Balanced Nonadaptive Redundancy Scheduling

Distributed computing systems implement redundancy to reduce the job completion time and variability. Despite a large body of work about redundancy, analytical performance evaluation techniques in queuing is still an open problem. In this work, we take one step forward analyze scheduling policies with redundancy. particular, study pattern shared servers among replicas different jobs. To end, employ combinatorics graph theory define derive indicators using statistics overlaps. We consider two classical nonadaptive policies: random round-robin. then propose policy based on combinatorial block designs. Compared conventional scheduling, proposed improves indicators. expansion property graphs associated round-robin design-based policies. It turns out superior results from better properties its graph. As indicated by indicators, simulation show that outperforms scenarios. Specifically, it reduces average waiting queue up 25% compared 100% policy.