We present a data transfer system for the grid environment built on top of the open source FDT tool (Fast Data Transfer) developed by Caltech in collaboration with the National University of Science and Technology (Pakistan). The enhancement layer above FDT consists of a client program - fdtcp (FDT copy) and a fdtd service (FDT daemon). This pair of components allows for GSI authenticated data transfers and offers to the user (or data movement production service) interface analogous to grid middle-ware data transfer services - SRM (i.e. srmcp) or GridFTP (i.e. globus-url-copy). fdtcp/fdtd enables third-party, batched file transfers. An important aspect is monitoring by means of the MonALISA active monitoring light-weight library ApMon, providing real-time monitoring and arrival time estimates as well as powerful troubleshooting mechanism.The actual transfer is carried out by the FDT application, an efficient application capable of reading and writing at disk speed over wide area networks. FDT's excellent performance was demonstrated e. g. during SuperComputing 2009 Bandwidth Challenge.We also discuss the storage technology interface layer, specifically focusing on the open source Hadoop distributed file system (HDFS), presenting the recently developed FDT-HDFS sequential write adapter.The integration with CMS PhEDEx is described as well. The PhEDEx project (Physics Experiment Data Export) is responsible for facilitating large-scale CMS data transfers across the grid.Ongoing and future development involves interfacing with next generation network services developed by OGF NSI-WG, GLIF and DICE groups, allowing for network resource reservation and scheduling.

Data distribution, storage and access are essential to CPU-intensive and data-intensive high performance Grid computing. A newly emerged file system, Hadoop distributed file system (HDFS), is deployed and tested within the Open Science Grid (OSG) middleware stack. Efforts have been taken to integrate HDFS with other Grid tools to build a complete service framework for the Storage Element (SE). Scalability tests show that sustained high inter-DataNode data transfer can be achieved for the cluster fully loaded with data-processing jobs. The WAN transfer to HDFS supported by BeStMan and tuned GridFTP servers shows large scalability and robustness of the system. The hadoop client can be deployed at interactive machines to support remote data access. The ability to automatically replicate precious data is especially important for computing sites, which is demonstrated at the Large Hadron Collider (LHC) computing centers. The simplicity of operations of HDFS-based SE significantly reduces the cost of ownership of Petabyte scale data storage over alternative solutions.

A set of software deployment tools has been developed for the installation, verification, and removal of a CMS software release.The tools that are mainly targeted for the deployment on the OSG have the features of instant release deployment, corrective resubmission of the initial installation job, and an independent web-based deployment portal with Grid security infrastructure login mechanism.We have been deploying over 500 installations and found the tools are reliable and adaptable to cope with problems with changes in the Grid computing environment and the software releases.We present the design of the tools, statistics that we gathered during the operation of the tools, and our experience with the CMS software deployment on the OSG Grid computing environment.

This paper presents the design and implementation of a Grid-enabled physics analysis environment for handheld and other resource-limited computing devices as one example of the use of mobile devices in eScience. Handheld devices offer great potential because they provide ubiquitous access to data and round-the-clock connectivity over wireless links. Our solution aims to provide users of handheld devices the capability to launch heavy computational tasks on computational and data Grids, monitor the jobs status during execution, and retrieve results after job completion. Users carry their jobs on their handheld devices in the form of executables (and associated libraries). Users can transparently view the status of their jobs and get back their outputs without having to know where they are being executed. In this way, our system is able to act as a high-throughput computing environment where devices ranging from powerful desktop machines to small handhelds can employ the power of the Grid. The results shown in this paper are readily applicable to the wider eScience community.

In Grids scheduling decisions are often made on the basis of jobs being either data or computation intensive: in data intensive situations jobs may be pushed to the data and in computation intensive situations data may be pulled to the jobs. This kind of scheduling, in which there is no consideration of network characteristics, can lead to performance degradation in a Grid environment and may result in large processing queues and job execution delays due to site overloads. In this paper we describe a Data Intensive and Network Aware (DIANA) meta-scheduling approach, which takes into account data, processing power and network characteristics when making scheduling decisions across multiple sites. Through a practical implementation on a Grid testbed, we demonstrate that queue and execution times of data-intensive jobs can be significantly improved when we introduce our proposed DIANA scheduler. The basic scheduling decisions are dictated by a weighting factor for each potential target location which is a calculated function of network characteristics, processing cycles and data location and size. The job scheduler provides a global ranking of the computing resources and then selects an optimal one on the basis of this overall access and execution cost. The DIANA approach considers the Grid as a combination of active network elements and takes network characteristics as a first class criterion in the scheduling decision matrix along with computations and data. The scheduler can then make informed decisions by taking into account the changing state of the network, locality and size of the data and the pool of available processing cycles.

