Attila Csaba Marosi

EDGeS: Bridging EGEE to BOINC and XtremWeb

Desktop Grids, such as XtremWeb and BOINC, and Service Grids, such as EGEE, are two different approaches for science communities to gather computing power from a large number of computing resources. Nevertheless, little work has been done to combine these two Grid technologies in order to establish a seamless and vast Grid resource pool. In this paper we present the EGEE Service Grid, the BOINC and XtremWeb Desktop Grids. Then, we present the EDGeS solution to bridge the EGEE Service Grid with the BOINC and XtremWeb Desktop Grids.

SZTAKI Desktop Grid (SZDG): A Flexible and Scalable Desktop Grid System

SZTAKI Desktop Grid (SZDG) is an extension of BOINC in order to make it more flexible, versatile and scalable in terms of enabling the interconnection of different BOINC projects and execution of parameter sweep applications from a generic, high level user interface without the intervention of the BOINC project administrator. The paper describes the main concepts and features of SZDG. Among the many novel features the two most important will be described in detail. First, the paper describes those extensions that enable the easy development and execution of parameter sweep applications on SZDGs. The second part of the paper describes how SZDGs can be organized into a hierarchical interconnection scheme that enables to use SZDGs as building blocks to create higher level SZDGs.

SZTAKI Desktop Grid: a Modular and Scalable Way of Building Large Computing Grids

So far BOINC based desktop grid systems have been applied at the global computing level. This paper describes an extended version of BOINC called SZTAKI desktop grid (SZDG) that aims at using desktop grids (DGs) at local (enterprise/institution) level. The novelty of SZDG is that it enables the hierarchical organisation of local DGs, i.e., clients of a DG can be DGs at a lower level that can take work units from their higher level DG server. More than that, even clusters can be connected at the client level and hence work units can contain complete MPI programs to be run on the client clusters. In order to easily create master/worker type DG applications a new API, called as the DC-API has been developed. SZDG and DC-API has been successfully applied both at the global and local level, both in academic institutions and in companies to solve problems requiring large computing power.

Integrated Monitoring Approach for Seamless Service Provisioning in Federated Clouds

Cloud Computing offers simple and cost effective outsourcing in dynamic service environments, and allows the construction of service-based applications using virtualization. By aggregating the capabilities of various IaaS cloud providers, federated clouds can be built. Managing such a distributed, heterogeneous environment requires sophisticated interoperation of adaptive coordinating components. In this paper we introduce an integrated federated management and monitoring approach that enables autonomous service provisioning in federated clouds. In this architecture, cloud brokers manage the number and the location of the utilized virtual machines for the received service requests. In order to provide seamless service executions, a state of the art monitoring solution is proposed that supports cloud selection performed by the management layer of the architecture. Our solution is able to cope with highly dynamic service executions by federating heterogeneous cloud infrastructures in a transparent and autonomous manner.

Towards a volunteer cloud system

The paper completes the work started in the EU FP7 EDGI project for extending service grids with volunteer (global) and institutional (local) desktop grids. The Generic BOINC Application Client (GBAC) concept described in the paper enables the transparent and automatic forwarding of parameter sweep application (parametric) jobs from service grid VOs (Virtual Organizations) into connected desktop grids without any porting effort. GBAC that introduces virtualization for the volunteer BOINC (Berkeley Open Infrastructure for Network Computing) clients can also be considered as a first step towards establishing volunteer cloud systems since it provides solutions for several problems of creating such a volunteer cloud system.

Sztaki Desktop Grid: Building a Scalable, Secure Platform for Desktop Grid Computing

In this paper we present a concept how separate desktop grids can be used as building blocks for larger scale grids by organizing them in a hierarchical tree. We describe an enhanced security model which satisfies the requirements of the hierarchical setup and is aimed for real-world deployment.

EDGeS: The common boundary between service and desktop grids

Service grids and desktop grids are both promoted by their supportive communities as great solutions for solving the available compute power problem and helping to balance loads across network systems. Little work, however, has been undertaken to blend these two technologies together. In this paper we introduce a new EU project, that is building technological bridges to facilitate service and desktop grid interoperability. We provide a taxonomy and background into service grids, such as EGEE and desktop grids or volunteer computing platforms, such as BOINC and XtremWeb. We then describe our approach for identifying translation technologies between service and desktop grids. The individual themes discuss the actual bridging technologies employed and the distributed data issues surrounding deployment.

GenWrapper: A generic wrapper for running legacy applications on desktop grids

Desktop Grids represent an alternative trend in Grid computing using the same software infrastructure as Volunteer Computing projects, such as BOINC. Applications to be deployed on a BOINC infrastructure need special preparations. However, there are many legacy applications, that have either no source code available or would require too much effort to port. For these applications BOINC provides a wrapper. This wrapper can handle the simple cases and it is configurable, but it can only be used to execute a list of legacy executables (tasks) one after the other. GenWrapper aims to provide a generic solution for wrapping and executing an arbitrary set of legacy applications by utilizing a POSIX like shell scripting environment to describe how the application is to be run and how the work unit should be processed. This is realized by an extended version of BusyBox providing the most common UNIX commands and a POSIX shell interpreter in a single executable with a special applet (BusyBox extension) to make BOINC API functions accessible from the shell on Windows, Linux and Mac OS X platforms. In this paper we present how GenWrapper works and how it can be used to port legacy applications to Desktop Grid systems.

ENABLING GENERIC DISTRIBUTED COMPUTING INFRASTRUCTURE COMPATIBILITY FOR WORKFLOW MANAGEMENT SYSTEMS

Solving workflow management system’s Distributed Computing Infrastructure (DCI) incompatibility and their workflow interoperability issues are very challenging and complex tasks. Workflow management systems (and therefore their workflows, workflow developers and also their end-users) are bounded tightly to some limited number of supported DCIs, and efforts required to allow additional DCI support. In this paper we are specifying a concept how to enable generic DCI compatibility for grid workflow management systems (such as ASKALON, MOTEUR, gUSE/WS-PGRADE, etc.) on job and indirectly on workflow level. To enable DCI compatibility among the different workflow management systems we have developed the DCI Bridge software solution. In this paper we will describe its internal architecture, provide usage scenarios to show how the developed service resolve the DCI interoperability issues between various middleware types. The generic DCI Bridge service enables the execution of jobs onto the existing major DCI platforms (such as Service Grids (Globus Toolkit 2 and 4, gLite, ARC, UNICORE), Desktop Grids, Web services, or even cloud based DCIs).

Workers in the Clouds

This paper introduces the existing connectivity and interoperability issues of Clouds, Grids and Clusters, and provides solutions to overcome these issues. The paper proposes several possible solution variants how to pool Cloud resources for executing bag of tasks type jobs. It presents two implementations based on BOINC and Condor. It details performance measurement results obtained by executing parameter study type applications using the two implementations.