IBM, Mirantis Launch OpenStack Benchmarking Tool
Ensuring the performance of an OpenStack cloud is not an easy task, but IBM and Mirantis are hoping to simplify it and assure enterprises who are wary of the open source cloud platform that OpenStack is a viable and well-performing system.
December 6, 2013
Ensuring the performance of an OpenStack cloud is not an easy task, but IBM and Mirantis are hoping to simplify it and assure enterprises who are wary of the open source cloud platform that OpenStack is a viable and well-performing system.
The two companies, both of which are OpenStack Foundation members, have launched Rally, a testing and benchmarking tool that measure OpenStack performance when running various enterprise workloads. As the company noted when notifying us of this news, Rally will help to reassure existing and potential customers of OpenStack's viability in the enterprise, which was recently called into question by Gartner.
"To accelerate OpenStack adoption among mainstream enterprises, it is essential to provide customer confidence in the product by establishing credible performance benchmarks. Our initiative with IBM is an important step, and we encourage others in the community to join us," said Adrian Ionel, Mirantis CEO, in a prepared statement.
According to a blog post by Kirill Ishanov, director of Mirantis Labs, the benchmark testing will be a combination of Mirantis and SoftLayer technology. Ishanov noted SoftLayer will provide the infrastructure to conduct the benchmark testing using more than 1,500 bare metal servers. The end goal is to improve the scalability of OpenStack — or, at least, prove it to skeptical would-be customers.
"However, the ultimate goal of Rally is to go beyond testing OpenStack performance and provide the OpenStack community with tooling and reproducible scaling tests that will improve the upstream OpenStack codebase and make upstream OpenStack both more relevant and easier to adopt in traditional enterprises," Ishanov wrote.
Using Rally, IBM and Mirantis will be able to codify behavioral properties and associated workflows for a given application workloads. Then a simulation is run to see how the workloads run and scale on a particular configuration of an OpenStack cloud.
It's not an insignificant amount of work, by any means, but assuming the results show OpenStack in a positive light, then it could go a long way towards providing the open source cloud platform's viability in the enterprise space. And that could be an excellent ace in the hand of an OpenStack cloud builder trying to position OpenStack against its many competitors.
About the Author
You May Also Like