Skip to content

High Performance Kubernetes Platform For Stateful Workloads


Enterprises need high-performance storage for their stateful applications. Their needs
vary from running Relational and NoSQL Databases to Big Data to AI/ML workloads. They
want near bare metal like performance along with scale. In this whitepaper, we compare
Robin Platform with open source GlusterFS and our analysis show that Robin platform
provides near bare-metal performance and could scale well to meet the needs of Big Data
and AI/ML applications.


As containers gain traction inside the enterprise and Kubernetes emerges as the standard
for container orchestration, users are looking to leverage the technology for running
mission-critical workloads such as stateful applications like databases, big data and AI/ML
applications. Unlike stateless applications, these applications have important storage and
networking requirements. The containers and Kubernetes are helping modern
enterprises to embrace agile and DevOps while also bringing better efficiencies to IT
operations. The key to enterprise IT transformation lies in leveraging a stack such as
Kuberntes for both states, stateless and stateful, for big data applications and AI/ML.

The Kubernetes community has focused their attention on the need to support stateful
workloads – the work done around StatefulSets is a good indicator of the progress. But this
effort is far from mature and there exists operational overhead in provisioning the
clusters needed for persistent volumes. Many IT organizations are spending multiple
cycles to get Kubernetes set up for stateful workloads, leading to friction and delays. The
problem gets bigger when big data and other data-intensive workloads become part of the
equation. Beyond the operational overhead, performance is also a critical criterion for
these workloads. The enterprise decision makers are torn between selecting a DIY
approach to running stateful workloads on Kubernetes and finding the right platform that
is suitable for data-intensive workloads.

If faster time to market is the driver for the adoption of cloud and IT modernization
strategies, building a platform for stateful workloads from vanillaKubernetes or one of the
platforms available for stateless applications is a waste of resources leading to
undifferentiated heavy lifting. The key to successful digital transformation lies in picking a platform that provides a competitive edge in the market without incurring high operational

Key evaluation criteria

– Does the Kubernetes platform give bare metal like performance?
– Are the performance guarantees available at scale?
– Is the performance predictable?