We present a large-scale measurement of clusters of hosts sharing the same local DNS servers. We analyze properties of these "LDNS clusters" from the perspective of content delivery networks, which commonly use DNS for load distribution. We found that not only LDNS clusters differ widely in terms of their size and geographical compactness but that the largest clusters are actually extremely compact. This suggests potential benefits of a load distribution strategy with nuanced treatment of different LDNS clusters based on the combination of their size and compactness. We further observed interesting variations in LDNS setups including a wide use of "LDNS pools" (which as we explain in the paper are different from setups where end-hosts simply utilize multiple resolvers).

IP Anycast has many attractive features for any service that involve the replication of multiple instances across the Internet. IP Anycast allows multiple instances of the same service to be “naturally” discovered, and requests for this service to be delivered to the closest instance. However, while briefly considered as an enabler for content delivery networks (CDNs) when they first emerged, IP Anycast was deemed infeasible in that environment. The main reasons for this decision were the lack of load awareness of IP Anycast and unwanted side effects of Internet routing changes on the IP Anycast mechanism. In this article we re-evaluate IP Anycast for CDNs by proposing a load-aware IP Anycast CDN architecture. Our architecture is prompted by recent developments in route control technology, as well as better understanding of the behavior of IP Anycast in operational settings. Our architecture makes use of route control mechanisms to take server and network load into account to realize load-aware Anycast. We show that the resulting redirection requirements can be formulated as a Generalized Assignment Problem and present practical algorithms that address these requirements while at the same time limiting connection disruptions that plague regular IP Anycast. We evaluate our algorithms through trace based simulation using traces obtained from a production CDN network.

Web hosting providers are increasingly looking into dynamic hosting to reduce costs and improve the performance of their platforms. Instead of provisioning fixed resources to each customer, dynamic hosting maintains a variable number of application instances to satisfy current demand. While existing research in this area has mostly focused on the algorithms that decide on the number and location of application instances, we address the problem of efficient enactment of these decisions once they are made. We propose a new approach to application placement and experimentally show that it dramatically reduces the cost of application placement, which in turn improves the end-to-end agility of the hosting platform in reacting to demand changes.

Because it is an integral part of the Internet routing apparatus, and because it allows multiple instances of the same service to be "naturally" discovered, IP Anycast has many attractive features for any service that involve the replication of multiple instances across the Internet. While briefly considered as an enabler when content distribution networks (CDNs) first emerged, the use of IP Anycast was deemed infeasible in that environment. The main reasons for this decision were the lack of load awareness of IP Anycast and unwanted side effects of Internet routing changes on the IP Anycast mechanism. Prompted by recent developments in route control technology, as well as a better understanding of the behavior of IP Anycast in operational settings, we revisit this decision and propose a load-aware IP Anycast CDN architecture that addresses these concerns while benefiting from inherent IP Anycast features. Our architecture makes use of route control mechanisms to take server and network load into account to realize load-aware Anycast. We show that the resulting redirection requirements can be formulated as a Generalized Assignment Problem and present practical algorithms that address these requirements while at the same time limiting session disruptions that plague regular IP Anycast. We evaluate our algorithms through trace based simulation using traces obtained from an operation CDN network.

This paper presents the architecture and the preliminary evaluation ofa request routing DNS server that decouples server selectionfrom the rest of DNS functionality. Our DNS server, which we refer toas MyXDNS, exposes well-defined APIs for uploading an externallycomputed server selection policy and for interacting with an external networkproximity service. With MyXDNS, researchers can explore their ownnetwork proximity metrics and request routing algorithms withouthaving to worry about DNS internals. Furthermore, MyXDNS is based onopen-source MyDNS and is available to public. Stress-testing of MyXDNSindicated that it achieves its flexibility at an acceptable cost: asingle MyXDNS running on a low-level server can process 3000 req/secwith sub-millisecond response even in the presence of continuousupdates to server selection policy.