José A. B. Fortes

CloudBLAST: Combining MapReduce and Virtualization on Distributed Resources for Bioinformatics Applications

This paper proposes and evaluates an approach to the parallelization, deployment and management of bioinformatics applications that integrates several emerging technologies for distributed computing. The proposed approach uses the MapReduce paradigm to parallelize tools and manage their execution, machine virtualization to encapsulate their execution environments and commonly used data sets into flexibly deployable virtual machines, and network virtualization to connect resources behind firewalls/NATs while preserving the necessary performance and the communication environment. An implementation of this approach is described and used to demonstrate and evaluate the proposed approach. The implementation integrates Hadoop, Virtual Workspaces, and ViNe as the MapReduce, virtual machine and virtual network technologies, respectively, to deploy the commonly used bioinformatics tool NCBI BLAST on a WAN-based test bed consisting of clusters at two distinct locations, the University of Florida and the University of Chicago. This WAN-based implementation, called CloudBLAST, was evaluated against both non-virtualized and LAN-based implementations in order to assess the overheads of machine and network virtualization, which were shown to be insignificant. To compare the proposed approach against an MPI-based solution, CloudBLAST performance was experimentally contrasted against the publicly available mpiBLAST on the same WAN-based test bed. Both versions demonstrated performance gains as the number of available processors increased, with CloudBLAST delivering speedups of 57 against 52.4 of MPI version, when 64 processors on 2 sites were used. The results encourage the use of the proposed approach for the execution of large-scale bioinformatics applications on emerging distributed environments that provide access to computing resources as a service.

Sky Computing

Infrastructure-as-a-service (IaaS) cloud computing is revolutionizing how we approach computing. Compute resource consumers can eliminate the expense inherent in acquiring, managing, and operating IT infrastructure and instead lease resources on a pay-as-you-go basis. IT infrastructure providers can exploit economies of scale to mitigate the cost of buying and operating resources and avoid the complexity required to manage multiple customer-specific environments and applications. The authors describe the context in which cloud computing arose, discuss its current strengths and shortcomings, and point to an emerging computing pattern it enables that they call sky computing.

From virtualized resources to virtual computing grids: the In-VIGO system

This paper describes the architecture of the first implementation of the In-VIGO grid-computing system. The architecture is designed to support computational tools for engineering and science research In Virtual Information Grid Organizations (as opposed to in vivo or in vitro experimental research). A novel aspect of In-VIGO is the extensive use of virtualization technology, emerging standards for grid-computing and other Internet middleware. In the context of In-VIGO, virtualization denotes the ability of resources to support multiplexing, manifolding and polymorphism (i.e. to simultaneously appear as multiple resources with possibly different functionalities). Virtualization technologies are available or emerging for all the resources needed to construct virtual grids which would ideally inherit the above mentioned properties. In particular, these technologies enable the creation of dynamic pools of virtual resources that can be aggregated on-demand for application-specific user-specific grid-computing. This change in paradigm from building grids out of physical resources to constructing virtual grids has many advantages but also requires new thinking on how to architect, manage and optimize the necessary middleware. This paper reviews the motivation for In-VIGO approach, discusses the technologies used, describes an early architecture for In-VIGO that represents a first step towards the end goal of building virtual information grids, and reports on first experiences with the In-VIGO software under development.

On the Use of Fuzzy Modeling in Virtualized Data Center Management

One of the most important goals of data-center management is to reduce cost through efficient use of resources. Virtualization techniques provide the opportunity of carving individual physical servers into multiple virtual containers that can be run and managed separately. A key challenge that comes with virtualization is the simultaneous on-demand provisioning of shared resources to virtual containers and the management of their capacities to meet service quality targets at the least cost. This paper proposes a two-level resource management system with local controllers at the virtual-container level and a global controller at the resource-pool level. Autonomic resource allocation is realized through the interaction of the local and global controllers. A novelty of the controller designs is their use of fuzzy logic to efficiently and robustly deal with the complexity of the virtualized data center and the uncertainties of the dynamically changing workloads. Experimental results obtained through a prototype implementation demonstrate that, for the scenarios under consideration, the proposed resource management system can significantly reduce resource consumption while still achieving application performance targets.

Guest Editors' Introduction: Resource Virtualization Renaissance

Virtualization technologies encompass a variety of mechanisms and techniques used to address computer system problems such as security, performance, and reliability by decoupling the architecture and user-perceived behavior of hardware and software resources from their physical implementation.

Time optimal linear schedules for algorithms with uniform dependencies

The authors address the problem of identifying optimal linear schedules for uniform dependence algorithms so that their execution time is minimized. Procedures are proposed to solve this problem based on the mathematical solution of a nonlinear optimization problem. The complexity of these procedures is independent of the size of the algorithm. Actually, the complexity is exponential in the dimension of the index set of the algorithm, and for all practical purposes, very small due to the limited dimension of the index set of algorithms of practical interest. A particular class of algorithms for which the proposed solution is greatly simplified is considered, and the corresponding simpler organization procedure is provided. >

A taxonomy of reconfiguration techniques for fault-tolerant processor arrays

Focuses on the characterization and classification of reconfiguration techniques. The techniques are differentiated according to the type of redundancy (time or hardware), allocation of redundancy (local or global), replacement unit, (processor or a set of processors), switching domain (global or local), and switching implementation (switching element, bus, or network). Typical techniques from four major classes-set switching, processor switching, local redundancy, and time redundancy-are reviewed. The proposed taxonomy can be used as a guide for future research in design and analysis of reconfiguration schemes.<<ETX>>

Toward hardware-redundant, fault-tolerant logic for nanoelectronics

This article provides an overview of several logic redundancy schemes, including von Neumanns multiplexing logic, N-tuple modular redundancy, and interwoven redundant logic. We discuss several important concepts for redundant nanoelectronic system designs based on recent results. First, we use Markov chain models to describe the error-correcting and stationary characteristics of multiple-stage multiplexing systems. Second, we show how to obtain the fundamental error bounds by using bifurcation analysis based on probabilistic models of unreliable gates. Third, we describe the notion of random interwoven redundancy. Finally, we compare the reliabilities of quadded and random interwoven structures by using a simulation-based approach. We observe that the deeper a circuits logical depth, the more fault-tolerant the circuit tends to be for a fixed number of faults. For a constant gate failure rate, a circuits reliability tends to reach a stationary state as its logical depth increases.

Predictive application-performance modeling in a computational grid environment

This paper describes and evaluates the application of three local learning algorithms-nearest-neighbor, weighted-average, and locally-weighted polynomial regression-for the prediction of run-specific resource-usage on the basis of run-time input parameters supplied to tools. A two-level knowledge base allows the learning algorithms to track short-term fluctuations in the performances of computing systems, and the use of instance editing techniques improves the scalability of the performance-modeling system. The learning algorithms assist PUNCH, a network-computing system at Purdue University, in emulating an ideal user in terms of its resource management and usage policies.

A virtual network (ViNe) architecture for grid computing

This paper describes a virtual networking approach for grids called ViNe. It enables symmetric connectivity among grid resources and allows existing applications to run unmodified. Novel features of the ViNe architecture include: easy virtual networking administration; support for physical private networks and support for multiple independent virtual networks in the same infrastructure. The requirements of an application-friendly virtual network environment are presented and it is shown how the proposed solution meets them. Qualitative arguments are provided to justify all design decisions. Also presented is an experimental evaluation of the round-trip latencies and bandwidths achieved by a reference implementation. Measurements are reported for WAN-scenarios involving three different institutions. Under favorable conditions, ViNe bandwidths are within 90 to 100% of the available physical network bandwidth