Search

The paper suggests a new approach based on blockchain technology and smart contracts to delegation of rights within distributed computing systems, which is fault-tolerant, safe and secure. The implementation of the proposed approach is based on the permissioned blockchains and on the Hyperledger Fabric blockchain platform in conjunction with Hyperledger Composer.

We present a cloud storage for collaborations of small and medium-sized experiments in the field of particle astrophysics. This storage provides a unified interface for accessing data from different experiments. In this article, we will focus on the capabilities of the storage for processing user requests for data, as well as on some technical details of the implementation of data selection. We have deployed a working prototype of the storage. Currently the prototype integrates data from such astrophysical experiments as TAIGA and KASCADE. As a result, users of the respective collaborations have the opportunity to collect scientific data from different experiments seamlessly within one request to conduct joint data analysis.

This paper presents a design and operation algorithms of a web-platform for convenient, secure and effective remote interaction on the principles of the open market of users and providers of scientific application software and databases.

This paper considers current trends in creating systems for convenient and secure remote submission (by authorized users) of jobs to computing resources of different types, including supercomputers, clusters, cloud resources, storages, databases, and grid infrastructures. Presently, large computing and storage resources are capable of solving, on their own, the majority of practical problems in the field of science and technology. Therefore, the focus in developing next-generation middleware shifts from global grid systems towards creating convenient and efficient means of access to large individual resources. A web platform for remote access to computing resources is a set of special web services and application-oriented web interfaces. Such web platforms, on a centralized basis, provide users with a number of services interrelated by a specific application area, principle of access, and interface. In this paper, general principles of creating such platforms are considered and some particular implementations of web platforms are briefly described.

The paper suggests a new approach based on blockchain technologies and smart contracts to creation of a distributed system for managing provenance metadata, as well as access rights to data in distributed storages, which is fault-tolerant, safe and secure from the point of view of preservation of metadata records from accidental or intentional distortions. The implementation of the proposed approach is based on the permissioned blockchains and on the Hyperledger Fabric blockchain platform in conjunction with Hyperledger Composer., Comment: 6 pages, 2 figures

We describe the prototype of a Web platform intended for sharing software programs for computer modeling in the rapidly developing field of the nonlinear optics phenomena. The suggested platform is built on the top of the HUBZero open-source middleware. In addition to the basic HUBZero installation we added to our platform the capability to run Docker containers via an external application server and to send calculation programs to those containers for execution. The presented web platform provides a wide range of features and might be of benefit to nonlinear optics researchers.

The paper examines the current trends in designing of systems for convenient and secure remote job submission to various computer resources, including supercomputers, computer clusters, cloud resources, data storages and databases, and grid infrastructures by authorized users, as well as remote job monitoring and obtaining the results. Currently, high-perfomance computing and storage resources are capable of solving independently the majority of practical problems in the field of science and technology. Therefore, the focus in the development of a new generation of middleware shifts from the global grid systems to building convenient and efficient web platforms for remote access to individual computing resources. The paper examines the general principles of the construction and briefly describes some of the specific implementations of the web platforms., 10 pages; 4th International Young Scientists Conference on Computational Science (YSC 2015)

An Open Grid Service Architecture (OGSA) Globus Toolkit 3 (GT3) evaluation group is active at CERN since GT3 was available in early beta version (Spring 2003). This activity focuses on the evaluation of the technology as promised by the OGSA/OGSI paradigm and on GT3 in particular. The goal is to study this new technology and its implications with the goal to provide useful input for the large grid initiatives active in the LHC Computing Grid (LCG) project. A particular effort has been devoted to investigate performance and deployment issues, having in mind the LCG requirements, in particular scalability and robustness.

In this paper we suggest a design of a web marketplace where users of scientific application software and databases, presented in the form of web services, as well as their providers will have presence simultaneously. The model, which will be the basis for the web marketplace is close to the customer-to-customer (C2C) model, which has been successfully used, for example, on the auction sites such as eBay (ebay.com). Unlike the classical model of C2C the suggested marketplace focuses on application software in the form of web services, and standardization of API through which application software will be integrated into the web marketplace. A prototype of such a platform, entitled eSciMart, is currently being developed at SINP MSU.

