Conference PaperOperational Lessons from ChameleonKeahey, Kate; Anderson, Jason; Ruth, Paul; Colleran, Jacob; Hammock, Cody; Stubbs, Joe; Zhen, ZhuoChameleon is a large-scale, deeply reconfigurable testbed built to support Computer Science experimentation. Unlike traditional systems of this kind, Chameleon has been configured using an adaptation of a mainstream open source infrastructure cloud system called OpenStack. We show that operating cloud systems requires both more skill and extra effort on the part of the operators - in particular where those systems are expected to evolve quickly - which can make systems of this kind expensive to run. We discuss three ways in which those operations costs can be managed: innovative mon- itoring and automation of systems tasks, building “operator co-ops”, and collaborating with users.2019-01-0110107209Proceedings of the Humanware Advancing Research in the Cloudhttps://doi.org/1743358National Science Foundation