Trace-driven Analysis of an Internet-scale Cloud Computing Platform
 
    在本文中,我们研究的一个重要云计算使用:即在执行互联网计算密集型任务的大型企业网络。我们的主要驱动的应用程序是一个互联网规模的云计算平台(ICCP),由世界五百强企业在公司内部大规模并行模拟发展。
 
In recent years, cloud computing have become a popular computing paradigm, where computation is moved away from personal computers or an individual application server to a “cloud” of computers in the network. Users of the cloud only need to be concerned with the computing service being asked for, as the underlying details of how it is achieved are hidden. This method of distributed computing is done through pooling all computer resources together and being managed by software rather than a human. The popular application of cloud computing have primarily been for the deployment of web applcations by end users, e.g., Amazon’s elastic compute cloud ,and the Google/IBM’s academic cluster computing initiative .
In this paper, we study an important use of cloud computing: that of performing compute-intensive tasks within an Internet-scale enterprise network. Our main driving application is an Internet-scale Cloud Computing Platform (ICCP) developed by a Fortune-500 company for massively parallel simulations within the company. ICCP has been operational for many years, and currently is deployed “live” on tens of thousands of machines that are globally distributed at various data centers. With ICCP, engineers no longer have to manually setup simulation machines, or determine where and when to schedule their simulation jobs. By pooling together machines all over the enterprise network, resources are used more efficiently as computers can be consolidated to be used for more tasks.
 
 
请点击下载:temp_10022815418016.pdf