Robert Ricci

An integrated experimental environment for distributed systems and networks

Three experimental environments traditionally support network and distributed systems research: network emulators, network simulators, and live networks. The continued use of multiple approaches highlights both the value and inadequacy of each. Netbed, a descendant of Emulab, provides an experimentation facility that integrates these approaches, allowing researchers to configure and access networks composed of emulated, simulated, and wide-area nodes and links. Netbeds primary goals are ease of use, control, and realism, achieved through consistent use of virtualization and abstraction.By providing operating system-like services, such as resource allocation and scheduling, and by virtualizing heterogeneous resources, Netbed acts as a virtual machine for network experimentation. This paper presents Netbeds overall design and implementation and demonstrates its ability to improve experimental automation and efficiency. These, in turn, lead to new methods of experimentation, including automated parameter-space studies within emulation and straightforward comparisons of simulated, emulated, and wide-area scenarios.

GENI: A federated testbed for innovative network experiments

GENI, the Global Environment for Networking Innovation, is a distributed virtual laboratory for transformative, at-scale experiments in network science, services, and security. Designed in response to concerns over Internet ossification, GENI is enabling a wide variety of experiments in a range of areas, including clean-slate networking, protocol design and evaluation, distributed service offerings, social network integration, content management, and in-network service deployment. Recently, GENI has been leading an effort to explore the potential of its underlying technologies, SDN and GENI racks, in support of university campus network management and applications. With the concurrent deployment of these technologies on regional and national R&E backbones, this will result in a revolutionary new national-scale distributed architecture, bringing to the entire network the shared, deeply programmable environment that the cloud has brought to the datacenter. This deeply programmable environment will support the GENI research mission and as well as enabling research in a wide variety of application areas.

A solver for the network testbed mapping problem

Network experiments of many types, especially emulation, require the ability to map virtual resources requested by an experimenter onto available physical resources. These resources include hosts, routers, switches, and the links that connect them. Experimenter requests, such as nodes with special hardware or software, must be satisfied, and bottleneck links and other scarce resources in the physical topology should be conserved when physical resources are shared. In the face of these constraints, this mapping becomes an NP-hard problem. Yet, in order to prevent mapping time from becoming a serious hindrance to experimentation, this process cannot consume an excessive amount of time.In this paper, we explore this problem, which we call the network testbed mapping problem.We describe the interesting challenges that characterize it, and explore its applications to emulation and other spaces, such as distributed simulation. We present the design, implementation, and evaluation of a solver for this problem, which is in production use on the Netbed shared network testbed. Our solver builds on simulated annealing to find very good solutions in a few seconds for our historical workload, and scales gracefully on large well-connected synthetic topologies.

Mobile Emulab: A Robotic Wireless and Sensor Network Testbed

Simulation has been the dominant research method- ology in wireless and sensor networking. When mobility is added, real-world experimentation is especially rare. However, it is becoming clear that simulation models do not sufficiently capture radio and sensor irregularity in a complex, real-world environment, especially indoors. Unfortunately, the high labor and equipment costs of truly mobile experimental infrastructure present high barriers to such experimentation. We describe our experience in creating a testbed to lower those barriers. We have extended the Emulab network testbed software to provide the first remotely-accessible mobile wireless and sensor testbed. Robots carry motes and single board computers through a fixed indoor field of sensor-equipped motes, all running the users selected software. In real-time, interactively or driven by a script, remote users can position the robots, control all the computers and network interfaces, run arbitrary programs, and log data. Our mobile testbed provides simple path planning, a vision-based tracking system accurate to 1 cm, live maps, and webcams. Precise positioning and automation allow quick and painless evaluation of location and mobility effects on wireless protocols, location algorithms, and sensor-driven applications. The system is robust enough that it is deployed for public use. We present the design and implementation of our mobile testbed, evaluate key aspects of its performance, and describe a few experiments demonstrating its generality and power.

