Reliability is widely identified as an increasingly relevant issue in heterogeneous service-oriented systems because processor failure affects the quality of service to users. Replication-based fault-tolerance is a common approach to satisfy application's reliability requirement. This study solves the problem of minimizing redundancy to satisfy reliability requirement for a directed acyclic graph (DAG)-based parallel application on heterogeneous service-oriented systems. We first propose the enough replication for redundancy minimization (ERRM) algorithm to satisfy application's reliability requirement, and then propose heuristic replication for redundancy minimization (HRRM) to satisfy application's reliability requirement with low time complexity. Experimental results on real and randomly generated parallel applications at different scales, parallelism, and heterogeneity verify that ERRM can generate least redundancy followed by HRRM, and the state-of-the-art MaxRe and RR algorithm. In addition, HRRM implements approximate minimum redundancy with a short computation time.

中文翻译：

---

最小化冗余以满足异构面向服务系统上并行应用程序的可靠性要求

在异构面向服务的系统中，可靠性被广泛认为是一个日益相关的问题，因为处理器故障会影响对用户的服务质量。基于复制的容错是满足应用程序可靠性要求的常用方法。本研究解决了最小化冗余的问题，以满足异构面向服务系统上基于有向无环图 (DAG) 的并行应用程序的可靠性要求。我们首先提出了冗余最小化的足够复制（ERRM）算法来满足应用程序的可靠性要求，然后提出冗余最小化的启发式复制（HRRM）算法来满足应用程序的低时间复杂度的可靠性要求。在不同规模、并行性和异构性的真实和随机生成的并行应用程序上的实验结果验证了 ERRM 可以生成最少的冗余，其次是 HRRM，以及最先进的 MaxRe 和 RR 算法。此外，HRRM 以较短的计算时间实现了近似最小冗余。