vSphere continues to deliver the ability to scale your infrastructure to meet the demands of modern application workloads such as Kubernetes clusters/pods, or high-performance application workloads.
Let’s glance at the increased scalability numbers and see how it can benefit you in your journey towards application modernisation.
Increased Cluster Scale
In vSphere 7 update 1, the total number of ESXi hosts in a vSphere Cluster is now increased to 96 hosts compared to 64 hosts in a previous release. Starting from vSphere 7 Update 1, you can run up to 10000 VMs in a vSphere cluster compared to 6400 VMs in vSphere 7.
This scale will prove to be one of the differentiating factors in your application modernisation journey with vSphere, considering containers/pods and VMs can now share the same space in your datacenter. We will briefly discuss this aspect in a later section, “The Cloud-Native Perspective,” of this blog.
Note: vSAN cluster continues to support 64 hosts.
Monster VMs
Starting from vSphere 7 Update 1, we now support a maximum of 768 vCPU and 24 TB vRAM per VM, leaving competitors far behind in this category.These scales are well suited to support memory-intensive database workloads such as SAP HANA and EPIC Cache Operational Database, to name a few.
The “Cloud–Native” perspective
Let’s take these numbers and look at the cloud-native world. Cloud-native applications are lightweight and scalable. With the current scale increase in vSphere 7 Update 1, we get a maximum of 393216 vCPUs (96 hosts x 4.096 vCPUs), and 2.3 PB of RAM (96 hosts x 24 TB) is available to run the containers in a single vSphere cluster.
According to the container-report, most container-based applications are lightweight, with each container consuming less than 1 vCPU and 400 MB of RAM. Let’s take an example of node.js, which most customers are running in a container-based environment and, on average, consumes 1/3 CPU and 384 MB RAM per container.
Suppose we keep the above numbers as a baseline. In that case, with 1 vCPU, we can run 393216 containers. If we go by the node.js example, we can potentially run a million containers in a single vSphere cluster.
With this, we have a range of 0.4M-1.0M containers running in a single vSphere cluster. Conservatively, it is fair to say we can run half a million (0.5M) containers/pods in a single vSphere cluster.
Conclusion
Over the years, we have proven how great the vSphere platform is for VM centric workloads. Now, the time has come for us to deliver on our promise to make vSphere/VCF the preferred choice to run cloud-native applications. Scalability will be one of the differentiating factors in getting it realised.
The Increased scale numbers in vSphere 7 update 1 are unprecedentedand leave our competitors far behind in this category. Customers can take the benefits of increased scale in running resource-intensive workloadsor in running lightweight, highly Scalable Tanzu Kubernetes Grid(TKG) workloads. We can now run half a million containers/pods in a single vSphere cluster potentially, all thanks to increased scale.
We are excited about these new releases and how vSphere is always improving to serve our customers and workloads better in the hybrid cloud. We will continue posting new technical and product information about vSphere with Tanzu & vSphere 7 Update 1 on Tuesdays, Wednesdays, and Thursdays through the end of October 2020! Join us by following the blog directly using the RSS feed, on Facebook, and on Twitter, and by visiting our YouTube channel which has new videos about vSphere 7 Update 1, too. As always, thank you, and please stay safe.
