论文部分内容阅读
Cloud providers (e.g., Google, Alibaba, Amazon) own large-scale datacenter networks that comprise thousands of switches and links. A load-balancing mechanism is supposed to effectively utilize the bisection bandwidth. Both Equal-Cost Multi-Path (ECMP), the canonical solution in practice, and alter-natives come with performance limitations or signif-icant deployment challenges. In this work, we pro-pose Closer, a scalable load balancing mechanism for cloud datacenters. Closer complies with the evaluation of technology including the deployment of Clos-based topologies, overlays for network virtualization, and virtual machine (VM) clusters. We decouple the sys-tem into centralized route calculation and distributed route decision to guarantee its flexibility and stabil-ity in large-scale networks. Leveraging In-band Net-work Telemetry (INT) to obtain precise link state in-formation, a simple but efficient algorithm implements a weighted ECMP at the edge of fabric, which enables Closer to proactively map the flows to the appropri-ate path and avoid the excessive congestion of a single link. Closer achieves 2 to 7 times better flow com-pletion time (FCT) at 70％network load than existing schemes that work with same hardware environment.