2018/12/13 by Aran Bergman, Bergman, Aran, Israel Cidon +12
Computer Science · #Caching and Content Delivery #FOS: Computer and information sciences #Network Traffic and Congestion Control #Networking and Internet Architecture (cs.NI) #Software-Defined Networks and 5G #cs.NI
paper · pdf · doi:10.48550/arxiv.1812.05582
14 pages, 15 figures. Copyright notice added after submission to IEEE. Fixed error in reference from figure 6 to figure 5
openalex publication_date 2018/12/13 · arxiv created 2018/12/20 · arxiv updated 2018/12/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We contend that, analogously to the transition from resource-limited on-prem computing to resource-abundant cloud computing, Internet data delivery should also be adapted to a reality in which the cloud offers a virtually unlimited resource, i.e., network capacity, and virtualization enables delegating local tasks, such as routing and congestion control, to the cloud. This necessitates rethinking the traditional roles of inter- and intra-domain routing and conventional end-to-end congestion control. We introduce Optimized Cloudified Delivery (OCD), a holistic approach for optimizing joint Internet/cloud data delivery, and evaluate OCD through hundreds of thousands of file downloads from multiple locations. We start by examining an OCD baseline approach: traffic from a source A to a destination B successively passes through two cloud virtual machines operating as relays - nearest to A and B; and the two cloud relays employ TCP split. We show that even this naive strategy can outperform recently proposed improved end-to-end congestion control paradigms (BBR and PCC) by an order of magnitude. Next, we present a protocol-free, ideal pipe model of data transmission, and identify where today's Internet data delivery mechanisms diverge from this model. We then design and implement OCD Pied Piper. Pied Piper leverages various techniques, including novel kernel-based transport-layer accelerations, to improve the Internet-Cloud interface so as to approximately match the ideal network pipe model.