We describe a set of web services, created to support scientists in performing complex, tasks (such as Monte Carlo production). The web services described in this paper provide a portal for scientists to execute complex applications which can consist of many consecutive steps (e.g. work flows). The main design goal of the web services discussed is to provide controlled access for (multiple) set(s) of users in different roles (e.g. scientists, administrators, grid operators,...) to complex applications without the added trouble of updating, configuring, and patching these ever evolving applications and keep the users focused on their core tasks (e.g. scientific analysis). The web services have been implemented using the Clarens grid toolkit. This Python (and Java) based toolkit provides, amongst others, x509 authorization, access control and VO management for its services. The (stateful) web services discussed in this paper re-use several of these Clarens components in providing access control and usage quotas. Initially the services described in this paper where developed to support users in (private) Monte Carlo production activities, however due to their generic design, can be used to expose other (potentially complex) applications to users as will be shown in this paper.

In this paper we describe progress in the NSF-funded Ultralight project and a recent demonstration of Ultralight technologies at SuperComputing 2005 (SC|05). The goal of the Ultralight project is to help meet the data-intensive computing challenges of the next generation of particle physics experiments with a comprehensive, network-focused approach. Ultralight adopts a new approach to networking: instead of treating it traditionally, as a static, unchanging and unmanaged set of inter-computer links, we are developing and using it as a dynamic, configurable, and closely monitored resource that is managed from end-to-end. Thus we are constructing a next-generation global system that is able to meet the data processing, distribution, access and analysis needs of the particle physics community. In this paper we present the motivation for, and an overview of, the Ultralight project. We then cover early results in the various working areas of the project. The remainder of the paper describes our experiences of the Ultralight network architecture, kernel setup, application tuning and configuration used during the bandwidth challenge event at SC|05. During this Challenge, we achieved a record-breaking aggregate data rate in excess of 150 Gbps while moving physics datasets between many sites interconnected by the Ultralight backbone network. The exercise highlighted the benefits of Ultralight's research and development efforts that are enabling new and advanced methods of distributed scientific data analysis.

In this paper we present the design and implementation of the mission-oriented USLHCNet for HEP research community and the UltraLight network testbed. The design philosophy for these networks is to help meet the data-intensive computing challenges of the next generation of particle physics experiments with a comprehensive, network-focused approach. Instead of treating the network as a static, unchanging and unmanaged set of intercomputer links, we are developing and using it as a dynamic, configurable, and closely monitored resource that is managed from end-to-end. In this paper we will present our work in the various areas of the project including infrastructure construction, protocol research and application development. Our goal is to construct a next-generation global system that is able to meet the data processing, distribution, access and analysis needs of the particle physics community.

In this paper we present the motivation, the design, and a recent demonstration of the UltraLight testbed at SC|05. The goal of the Ultralight testbed is to help meet the data-intensive computing challenges of the next generation of particle physics experiments with a comprehensive, network- focused approach. UltraLight adopts a new approach to networking: instead of treating it traditionally, as a static, unchanging and unmanaged set of inter-computer links, we are developing and using it as a dynamic, configurable, and closely monitored resource that is managed from end-to-end. To achieve its goal we are constructing a next-generation global system that is able to meet the data processing, distribution, access and analysis needs of the particle physics community. In this paper we will first present early results in the various working areas of the project. We then describe our experiences of the network architecture, kernel setup, application tuning and configuration used during the bandwidth challenge event at SC|05. During this Challenge, we achieved a record-breaking aggregate data rate in excess of 150 Gbps while moving physics datasets between many Grid computing sites.

Selecting optimal resources for submitting jobs on a computational Grid or accessing data from a data grid is one of the most important tasks of any Grid middleware. Most modern Grid software today satisfies this responsibility and gives a best-effort performance to solve this problem. Almost all decisions regarding scheduling and data access are made by the software automatically, giving users little or no control over the entire process. To solve this problem, a more interactive set of services and middleware is desired that provides users more information about Grid weather, and gives them more control over the decision making process. This paper presents a set of services that have been developed to provide more interactive resource management capabilities within the Grid Analysis Environment (GAE) being developed collaboratively by Caltech, NUST and several other institutes. These include a steering service, a job monitoring service and an estimator service that have been designed and written using a common Grid-enabled Web Services framework named Clarens. The paper also presents a performance analysis of the developed services to show that they have indeed resulted in a more interactive and powerful system for user-centric Grid-enabled physics analysis.

The Grid Analysis Environment (GAE), which is a continuation of the CAIGEE project [5], is an effort to develop, integrate and deploy a system for distributed analysis. The current focus within the GAE is on the CMS experiment [1] however the GAE design abstracts from any specific scientific experiment and focuses on scientific analysis in general. The GAE project does not intend to reinvent services, but rather to integrate existing services into a collaborative system of web services.

