Leonhard Nobach

PeerfactSim.KOM: A simulation framework for Peer-to-Peer systems

Since P2P systems have become popular in the late nineties, simulation of these systems has always been a preferable method of performance evaluation. Simulations facilitate the development and evaluation of new protocols and mechanisms, while enabling a comparison of existing solutions. In this paper, we present PeerfactSim.KOM, a discrete-event P2P simulator that is suitable for a wide range of varying scenarios in the area of P2P. It consists of a layered architecture, provides a broad selection of P2P protocols for the modeled layers, and eases the implementation of new components through its modular design. In addition, the simulator provides helpful tools to configure and evaluate a simulation scenario.

Open, elastic provisioning of hardware acceleration in NFV environments

Network Functions Virtualization (NFV) is a new paradigm to move network tasks currently running on dedicated, vendor-specific hardware to elastic, virtualized environments, similar to IaaS cloud computing. A major challenge of NFV is to reach the performance known from dedicated hardware appliances, which often leverage ASIC, FPGA or NPU-based hardware acceleration to increase throughput and reduce delay. In this paper, a framework for elastic provisioning, programming and configuration of acceleration hardware for virtual network functions (VNFs) is proposed. Using this framework, VNFs can offload selected parts of their workload to heterogeneous acceleration processors, which may be shared among all VNF instances in the framework for improved resource utilization.

BlockTree: Location-aware decentralized monitoring in mobile ad hoc networks

Mobile ad hoc networks (MANETs) represent a crucial alternative to deploy applications in urban areas. In those networks, it is inevitable that all nodes are aware of the current system state to adapt their behavior according to the varying conditions. However, existing decentralized monitoring solutions for MANETs only locate the required information at a set of nodes, which are in charge of serving the remaining network, while the availability of information depends on the accessibility of those nodes. To avoid these limitations, BlockTree is a novel, fully decentralized monitoring approach for MANETs that leverages each nodes resources to capture and distribute the system state to all nodes. Exploiting its hierarchical structure, BlockTree introduces the concept of location-aware monitoring delivering detailed as well as aggregated information. Through robust communication paired with the stateless design, BlockTree provides accurate results in the presence of fast moving nodes or over an error-prone communication medium.

Towards Decentralized, Energy- and Privacy-Aware Device-to-Device Content Delivery

Device-to-Device (D2D) content delivery is a new approach to directly exchange content between mobile devices, which allows to offload traffic from infrastructure-based networks and thus reduces the risk of congestion. While centralized D2D approaches rely on the mobile operator to discover nearby devices and initiate a content transfer, in decentralized D2D the devices autonomously and opportunistically organize themselves to deliver content to each other. The latter approach is more flexible as it does not depend on a single operator, however, it typically requires more energy for scanning other devices. Another issue is privacy, since the decentralized approach reveals a user’s interest for content to all devices in proximity. Therefore, this paper sketches an new approach towards decentralized energy- and privacy-aware D2D content delivery. The proposed approach addresses the energy loss that occurs when constantly and spontaneously scanning multiple unknown devices for content. Furthermore, the paper identifies privacy requirements and proposes first steps towards a privacy-aware D2D solution.

SliM: Enabling efficient, seamless NFV state migration

Instance migration and scale-in/out operations in network functions virtualization (NFV) require state transfer mechanisms, which are known to cause service degradation through increased jitter and packet loss. Techniques such as packet duplication for state synchronization mitigate this problem, however, they incur significant additional costs. In this paper, we provide a novel interface to the VNF to announce “statelets” for incoming packets, which comprise only the information in the packet which is required for a VNFs internal state change. Based on this interface, we design and implement SliM, a statelet-based framework for seamless VNF migration. First evaluation results show that SliM operates seamlessly at very high dataplane utilization of physical links, up to 3 times the utilization level at which existing approaches are failing due to insufficient bandwidth for state synchronization.

Evaluating device-to-device content delivery potential on a mobile ISP's dataset

Device-to-Device (D2D) content delivery is an emerging approach, where end-user devices exchange content with other end-user devices in communication range, instead of retrieving content from an operators infrastructure. This way, the operator network can be offloaded from congestion caused by the transmission of popular content, and the content consumers quality of experience may increase. However, D2D content delivery is only effective in situations where a device in proximity has the requested content available, which is more likely to happen with popular content in crowded areas. The availability of content in communication range of a consumer constitutes an upper bound of the success of a D2D content delivery mechanism, which is referred to as the potential of D2D delivery. This paper provides a quantitative answer to the question of this potential, and identifies the most important properties a D2D mechanism must provide. An evaluation model is proposed and developed, which can be applied to real-world mobile user traces to determine the quota of content requests that could be served via D2D content delivery. The model is applied on a dataset of a major European Internet service provider and the evaluation results are discussed. The paper concludes that there is potential to deliver up to 60% of requests for popular content via D2D, if a reliable mechanism to predict a users content consumption is available.

