“…To address this issue, over the last decade, there has been a slew of proposals in the literature on how to improve congestion control in datacenters and efficiently share network bandwidth among competing flows and applications. Some of these proposals focus on providing per-flow fairness [18,20,34] with various network-level objectives, such as minimizing per-packet latency [25] or flow completion time [5,6,44] using network-level properties, such as flow size or deadlines [5,6,13,25,44,55]. Other works aim to provide isolation among tenants or applications when running in shared datacenters [11,12,23,27,32,48,57].…”