Dave Oran

Self-verifying names for read-only named data

Information-centric networks must ensure the authenticity and integrity of named data. ICN designs such as Content-Centric Networking apply a digital signature to a collection of packets for this purpose. This paper shifts the mode of ICN authentication: Self-verifying names ensure data authenticity for read-only named data; signatures or other means ensure name authenticity. The paper considers how self-verifying names might be used in CCN.

Toward fast NDN software forwarding lookup engine based on hash tables

In Named Data Networking (NDN), forwarding lookup is based on tokenized variable-length names instead of fixed-length host addresses, and therefore it requires a new approach for designing a fast packet forwarding lookup engine. In this paper, we propose a design of an NDN software forwarding lookup engine based on hash tables and evaluate its performance with different design options. With a good hash function and table design combined with Bloom filters and data prefetching, we demonstrate that our design reaches about 1.5MPPS with a single thread on an Intel 2.0GHz Xeon processor.

MIRCC: Multipath-aware ICN Rate-based Congestion Control

Information-Centric Network (ICN) has yet to determine its approach to congestion control, including whether window-based or rate-based congestion control would be best. IP window-based schemes have been studied extensively and deployed on a grand scale. Consequently, most ICN congestion control work has concentrated on window-based approaches. Not only does rate-based congestion control have properties of interest, however, but ICNs well-known differences from IP, including receiver-driven flow control, stateful forwarding, symmetric paths, and lack of installed base may well lead to a different congestion control approach being best for ICN. This paper presents MIRCC, a rate-based, multipath-aware ICN congestion control approach inspired by but noticeably differing from RCP. We first explain our ICN-appropriate mechanisms for calculating and signaling flow rates. We then present MIRCCs algorithm for calculating per-link rates, and its convergence advantages over RCPs algorithm. Finally, we explore several approaches for making our scheme multipath-aware, finding an interesting solution to this challenging problem. To characterize MIRCCs behavior, we use simulation results throughout.

TCP/ICN: Carrying TCP over Content Centric and Named Data Networks

Todays Internet applications and protocols are not compatible with Information Centric Networking (ICN) protocols and there is no straightforward way of rapidly switching protocol architectures. Network operators incrementally deploying an ICN infrastructure will have to provide compatibility with existing TCP/IP applications and manage co-existence of IP and ICN networks. One approach to co-existence is to allow TCP and the applications using it to work transparently over an ICN substrate instead of over IP. This paper presents a TCP/ICN proxy capable of carrying TCP traffic between TCP/IP endpoints over ICN network. The main challenge for this approach to co-existence is transforming the TCP push model to the ICN pull model. We evaluated several alternative TCP/ICN proxy designs in a simulation environment. We chose the most promising of these designs and developed a proof-of-concept *nix implementation. Performance measurements of both simulation and real implementation demonstrate that with our proxy design TCP can traverse ICN networks without significant additional delay or loss of goodput.

Network-Aware Feasible Repairs for Erasure-Coded Storage

A significant amount of research on using erasure coding for distributed storage has focused on reducing the amount of data that needs to be transferred to replace failed nodes. This continues to be an active topic as the introduction of faster storage devices looks to put an even greater strain on the network. However, with a few notable exceptions, most published work assumes a flat, static network topology between the nodes of the system. We propose a general framework to find the lowest cost feasible repairs in a more realistic, heterogeneous and dynamic network, and examine how the number of repair strategies to consider can be reduced for three distinct erasure codes. We devote a significant part of the paper to determining the set of feasible repairs for random linear network coding (RLNC) and describe a system of efficient checks using techniques from the arsenal of dynamic programming. Our solution involves decomposing the problem into smaller steps, memorizing, and then reusing intermediate results. All computationally intensive operations are performed prior to the failure of a node to ensure that the repair can start with minimal delay, based on up-to-date network information. We show that all three codes benefit from being network aware and find that the extra computations required for RLNC can be reduced to a viable level for a wide range of parameter values.

Path switching in content centric and named data networks

ICN communication is inherently multipath and potentially multi-destination. Content Centric and Named Data Networks at present do not offer a mechanism to direct traffic onto a specific path in multipath or a specific destination in a multi-destination environment, because the forwarding plane multiplexes packets across nexthops dynamically. This makes it challenging to provide practical multipath traceroute and ping applications, or implement multipath-aware congestion control, traffic engineering or SDN solutions. The symmetry of forward and reverse paths in Content Centric and Named Data Networks allows one to compute an end-to-end path label in a Data message on the reverse path and subsequently use this label to forward an Interest message through a specific nexthop. ICN Path Switching is a method of high-speed Interest forwarding in Content Centric and Named Data networks based on exact matching of a nexthop label retrieved from the Interests path label against a nexthop ID in the ICN Forwarders Adjacency database. ICN Path Switching maintains all major characteristics of CCN / NDN architectures, such as multicasting, caching, flow balance, etc. Simulations demonstrate that path labels are consistent with ICN control plane routing state in the presence of route updates. Analysis of ICN Path Switching with regards to Multiprotocol Label Switching (MPLS) and Segment Routing architectures suggests that it offers similar advantages at lower complexity with the potential to simplify network operations.