Michael Rabinovich

On modern DNS behavior and properties

Thomas Callahan, Mark Allman, Michael Rabinovich
Appears in: 
CCR July 2013

The Internet crucially depends on the Domain Name System (DNS) to both allow users to interact with the system in human-friendly terms and also increasingly as a way to direct traffic to the best content replicas at the instant the content is requested. This paper is an initial study into the behavior and properties of the modern DNS system. We passively monitor DNS and related traffic within a residential network in an effort to understand server behavior--as viewed through DNS responses?and client behavior--as viewed through both DNS requests and traffic that follows DNS responses.

Public Review By: 
Sharad Agarwal

Studies by online content providers including Amazon, Google and Microsoft, and by network game researchers have quantified the impact of network latency on user behavior. DNS is an important part of that latency -- both in contributing to initial connection setup latency but also in picking a server that has low network distance and low load for the client to use. A number of measurement studies of DNS behavior on the Internet have been published in the past. This paper is a more recent one. The authors have studied 14 months of data from a 90 home neighborhood in the US, served by bi-directional 1 Gbps fiber links. This data includes 200 million DNS queries and 1.1 billion flows. There are a number of notable findings in this paper. 63% of hostnames were requested only once throughout the 14 month window. Google's public DNS resolver served only 1% of queries. 75% of hostnames mapped to only 1 IP address, and those tended to not be optimized for geographic locality to the client. Two-thirds of DNS transactions completed in under 1ms, but 25% took between 10ms and 1s. 40% of DNS responses went unused, perhaps as a result of DNS prefetching. While the contribution of this paper is time-bounded until DNS behavior changes again, there is value to the community here. DNS researchers will find the results of interest, either in confirming that previously observed behavior is still happening or in seeing new behavior. Other researchers may find the data useful in building models for evaluation. However, as all the reviewers pointed out, the findings could be skewed by the small population of fiber-connected homes in the US. For instance, the paper finds heavy use of the Chrome web browser among their users, but Chrome commands roughly 16% of the browser market. This can skew some numbers, such as DNS prefetching.

On grappling with meta-information in the internet

Tom Callahan, Mark Allman, Michael Rabinovich, and Owen Bell
Appears in: 
CCR October 2011

The Internet has changed dramatically in recent years. In particular, the fundamental change has occurred in terms of who generates most of the content, the variety of applications used and the diverse ways normal users connect to the Internet. These factors have led to an explosion of the amount of user-specific meta-information that is required to access Internet content (e.g., email addresses, URLs, social graphs).

Public Review By: 
Stefan Saroiu

For most users, the Internet is increasingly becoming like a messy drawer. It is full of notes, lists, scraps of papers, old photos, new photos, tools, and so on, that users have accumulated over the years. Users have two choices. The first choice is to use a collection of item-specific organizers (i.e., content-specific applications) – such as an organizer for photos, an organizer for notes, and one for lists. The second choice is to hire a person (i.e. the “cloud”) – the external organizer who will clean up and keep track of everything. The first choice is difficult and the second requires delegating trust. Both are suboptimal. This paper tries to clean up the messy drawer. The authors put forward an architecture for dealing with meta-information – all these user-generated content that people hang to. The system is a combination of a personal naming system (DNS) and a distributed file store. It provides unified personal naming, user-directed actions on receipt of communication, sharing application state across devices, and sharing application configuration across devices. The paper is quick to point out that many of these solutions have been implemented as point-solutions already and the main contribution is to simply show the power and extensibility of the architecture. Although the paper brings together a collection of well-known techniques, the paper’s main goal (as the authors themselves point out) is “to start a conversation and not close a door.” The reviewers themselves went back-and-forth on weighting the paper’s motivation against its lack of technical novelty. In the end, this paper felt like a good fit for CCR because it does its job well – it starts a conversation around the need for organizing meta-information in the Internet.

Syndicate content