The lack of application support is probably the biggest obstacle to ICN/NDN deployment. One approach to tackle this problem is to NDNize existing applications by translating between application-level protocols and NDN, which can benefit from NDN's architectural advantages while minimizing development efforts needed. In this paper, we validate the effectiveness of this approach by applying it to Internet livestreaming, and develop PCLive , a livestreaming system with NDN embedded as its distribution network. PCLive makes minimal changes to an Internet livestreaming architecture, achieving the maximum compatibility with existing components including video players, OBS, and video transcoders. By solving a number of design issues such as HLS/NDN protocol translation, data translation, naming and security, PCLive is able to run over an NDN network and enjoy its architectural benefits. Since December 2021, PCLive has been running on an NDN testbed consisting of cloud servers from seven cities. It can serve almost four times as many clients as an existing livestreaming system can over IP under the same network conditions; at the same time, the average throughput of the bottleneck link in the NDN testbed is 34.8% lower than that in IP. We also evaluate congestion control and adaptive forwarding with PCLive.
Benchmarking Named Data Networking (NDN)/Content Centric Networking (CCN) forwarders is becoming an important task as the demand for fast forwarding is becoming inevitable for their dissemination. Many full-fledged software-based forwarders have been implemented with a throughput of 100 Gbps, and recently, prototypes of some hardware-based forwarders using a P4 switch have been implemented with a throughput of more than 1 Tbps. Many studies have placed stress on NDN forwarders with uniform request patterns. However, these request patterns enable only the maximum throughput to be measured. In contrast, this study addresses the generation of non-uniform request patterns at a rate of Tbps to evaluate the throughput of NDN forwarders.
Programmable switches provide a solution for implementing highspeed Named Data Networking (NDN) forwarding. However, the challenge arises from the packets in the NDN network that carry hierarchical names of varying lengths, coupled with the inherent limitation of programmable switches in parsing variable-length packet content and storing large NDN forwarding tables. To address this issue, we propose Pegasus, an NDN router framework that combines the programmable switch with commodity servers to realize the high speed and reliability of NDN packet forwarding. The main idea is to maximize the involvement of the programmable switch in NDN packet handling by designing a parser that supports variable-length names and a Pending Interest Table (PIT) for fast forwarding. We implement a multi-core parallel software forwarder on servers to serve as the backend router to efficiently process packets that the switch cannot handle. Experimental results show that Pegasus can process NDN names with diverse lengths at the maximum throughput of 780 Gbps in our testbed.
Inter-domain routing (IDR), in which autonomous systems (ASes) co-operate to exchange information so that packets can be forwarded to their intended destinations, is a crucial component of any global network service. IDR in today's Internet is already challenging because of the need to accommodate each AS's route selection policies. Policies are determined by business (i.e., generating revenue or increasing costs for the AS), performance, and reliability considerations. IDR for information-centric networking (ICN) services is further complicated by the scale and topology-independence of the data namespace. On the other hand, ICN approaches that offer built-in origin authenticity and integrity have potential to overcome some of the issues with the current Border Gateway Protocol-based legacy IDR system, which was originally deployed without security mechanisms. In this paper, we survey a set of representative IDR solutions for information-centric networking proposed in the literature. We describe key design aspects of such systems, and characterize the surveyed systems in terms of those aspects. We point out tradeoffs involved in minimizing network resources wasted on delivery of data that the application will consider bogus; this is important at the inter-domain level, where transit service involves compensation between ASes. Finally, we discuss the issue of trust, and identify potential research directions for IDR in the context of ICN.
Information-centric networking (ICN) is a prominent architecture that realizes content-aware network services through name-based communications. A programmable ICN router implemented on a field-programmable gate array (FPGA) accelerator can achieve predictable performance for advanced service requirements, such as low latency and high throughput. However, owing to the tight resource constraints, implementing ICN functions on an FPGA is a huge challenge, as ICN requires frequent update tables for maintaining long and variable-length content names and access to caching devices capable of storing large-volume content. In this study, we designed and implemented an FPGA router that incorporates an ICN by applying the CCNx v1.0 protocol specification. The FPGA router implemented a unified status table on a large-capacity DRAM that stored 10 million variable-length content name prefixes. Additionally, we introduced a DRAM bank allocation that is unaffected by slow random accesses and reduces table access latency, and a Row-Bank-Column memory address mapping scheme that reduces the access time to heavily loaded in-network cache storage. We present the evaluation results of the proposed architecture implemented on the NetFPGA-SUME board, revealing 10 Gbps or 2.8 Mpps throughput and ≤ 300 ns jitter.
