Book Image

Mastering KVM Virtualization - Second Edition

By : Vedran Dakic, Humble Devassy Chirammal, Prasad Mukhedkar, Anil Vettathu
Book Image

Mastering KVM Virtualization - Second Edition

By: Vedran Dakic, Humble Devassy Chirammal, Prasad Mukhedkar, Anil Vettathu

Overview of this book

Kernel-based Virtual Machine (KVM) enables you to virtualize your data center by transforming your Linux operating system into a powerful hypervisor that allows you to manage multiple operating systems with minimal fuss. With this book, you'll gain insights into configuring, troubleshooting, and fixing bugs in KVM virtualization and related software. This second edition of Mastering KVM Virtualization is updated to cover the latest developments in the core KVM components - libvirt and QEMU. Starting with the basics of Linux virtualization, you'll explore VM lifecycle management and migration techniques. You’ll then learn how to use SPICE and VNC protocols while creating VMs and discover best practices for using snapshots. As you progress, you'll integrate third-party tools with Ansible for automation and orchestration. You’ll also learn to scale out and monitor your environments, and will cover oVirt, OpenStack, Eucalyptus, AWS, and ELK stack. Throughout the book, you’ll find out more about tools such as Cloud-Init and Cloudbase-Init. Finally, you'll be taken through the performance tuning and troubleshooting guidelines for KVM-based virtual machines and a hypervisor. By the end of this book, you'll be well-versed with KVM virtualization and the tools and technologies needed to build and manage diverse virtualization environments.
Table of Contents (22 chapters)
Section 1: KVM Virtualization Basics
Section 2: libvirt and ovirt for Virtual Machine Management
Section 3: Automation, Customization, and Orchestration for KVM VMs
Section 4: Scalability, Monitoring, Performance Tuning, and Troubleshooting

Tuning the CPU and memory with NUMA

Before we start tuning the CPU and memory for NUMA-capable systems, let's see what NUMA is and how it works.

Think of NUMA as a system where you have more than one system bus, each serving a small set of processors and associated memory. Each group of processors has its own memory and possibly its own I/O channels. It may not be possible to stop or prevent running VM access across these groups. Each of these groups is known as a NUMA node.

In this concept, if a process/thread is running on a NUMA node, the memory on the same node is called local memory and memory residing on a different node is known as foreign/remote memory. This implementation is different from the Symmetric Multiprocessor System (SMP), where the access time for all of the memory is the same for all the CPUs, as memory access happens through a centralized bus.

An important subject in discussing NUMA is the NUMA ratio. The NUMA ratio is a measure of how quickly a CPU...