Skip to Main Content
All distributed computing systems face the architectural question of the location (and nature) of programmability in the telecommunications networks, computers, and other peripheral devices comprising them. The perspective of this paper is that network elements should be as programmable as possible, to enable the most flexible distributed computing systems. There has been a persistent confluence among operating systems, programming languages, networking and distributed systems. We demonstrate how these interactions led to what is called "active networking," and in the spirit of "vox audita peril, littera scripta manel" (the spoken word perishes, but the written word remains), include an account of how it was made to happen. Lessons are drawn both from the broader research agenda, and the specific goals pursued in the SwitchWare project. We speculate on likely futures for active networking.