To improve the latency sensitive workloads, you can configure the latency sensitivity of a virtual machine.

With vSphere 8.0, you can use the Virtual Hyperthreading (vHT) feature to configure low latency VMs and expose vHT to the guest operating systems. When you enable vHT, each guest vCPU is treated as a single hyperthread of a virtual core.

For more information about the vHT feature, see the vSphere Resource Management documentation.

Prerequisites

Verify that the virtual machine is of hardware version 20 or later.

Procedure

  1. Navigate to a virtual machine in the inventory and click Actions.
  2. Click Edit Settings.
  3. On the VM Options tab, click Advanced.
  4. From the Latency Sensitivity drop-down menu, select a setting.
    Option Description
    Normal The default setting.

    The CPU scheduler for a VM with normal latency sensitivity can move the virtual CPUs of the VM across any physical CPU of the host, depending on the system load.

    High High Latency Sensitivity requires you to set CPU and 100% memory reservation for the VM. Scheduling of the VM is adjusted for low-latency workload requirements. Each virtual CPU is granted exclusive access to a physical core.
    High with Hyperthreading High Latency Sensitivity requires you to set CPU and 100% memory reservation for the VM. Each virtual CPU is granted exclusive access to a hyperthread of a physical core. Each consecutive pair of virtual machines vCPUs is assigned to the pair of hyperthreads on a physical core.
    For more information on how to calculate the full CPU reservation for vHT, see vHT Full CPU Reservation section in the vSphere Resource Management documentation.
  5. Click OK.