Communication models are important because in most systems, and certainly in large or distributed ones, it is often difficult to distinguish between cause and effect, and to know if solutions match with problems. We proceed with the premise that challenges in today's networked systems may be due to their underlying communication models.
The semantic naming and data-centric security paradigm of Named Data Networking opens up new possibilities for building decentralized applications. In this poster, we identify some factors that lead to centralization and non-interoperability of cloud services. We present the preliminary design of a photo sharing application as a simple example to articulate how NDN can overcome the lack of cloud-independent user identities, illustrating the process and considerations involved in designing decentralized applications that can provide the features offered by existing cloud services.
Although multiple routing protocols and forwarding strategies have been proposed for NDN, there is a lack of understanding about the synergy between them. In this work, we investigate the effectiveness of NDN forwarding strategy, routing, and the combination of the two in maximizing data fetching success in the face of network failures. Through emulation experiments, we first evaluate the ASF (Adaptive SRTT-based Forwarding) strategy and NLSR (Named-data Link State Routing) protocol separately. Our results show that ASF with static routing outperforms NLSR with best-route strategy in most cases, although its data delivery performance exhibits a bias toward popular producers. We then conduct experiments that combine ASF and NLSR. The results show that the combination of ASF with frequent probing and NLSR with slow routing adaptation leads to better data delivery performance than using either ASF or NLSR alone. Our results provide insights into the future design and deployment of routing and forwarding strategies in NDN networks.
The decade-long experiences from developing applications over Named Data Networking (NDN) have taught us the importance of well-designed libraries that offer support to application developers to support data security. NDN trust schema provides a critical component in the NDN security support, however its implementation and support only started receiving significant attention in recent years. This paper first provides a summary of the existing API support for trust schema, then takes a step forward by developing a new trust schema API, named Envelope. Envelope addresses the application requirements by offering comprehensive trust schema functionalities, an easy-to-write schema language, and an extensible design. To demonstrate the usefulness of Envelope , we develop a blog application which uses Envelope to secure its data. Our results show that Envelope provides effective trust schema support for applications with acceptable overhead.
Logging is a critical function to enable auditing and enhance security of distributed applications. This paper describes the design of Mnemosyne, a distributed logger running over Named Data Networking(NDN), to meet this need for NDN-based distributed applications. Mnemosyne assures the immutability of logged events by interlocking all event records in a DAG-based ledger. Mnemosyne provides a high logging throughput and system resiliency against network component failures. We implemented Mnemosyne and evaluated its design through an emulated deployment setting.
As a data-centric network architecture, Named Data Networking (NDN) has a unique feature in its stateful forwarding plane, where Interest packets are routed towards data sources, leaving behind breadcrumb traces that steer requested data packets back to consumers. However, if one wishes to run NDN on LEO satellite networks (satnet), the frequent connectivity handovers in such an environment would disrupt the states of NDN's forwarding plane. In this poster, we first graphically illustrate several functions enabled by NDN's stateful forwarding plane, then describe the disruptions to this forwarding plane by frequent handovers due to fast LEO satellite movement, and explain the difference between the LEO satellite handover problem and today's mobile IP node handover. We argue that effective solutions to the above problems should be developed to enable NDN deployment over LEO satnets.
We present a name-based sidecar-assisted networking approach that enables off-the-shelf TCP/IP and HTTP protocols to effectively handle network disruptions. We compare the performance of our approach with the Name Data Networking by deploying and testing them in a hardware networking testbed and show, on average, in 85% of experiments, the sidecar approach manages to transfer data.
