To provide greater resiliency and to protect against memory errors, vSphere ESXi Hypervisor can now take advantage of new hardware vendor–enabled Reliable Memory Technology, a CPU hardware feature through which a region of memoryis reported from the hardware to vSphere ESXi Hypervisor as being more “reliable.” This information is then used to optimize the placement of the VMkernel and other critical components such as the initial thread, hostd and the watchdog process and helps guard against memory errors.
Because vSphere ESXi Hypervisor runs directly in memory, an error in it can potentially crash it and the virtual machines running on the host. The most critical component to vSphere ESXi Hypervisor is the VMkernel, which is a purpose-built operating system (OS) to run virtual machines. Similarly as with SATA and SAS hard disks,users are now able to hot-add or hot-remove an SSD device while a vSphere host is running, and the underlying storage stack detects the operation. Solid-state disks (SSDs) are becoming more prevalent in the enterprise datacenter, and this same capability has been expanded to support SSD devices. The ability to hot-swap traditional storage devices such as SATA and SAS hard disks on a running vSphere host has been a huge benefit to systems administrators in reducing the amount of downtime for virtual machine workloads.