arXiv subjects

Ramesh K. Sitaraman

Publications and source records attributed to Ramesh K. Sitaraman.

20 records · Page 2Linked to original sources

arXiv2011

Energy-Aware Load Balancing in Content Delivery Networks

Internet-scale distributed systems such as content delivery networks (CDNs) operate hundreds of thousands of servers deployed in thousands of data center locations around the globe. Since the energy costs of operating such a large IT infrastructure are a significant fraction of the total operating costs, we argue for redesigning CDNs to incorporate energy optimizations as a first-order principle. We propose techniques to turn off CDN servers during periods of low load while seeking to balance three key design goals: maximize energy reduction, minimize the impact on client-perceived service availability (SLAs), and limit the frequency of on-off server transitions to reduce wear-and-tear and its impact on hardware reliability. We propose an optimal offline algorithm and an online algorithm to extract energy savings both at the level of local load balancing within a data center and global load balancing across data centers. We evaluate our algorithms using real production workload traces from a large commercial CDN. Our results show that it is possible to reduce the energy consumption of a CDN by more than 55% while ensuring a high level of availability that meets customer SLA requirements and incurring an average of one on-off transition per server per day. Further, we show that keeping even 10% of the servers as hot spares helps absorb load spikes due to global flash crowds with little impact on availability SLAs. Finally, we show that redistributing load across proximal data centers can enhance service availability significantly, but has only a modest impact on energy savings.

cs.NI↗

arXiv2011

Algorithms for Constructing Overlay Networks For Live Streaming

We present a polynomial time approximation algorithm for constructing an overlay multicast network for streaming live media events over the Internet. The class of overlay networks constructed by our algorithm include networks used by Akamai Technologies to deliver live media events to a global audience with high fidelity. We construct networks consisting of three stages of nodes. The nodes in the first stage are the entry points that act as sources for the live streams. Each source forwards each of its streams to one or more nodes in the second stage that are called reflectors. A reflector can split an incoming stream into multiple identical outgoing streams, which are then sent on to nodes in the third and final stage that act as sinks and are located in edge networks near end-users. As the packets in a stream travel from one stage to the next, some of them may be lost. A sink combines the packets from multiple instances of the same stream (by reordering packets and discarding duplicates) to form a single instance of the stream with minimal loss. Our primary contribution is an algorithm that constructs an overlay network that provably satisfies capacity and reliability constraints to within a constant factor of optimal, and minimizes cost to within a logarithmic factor of optimal. Further in the common case where only the transmission costs are minimized, we show that our algorithm produces a solution that has cost within a factor of 2 of optimal. We also implement our algorithm and evaluate it on realistic traces derived from Akamai's live streaming network. Our empirical results show that our algorithm can be used to efficiently construct large-scale overlay networks in practice with near-optimal cost.

cs.NI↗