State Vector Sync (SVS) is a Distributed Dataset Synchronization (Sync) protocol designed to support distributed applications running over NDN. The design of SVS has two unique features that set it apart from all the previous Sync protocol designs. First, SVS encodes the raw information of data namespace to be synchronized in its Sync Interest packets. Second, and related, it uses Sync Interests as notifications which do not solicit data replies. To reveal insights of how its unique design features enable SVS to outperform its counterparts, in this poster we describe the operation of two types of timers used in SVS and their effectiveness in minimizing protocol overhead while keeping synchronization delay low.
We focus on the security and performance characteristics of the QUIC protocol, exploring its security qualitatively and its performance quantitatively through experimentation. Performance comparisons between QUIC and traditional TCP-based counterparts were made through experiments under various dimensions. These comparisons were based on measurements of running code on real computing and networking resources within Washington University's Open Network Lab (ONL). The experimental results show that QUIC clients perform as well as or better than TCP clients for single-stream resources with limited bandwidth. However, minimal performance differences exist between QUIC and TCP for multiple streams.
High-quality network traffic measurements from realistic network deployments are crucial to analyze and better understand emerging network technologies for the purpose of maturing them. However, achieving this measurement goal for the Named Data Networking (NDN) protocol remains a challenge mainly due to the lack of real-world deployments. To address this gap, we have created a dataset of NDN traffic traces and a software toolkit for capturing, analyzing, and replaying these traces. Our dataset, obtained directly from the real routers of the official NDN testbed, is the first non-synthetic dataset of this scale openly available to the research community. This paper presents the dataset and the tools, discusses its properties, and shares insights applicable to other NDN research.
This paper discusses challenges and opportunities of considering the Metaverse as an Information-Centric Network (ICN). The Web today essentially represents a data-centric application layer: data named by URLs is manipulated with REST primitives. However, the semantic gap with the underlying host-oriented transport is significant, typically leading to complexity, centralization, and brittleness. Popular interest in "the Metaverse" suggests that the end-user experience of the Web will evolve towards always-on eXtended Reality (XR). With the benefit of a historical perspective, computing advances, and decades of experience with a global network, there is an opportunity to holistically consider the Metaverse not as an application of the current network, but an evolution of the network itself, reducing rather than widening the gap between network architecture and application semantics. An ICN architecture offers the possibility to achieve this with less overhead, low latency, better security, and more disruption tolerance suitable to diverse uses cases, even those facing intermittent connectivity.
Information-Centric Networking (ICN), with its data-oriented operation and generally more powerful forwarding layer, provides an attractive platform for distributed computing. This paper provides a systematic overview and categorization of different distributed computing approaches in ICN encompassing fundamental design principles, frameworks and orchestration, protocols, enablers, and applications. We discuss current pain points in legacy distributed computing, attractive ICN features, and how different systems use them. This paper also provides a discussion of potential future work for distributed computing in ICN.
Named Data Networking (NDN) provides native support for multi-party communication. However, the current NDN forwarder lacks a duplicate suppression mechanism for multicasting in a multi-access network, potentially leading to network congestion and significant degradation in overall packet delivery performance. In this paper, we introduce Adaptive Duplicate Suppression (ADS) for one-hop multicasting in multi-access NDN networks. ADS utilizes the duplicate count per Interest and Data name observed in the network to dynamically adjust the suppression time that a node waits before forwarding a packet. We have implemented ADS in the NDN forwarding daemon (NFD) and assessed its performance using Mini-NDN. Our evaluation demonstrates that ADS can effectively reduce redundant network traffic under various network conditions, resulting in significantly improved application goodput and reduced transfer times.
Incremental deployment of new Internet architecture is a key challenge for the smooth evolution of the current Internet. In NDN, the overlay-based deployment is considered as one of the promising options to provide NDN services over the Internet. To achieve an incremental deployment, it is required to design a bootstrapping mechanism that allows consumers to consistently access to an overlay NDN network in a situation where Autonomous Systems (AS) are gradually deploying NDN routers. In this paper, we analyzed the current bootstrapping and identified its potential issue in specifying the IP address of the closest NDN router. We propose a robust bootstrapping architecture that can work without specifying the exact IP address of a single NDN router. By using in-network indirection, our scheme can provide consistent access to the NDN network independent of the deployment status of each AS.
