Layers of cloud infrastructure: Resource Virtualization

As developers, we are more concerned with what is the cloud computing infrastructure? What about resource virtualization? And what specific characteristics it has. And so on, a series of problems have collapsed. In fact, the nature of cloud computing infrastructure and resource virtualization is not open to analysis can be said that they are parallel computing.

The field of computing is in the middle of a bitter struggle, and the dilemma is the contradiction between the explosive growth of data to be processed and the lack of capacity and computational power of the current machine. Due to the increasing number of data to be processed, it is difficult to store in one or a limited number of storage servers, and more than one or a limited number of compute servers can handle such large amounts of data. So how to store and compute these massive amounts of data has become one of the hottest topics in the IT industry.

Cloud computing is a computing model that represents a way to share resources for design, development, deployment, operational applications, scalable shrinkage of resources, and support for application continuity. Most of the current cloud computing infrastructure is made up of user terminals delivering service-enabled networks to data centers, as well as different levels of virtualization technology built on servers that allow people to use these services in any place where there is a network infrastructure available. Therefore, the basic concept of the cloud is to automatically split the huge computing process into countless smaller subroutines through the network, and then the processing results are passed back to the user terminal by a large system of multiple servers. With this technology, remote service providers can reach tens of billions of millions of messages in a matter of seconds to achieve the same powerful network services as supercomputers.

You might say, isn't that the concept of distributed computing? Yes, cloud computing can be said to be distributed computing, parallel computing, grid computing, such as the same line of technology, can even say that their genes are the same. But they are different in their appearance, and they differ in their technical architecture. Simply put, cloud computing is a commercially packaged noun that finds a profit model for distributed storage and distribution computing. Conceptually, cloud computing can be seen as the "storage Cloud + computing Cloud" organic combination, that is, "cloud computing = Storage Cloud + computing cloud." The basic technology of storage cloud is distributed storage, while the base technology of computing cloud is distributed computing, more precisely in parallel computing.

Therefore, the infrastructure of cloud computing first is to ensure that parallel computing can be implemented. The function of parallel computation is to split the large computing task, then distribute it to each node in the cloud for distributed parallel computation, and finally collect the result and deal with it uniformly. If cloud computing is a distillation of parallel computing, the cloud computing infrastructure is more advanced on another level: computing resource virtualization. Simply put, all computing resources in the computing cloud are considered to be a pool of compute resources that can be allocated and recycled, and users can request corresponding computing resources based on their actual needs.

This resource virtualization benefits from the recent emergence of virtual machine technology, the use of virtual machines to achieve the virtualization of resources, to avoid the characteristics of hardware heterogeneity. No matter what kind of hardware machine is saved together, its computational resources can be quantified to compute resource pool, and be dynamically allocated and dynamically adjusted. Dynamic adjustment refers to the adjustment of resource size without restarting the system, which is one of the greatest uses of virtualization technology.

This virtualization is similar to the virtualization technology we use to install virtual machines on our own machines, and the difference is that the mode of use of individual users is to virtualize the resources of a physical machine into multiple copies so that they can start multiple operating systems at the same time; The virtualization technology in the cloud is to virtualize the resources of multiple physical machines into a large resource pool, making the user feel like a machine using a huge resource.

In this perspective, cloud computing is not a new technology, but rather a model of resource utilization. We can think of cloud computing as a phase upgrade of the previous generation computing pattern (such as grid computing, transparent computing, utility computing). The essence of cloud computing is a methodology for infrastructure management, which consists of a large number of computing resources that make up the IT resource pool for dynamically creating highly virtualized resources for users. In a cloud computing environment, all computing resources, such as servers, can dynamically add and subtract from the hardware infrastructure to meet the needs of the task. So the most real and complete infrastructure of cloud computing is an end-to-end solution that integrates multiple products and services. The essence of cloud computing infrastructure is to maximize the utilization of IT investments through the consolidation, sharing, and dynamic availability of hardware devices. Therefore, the nature of the computing cloud's infrastructure can be seen as: Parallel computing + resource virtualization.

Cloud computing is a hot technical term in recent years, many experts believe that cloud computing will change the technology base of the Internet, and even affect the entire industry pattern. Because of this, many companies are studying cloud computing technology and cloud-based services. Intel, as a powerful chip maker, occupies an important position in the industry. But there have always been voices questioning what Intel has done in the field of cloud computing, or that Intel will only take the opportunity to hype it up. So what does Intel do about cloud computing?

Intel divides the cloud computing infrastructure into a cloud data center (the local side) and an application (the access side). For the Bureau, Intel's strategy is to optimize and improve the parallel computing capabilities of the data center, as simple scaling is inefficient.

Currently, Intel's strategy for upgrading cloud computing infrastructure is based on the Intel 5600 platform, which enables a new generation of servers to be more scalable and can support more processor cores in the same cabinet space, dramatically increasing memory capacity and built-in storage capacity, The computing density and storage density of the product unit space are greatly improved, which is more beneficial to the application of parallel computing, virtualization, server consolidation, database and enterprise on-demand expansion, which will undoubtedly become the ideal choice for enterprise deployment virtualization and cloud environment.