4.3 Interworking
Summary
- Three different designs were implemented to interwork HIPPI with wide area ATM networks over both SONET and all-optical transmission infrastructure; explorations included the use of 4x155 Mbps striping and non-striped 622 Mbps access, local HIPPI termination and wide area HIPPI bridging; resulting transfer rates ranged from 370 to 450 Mbps
- A HIPPI-SONET gateway was implemented which allowed transfer of full 800 Mbps HIPPI rates across striped 155 Mbps wide area SONET links; capabilities included variable bandwidth allocation of up to 1.2 Gbps and optional use of forward error correction, with a transfer rate of 790 Mbps obtained for HIPPI traffic
- Seamless ATM DAN-LAN-WAN interworking was explored through implementation of interface devices which provided physical layer interfacing between 500 Mbps DAN Glink transmission, LAN ATM switch ports, and a wide area striped 155 Mbps ATM/SONET network; interface functions included translation of non-standard DAN ATM formats and HEC generation
- An investigation of IP processor-based interworking at gigabit speeds concluded that, for a 622 Mbps link rate, a 100 MHz RISC processor could perform basic IP packet processing with sizes as small as 83 Bytes/packet, but that I/O port processing will in general require a dedicated processor for each flow direction, with an evolution to distributed architectures based on hardware switching fabrics
A significant amount of work was carried out in the testbeds on devices to allow the interworking of different high speed technologies. We use the term interworking here to distinguish this work from more general systems-level internetworking research. The testbed work in this area can be grouped into the following categories: HIPPI-ATM, HIPPI-SONET, and DAN/LAN/WAN ATM. A preliminary investigation into issues associated with using an IP protocol for generic packet forwarding at gigabit speeds was also conducted.
(The area of general internetworking at gigabit speeds was specifically not included as a research topic when the testbeds were formed. It was felt that work was first required on the underlying network technologies, with internetworking research more logically undertaken following completion of the initial testbed initiative.)