HPE G10 Servers: Best and Optimized Setting for VMware vSphere

by Davoud Teimouri · Published 16/08/2019 · Updated 29/06/2023

Optimizing HPE server configuration is always one of biggest challenges for virtual environments administrators. The administrators always trying to provide best performance by changing configurations on hypervisor, virtual machines or other components or virtual infrastructure. There are best practices which published by server vendors to achieve best performance on their server platform.

Server hardware is one most important component in every environment, server provides main power and resource: Computing Resources. Processor and memory and other server’s component made to work almost like as human brain.

On This Post:

Some Important Things!

Human brain needs consumes about 20 percent of the body’s energy. Consume more energy is equal to more heat in human body. Server components needs energy and cooling, like human body. Energy and cooling needs money. So there is a challenge to keep balance between performance and cost of services in any IT environments.

What’s Important About Server Hardware?

In fact, processors and cooling system consume most power which provided by power modules. Don’t think about single server, think about hundreds of servers and thousands processors, thousand x 200W! (At least). Best performance has more cost for any environment also needs more maintenance.

What’s Best Practices?

Best practices are depended to workload type. AI workload needs apply different configuration compare to virtualization workload. We are talking about virtualization workload in this post.

Vendors offers balanced between power usage and performance always by default. You should decide about performance and power consumption.

Let’s Answer Some Questions?

Do you need to low latency response?

Do you have latency sensitive services?

Modern processor has modern features to balance between power and performance and those features helps in most of case to achieve better results. You know that what’s C-State, P-State or T-State in processors. All these features calling power saving feature which helping to reduce cost of cooling and energy and provides acceptable level of performance.

Who’s Responsible?

Modern hardware platforms and modern operating systems have abilities to controlling power management features and offering different profiles to manage different workloads.

In most virtualization platforms such as VMware vSphere and in the most of cases, allow operating system to control power management is best choice. Online switching between different profiles of power management is available at this situation.

Best Practices for HPE G10 Servers and VMware vSphere

Starting with 10th generation, HPE provides some workload profiles to help administrator in BIOS/Platform configuration options.

Workload Profiles is one of the HPE Intelligent System Tuning (IST) features and allows you to tune the resources in your HPE ProLiant server by choosing a preconfigured workload profile. The server will automatically configure the BIOS settings to match the selected workload.

The workload profiles are as follows:

General Power Efficient Compute

General Peak Frequency Compute
General Throughput Compute
Virtualization – Power Efficient

Virtualization – Max Performance
Low Latency
Mission Critical

Transactional Application Processing
High Performance Compute (HPC)
Decision Support

Graphic Processing
I/O Throughput
Custom

There are two workload profiles for virtualization that all available virtualization technologies will be enabled by choosing each of them:

Virtualization – Power Efficient
Virtualization – Max Performance

You can use Virtualization – Max Performance, if you are sure about your workload and workload is absolutely low latency. By choosing the mentioned workload profile, hypervisor can not control power management anymore.

Personally, I prefer Virtualization – Power Efficient because it will balance performance and energy, also allows to have more control on power management via hypervisor.

Also you can use Custom but you need to know what you are doing! Because you have to choose right settings for all configuration.