USENIX Courses

Watering the Roots of Resilience - Learning from Failure with Decision Trees

Explore how SREs can align mental models with system reality using resilience stress testing and decision trees. Learn practical tools for documenting, visualizing, and improving complex software systems.

• YouTube
• 41 minutes
• Self-Paced
• Conference Talk

Lessons Learned from 7 Years of Running Developer Platforms

Insights on platform engineering best practices, including product management, developer retention, trust-building, and re-skilling ops staff, drawn from diverse organizations' experiences over the past decade.

• YouTube
• 32 minutes
• Self-Paced
• Conference Talk

Hell Is Other Platforms

Explore the pitfalls of blindly adopting others' platform strategies. Learn to retain agency, identify needs, and avoid common mistakes in platform engineering for your unique business context.

• YouTube
• 27 minutes
• Self-Paced
• Conference Talk

On the Wings of SREs - J.P. Morgan's Journey into the Cloud

Explore J.P. Morgan's transition to public cloud, focusing on SRE's role in overcoming regulatory, technical, and organizational challenges while ensuring stability and reliability.

• YouTube
• 20 minutes
• Self-Paced
• Conference Talk

Scaling Telemetry Systems with Streaming

Explore the evolution of Honeycomb's Kafka cluster and telemetry systems, covering scaling strategies, infrastructure choices, and best practices for handling 10x data volume growth.

• YouTube
• 41 minutes
• Self-Paced
• Conference Talk

OpenTelemetry Metrics 101

Demystifying OpenTelemetry metrics: Learn about different metric instruments, their implementation, and how they can enhance your understanding of system performance and error rates.

• YouTube
• 42 minutes
• Self-Paced
• Conference Talk

How to Take Prometheus Planet Scale - Massively Large Scale Metrics Installations

Explore scaling Prometheus for massive metrics installations, covering field hint indices, query push down, GitOps deployment, and lessons learned from eBay's journey to planet-scale observability.

• YouTube
• 39 minutes
• Self-Paced
• Conference Talk

Incident Archaeology - Extracting Value from Paperwork and Narratives

Discover how Spotify transforms incident reports into valuable insights for improving system operations and work processes, extracting meaningful data from seemingly mundane paperwork.

• YouTube
• 19 minutes
• Self-Paced
• Conference Talk

Building an APM with OpenTelemetry and OpenSource

Explore building an open-source APM using OpenTelemetry, Prometheus, and Jaeger. Learn implementation strategies, risks, and upcoming improvements in the OTel community for cost-effective application performance monitoring.

• YouTube
• 18 minutes
• Self-Paced
• Conference Talk

Chaos-Driven Development - TDD for Distributed Systems

Explore chaos experimentation as a test-driven development approach for distributed systems, enhancing reliability and validating changes throughout the software lifecycle.

• YouTube
• 18 minutes
• Self-Paced
• Conference Talk

SRE in Transition - From Startup to Established Business

Explore how SRE teams evolve as startups grow, focusing on organizational changes, advocacy strategies, and overcoming technical debt to support rapid scaling and maintain operational excellence.

• YouTube
• 16 minutes
• Self-Paced
• Conference Talk

The Revolution Will Not Be Terraformed - SRE and the Anarchist Style

Exploring SRE as a cultural force for change, examining its evolution and potential to drive reliability in organizations while drawing parallels to social movements and people-centric approaches.

• YouTube
• 19 minutes
• Self-Paced
• Conference Talk

Empowering Azure Storage with RDMA

Exploring Azure's implementation of RDMA for storage, addressing challenges in regional deployment and achieving significant performance improvements and CPU savings.

• YouTube
• 20 minutes
• Self-Paced
• Conference Talk

Better Together - Jointly Optimizing ML Collective Scheduling and Execution Planning Using SYNDICATE

Optimizing ML training with SYNDICATE: A framework that minimizes communication bottlenecks and speeds up training for large-scale models through novel motif abstraction and joint optimization techniques.

• YouTube
• 22 minutes
• Self-Paced
• Conference Talk

Building Flexible, Low-Cost Wireless Access Networks With Magma

Magma: An open system for building affordable wireless networks in underserved areas, leveraging Internet design patterns and SDN principles to reduce costs and complexity while maintaining key cellular features.

• YouTube
• 20 minutes
• Self-Paced
• Conference Talk