QuickCast: Fast and Efficient Inter-Datacenter Transfers using Forwarding Tree Cohorts

TL;DR

QuickCast introduces a novel method for inter-datacenter data transfers that employs multiple forwarding trees to significantly reduce transfer times and bandwidth usage, outperforming previous multicast approaches.

Contribution

It presents the first comprehensive solution for partitioning receivers, constructing multiple forwarding trees, and scheduling flows to optimize transfer efficiency.

Findings

Speeds up average receiver completion time by up to 10x

Uses only 1.04x more bandwidth compared to single-tree methods

Improves overall completion time for all receivers by up to 1.6x at high loads

Abstract

Large inter-datacenter transfers are crucial for cloud service efficiency and are increasingly used by organizations that have dedicated wide area networks between datacenters. A recent work uses multicast forwarding trees to reduce the bandwidth needs and improve completion times of point-to-multipoint transfers. Using a single forwarding tree per transfer, however, leads to poor performance because the slowest receiver dictates the completion time for all receivers. Using multiple forwarding trees per transfer alleviates this concern--the average receiver could finish early; however, if done naively, bandwidth usage would also increase and it is apriori unclear how best to partition receivers, how to construct the multiple trees and how to determine the rate and schedule of flows on these trees. This paper presents QuickCast, a first solution to these problems. Using simulations on real-world network topologies, we see that QuickCast can speed up the average receiver's completion time by as much as $10\times$ while only using $1.04\times$ more bandwidth; further, the completion time for all receivers also improves by as much as $1.6\times$ faster at high loads.