Increasing the Performability of Computer Clusters Using RADIC II

Performance and availability form an undissociable binomial for some kind of applications. Therefore, the fault tolerant solutions must take into consideration these two constraints when it has been designed. Our previous work, called RADIC, implemented a basic level protection allowing to recover from faults just using the active cluster resources, changing the system configuration. However, Such approach may genenerate some performance degradation in some cases. In this paper, we present RADIC II, which incorporates a new protection level using dynamic redundancy, allowing to mitigate or avoid the recovery side-effects. Such functionality allows restoring a changed system configuration and it can avoid the configuration changes. The results has shown that RADIC-II operates correctly and becomes itself as a good approach to provide high availability to the parallel applications without suffer a system degradation in post-recovery execution.