Mumtaz Siddiqui

ASKALON: a Grid application development and computing environment

We present the ASKALON environment whose goal is to simplify the development and execution of workflow applications on the Grid. ASKALON is centered around a set of high-level services for transparent and effective Grid access, including a Scheduler for optimized mapping of workflows onto the Grid, an Enactment Engine for reliable application execution, a Resource Manager covering both computers and application components, and a Performance Prediction service based on training phase and statistical methods. A sophisticated XML-based programming interface that shields the user from the Grid middleware details allows the high-level composition of workflow applications. ASKALON is used to develop and port scientific applications as workflows in the Austrian Grid project. We present experimental results using two real-world scientific applications to demonstrate the effectiveness of our approach.

Grid capacity planning with negotiation-based advance reservation for optimized QoS

Advance reservation of grid resources can play a key role in enabling grid middleware to deliver on-demand resource provision with significantly improved quality-of-service (QoS). However, in the grid, advance reservation has been largely ignored due to the dynamic grid behavior, underutilization concerns, multi-constrained applications, and lack of support for agreement enforcement. These issues force the grid middleware to make resource allocations at run-time with reduced QoS. To remedy these, we introduce a new, 3-layered negotiation protocol for advance reservation of the grid resources. We model resource allocation as an online strip packing problem and introduce a new mechanism that optimizes resource utilization and QoS constraints while generating the contention-free solutions. The mechanism supports open reservations to deal with the dynamic grid and provides a practical solution for agreement enforcement. We have implemented a prototype and performed experiments to demonstrate the effectiveness of our approach

ASKALON: A Development and Grid Computing Environment for Scientific Workflows

Most existing Grid application development environments provide the application developer with a nontransparent Grid. Commonly, application developers are explicitly involved in tedious tasks such as selecting software components deployed on specific sites, mapping applications onto the Grid, or selecting appropriate computers for their applications. Moreover, many programming interfaces are either implementation-technology-specific (e.g., based on Web services [24]) or force the application developer to program at a low-level middleware abstraction (e.g., start task, transfer data [22, 153]). While a variety of graphical workflow composition tools are currently being proposed, none of them is based on standard modeling techniques such as Unified Modeling Language (UML).

Applying Advance Reservation to Increase Predictability of Workflow Execution on the Grid

In this paper we present an extension to devise and implement advance reservation as part of the scheduling and resource management services of the ASKALON Grid application development and runtime environment. The scheduling service has been enhanced to offer a list of resources that can execute a specific task and to negotiatewith the resource manager about resources capable of processing tasks in the shortest possible time. We introduce progressive reservation approach which tries to allocate resources based on a fair-share principle. Experiments are shown that demonstrate the effectiveness of our approach, and that reflect different QoS parameters including performance, predictability, resource usage and resource fairness.

GLARE: A Grid Activity Registration, Deployment and Provisioning Framework

Resource management is a key concern for implementing effective Grid middleware and shielding application developers from low level details. Existing resource managers concentrate mostly on physical resources. However, some advanced Grid programming environments allow application developers to specify Grid application components at high level of abstraction which then requires an effective mapping between high level application description (activity types) and actual deployed software components (activity deployments). This paper describes GLARE framework that provides dynamic registration, automatic deployment and on-demand provision of application components (activities) that can be used to build Grid applications. GLARE simplifies description and presentation of both activity types and deployments so that they can easily be located in the Grid and thus become available on-demand. GLARE has been implemented based on a super-peer model with support for activity leasing, self management, and fault tolerance. Experiments are shown to reflect the effectiveness of the GLARE.

GridARM: askalon's grid resource management system

The emergence of Grid computing has accentuated the need of an adaptable, scalable and extensible resource management system. In this paper we introduce GridARM system which renders the boundaries of resource brokerage, virtual organization wide authorization and advanced reservation, and represents a scalable and adaptive Grid resource management as a middleware infrastructure. The GridARM system provides mechanisms for Grid resource discovery, selection and allocation along with resource requestor and provider interaction. Experiments are presented that demonstrate the effectiveness of our approach.

Semantic-Based On-demand Synthesis of Grid Activities for Automatic Workflow Generation

On-demand synthesis of grid activities can play a significant role in automatic workflow composition and in improving quality of the grid resource provisioning. However, in the grid, synthesis of activities has been largely ignored due to the limited expressiveness of the representation of activity capabilities and the lack of adapted resource management means to take advantage of such activity synthesis. This paper introduces a new mechanism for automatic synthesis of available activities in the grid by applying ontology rules. Rule-based synthesis combines multiple primitive activities to form new compound activities. The synthesized activities can be provisioned as new or alternative options for negotiation as well as advance reservation. This is a major advantage compared to other approaches that only focus on resource matching and brokerage. Furthermore, the new synthesized activities provide aggregated capabilities that otherwise may not be possible, leading towards an automatic generation of grid workflows. We developed a prototype to demonstrate advantages of our approach.

Advanced Reservation and Co-Allocation of Grid Resources: A Step towards an invisible Grid

The grid resource management mainly concerns with provision of the grid resources on-demand. Grid resources are heterogeneous in nature, distributed under multiple trust domains and controlled by their local management systems. In order to provide a grid level smart and robust resource management that shields the grid middleware complexities, we need a better control over grid resources. A mechanism for the provision of service level agreement (SLA) between resource requester and provider could leads us to achieve this goal. Advanced reservation is a promise by the system that a certain resource capability would be available some time in future. In this paper we propose a distributed system for advanced reservation and co-allocation of the grid resources in which clients can negotiate with resource provider for the better compromise between application requirements and resource capabilities

Grid Activity Registration, Deployment and Provisioning Framework

Resource provisioning is a key concern for implementing an effective resource management as part of the Grid runtime environment; it delivers both physical and logical resources on-demand and shields the application developers from low level details. The previous chapter gives a general overview of the resource management (GridARM) with a detailed description of selection and brokerage problem of physical resources. This chapter introduces GLARE, an integral part of GridARM, that covers logical resources, particularly Grid activities [158]. Existing Grid resource managers concentrate mostly on physical resources. However, some advanced Grid programming environments allow application developers to specify Grid application components (activities) at a higher level of abstraction which then requires an effective mapping between high level resource descriptions i.e. activity types and actual installations i.e. activity deployments This chapter describes GLARE that provides dynamic registration, automatic deployment and on-demand provisioning of activities that can be used to build Grid applications. GLARE simplifies description and representation of both activity types (abstract descriptions) and activity deployments (concrete deployments) so that they can easily be located in the Grid and become available on-demand. GLARE has been implemented as a distributed registry and deployment service by following the superpeer model of GridARM [154].

Semantically-enhanced on-demand resource provision and management for the grid

On-demand resource provision can play a significant role in shielding the Grid middleware complexities and leading towards an invisible Grid. However, in the Grid, on-demand provision has been mostly ignored due to the dynamic Grid behavior, multi-constrained environment, and lack of support for a powerful description, discovery, and correlation mechanism. These problems force the Grid users to perform an impractical manual selection of the resources. A remedy is proposed as a dynamically scalable and customizable resource management, with an ontology-based resource description and correlation mechanism. The classic syntax-based symmetric resource description model is replaced with an extensible semantics-based asymmetric model. Now the resources can be clearly described, unambiguously interpreted, and automatically delivered on-demand. A WSRF-based implementation and an OWL-based semantics enhancement is provided with the demonstrations to prove the effectiveness of the proposed approach.