DNS-based Internet client clustering and characterization

摘要: This paper proposes a novel protocol which uses the Internet domain name system (DNS) to partition Web clients into disjoint sets, each of is associated with single DNS server. We define an L-DNS cluster be grouping that use same Local server resolve host names. identify such clusters in real-time using data obtained from Server conjunction server's authoritative DNS-both instrumented implementation our clustering algorithm. Using these clusters, we perform measurements four distinct locations. Our results show enables better estimation proximity client than previously proposed techniques. Thus, content distribution network, DNS-based scheme redirects request web one many servers based on client's coordinates (e.g., hops/latency/loss-rates) would