VMware Cloud Community
bigdazza75
Enthusiast
Enthusiast

Large "R Server for Windows" vCPU Allocation / Scalability

We have a generic 4 node VMware production cluster running all the traditional production Wintel infrastructure services. A small team here has "R Server for Windows" running on VMs running 4x vCPU and 64GB RAM, and they run their R machine learning code on these VMs. When this happens it takes around 10 minutes to do the analytics. They are in a Resource Pool limiting their VMs to an overall maximum CPU allocation. Now they want to reduce improve scalability of the R Server to get their processing time down to (say) 5 minutes, and are asking for these machines to have 16 or even 32 vCPU. They're advisory is that the application can only scale horizontally. I'm not too keen to be allocating any VMs this level of resource, but wondered if you guys had thoughts on the wisdom of such a configuration?

Reply
0 Kudos
1 Reply
mhampto
VMware Employee
VMware Employee

Do the VM's in the resource pool reach the limit set? If not, are the virtual machines utilizing 100% CPU when running the analytics in their current configuration?

If the VM's are capping out the resource pool, more vCPU's will not change this constraint. Adding more resources to the pool would be needed before evaluating further changes.

If the virtual machines are not capping the pool, and they are not using 100% CPU utilization in the VM's.  There needs to be a case made how spreading the load to more vCPU's will improve performance as well as the host needs to be reviewed for any constraints that could be causing an underlying bottleneck.

If the virtual machines are not capping the pool and are using 100% utilization, then there could be a need for more resources.  This also requires a review of the environment for possible over commitment when adding vCPU's.

Reply
0 Kudos