Multi-Path Routing on the Jellyfish Networks

TL;DR

This paper improves multi-path routing in Jellyfish network topologies by enhancing path selection heuristics and evaluating adaptive routing schemes, leading to significantly better performance than existing methods.

Contribution

It introduces improved heuristics for path selection in Jellyfish networks and evaluates various routing mechanisms, identifying a highly effective adaptive routing scheme.

Findings

Enhanced KSP with randomization and edge-disjointness improves performance.

Adaptive routing schemes outperform traffic oblivious methods.

Identified a superior adaptive routing scheme with higher performance.

Abstract

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.