Performance Best Practices for VMware vSphere 9.1

We are pleased to announce the availability of Performance Best Practices for VMware vSphere 9.1. This is a comprehensive book designed to help system administrators obtain the best performance from their vSphere 9.1 deployments.

The book covers new features as well as updating and expanding on topics covered in previous versions of Performance Best Practices for VMware vSphere.

Topics include:

• Expanded guidance on power management, including C-states and Intel Hardware P-States (HWP)
• Expanded guidance for specific processor families, including Intel Granite Rapids and AMD EPYC
• New coverage on using Intel QAT to reduce the CPU cost of encrypted vMotion
• New discussion of hardware locality in NUMA systems
• Expanded coverage of memory tiering
• Expanded guidance on NVMe performance
• Additional detail about Receive Side Scaling (RSS)
• Expanded guidance on vSAN Express Storage Architecture (ESA)
• Broadened coverage of VCF Single Sign-On
• Storage hardware considerations
• Network hardware considerations
• Hyper-threading
• NUMA and vNUMA
• Memory sizing, overcommit, page sharing, and swapping optimizations
• Performance of VMware vSAN, SAN, iSCSI, NFS, NVMe, and NVMe over Fabrics storage
• Virtual machine encryption recommendations
• Network performance
• Running storage latency-sensitive workloads
• Running network latency-sensitive workloads
• Network I/O Control (NetIOC)
• DirectPath I/O
• Microsoft Virtualization-Based Security (VBS)
• Selecting virtual network adapters
• vCenter database performance
• vSphere Client performance
• vMotion, Storage vMotion, and Cross-Host Storage vMotion
• Distributed Resource Scheduler (DRS) and Distributed Power Management (DPM)
• vSphere High Availability and Fault Tolerance
• VMware vSphere Lifecycle Manager
• VMware VCF Single Sign-On
• vSphere Content Library
• vSphere Kubernetes Service (VKS)

The full book can be found here.