New kid on the block: network functions visualization: from big boxes to carrier clouds

Network management currently undergoes massive changes towards realizing more flexible management of complex networks. Recent efforts include slicing data plane resources by network (link) virtualization and applying operating system design principles to Software Defined Networking to rethink network management. Driven by network operators, network management principles are currently envisioned to be even further improved by virtualizing network (middlebox) functions. The resulting Network Functions Virtualization (NFV) paradigm abstracts network functions from dedicated hardware to virtual machines running on commodity hardware. This change in the design of carrier networks is inspired by the success of virtualization in the server market. By deploying NFV, network operators envision to achieve benefits similar to the server market and elastic cloud services, e.g., flexible and dynamic service provisioning, increased resource utilization, improved energy efficiency, and ultimately decreased operational costs. Despite these efforts, the ability of NFV to satisfy performance demands is often questioned. Tackling these challenges opens a set of research questions that felt short in the current discussion and are of particular relevance to the SIGCOMM community. In this position paper, we therefore provide an overview on the current state-of-the-art and open research questions.

Bare-Metal Switches and Their Customization and Usability in a Carrier-Grade Environment

The current ecosystem of network elements, such as switches and appliances, is largely dominated by devices supplied and sold with a bundled operating system, and software dedicated to manage the devices forwarding hardware, however, these platforms are not open-source and cannot be arbitrarily customized, and there is no cost transparency or flexibility in choosing software different to the bundled components.,,,,In this paper, we explore the capabilities of bare-metal switches, which are equipped with commodity switching hardware components, but shipped without an operating system. We evaluate the feasibility of these commonly lower-cost devices to meet the requirements of a customized, carrier-grade network function. Therefore, we have implemented a prototype on generic hardware, re-using as much open-source software as possible. Our Broadband Remote Access Server (BRAS) prototype can lower the cost compared to proprietary network appliances, and, known to have a hardware backplane capacity of 720 Gbps, the merchant-silicon / ASIC approach can highly outperform the state of the art of current x86-based virtualized network functions, while implementing the most important BRAS features.

Statelet-Based Efficient and Seamless NFV State Transfer

Network functions virtualization (NFV) environments can provide increased elasticity and flexibility for operators, as network-related services can be scaled and moved as needed. Such operations require a seamless transfer of state to provide a service without interruption or performance degradation. In this paper, we propose and analyze a novel approach for efficient and seamless NFV state transfers. Our approach is based on the concept of statelets, which are compact representations of information in incoming packets that change the state of a virtualized network function. We present and describe slim migration (SliM), a system for efficient NFV state transfers using a statelet interface that we have implemented as an add-on to the data plane development kit, a high-performance packet I/O library. We have evaluated SliM in a testbed and present results that show its benefits in terms of lower delays and lower packet-loss rates. Moreover, our analysis and evaluation results show that SliM offers three times as much shared link capacity to the dataplane as previous approaches, while reducing the duration of a state transfer to one-third of their time.

Benefits of conditional FPGA provisioning for virtualized network functions

Network Functions Virtualization (NFV) stands for a major paradigm shift in computer networks. Despite the flexibility improvements which NFV offers, the commonly used COTS processors show performance limitations compared to specialized circuits. A trade-off can be achieved by reconfigurable hardware like FPGAs, which provide high, guaranteed performance and flexibility. However, FPGAs are costly, and the network function resources — programmable gates — have a limited ability to scale in, as they must stay occupied even if the performance requirements are currently low. In this work, we envision to evaluate the advantages that arise from a dynamic provisioning of FPGA resources on the datapath of virtual network functions. In a first step, we evaluate performance characteristics of FPGA and COTS processor resources running an example DPI NF. Given a lease cost model, we furthermore analytically evaluate the advantage of dynamically selecting FPGA or COTS processor resources for this NF, depending on the current performance demands. Our evaluation shows that we can save up to 39% of costs by a dynamic provisioning based on the expected load.