vSphere High Performance Cookbook电子书

vSphere High Performance Cookbook

Table of Contents

vSphere High Performance Cookbook

Credits

About the Author

About the Reviewers

www.PacktPub.com

Support files, eBooks, discount offers and more

Why Subscribe?

Free Access for Packt account holders

Instant Updates on New Packt Books

Preface

What this book covers

What you need for this book

Who this book is for

Conventions

Reader feedback

Customer support

Errata

Piracy

Questions

1. CPU Performance Design

Introduction

Critical performance consideration – VMM scheduler

Getting ready

How to do it...

How it works...

There's more...

CPU scheduler – processor topology/cache aware

Getting ready

How to do it...

How it works...

Ready time – warning sign

Getting ready

How to do it...

How it works...

Hyperthreaded core sharing

Getting ready

How to do it...

How it works...

There's more...

Spotting CPU overcommitment

Getting ready

How to do it...

How it works...

Fighting guest CPU saturation in SMP VMs

Getting ready

How to do it...

How it works...

Controlling CPU resources using resource settings

Getting ready

How to do it...

What is most important to monitor in CPU performance

Getting ready

How to do it...

CPU performance best practices

Getting ready

How to do it…

2. Memory Performance Design

Introduction

Virtual memory reclamation techniques

Getting ready

How to do it...

How it works...

Transparent page sharing

Memory ballooning

Monitoring host-swapping activity

Getting ready

How to do it...

How it works...

There's more...

Monitoring host-ballooning activity

Getting ready

How to do it...

How it works...

There's more...

Keeping memory free for VMkernel

Getting ready

How to do it...

How it works...

Key memory performance metrics to monitor

Getting ready

How to do it...

How it works...

What metrics not to use

Getting ready

How to do it...

Identifying when memory is the problem

Getting ready

How to do it...

Analyzing host and VM memory

Getting ready

How to do it...

How it works...

Memory performance best practices

How to do it…

3. Networking Performance Design

Introduction

Designing a network for load balancing and failover for vSphere Standard Switch

Getting ready

How to do it...

How it works...

Route based on the originating virtual switch port ID (default)

Route based on source MAC hash

Route based on IP hash

Link status only

Beacon probing

Designing a network for load balancing and failover for vSphere Distributed Switch

Getting ready

How to do it...

How it works...

What to know when offloading checksum

Getting ready

How to do it...

How it works...

Selecting the correct virtual network adapter

Getting ready

How to do it...

How it works...

Improving performance through VMDirectPath I/O

Getting ready

How to do it...

Improving performance through NetQueue

Getting ready

How to do it...

How it works...

Improving network performance using the SplitRx mode for multicast traffic

Getting ready

How to do it...

How it works...

Designing a multi-NIC vMotion

Getting ready

How to do it…

Improving network performance using network I/O control

Getting ready

How to do it...

Monitoring network capacity and performance matrix

Getting ready

How to do it...

4. DRS, SDRS, and Resource Control Design

Introduction

Using DRS algorithm guidelines

Getting ready

How to do it...

How it works...

Using resource pool guidelines

Getting ready

How to do it…

How it works...

Avoiding using resource pool as folder structure

How to do it...

How it works...

Choosing the best SIOC latency threshold

Getting ready

How to do it...

How it works...

Using storage capability and profile driven storage

Getting ready

How to do it...

How it works...

Anti-affinity rules in the SDRS cluster

Getting ready

How to do it...

Avoiding the use of SDRS I/O Metric and array-based automatic tiering together

Getting ready

How to do it...

Using VMware SIOC and array-based automatic tiering together

Getting ready

How to do it...

How it works...

5. vSphere Cluster Design

Introduction

Trade-off factors while designing scale up and scale out clusters

Getting ready

How to do it...

How it works...

Using VM Monitoring

Getting ready

How to do it…

vSphere Fault Tolerance design and its impact

Getting ready

How to do it...

How it works...

DPM and its impact

Getting ready

How to do it...

How it works...

Choosing the reserved cluster failover capacity

Getting ready

How to do it...

How it works...

See also

Rightly choosing the vSphere HA cluster size

Getting ready

How to do it...

6. Storage Performance Design

Introduction

Designing the host for a highly available and high-performing storage

Getting ready

How to do it...

Designing a highly available and high-performance iSCSI SAN

Getting ready

How to do it...

How it works...

Jumbo frames

Pause frames

TCP delayed Ack

Designing a highly available and high-performing FC storage

Getting ready

How to do it...

How it works...

RAIDlevel data protection

Performance impact of queuing on the storage array and host

Getting ready

How to do it...

How it works...

Factors that affect storage performance

Getting ready

How to do it...

Using VAAI to boost storage performance

Atomic test & set (ATS)

Clone blocks/full copy/XCOPY

Zero blocks/write same

Getting ready

How to do it...

How it works...

Selecting the right VM disk type

Getting ready

How to do it...

How it works...

Monitoring command queuing

Getting ready

How to do it...

How it works...

Identifying a severely overloaded storage

Getting ready

How to do it…

7. Designing vCenter and vCenter Database for Best Performance

Introduction

vCenter Single Sign-On and its database preparation

Getting ready

How to do it...

vCenter Single Sign-On and its deployment

Getting ready

How to do it...

Things to bear in mind while designing the vCenter platform

How to do it...

Designing vCenter Server for redundancy

How to do it…

Designing a highly available vCenter database

How to do it...

vCenter database size and location affects performance

How to do it...

Considering vCenter Server Certificates to minimize security threats

Getting ready

How to do it...

See also

Designing vCenter Server for Auto Deploy

Getting ready

How to do it...

8. Virtual Machine and Application Performance Design

Introduction

Setting the right time in Guest OS

Getting ready

How to do it...

See Also

vNUMA (Virtual NUMA) considerations

Getting ready

How to do it…

Choosing the SCSI controller for storage

Getting ready

How to do it...

Impact of VM swap file placement

Getting ready

How to do it...

Using large pages in virtual machines

Getting ready

How to do it...

Guest OS networking considerations

Getting ready

How to do it...

See Also

When you should or should not virtualize an application

Getting ready

How to do it...

Measuring the application's performance

Getting ready

How to do it...

Index