Supporting resource reservation and allocation for unaware applications in Grid systems

Abstract

SUMMARYThe dynamics of resource request rates in a Grid system can be wide ranging, to the point that request peaks for a single resource can be difficult to handle and end up greatly increasing the response time. Once a request has been submitted by a client, this has to cope with the potential overload arising. However, it is impractical to cure overload once it takes place by negotiating a different service or finding an equivalent resource, since the client would then bear the delay due to negotiation and re-submission. Instead, in order to effectively exploit Grid resources, it is crucial that applications perform reservation of resources before using them. Reservation allows a management system to consider application needs in advance and take suitable action to improve resource availability. In particular, this enables additional resources to be secured beforehand in the background when appropriate to avoid a potential overload, rather than paying the involved costs when overload arises. This paper proposes a software architecture that integrates applications with Globus services to conveniently handle resource reservation and allocation. Within the architecture, the computational reflection technology transparently connects applications with components that take care of advance reservation, as they dynamically sense the applications' resource needs. This dynamic information augments static knowledge gathered offline from static program code analysis.

The Agreement Utopia

“…On the other hand, Q ic (quality deterioration due to client information) represents the difficulty of the client to specify parameters for the required QoS. In fact, he/she does not really know exactly if the used parameters are correct for the QoS, even though an automatic tool can help the user to analyse the application needs [3] and this situation is difficult to identify for the user. For example, if the user wants to run a complex algorithm on a set of data, he/she will require a resource with a lot of computational power (memory, CPU speed, I/O speed, etc.)…”

Design Pattern Usage in Grid Computing

“…Behavioral Provides an operation signature as an interface and defines corresponding implementations [32] Facade Structural Presents a uniform outlook to the user in a portable manner [34]; Shields clients from directly accessing and knowing about many small classes [11] Factory Creational Uses the factory design pattern to instantiate ports [19]; Implementation of job managers [23] Model-View-Controller Structural Consequent usage of the Model-View-Controller pattern in a control system architecture [14]; Provides a higher abstraction layer for managing a large number of concurrent requests [1]; Communicating the results between different layers [31]; Implementation of a registration service [27]; Separation of control and presentation from the application logic required for invoking Grid services [28]; Table II summarizes the design patterns found in our literature review.…”

Providing QoS strategies and cloud‐integration to web servers by means of aspects

“…Further issues relating to communication and resource provisioning in cloud‐like environments have been previously analysed by the authors of this paper, and the proposed solutions could be integrated here to solve some practicalities .…”