In this paper, we present a novel approach to exploit the relationships among domain names to improve the cache hit rate for a local DNS server. Using these relationships, an authoritative DNS server (ADNS) can piggyback resolutions for future queries as part of the response message for an initial query. The approach improves the cache hit rate as well as reducing the total queries and responses. The approach is particularly attractive because it can be implemented with no changes to the existing DNS protocol.Trace-based simulations show more than 50% of cache misses can be reduced in the best case while straightforward policies, using frequency and relevancy data for an ADNS, reduce cache misses by 25-40% and DNS traffic by 20-35%. These percentages improve if we focus the policies on resource records with smaller authoritative TTLs. We also show improved performance for hybrid approaches that combine the approach with renewal-based approaches.In conjunction with this work we also did a study on current DNS performance for 20 locations in the United States. The outcome of this study is that the current average DNS latency is generally in the range of 200-300ms, but range from 500ms to multiple seconds if we look at the 95% response time. Approaches, such as what we propose, that reduce the amount of DNS traffic will improve the overall response time for applications.

No abstract

Persistent connections address inefficiencies associated with multiple concurrent connections. They can improve response time when successfully used with pipelining to retrieve a set of objects from a Web server. In practice, however, there is inconsistent support for persistent connections, particularly with pipelining, from Web servers, user agents, and intermediaries. Web browsers continue to open multiple concurrent TCP connections to the same server. This paper proposes a new idea of packaging the set of objects embedded on a Web page into a single bundle object for retrieval by clients. Our analysis indicates that if embedded objects on a Web page are delivered to clients as a single bundle, the response time experienced by the clients is as good as or better than that provided by currently deployed mechanisms. We also show that, relative to the currently used retrieval methods, our approach reduces the load on the network and servers. The key contribution of our work is a mechanism that gives Web servers better control over the number and duration of TCP connections they support. Implementation of the mechanism requires no changes to the HTTP protocol.