Guest: Thales Cervi
Project: StarlingX | Company/Organization: Encora | OpenInfra Foundation 
Show: The Source
Topics: Edge Computing, Open Source

Managing distributed infrastructure at the edge is fundamentally different from running traditional cloud environments. When you’re dealing with thousands of remote sites, limited resources, and zero tolerance for downtime, the operational complexity multiplies exponentially. Thales Cervi, Member of the StarlingX Technical Steering Committee at OpenInfra Foundation, explains why major telecom operators worldwide have standardized on StarlingX for their most demanding edge deployments.

What StarlingX Solves

StarlingX isn’t just another Kubernetes distribution. The platform combines Linux, Kubernetes, and OpenStack services into an integrated stack specifically designed for distributed edge computing. Cervi describes it as providing flexible, reliable cloud infrastructure that automates operations and ensures reliability across day two and day three operations.

The differentiator lies in how StarlingX addresses the unique challenges of edge deployment. Organizations running workloads that demand low latency and distributed processing—from 5G radio access networks to IoT gateways—need infrastructure that works reliably without constant human intervention.

Production-Proven Reliability

Major telecom operators have deployed StarlingX in production environments running mission-critical services. This real-world validation stems from StarlingX’s focus on automated monitoring, health management, and self-recovery capabilities.

“The cycle of feedback is complete,” Cervi explains. “You deliver something, people use it, they come with problems and issues, then you solve that and release it again. There’s a lot of community work and contribution happening there.”

One critical capability the community developed through this feedback loop is seamless upgrades across distributed deployments. When you’re managing hundreds or thousands of nodes, upgrading the platform must be controlled and automated. The software management services in StarlingX now handle both version upgrades and security patching with minimal disruption.

StarlingX 11.0 Enhancements

The latest release delivers significant improvements across reliability, security, and performance. The software management services reach what Cervi calls “state of the art” for automated upgrades and patching. Network security now includes encrypted pod-to-pod traffic, removing that burden from applications while securing platform communications.

Integration with Rook Ceph transforms storage operations. Previously, Ceph ran directly on host platforms with complex configurations. Now Rook Ceph runs in Kubernetes, allowing dedicated storage nodes that improve operational efficiency. The StarlingX OpenStack distribution can leverage this storage backend directly.

Network performance gets a boost through Open vSwitch integration with DPDK (Data Plane Development Kit). This moves packet processing from kernel space to user space, dramatically improving network throughput for virtualized workloads. The platform supports both standard and real-time Linux kernels, giving operators fine-grained control over latency-sensitive applications.

CPU isolation features let organizations dedicate specific cores to critical applications, ensuring predictable performance for time-sensitive workloads running on shared infrastructure.

Beyond Telecom

While telecom remains the primary use case, StarlingX is gaining traction in automotive, healthcare, and enterprise cloud environments. Cervi notes increased interest from companies exploring OpenStack for enterprise workloads, and StarlingX provides a containerized, cloud-native way to run those environments.

The community recognizes that broader adoption requires better onboarding. Documentation improvements focus on making StarlingX accessible to newcomers who haven’t worked with the platform before. The goal is enabling developers to download an official build, deploy in a virtual environment, understand the capabilities, and then move to production hardware.

Universities are also exploring StarlingX for research and education, expanding the community beyond production deployments.

Production Deployments at Scale

Real-world deployments validate StarlingX’s capabilities. Telecom operators running the platform in their backbone infrastructure rely on its combination of automation, reliability, and performance. These aren’t test environments—they’re production systems handling revenue-generating services.

The platform’s architecture supports running both traditional virtualized workloads through OpenStack and cloud-native applications on Kubernetes. This flexibility matters when organizations need to support existing applications while modernizing their infrastructure stack.

The Open Source Advantage

StarlingX demonstrates how open source communities solve complex infrastructure challenges. The feedback loop between production users and developers drives continuous improvement. Features like automated upgrades, improved documentation, and new integrations emerge from real operational needs, not vendor roadmaps.

As edge computing becomes critical infrastructure for more industries, platforms like StarlingX provide the foundation for reliable, scalable distributed systems. The combination of proven production deployments and active community development positions StarlingX as essential infrastructure for organizations building at the edge.