Ashok Narayanan

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.

Named data networking on a router: fast and dos-resistant forwarding with hash tables

Named data networking (NDN) is a new networking paradigm using named data instead of named hosts for communication. Implementation of scalable NDN packet forwarding remains a challenge because NDN requires fast variable-length hierarchical name-based lookup, per-packet data plane state update, and large-scale forwarding tables. In this paper, we review various design options for a hash table-based NDN forwarding engine and propose a design that enables fast forwarding while achieving DoS (Denial-of-Service) resistance. Our forwarding engine features (1) name lookup via hash tables with fast collision-resistant hash computation, (2) an efficient FIB lookup algorithm that provides good average and bounded worst-case FIB lookup time, (3) PIT partitioning that enables linear multicore speedup, and (4) an optimized data structure and software prefetching to maximize data cache utilization. We have implemented an NDN data plane with a software forwarding engine on an Intel Xeon-based line card in the Cisco ASR 9000 router. By simulation with names extracted from the IR-Cache traces, we demonstrate that our forwarding engine achieves a promising performance of 8.8 MPPS and our NDN router can forward the NDN traffic at 20 Gbps or higher.

An improved hop-by-hop interest shaper for congestion control in named data networking

Hop-by-hop interest shaping has been proposed as a viable congestion control mechanism in Named Data Networking (NDN). Interest shaping exploits the strict receiver-driven traffic pattern and the symmetric bidirectional forwarding in NDN to control the returning data rate. In this paper, we point out that both interests and contents contribute to congestion and their interdependence must be considered in any interest shaping algorithm. We first analyze this issue mathematically by formulating it as an optimization problem to obtain the optimal shaping rate. Then a practical interest shaping algorithm is proposed to achieve high link utilization without congestive data loss. We further note that flow differentiation in NDN is complicated and design our scheme independently of traffic flows. We demonstrate our hop-by-hop interest shaper in conjunction with simple Additive-Increase-Multiplicative-Decrease (AIMD) clients using the ns3-based NDN simulator (ndnSIM). Our results show that the proposed shaping algorithm can effectively control congestion and achieve near-optimal throughput.

Named data networking on a router: forwarding at 20gbps and beyond

Named data networking (NDN) is a new networking paradigm using named data instead of named hosts for communication. Implementation of scalable NDN packet forwarding remains a challenge because NDN requires fast variable-length hierarchical name-based lookup, per-packet data plane state update, and large-scale forwarding tables. We have designed and implemented an NDN data plane with a software forwarding engine on an Intel Xeon-based line card in a Cisco ASR9000 router. In order to achieve high-speed forwarding, our design features (1) name lookup via hash tables with fast collision-resistant hash computation, (2) an efficient and secure FIB lookup algorithm that provides good average and bounded worst-case FIB lookup time, (3) PIT partitioning that enables linear multi-core speedup, and (4) an optimized data structure and software prefetching to maximize data cache utilization. In this demonstration, we showcase our NDN router implementation on the ASR9000 and demonstrate that it can forward real NDN traffic at 20Gbps or higher.

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.

Secure Fragmentation for Content-Centric Networks

Content-Centric Networking (CCN) is a communication paradigm that emphasizes content distribution. Named-Data Networking (NDN) is an instantiation of CCN, a candidate Future Internet Architecture. NDN supports human-readable content naming and router-based content caching which lends itself to efficient, secure, and scalable content distribution. Because of NDNs fundamental requirement that each content object must be signed by its producer, fragmentation has been considered incompatible with NDN since it precludes authentication of individual content fragments by routers. The alternative is to perform hop-by-hop reassembly, which incurs prohibitive delays. In this paper, we show that secure and efficient content fragmentation is both possible and even advantageous in NDN and similar content-centric network architectures that involve signed content. We design a concrete technique that facilitates efficient and secure content fragmentation in NDN, discuss its security guarantees and assess performance. We also describe a prototype implementation and compare performance of cut-through with hop-by-hop fragmentation and reassembly.