DDCCast: Meeting Point to Multipoint Transfer Deadlines Across Datacenters using ALAP Scheduling Policy

Abstract

Large cloud companies manage dozens of datacenters across the globe connected using dedicated inter-datacenter networks. An important application of these networks is data replication which is done for purposes such as increased resiliency via making backup copies, getting data closer to users for reduced delay and WAN bandwidth usage, and global load balancing. These replications usually lead to network transfers with deadlines that determine the time prior to which all datacenters should have a copy of the data. Inter-datacenter networks have limited capacity and need be utilized efficiently to maximize performance. In this report, we focus on applications that transfer multiple copies of objects from one datacenter to several datacenters given deadline constraints. Existing solutions are either deadline agnostic, or only consider point-to-point transfers. We propose DDCCast, a simple yet effective deadline aware point to multipoint technique based on DCCast and using ALAP traffic allocation. DDCCast performs careful admission control using temporal planning, uses rate-allocation and rate-limiting to avoid congestion and sends traffic over forwarding trees that are carefully selected to reduce bandwidth usage and maximize deadline meet rate. We perform experiments confirming DDCCast's potential to reduce total bandwidth usage by up to $45\%$ while admitting up to $25\%$ more traffic into the network compared to existing solutions that guarantee deadlines.