We describe the NSF-funded UltraLight project. The project's goal is to meet the data-intensive computing challenges of the next generation of particle physics experiments with a comprehensive, network-focused agenda. In particular we argue that instead of treating the network traditionally, as a static, unchanging and unmanaged set of inter-computer links, we instead will use it as a dynamic, configurable, and closely monitored resource, managed end-to-end, to construct a next-generation global system able to meet the data processing, distribution, access and analysis needs of the high energy physics (HEP) community. While the initial UltraLight implementation and services architecture is being developed to serve HEP, we expect many of UltraLight's developments in the areas of networking, monitoring, management, and collaborative research, to be applicable to many fields of data intensive e-science. In this paper we give an overview of, and motivation for the UltraLight project, and provide early results within different working areas of the project.

Grid based systems require a database access mechanism that can provide seamless homogeneous access to the requested data through a virtual data access system, i.e. a system which can take care of tracking the data that is stored in geographically distributed heterogeneous databases. This system should provide an integrated view of the data that is stored in the different repositories by using a virtual data access mechanism, i.e. a mechanism which can hide the heterogeneity of the backend databases from the client applications. This paper focuses on accessing data stored in disparate relational databases through a web service interface, and exploits the features of a Data Warehouse and Data Marts. We present a middleware that enables applications to access data stored in geographically distributed relational databases without being aware of their physical locations and underlying schema. A web service interface is provided to enable applications to access this middleware in a language and platform independent way. A prototype implementation was created based on Clarens [4], Unity [7] and POOL [8]. This ability to access the data stored in the distributed relational databases transparently is likely to be a very powerful one for Grid users, especially the scientific community wishing to collate and analyze data distributed over the Grid.

High energy physics (HEP) and other scientific communities have adopted service oriented architectures (SOA) as part of a larger grid computing effort. This effort involves the integration of many legacy applications and programming libraries into a SOA framework. The grid analysis environment (GAE) (Lingen et al., 2004) is such a service oriented architecture based on the Clarens grid services framework (Steenberg et al., 2004) and is being developed as part of the compact muon solenoid (CMS) experiment at the large hadron collider (LHC) at European Laboratory for Particle Physics (CERN). Clarens provides a set of authorization, access control, and discovery services, as well as XMLRPC and SOAP access to all deployed services. Two implementations of the Clarens Web services framework (Python and Java) offer integration possibilities for a wide range of programming languages. This paper describes the Java implementation of the Clarens Web services framework called 'JClarens' and several Web services of interest to the scientific and grid community that have been deployed using JClarens.

Effective scheduling in the Grid consisting of heterogeneous and distributed resources is imperative in order to counter unacceptably large overheads of the Grid. We proposed the grid middleware (pyBubble) supporting the DAG based co-scheduling for improving the performance of the RPC mechanism. DAG based co-scheduling reduces redundant transmission of input and output data from execution of the sequence of related client requests, thereby decongesting the network. We demonstrate the efficiency of DAG based co-scheduled RPC in experiments compared with the overhead of the traditional RPC mechanism.

This paper describes progress made in the development of the Clarens Web Services Framework, including a second Java-based server implementation, improved performance, a global lookup and discovery service leveraging of the MonALISA monitoring system, and adapting the framework to a secure message-based transport protocol.

Looks at the UltraLight project which treats the network interconnecting globally distributed data sets as a dynamic, configurable, and closely monitored resource to construct a next-generation system that can meet the high-energy physics community's data-processing, distribution, access, and analysis needs.

The grid is emerging as a great computational resource but its dynamic behavior makes the Grid environment unpredictable. Systems and networks can fail, and the introduction of more users can result in resource starvation. Once a job has been submitted for execution on the grid, monitoring becomes essential for a user to see that the job is completed in an efficient way, and to detect any problems that occur while the job is running. In current environments once a user submits a job he loses direct control over the job and the system behaves like a batch system: the user submits the job and later gets a result back. The only information a user can obtain about a job is whether it is scheduled, running, cancelled or finished. Today users are becoming increasingly interested in such analysis grid environments in which they can check the progress of the job, obtain intermediate results, terminate the job based on the progress of job or intermediate results, steer the job to other nodes to achieve better performance and check the resources consumed by the job. In order to fulfill their requirements of interactivity a mechanism is needed that can provide the user with real time access to information about different attributes of a job. In this paper we present the design of a Job Monitoring Service, a web service that will provide interactive remote job monitoring by allowing users to access different attributes of a job once it has been submitted to the interactive Grid Analysis Environment (1).