Cloud Data Center Network Architectures and Technologies

Lei Zhang, Le Chen

• Publisher: CRC Press
• Year: 2021
• Print ISBN: 9780367695705
• eBook ISBN: 9781000375619
• Topic: Computer Science
• Subtopic: Cloud Computing
• Index: Computer Science

Cloud Data Center Network Architectures and Technologies has been written with the support of Huawei's vast technical knowledge and experience in the data center network (DCN) field, as well as its understanding of customer service requirements. This book describes in detail the architecture design, technical implementation, planning and design, and deployment suggestions for cloud DCNs based on the service challenges DCNs encounter. It starts by describing the overall architecture and technical evolution of DCNs, with the aim of helping readers understand the development of DCNs. It then proceeds to explain the design and implementation of cloud DCNs, including the service model of a single data center (DC), construction of physical and logical networks of DCs, construction of multiple DCNs, and security solutions of DCs. Next, this book dives deep into practices of cloud DCN deployment based on real-world cases to help readers better understand how to build cloud DCNs. Finally, this book introduces DCN openness and some of the hottest forward-looking technologies.

In summary, you can use this book as a reference to help you to build secure, reliable, efficient, and open cloud DCNs. It is intended for technical professionals of enterprises, research institutes, information departments, and DCs, as well as teachers and students of computer network-related majors in colleges and universities.

Authors

Lei Zhang

Mr. Zhang is the Chief Architect of Huawei's DCN solution. He has more than 20 years' experience in network product and solution design, as well as a wealth of expertise in product design and development, network planning and design, and network engineering project implementation. He has led the design and deployment of more than 10 large-scale DCNs for Fortune Global 500 companies worldwide.

Le Chen

Mr. Chen is a Huawei DCN Solution Documentation Engineer with eight years' experience in developing documents related to DCN products and solutions. He has participated in the design and delivery of multiple large-scale enterprise DCNs. Mr. Chen has written many popular technical document series, such as DCN Handbook and BGP Topic.

CHAPTER 1

Introduction to Cloud DCNs

A CLOUD DATA CENTER (DC) is a new type of DC based on cloud computing architecture, where the computing, storage, and network resources are loosely coupled. Within a cloud DC, various IT devices are fully virtualized, while also being highly modularized, automated, and energy efficient. In addition, a cloud DC features virtualized servers, storage devices, and applications, enabling users to leverage various resources on demand. Automatic management of physical and virtual servers, service processes, and customer service charging is also provided. Starting with cloud computing and virtualization, this chapter describes the software-defined networking (SDN) technology used by cloud data center networks (DCNs) to tackle the challenges introduced by this new architecture.

1.1 Cloud Computing

Before examining cloud DCNs in more detail, we should first take a closer look at cloud computing. The pursuit of advanced productivity is never ending. Each industrial revolution has represented a leap in human productivity, as our society evolved from the mechanical and electric eras through to the current automatic and intelligent era.

Since the 1980s, and owing to the advances of global science and technology, culture, and the economy, we have gradually transitioned from an industrial society to an information society. By the mid-1990s, economic globalization had driven the rapid development of information technologies, with the Internet becoming widely applied by all kinds of businesses. As the global economy continues to grow, cracks have begun to appear in the current processes of enterprise informatization. Constrained by complex management modes, spiraling operational expenses, and weak scale-out support, enterprises require effective new information technology solutions. Such requirements have driven the emergence of cloud computing.

The US-based National Institute of Standards and Technology (NIST) defines the following five characteristics of cloud computing:

• On-demand self-service: Users can leverage self-services without any intervention from service providers.
• Broad network access: Users can access a network through various terminals.
• Resource pooling: Physical resources are shared by users, and resources in a pool are region-independent.
• Rapid elasticity: Resources can be quickly claimed or released.
• Measured service: Resource measurement, monitoring, and optimization are automatic.

“On-demand self-service” and “broad network access” express enterprises’ desire for higher productivity and particularly the need for service automation. “Resource pooling” and “rapid elasticity” can be summarized as flexible resource pools, while “measured services” emphasize that operational support tools are required to tackle the considerable challenges of automation and virtualization. More intelligent and refined tools are also required to reduce the operating expense (OPEX) of enterprises.

Cloud computing is no longer just a term specific to the IT field. Instead, it now represents an entirely new form of productivity, as it creates a business model for various industries, drives industry transformation, and reshapes the industry chain. Cloud computing introduces revolutionary changes to traditional operations and customer experience, and seizing the opportunities of cloud computing will boost growth throughout the industry.

