2014 IEEE 30th International Conference on Data Engineering (ICDE) (2014)
Chicago, IL, USA
March 31, 2014 to April 4, 2014
Peter Alvaro , UC Berkeley, USA
Neil Conway , UC Berkeley, USA
Joseph M. Hellerstein , UC Berkeley, USA
David Maier , Portland State University, USA
Distributed consistency is perhaps the most discussed topic in distributed systems today. Coordination protocols can ensure consistency, but in practice they cause undesirable performance unless used judiciously. Scalable distributed architectures avoid coordination whenever possible, but undercoordinated systems can exhibit behavioral anomalies under fault, which are often extremely difficult to debug. This raises significant challenges for distributed system architects and developers. In this paper we present BLAZES, a cross-platform program analysis framework that (a) identifies program locations that require coordination to ensure consistent executions, and (b) automatically synthesizes application-specific coordination code that can significantly outperform general-purpose techniques. We present two case studies, one using annotated programs in the Twitter Storm system, and another using the Bloom declarative language.
Servers, Storms, Fault tolerance, Fault tolerant systems, Semantics, Topology, Twitter
P. Alvaro, N. Conway, J. M. Hellerstein and D. Maier, "Blazes: Coordination analysis for distributed programs," 2014 IEEE 30th International Conference on Data Engineering (ICDE), Chicago, IL, USA, 2014, pp. 52-63.