Jan Meizner

The Collage Authoring Environment

Abstract The Collage Authoring Environment is a software infrastructure which enables domain scientists to collaboratively develop and publish their work in the form of executable papers. It corresponds to the recent developments in both e-Science and computational technologies which call for a novel publishing paradigm. As part of this paradigm, static content (such as traditional scientific publications) should be supplemented with elements of interactivity, enabling reviewers and readers to reexamine the reported results by executing parts of the software on which such results are based as well as access primary scientific data. Taking into account the presented rationale we propose an environment which enables authors to seamlessly embed chunks of executable code (called assets) into scientific publications and allow repeated execution of such assets on underlying computing and data storage resources, as required by scientists who wish to build upon the presented results. The Collage Authoring Environment can be deployed on arbitrary resources, including those belonging to high performance computing centers, scientific e-Infrastructures and resources contributed by the scientists themselves. The environment provides access to static content, primary datasets (where exposed by authors) and executable assets. Execution features are provided by a dedicated engine (called the Collage Server) and embedded into an interactive view delivered to readers, resembling a traditional research publication but interactive and collaborative in its scope. Along with a textual description of the Collage environment the authors also present a prototype implementation, which supports the features described in this paper. The functionality of this prototype is discussed along with theoretical assumptions underpinning the proposed system.

Component Approach to Computational Applications on Clouds

Abstract Running computational science applications on the emerging cloud infrastructures requires appropriate programming models and tools. In this paper we investigate the applicability of the component model to developing such applications. The component model we propose takes advantages of the features of the IaaS infrastructure and offers a high-level application composition API. We describe experiments on a scientific application from the bioinformatics domain, using a hybrid cloud infrastructure which consists of a private cloud running Eucalyptus and the Amazon EC2 public cloud. The measured performance of virtual machine startup time and virtualization overhead indicate promising prospects for exploiting such infrastructures along with the proposed component-based approach.

Managing entire lifecycles of e-science applications in the gridspace2 virtual laboratory --- from motivation through idea to operable web-accessible environment built on top of PL-Grid e-infrastructure

The GridSpace2 environment, developed in the scope of the PL-Grid Polish National Grid Initiative, constitutes a comprehensive platform which supports e-science applications throughout their entire lifecycle. Application development may involve multiple phases, including writing, prototyping, testing and composing the application. Once the application attains maturity it becomes operable and capable of being executed, although it may still be subject to further development --- including actions such as sharing with collaborating researchers or making results publicly available with the use of dedicated publishing interfaces. This paper describes each of these phases in detail, showing how the GridSpace2 platform can assist the developers and publishers of computational experiments.

Evaluation of Cloud Providers for VPH Applications

Infrastructure as a Service (IaaS) clouds are considered interesting sources of computing and storage resources for scientific applications. However, given the large number of cloud vendors and their diverse offerings, it is not trivial for research projects to select an appropriate service provider. In this paper, we present the results of evaluation of public cloud providers, taking into account the requirements of the biomedical applications within the VPH-Share project. We performed a broad analysis of nearly 50 cloud providers and analyzed the performance and cost of 26 virtual machine instance types offered by the top three providers who meet our criteria: Amazon EC2, Rack Space and Soft Layer. We hope our results will be helpful for other research projects that are considering clouds as a potential source of computing and storage resources.