1.2 Virtualization Technologies Introduced by Cloud Computing

Virtualization is a broad term. According to the Oxford Dictionary, “virtual” refers to something that is “physically non-existent, but implemented and presented through software.” Put another way, a virtual element is a specific abstraction of an element. Virtualization simplifies the expression, access, and management of computer resources, including infrastructures, systems, and software, and provides standard interfaces for these resources. Virtualization also reduces the dependency of service software on the physical environment, enabling enterprises to achieve higher stability and availability based on simplified operation processes, improve resource utilization, and reduce costs.

Throughout the years, virtualization technologies have flourished in the computing, network, and storage domains, and have become interdependent on one another. The development of computing virtualization technologies is undoubtedly critical, while the development of network and storage virtualization technologies is intended to adapt to the changes and challenges introduced by the former. In computing virtualization, one physical machine (PM) is virtualized into one or more virtual machines (VMs) using a Virtual Machine Manager (VMM), which increases utilization of computer hardware resources and improves IT support efficiency.

A VMM is a software layer between physical servers and user operating systems (OSs). By means of abstraction and conversion, the VMM enables multiple user OSs and applications to share a set of basic physical hardware. Consequently, the VMM can be regarded as a meta OS in a virtual environment. It can allocate the correct amount of logical resources (such as memory, CPU, network, and disk) based on VM configurations, load the VM’s guest OS, and coordinate access to all physical devices on the VM and server, as shown in Figure 1.1.

FIGURE 1.1 Virtualization.

The following types of VMMs are available:

• Hypervisor VM: runs on physical hardware and focuses on virtual I/O performance optimization. It is typically used for server applications.
• Hosted VM: runs on the OS of a PM and provides more upper-layer functions such as 3D acceleration. It is easy to both install and use, and is typically utilized for desktop applications.

While multiple computing virtualization technologies exist, they often use different methods and levels of abstraction to achieve the same effect. Common virtualization technologies include the following:

1. Full virtualization
   Also known as original virtualization. As shown in Figure 1.2, this model uses a VM as the hypervisor to coordinate the guest OS and original hardware. The hypervisor obtains and processes virtualization-sensitive privileged instructions so that the guest OS can run without modification. As all privileged instructions are processed by the hypervisor, VMs offer lower performance than PMs. While such performance varies depending on implementation, it is usually sufficient to meet user requirements. With the help of hardware-assisted virtualization, full virtualization gradually overcomes its bottleneck. Typical hardware products include IBM CP/C MS, Oracle VirtualBox, KVM, VMware Workstation, and ESX.

   

   FIGURE 1.2 Full virtualization.

2. Paravirtualization
   Also known as hyper-virtualization. As shown in Figure 1.3, paravirtualization, similar to full virtualization, uses a hypervisor to implement shared access to underlying hardware. Unlike full virtualization, however, paravirtualization integrates virtualization-related code into the guest OS so that it can work with the hypervisor to implement virtualization. In this way, the hypervisor does not need to recompile or obtain privileged instructions, and can achieve performance close to that of a PM. The most well-known product of this type is Xen. As Microsoft Hyper-V uses technologies similar to Xen, it can also be classified as paravirtualization. A weakness of paravirtualization is its requirement that a guest OS be modified, and only a limited number of guest OSs are supported, resulting in a poor user experience.

   

   FIGURE 1.3 Paravirtualization.

3. Hardware emulation
   The most complex virtualization techno...

Table of contents

• Cover
• Half Title
• Series Page
• Title Page
• Copyright Page
• Table of Contents
• Summary
• Acknowledgments
• Authors
• Chapter 1 ▪ Introduction to Cloud DCNs
• Chapter 2 ▪ DCN Challenges
• Chapter 3 ▪ Architecture and Technology Evolution of DCNs
• Chapter 4 ▪ Functional Components and Service Models of Cloud DCNs
• Chapter 5 ▪ Constructing a Physical Network (Underlay Network) on a DCN
• Chapter 6 ▪ Constructing a Logical Network (Overlay Network) in a DC
• Chapter 7 ▪ Constructing a Multi-DC Network
• Chapter 8 ▪ Building E2E Security for Cloud DCNs
• Chapter 9 ▪ Best Practices of Cloud DCN Deployment
• Chapter 10 ▪ Openness of DCN
• Chapter 11 ▪ Cutting-Edge Technologies
• Chapter 12 ▪ Components of the Cloud DCN Solution
• Acronyms and Abbreviations