Skip to main content

CometCloud Introducation

 The demands placed on cloud computing environments are often highly dynamic and heterogeneous, with varying workloads and quality of service (QoS) requirements. Applications may have different needs, such as high throughput or budget constraints, and the performance of cloud services can fluctuate due to changing loads, failures, and network conditions. Integrating public cloud platforms with existing grids and data centers can enable on-demand scaling, but this integration and interoperability can be challenging.

In this chapter, the authors present CometCloud, an autonomic cloud engine designed to create a virtual computational cloud with resizable computing capability. CometCloud aims to seamlessly integrate local computational environments (data centers, grids) with public cloud services (such as Amazon EC2 and Eucalyptus) on-demand. It provides abstractions and mechanisms to support various programming paradigms and application requirements. The key features of CometCloud are policy-based autonomic cloud bridging and cloudbursting.

Autonomic cloud bridging enables the on-the-fly integration of local computational environments and public cloud services. Users can leverage their private cloud or data center resources before scaling out to a public cloud. CometCloud supports the integration of heterogeneous and dynamic cloud/grid infrastructures, allowing for cloudbursting to address dynamic workloads and extreme requirements.

CometCloud is built on a decentralized coordination substrate, which facilitates the coordination of scheduling tasks across a dynamic set of users and dynamically provisioned workers on available private and/or public cloud resources. The coordination substrate considers QoS constraints, such as cost and performance, along with policies, performance history, and resource state to determine the appropriate allocation of public and private clouds for specific application requests.

The chapter also showcases two applications enabled by CometCloud: a computationally intensive value at risk (VaR) application and a high-throughput medical image registration application. The VaR application calculates risk measures for a firm's holdings within a limited time, while the computational requirements may change significantly. Image registration involves aligning images from different perspectives or timeframes, which is critical for subsequent image analysis.

The chapter proceeds to explain the CometCloud architecture in detail, followed by an exploration of policy-driven autonomic cloudbursts, including real-world application examples and cloud bridging over a virtual cloud. The runtime behavior of CometCloud is discussed, and the chapter provides an overview of the VaR and image registration applications. The authors evaluate the autonomic behavior of CometCloud, and the chapter concludes with a summary.

Overall, CometCloud aims to address the dynamic demands of cloud computing environments by providing seamless integration, autonomic scaling, and support for various applications and QoS requirements.

Labels:

Comments

Post a Comment

Popular posts from this blog

2.1 VIRTUAL MACHINES PROVISIONING AND MANAGEABILITY

In this section, we will have an overview on the typical life cycle of VM and its major possible states of operation, which make the management and automation of VMs in virtual and cloud environments easier than in traditional computing environments As shown in Figure above, the cycle starts by a request delivered to the IT department, stating the requirement for creating a new server for a particular service.  IT administration to start seeing the servers’ resource pool, matching these resources with the requirements, and starting the provision of the needed virtual machine.  Once provisioned machine started, it is ready to provide the required service according to an SLA, or a time period after which the virtual is being released.
Post a Comment
Read more

1.2 ROOTS OF CLOUD COMPUTING

We can track the roots of clouds computing by observing the advancement of several technologies, especially in hardware (virtualization, multi-core chips), Internet technologies (Web services, service-oriented architectures, Web 2.0), distributed computing (clusters, grids), and systems management (autonomic computing, data center automation).  Below Figure shows the convergence of technology fields that significantly advanced and contributed to the advent of cloud computing. . We present a closer look at the technologies that form the base of cloud computing, with the aim of providing a clearer picture of the cloud ecosystem as a whole. 1.2.1 From Mainframes to Clouds 1.2.2 SOA, Web Services, Web 2.0, and Mashups 1.2.3 Grid Computing 1.2.4 Utility Computing 1.2.5 Hardware Virtualization 1.2.6 Virtual Appliances and the Open Virtualization Format 1.2.7 Autonomic Computing ______ Cloud computing has its roots in several technologies and developments, including virtualization, gr...
Post a Comment
Read more

2.1.1 VM Provisioning Process

  Steps to Provision VM. Here, we describe the common and normal steps of provisioning a virtual server: Firstly, you need to select a server from a pool of available servers (physical servers with enough capacity) along with the appropriate OS template you need to provision the virtual machine. Secondly, you need to load the appropriate software (operating system you selected in the previous step, device drivers, middleware, and theneeded applications for the service required). Thirdly, you need to customize and configure the machine (e.g., IP address, Gateway) to configure an associated network and storage resources. Finally, the virtual server is ready to start with its newly loaded software. These are the tasks required or being performed by an IT or a data center’s specialist to provision a particular virtual machine.
Post a Comment
Read more