The focus in development of a new generation of middleware shifts from the global grid systems to building convenient and efficient web platforms for remote access to individual computing resources. Further line of their development, suggested in this work, is related not only with the quantitative increase in their number and with the expansion of scientific, engineering, and manufacturing areas in which they are used, but also with improved technology for remote deployment of application software on the resources interacting with the web platforms. Currently, the services for providers of application software in the context of scientific-oriented web platforms is not developed enough. The proposed in this work new web platforms of application software market should have all the features of the existing web platforms for submissions of jobs to remote resources plus the provision of specific web services for interaction on market principles between the providers and consumers of application packages. The suggested approach will be approved on the example of simulation applications in the field of nonlinear optics.

At the paper we propose a new approach to setting up a user-friendly and yet secure authentication and authorization procedure in a distributed computing system. The security concept of the most heterogeneous distributed computing systems is based on the public key infrastructure along with proxy certificates which are used for rights delegation. In practice a contradiction between the limited lifetime of the proxy certificates and the unpredictable time of the request processing is a big issue for the end users of the system. We propose to use unlimited in time hashes which are individual for each request instead of proxy certificate. Our approach allows to avoid using of the proxy certificates. Thus the security infrastructure of distributed computing system becomes easier for development, support and use.

The integration of IMPALA/BOSS tools for CMS MC production with GRID is presented. A package called DOLLY has been designed and developed, which clones the scripts on the user interface and submits them by BOSS through the GRID to the computer element. These scripts initialize the locally installed IMPALA, which generates a production task and starts it on the same working node.

We present a new version of the CompHEP program package, version 4.5. We describe new options and techniques implemented in the version: interfaces to ROOT and HERWIG, parallel calculations, generation of the XML-based header in event files (HepML), full implementation of the Les Houches agreements (LHA I, SUSY LHA, LHA PDF, Les Houches Event format), cascade matching for intermediate scalar resonances, etc.

In the framework of this work an approach for batch processing of computer jobs prepared for various runtime environments in grid is proposed. This method is based on the virtualization (using virtual machines) of working nodes of grid resource centers and enables executing applied jobs irrespective of runtime environment it has been initially developed for. In particular, jobs developed for execution in the environment of the widespread OS MS Windows, can be processed in resource centres of the grid system whose working nodes operate under OS Linux.

'Pilot' is a grid job execution service for workflow jobs. The main goal for the service is to automate computations with multiple stages since they can be expressed as simple workflows. Each job is a directed acyclic graph of tasks and each task is an execution of something on a grid resource (or 'computing element'). Tasks may be submitted to any WS-GRAM (Globus Toolkit 4) service. The target resources for the tasks execution are selected by the Pilot service from the set of available resources which match the specific requirements from the task and/or job definition. Some simple conditional execution logic is also provided. The 'Pilot' service is built on the REST concepts and provides a simple API through authenticated HTTPS. This service is deployed and used in production in a Russian national grid project GridNNN.

Grid systems are used for calculations and data processing in various applied areas such as biomedicine, nanotechnology and materials science, cosmophysics and high energy physics as well as in a number of industrial and commercial areas. Traditional method of execution of jobs in grid is running jobs directly on the cluster nodes. This puts restrictions on the choice of the operational environment to the operating system of the node and also does not allow to enforce resource sharing policies or jobs isolation nor guarantee minimal level of available system resources. We propose a new approach to running jobs on the cluster nodes when each grid job runs in its own virtual environment. This allows to use different operating systems for different jobs on the same nodes in cluster, provides better isolation between running jobs and allows to enforce resource sharing policies. The implementation of the proposed approach was made in the framework of gLite middleware of the EGEE/WLCG project and was successfully tested in SINP MSU. The implementation is transparent for the grid user and allows to submit binaries compiled for various operating systems using exactly the same gLite interface. Virtual machine images with the standard gLite worker node software and sample MS Windows execution environment were created.

This paper describes a dynamic-debugging system for programs written in REDUCE. With the help of the debugger the user can trace the evaluation of the functions defined in the input language REDUCE and, moreover, interrupt the evaluation, if necessary. Operational experience has shown that the debugger is highly effective for training beginners and for debugging large programs in REDUCE and RLISP.

The paper describes some special aspects of the security infrastructure for distributed com- puting systems. Most heterogeneous and geographically dispersed distributed computing systems, e.g. GRID, use the Public Key Infrastructure (PKI). One of the main problem in such systems is the necessity to use time-limited proxy certificates for delegation of rights from user to an execution remote service which acts on behalf of the user. The problem is that there exists a contradiction between the limited lifetime of the proxy certificates and unpredictable time of the request processing. Our approach allows to avoid using the proxy certificates. This makes the security infrastructure of distributed computing systems simpler for development, support and use. In particular, the proxy renewal service becomes unnecessary at all.