During the VMware Explore US, the vSphere 8 has been announced. Now let’s have a look at some new core storage enhanced features.
The new version of vSphere will bring NVMe over Fabrics (NVMeoF) support for vSphere Virtual Volumes (vVols). NVMe-oF provides better performance and lower latency over typical SCSI. NVMe is designed for flash and connecting to an all-flash NVMe array using SCSI is an inherent bottleneck. With NVMe-oF vVols, each vVol object becomes an NVMe Namespace. These Namespaces are then grouped into an ANA group (Asymmetrical Namespace Access). With NVMe, many of the commands are In-Band for more efficient communication between vSphere hosts and the array.
In the vSphere 8, the set up of NVMe in vVOLs is simplified. When deploying NVMe in vCenter, once VASA is registered, the underlying setup is completed in the background, and the discovery of the NVMe controller is automatic. Once the datastore is created, the vPE (virtual Protocol Endpoints) and connection are all handled by VASA.
New enhancements to NVMe-oF:
- Support 256 Namespaces and 2K paths
- Extend reservation support for NVMe devices
- Auto- Discovery of NVMe Discovery Services support for ESXi
New enhancements to vVOLs:
- VM swap improvement: Reduced time when powering on or off and during better vMotion performance
- Keep config-vVol bound: Avoid additional latency from VM home queries from the vSphere system.
Container Storage Enhancements – Cloud Native Storage
In vSphere 8, VMware introduced VMFS provisioning storage policy for cloud-native storage. Storage Policy Based Management (SPBM) allows for provisioning rules for volume creation and supports SPBM compliance checks.
NFS Resiliency Enhancements
vSphere 8 will bring NFS enhancement increasing resilience through services, checks, and permission validations such as retrying NFS mounts on failures and NFS mount validations.
Unmap Space Reclamation Enhancement
vSphere 8 will allow changing the unmap rate best suited for their array’s capability and vendor recommendation.
The higher unmap rate has benefited many array vendors quickly reclaim space. But we heard from some customers, even with the lowest unmap rate of 25 MB/sec, the rate can be disruptive when multiple hosts send unmap commands concurrently. The disruption can increase when scaling the number of hosts per datastore.
Example of potential overload: 25 MB/s * 100 datastores * 40 hosts ~ 104GB/s
To help customers in situations where the 25MB/s unmap rate can be disruptive, we have reduced the minimum rate to 10MB/s, configurable per datastore.
This allows customers to reduce the potential impact of numerous unmap commands being sent to a single datastore. If needed, you can also disable space reclamation completely for a given datastore.
If you want to chat with me please use Twitter: @AngrySysOps
Join my VMware Knowledge Base Group: https://bit.ly/3w54tbc
Visit my FB page: https://www.facebook.com/AngrySysOps
Subscribe to my channel : https://bit.ly/3vY16CT