburner and the single-copy implementation of TCP/IP are presented.<<ETX>>

The Demand Priority MAC protocol

A new technology needs to offer more than just 100 Mb/s. To succeed in the LAN marketplace, a new LAN technology must be very cost competitive with the established LANs, such as Ethernet and Token Ring, while also providing backwards compatibility with existing network software. We describe a new 100-Mb/s LAN technology that has these characteristics This technology is being defined as an open standard within the IEEE Project 802.12 Demand Priority group. Two important objectives were established for this LAN technology: first, it should be able to use the unshielded twisted pair (UTP) wiring found in a large number of installations and, in particular, to use the same wiring as defined for use in 1OBase-T. This objective was later extended to encompass support for the shielded twisted pair (STP) used for IEEE 802.5. This will enable the majority of current LAN users to benefit from their enormous investment in cable plant. The second objective was that the network should support new applications, such as video conferencing and remote training, while also providing backwards compatibility with the massive installed software base. Both objectives have been met. The Demand Priority MAC protocol currently being standardized in IEEE 802.12, offers substantial benefits over the CSMA/CD protocol of IEEE 802.3. By preserving both the current wiring infrastructure and investment in software, and by using the very simple Demand Priority MAC protocol, 100 Mb/s LANs could soon be as low-cost as 10Base-T is today. >

S++-a new MAC protocol for Gb/s local area networks

A media access control (MAC) layer protocol called S++, which offers several features that are desirable for gigabit per second local area networks, is described. The performance of the protocol has been investigated by detailed simulations which have been confirmed using an analytical model. A number of results that show how S++ offers consistently lower mean delays than the distributed queue dual bus (DQDB) protocol when used on a folded bus network are presented. Further results illustrate additional properties, which include the provision of pseudopriorities, a reduction in message reassembly time compared with DQDB, and the rapid redistribution of bandwidth under varying loads. >

HANGMAN Gb/s network

The design and implementation of the Hewlett-Packard active node gigabit-per-second metropolitan area network (HANGMAN) prototype network are discussed. The three main areas addressed are the physical-layer transmission system, the MAC sublayer protocols, and the architecture of the network interface unit. It is shown that low-cost gigabit-per-second transmission systems are practical, particularly in the local area environment where network links are typically limited to a few hundred meters. A MAC protocol that provides a synchronous service as well as the conventional asynchronous data service is described. The node architecture is presented and the way in which a single node can support multiple concurrent physical connections and how this architecture might be used in the future to develop high-performance protocol implementations are also discussed.<<ETX>>

AAL5 at a Gigabit for a Kilobuck

We present a novel LAN that has been designed to meet three criteria: it should be low cost, support standard protocols, and provide high performance. The LAN interconnects many workstations in a ring topology with a link rate of 1 Gbit/s. The packet format is the same as that of a B-ISDN cell except that our packets can have arbitrary length. The network also provides hardware support for ATM Adaptation Layer 5 as weIl as TCP/IP.We have implemented the ring network and we describe a network interface card which provides hardware support for critical functions such as calculating checksums. This card is used in conjunction with a second card that supports a single-copy implementation of the TCP/IP protocols. The application-to-application throughput has been measured at rates in excess of 200 Mbit/s between two workstations.

The S++ MAC protocol

Abstract In this paper we describe the S++ protocol, a new protocol designed for Gbit/s LANs. The S++ protocol has evolved from our experience with an earlier protocol, called S, which was implemented as part of a Gbit/s LAN project. Our experience with S enabled us to identify ways by which the performance could be significantly improved while retaining the inherent elegance and ease-of-implementation of the original protocol. We present simulation results for S++ which show how the protocol provides these characteristics. In addition we compare the performance of S++ to that of a well known MAC protocol, DQDB.