Case Study: NVIDIA achieves resilient Kubernetes storage and zero-downtime maintenance with Portworx

Nvidia achieves ~99.9% uptime for chip design workloads with Portworx

Nvidia's infrastructure team faced the challenge of managing persistent storage for hundreds of containerized applications supporting its massive AI and chip design workloads across multiple data centers. They needed to improve resilience, reduce downtime, and provide developers with self-service access while maintaining enterprise-grade reliability for their Kubernetes environments.

By implementing Portworx Enterprise and PX-Backup, Nvidia achieved a resilient, enterprise-grade storage solution for Kubernetes. Portworx provided the replication and fault tolerance needed to operate over 500 applications across hundreds of nodes with approximately 99.9% uptime, including zero-downtime maintenance, thus ensuring high availability for their critical design and simulation workloads.

Nvidia