Elastic component‐based applications in PaaS clouds

Abstract

Elasticity is the capability of an application to adapt its resource usage to the current workload of the system. Existing platform-as-a-service (PaaS) solutions concentrate on web applications and do not support elasticity for other kinds of applications. To change this, in this paper, the vision and partial implementation for a component-based PaaS cloud is proposed consisting of a programming model and an autonomic manager for safeguarding non-functional application requirements. To illustrate this vision, the paper focuses on two key features of a PaaS infrastructure, the scale-out of services and the on-demand deployment of application resources. The former allows for increasing the performance by distributing service calls among several service providers working in parallel, and the latter refers to the automatic packaging and transfer of needed deployment units. It will be shown how these aspects have been solved within the Jadex PaaS cloud infrastructure. Both concepts have been validated using an application scenario, which highlights the advantages of automatic service scaling and deployment for developers and users.An example is a complex calculation algorithm. If it is deployed as is in the cloud, there is no elasticity regarding the size of the calculation problem, as according to Amdahl's law [5], the computation speed cannot be increased by scaling out. The developer would have to split the computation manually into parallelizable chunks, for example, by applying suitable algorithmic skeletons [6] such as map-reduce.The work presented in this paper aims at supporting the development of cloud-aware componentbased applications. Programming and adaptation management concepts and a PaaS infrastructure are introduced, which empower developers to achieve application elasticity. This paper expands on a vision of elastic component-based applications presented earlier [7]. The vision focuses on programming and adaptation management concepts that allow considering explicit non-functional requirements (NFRs) and non-functional properties (NFPs) seamlessly during design, implementation, and operation of applications. In addition, this paper especially presents required features for a PaaS infrastructure suitable to realize this vision. An initial prototype of such a PaaS infrastructure is presented with a focus on service scale-out and on-demand deployment, as well as an application scenario running on the prototype infrastructure.This paper is structured as follows. In Section 2, the vision of elastic component-based applications and the chosen approach are presented. As two fundamental building blocks of the approach, Section 3 introduces a generic component model for elastic application programming, and Section 4 presents adaptation management for elastic applications. In Section 5, details of the elastic PaaS infrastructure are presented by discussing how service scale-out and on-demand deployment can be realized. Afterwards, Section 6 discusses related work, and Section 7 finally concludes the paper. VISI...

Collaborative Business Process Management Through a Platform Based on Cloud Computing

“…In [29] it is highlighted the fact that SMEs are falling behind in cloud usage due to missing IT-competence and hence losing the ability to efficiently adapt their IT to their business needs, and the authors propose a PaaS architecture to cope with this issue. Authors of [30] propose a PaaS model for cloud applications implemented in terms of active components to accomplish non-functional requisites. This implies the development of a platform that manages elasticity in terms of these components and the non-functional requisites.…”

Intelligent Distributed Computing

“…Pokahr [8] focuses on the effective utilization of theoretically unlimited distributed and virtual resources, which are provided by the Cloud computing paradigm. In this context, intelligence is necessary to allow for exploiting the elastic computing infrastructure by a distributed application.…”

Performance testing as a service using cloud computing environment: A survey

“…Additionally, the two layers of the cloud architecture are associated with networking and security components 16 . The major three cloud service models are SaaS, platform as a service (PaaS), and infrastructure as a service (IaaS) 17 . SaaS provides applications and allows users to access them via the internet.…”

“…16 The major three cloud service models are SaaS, platform as a service (PaaS), and infrastructure as a service (IaaS). 17 SaaS provides applications and allows users to access them via the internet. Gmail 18 is an example of SaaS.…”