Testing Architectures for Large Scale Systems

Typical distributed testing architectures decompose test cases in actions and dispatch them to different nodes. They use a central test controller to synchronize the action execution sequence. This architecture is not fully adapted to large scale distributed systems, since the central controller does not scale up. This paper presents two approaches to synchronize the action execution sequence in a distributed manner. The first approach organizes the testers in a B-tree manner synchronizing through messages exchanged among parents and children. The second approach synchronizes through gossiping messages exchanged among consecutive testers. We compare these two approaches and discuss their advantages and drawbacks.