Fast and flexible: parallel packet processing with GPUs and click

We introduce Snap, a framework for packet processing that outperforms traditional software routers by exploiting the parallelism available on modern GPUs. While obtaining high performance, it remains extremely flexible, with packet processing tasks implemented as simple modular elements that are composed to build fully functional routers and switches. Snap is based on the Click modular router, which it extends by adding new architectural features that support batched packet processing, memory structures optimized for offloading to coprocessors, and asynchronous scheduling with in-order completion. We show that Snap can run complex pipelines at high speeds on commodity PC hardware by building an IP router incorporating both an IDS-like full-packet string matcher and an SDN-like packet classifier. In this configuration, Snap is able to forward 40 million packets per second, saturating four 10 Gbps NICs at packet sizes as small as 128 byes. This represents an increase in throughput of nearly 4x over the baseline Click running comparable elements on the CPU.

Integrated network experimentation using simulation and emulation

Discrete-event packet-level network simulation is well-known and widely used. Network emulation is a hybrid approach that combines real elements of a deployed networked application-such as end hosts and protocol implementations-with synthetic, simulated, or abstracted elements-such as the network links, intermediate nodes and background traffic. A key difference between the two approaches is that in the former, the notion of time is virtual and is independent of real time, whereas the latter must execute in real time. Emulation gains realism while naturally foregoing complete repeatability; historically, emulation was also tedious to control and manage. We define integrated network experimentation as spatially combining real elements with simulated elements in the same experimental run, each modeling different portions of a network topology. Integrated experiments enable new validation techniques and larger experiments than obtainable by using real elements alone. This paper highlights the key issues in integrated network experimentation and presents some of the design techniques we use in designing, building, and putting into public production use such an integrated environment, running on a space-shared cluster.

SMORE: software-defined networking mobile offloading architecture

We present our Software-defined network Mobile Offloading aRchitecturE (SMORE). SMORE realizes traffic offloading in mobile networks without requiring any changes to the functionality of existing mobile network nodes. At the same time, it is fully aware of mobile network functionality, including mobility.

GPUstore: harnessing GPU computing for storage systems in the OS kernel

Many storage systems include computationally expensive components. Examples include encryption for confidentiality, checksums for integrity, and error correcting codes for reliability. As storage systems become larger, faster, and serve more clients, the demands placed on their computational components increase and they can become performance bottlenecks. Many of these computational tasks are inherently parallel: they can be run independently for different blocks, files, or I/O requests. This makes them a good fit for GPUs, a class of processor designed specifically for high degrees of parallelism: consumer-grade GPUs have hundreds of cores and are capable of running hundreds of thousands of concurrent threads. However, because the software frameworks built for GPUs have been designed primarily for the long-running, data-intensive workloads seen in graphics or high-performance computing, they are not well-suited to the needs of storage systems. In this paper, we present GPUstore, a framework for integrating GPU computing into storage systems. GPUstore is designed to match the programming models already used these systems. We have prototyped GPUstore in the Linux kernel and demonstrate its use in three storage subsystems: file-level encryption, block-level encryption, and RAID 6 data recovery. Comparing our GPU-accelerated drivers with the mature CPU-based implementations in the Linux kernel, we show performance improvements of up to an order of magnitude.

Designing a federated testbed as a distributed system

Traditionally, testbeds for networking and systems research have been stand-alone facilities: each is owned and operated by a single administrative entity, and is intended to be used independently of other testbeds. However, this isolated facility model is at odds with researchers’ ever-increasing needs for experiments at larger scale and with a broader diversity of network technologies. The research community will be much better served by a federated model. In this model, each federated testbed maintains its own autonomy and unique strengths, but all federates work together to make their resources available under a common framework.

The InstaGENI initiative: An architecture for distributed systems and advanced programmable networks

In this paper, we describe InstaGENI, a distributed cloud based on programmable networks designed for the GENI Mesoscale deployment and large-scale distributed research projects. The InstaGENI architecture closely integrates a lightweight cluster design with software-defined networking, Hardware-as-a-Service and Containers-as-a-Service, remote monitoring and management, and high-performance inter-site networking. The initial InstaGENI deployment will encompass 34 sites across the United States, interconnected through a specialized GENI backbone network deployed over national, regional and campus research and education networks, with international network extensions to sites across the world.