The Jellyfish network has recently be proposed as an alternate to the fat-tree network as the interconnect for data centers and high performance computing clusters. Jellyfish adopts a random regular graph as its topology and has been showed to be more cost-effective than fat-trees. Effective routing on Jellyfish is challenging. It is known that shortest path routing and equal-cost multi-path routing (ECMP) do not work well on Jellyfish. Existing schemes use variations of k-shortest path routing (KSP). In this work, we study two routing components for Jellyfish: path selection that decides the paths to route traffic, and routing mechanisms that decide which path to be used for each packet. We show that the performance of the existing KSP can be significantly improved by incorporating two heuristics, randomization and edge-disjointness. We evaluate a range of routing mechanisms including traffic oblivious and traffic adaptive schemes and identify an adaptive routing scheme that has significantly higher performance than others including the Universal Globally Adaptive Load-balance (UGAL) routing.
翻译:Jellyfish 网络最近被提议作为脂肪树网络的替代物,作为数据中心和高性能计算群群的互连。 Jellyfish 采用随机的常规图表作为其地形学,并显示其比脂肪树更具成本效益。 Jellyfish 的有效路线是具有挑战性的。众所周知,最短路线路线和同等成本的多途径路线(ECMP)对Jellyfish 并不会很好地发挥作用。 现有的计划使用 k-horsttest 路径(KSP ) 的变异。 在这项工作中,我们研究了Jellyfish 的两个路线构成:决定交通路线路径的路径选择,以及决定每包使用哪条路径的路线机制。我们表明,现有的KSP的性能可以通过纳入两条超高路线、随机化和边缘偏离来大大改进。我们评估一系列的路线机制,包括交通偏差和交通适应性适应性计划,并确定比包括全球全球适应性负力平衡(UGAL) 等其他功能要高得多的适应性路由。