Large-scale performance tests (Distributed algorithms) (Programming)
Conducted byRichard Ekwall
DescriptionSeveral consensus and atomic broadcast algorithms are tested on a distributed system with a large number of nodes in order to examine how well the algorithms scale as the size of the system increases. The number of nodes available in Grid'5000 allow us to perform experiments that wouldn't have been possible in our laboratory. Furthermore, by executing experiments on several different sites in Grid'5000, we can also measure the influence of the inter-site latency on the performance of the different algorithms.
Tools usedNo information
Shared by: Richard Ekwall
Last update: 0000-00-00 00:00:00