Dodoor: Efficient Randomized Decentralized Scheduling with Load Caching for Heterogeneous Tasks and Clusters
arXiv:2510.12889 · doi:10.1007/978-3-032-35251-4_8
Abstract
This paper presents Dodoor, a randomized decentralized scheduler for heterogeneous clusters. Dodoor removes hot-path probing via batched cache refreshes and introduces a heterogeneity-aware resource-load score that ranks sampled candidates using multidimensional fit and queued-duration pressure. On a 101-node CloudLab cluster, Dodoor cuts scheduler messages by 55-66% while improving throughput by up to 33.2% (Azure) and 21.5% (FunctionBench) compared with decentralized baseline schedulers. Dodoor also reduces mean makespan latency by up to 12.1% and 7.2%, and tail latency by up to 21.9% and 24.6%.
14 pages, 5 figures. Published in Euro-Par 2026