• Corpus ID: 11795237

Redundancy and Replication Fault Tolerance on the System Level

@inproceedings{FriedrichAlexander2014RedundancyAR,
  title={Redundancy and Replication Fault Tolerance on the System Level},
  author={Kurt Kanzenbach Friedrich-Alexander},
  year={2014}
}

• Kurt Kanzenbach Friedrich-Alexander
• Published 2014
• Computer Science

In the past decade the clock rates and densities of processors, enabled by new and smaller manufacture processes, increased. Due to this development current processors become less and less reliable and more vulnerable to physical effects such as the cosmic radiation, which can result in transient failures. One common approach to address hardware failures like these is to use redundant hardware. However, this strategy is expensive and not suitable in all cases. One alternative is to use redundancy and replication on the system level without exploiting extra hardware. Since software techniques may be implemented on different levels of the software stack, this seminar paper introduces and compares software-only approaches using redundancy and replication in order to detect and recover from hardware faults. In particular, two compiler-based, one process-based and one hypervisor-based techniques are discussed. The evaluation demonstrates that it is possible to detect and recover from hardware failures on the software or system level, whereas implementing fault tolerance on each software-level has its own advantages and drawbacks.