Uploaded November 2025 | Updated September 2026, 2 weeks ago
Linux users often ask: Why is my application slow? What caused it to crash? Was it a client-side issue—and if so, where? At SambaXP 2025, the Azure Files team introduced a new set of eBPF-based tools to help answer these questions by improving observability and debugging for Linux SMB client issues. We also shared a conceptual overview of the Always-On Diagnostics (AOD) project – a daemon that continuously monitors anomalies and automatically captures relevant logs when issues occur.
Since then, we’ve continued developing AOD and expanded the eBPF tooling to support the Linux NFS client. This talk will demonstrate how these tools can capture valuable diagnostic data in real-world anomalous scenarios. After a technical introduction to the standalone eBPF scripts, we’ll walk through the design of the AOD daemon, explain how the eBPF tools integrate into its system, and present the overall architecture. The session will conclude with a live demonstration of the diagnostics workflow in action – showing how AOD detects anomalies, collects logs, and can help pinpoint and contextualize client-side issues as they happen. While prior exposure to eBPF concepts may be helpful, it is not required. The session will begin with foundational explanations before diving deeper, making it accessible to all attendees.
Learn how to use the AOD daemon to capture hard-to-reproduce anomalies on Linux SMB and NFS clients, improving visibility into client-side behavior. Explore the eBPF scripts that power AOD—and understand how to extend or adapt them for custom observability needs. Understand the architecture and technical details behind these tools. Provide feedback and insights to help shape the future direction of these tools for the broader open-source community and ensure they meet the real-world needs of those working with Linux SMB and NFS workloads.
Presented by Meetakshi Setiya, Microsoft
Learn More:
• SDC Website: snia.org/sniadeveloper
• SNIA Website: snia.org
• SNIA Educational Library: snia.org/library
• X: twitter.com/SNIA
• LinkedIn: linkedin.com/company/snia
Linux users often ask: Why is my application slow? What caused it to crash? Was it a client-side issue—and if so, where? At SambaXP 2025, the Azure Files team introduced a new set of eBPF-based tools to help answer these questions by improving observability and debugging for Linux SMB client issues. We also shared a conceptual overview of the Always-On Diagnostics (AOD) project – a daemon that continuously monitors anomalies and automatically captures relevant logs when issues occur.
Since then, we’ve continued developing AOD and expanded the eBPF tooling to support the Linux NFS client. This talk will demonstrate how these tools can capture valuable diagnostic data in real-world anomalous scenarios. After a technical introduction to the standalone eBPF scripts, we’ll walk through the design of the AOD daemon, explain how the eBPF tools integrate into its system, and present the overall architecture. The session will conclude with a live demonstration of the diagnostics workflow in action – showing how AOD detects anomalies, collects logs, and can help pinpoint and contextualize client-side issues as they happen. While prior exposure to eBPF concepts may be helpful, it is not required. The session will begin with foundational explanations before diving deeper, making it accessible to all attendees.
Learn how to use the AOD daemon to capture hard-to-reproduce anomalies on Linux SMB and NFS clients, improving visibility into client-side behavior. Explore the eBPF scripts that power AOD—and understand how to extend or adapt them for custom observability needs. Understand the architecture and technical details behind these tools. Provide feedback and insights to help shape the future direction of these tools for the broader open-source community and ensure they meet the real-world needs of those working with Linux SMB and NFS workloads.
Presented by Meetakshi Setiya, Microsoft
Learn More:
• SDC Website: snia.org/sniadeveloper
• SNIA Website: snia.org
• SNIA Educational Library: snia.org/library
• X: twitter.com/SNIA
• LinkedIn: linkedin.com/company/snia
