At VMware Explore 2022 US event, vSphere on DPUs was announced as part of vSphere 8, and today vSphere 8 is available to the public. This version of vSphere has a substantial number of new features on many areas from multi-cloud, containers, core vSphere, AI/ML, and of course Data Processing Units (DPUs). More information about vSphere 8 can be found here.
This new DPU feature in vSphere 8 is called vSphere Distributed Services Engine, and there is no need to install any additional appliances; in fact, it is super easy to get started. Enabling the offload capability is done within Distributed Switches, allowing to bring the intelligence from ESXi, vCenter and NSX into the DPUs for enhanced performance, better workload consolidation, simplified management, and stronger security.
vSphere on DPUs not only brings the capability of utilizing new hardware technology and offloading services to such devices, but more importantly, the introduction of a new data path only available with this feature. While utilizing vSphere Distributed Services Engine, customers can leverage UPTv2 and/or MUX mode to achieve better performance, and reduce network hops as well as CPU resources on X86 servers. UPTv2 delivers passthrough to the VMs by leveraging VMXNET3 drivers rather than relying on vendor specific drivers, and most importantly it still makes those awesome vSphere features available such as HA, and DRS compared to SR-IOV where those features are not available.
As explained in a previous post, ESXi is installed on the DPU so that services such as NSX run on the same hypervisor. However, the installation is the same as you would install ESXi on a X86 server. During installation, the system will detect the DPU, and you will have the option to install/update ESXi on BOTH the x86 server and the DPU. So simple. Wait, what about NSX? Well, to install NSX is also the same procedure as configuring your X86 servers. We will leverage vLCM to install NSX to both the 86 server and the DPU. And yes, I said vLCM, meaning that for updates/patches you can use vLCM on the host and the DPU will be detected and updated to the same version as the “parent” host. Even though we have another instance of ESXi the management has been simplified so that you are still only managing your existing X86 servers, as the DPUs are part of those servers, not separate instances. So, we are leveraging DPUs to offload services to it in order to obtain performance, management, and security enhancements; not to run VMs on DPUs.
There is a lot more to talk about in this area, so keep an eye out for more information. It is very exciting what the future holds for DPUs. The number and types of workloads that can take advantage of these devices is unknown, but I’m sure it will be many.
We are experiencing the beginning of the Modern Heterogeneous Compute Infrastructure with DPUs and vSphere 8.