Composing, execution and sharing of multiscale applications

This paper presents the research which led to elaboration of an environment for composing, executing and sharing multiscale applications. The resulted environment supports ability to connect software modules to form large-scale, multiscale simulations and directly execute them on distributed e-infrastructures suitable for particular application models chosen by users. It also enables hybrid execution, i.e. different parts of the same application can be executed on various types of e-infrastructures i.e. on a grid (e.g. EGI), HPC (e.g. PRACE) or on a cloud. The environment is web based and gives the user a direct access to the distributed resources from a single browser. It supports a variety of possible realizations of multiscale simulations in a unified and non-invasive way and enables storing model metadata such as scale, inputs and outputs.The presented environment consists of an application composition tool called Multiscale Application Designer (MAD), an application module description registry MAPPER Memory (MaMe) and GridSpace (GS) supporting execution of applications on various infrastructures. We present an architecture of the current implementation along with a detailed description of the tools and their current features. Additionally, we report on validation of our tools by multiscale application developers. We compare the processes of creating and running applications with and without the tools and we present a case study based on a sample multiscale application skeleton. Environment supporting composition and sharing of multiscale applications.Direct execution of multiscale applications on distributed e-infrastructures.Support for hybrid execution on different types of e-infrastructures.Support for a variety of realizations of multiscale simulations in a non-invasive way.Validation by multiscale application developers.

ViroLab Security and Virtual Organization Infrastructure

This paper introduces security requirements and solutions present in the ViroLab Virtual Laboratory. Our approach is to use a federated Single Sign-On mechanism based on the Shibboleth framework that enables multiple partners to authenticate against their local identity systems and use resources provided by all other partners. Since the basic Shibboleth capabilities do not meet our specific requirements related to supporting non-web-based services, we created a set of custom tools that allow us to develop a homogeneous, Shibboleth-based security solution for both Web and non-web-based software components. This paper describes these tools in detail, together with other services of the virtual laboratory which have been integrated with the security infrastructure. A decentralized, attribute-based approach facilitating the creation and management of virtual organizations is the key achievement of our work.

Cloud computing infrastructure for the VPH community

Abstract As virtualization technologies mature and become ever more widespread, cloud computing has emerged as a promising paradigm for e-science. In order to facilitate successful application of cloud computing in scientific research – particularly in a domain as security-minded as medical research – several technical challenges need to be addressed. This paper reports on the successful deployment and utilization of a cloud computing platform for the Virtual Physiological Human (VPH) research community, originating in the VPH-Share project and continuing beyond the end of this project. The platform tackles technical issues involved in porting existing desktop applications to the cloud environment and constitutes a uniform research space where application services can be developed, stored, accessed and shared using a variety of computational infrastructures. The paper also presents examples of application workflows which make use of the presented infrastructure – both internal and external to the VPH community.

Enabling Multiscale Fusion Simulations on Distributed Computing Resources

We describe a way to support the execution of multiphysics simulations on PL-Grid resources. To achieve this, we extended the existing programming and execution framework for multiscale applications to support execution of legacy, computationally intensive applications, which apply various computational patterns. In particular, we focus on a stability simulation involving the plasma edge in a Tokamak device. We also show how to support the parameter sweep pattern of execution used in that application. We combine two approaches for building multiphysics applications: visual composition enabled by the Multiscale Application Designer and a script-based solution supported by the GridSpace platform. The usage and benefits of the PL-Grid e-infrastructure for application execution are outlined.

The Collage Authoring Environment: From Proof-of-Concept Prototype to Pilot Service☆

Abstract The aim of this paper is to present the pilot service of the Collage Authoring Environment enabling executable scientific publications that is based on the GridSpace2 distributed computing platform and integrated with the online publisher platform ScienceDirect, provided under the auspices of Elsevier. The scope of this paper includes the work carried out when adapting Collage from a proof-of-concept prototype that was awarded the Grand Prize in the Elsevier Executable Paper Grand Challenge into a robust pilot service deployment supporting real-life use cases.

FLEXIBLE AND SECURE ACCESS TO COMPUTING CLUSTERS

The investigation presented in this paper was prompted by the need to provide a manageable solution for secure access to computing clusters with a federated authentication framework. This requirement is especially important for scientists who need direct access to computing nodes in order to run their applications (e.g. chemical or medical simulations) with proprietary, open-source or custom-developed software packages. Our existing software, which enables non-Web clients to use Shibboleth-secured services, has been extended to provide direct SSH access to cluster nodes using the Linux Pluggable Authentication Modules mechanism. This allows Shibboleth users to run the required software on clusters. Validation and performance comparison with existing SSH authentication mechanisms confirm that the presented tools satisfy the stated requirements.