USENIX Courses

Care and Feeding of Data Processing Pipelines

Discover essential strategies for managing data processing pipelines, from preventing failures and monitoring data correctness to implementing canary deployments and auto-scaling mechanisms for robust system reliability.

• YouTube
• 39 minutes
• Self-Paced
• Free Video

Deploying Nagios in a Large Enterprise Environment

Discover scalability, security, and integration strategies for implementing Nagios monitoring systems in enterprise-scale deployments, including proprietary applications and closed devices.

• YouTube
• 1 hour 1 minute
• Self-Paced
• Free Video

Experiences with Scalable Network Operations at Akamai

Discover how Akamai manages its global content delivery network through automation, scaling strategies, and distributed systems management across 20,000+ servers in 72 countries.

• YouTube
• 1 hour 19 minutes
• Self-Paced
• Free Video

Autonomic Administration - Introduction to Network Management and Future Technologies

Explore the future of network management through autonomic computing principles, focusing on innovative solutions for complex system administration challenges and emerging technologies.

• YouTube
• 1 hour 26 minutes
• Self-Paced
• Free Video

Data Center Growing Pains - Environmental Challenges and Solutions

Discover strategies for managing data center growth challenges, power consumption, and environmental compliance through Sun Microsystems' innovative approaches and real-world experiences.

• YouTube
• 57 minutes
• Self-Paced
• Free Video

Should the Root Prompt Require a Road Test? Evaluating System Administrator Certification

Explore the concept of practical skill assessment for system administrators, comparing certification tests with hands-on evaluation methods for measuring core competencies and real-world abilities.

• YouTube
• 42 minutes
• Self-Paced
• Free Video

Using Throttling and Traffic Shaping to Combat Botnet Spam

Discover effective strategies for combating botnet spam through traffic shaping and throttling techniques, while understanding spammer behavior patterns and implementing practical connection management solutions.

• YouTube
• 1 hour 14 minutes
• Self-Paced
• Free Video

Fifty Shades of Caching and How LLMs Paint It Black

Explore caching technologies from CDNs to memory stores and discover how LLM traffic challenges traditional caching strategies in this practical deep dive with real-world examples.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

Gaining Insights from a Black Box System

Discover how to monitor service health as black boxes using multiple measurement techniques for robust observability, system reliability, and enhanced user experience at Netflix.

• YouTube
• 29 minutes
• Self-Paced
• Free Video

ACK to the Future - TCP in 2025

Discover TCP optimization techniques for 2025, covering congestion control algorithms, receive window sizing, and diagnostic tools to maximize network performance and troubleshoot issues.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

Challenges of Making Large AI Clusters Reliable

Discover the unique challenges of maintaining reliability in large AI clusters and how SRE practices must adapt beyond traditional datacenter approaches for high-performance computing environments.

• YouTube
• 46 minutes
• Self-Paced
• Free Video

MLOps 2025 - A Journey into the Past and the Future

Explore MLOps evolution, production challenges, and best practices for building robust, scalable machine learning systems at enterprise scale.

• YouTube
• 42 minutes
• Self-Paced
• Free Video

Service Messy - Pagerduty's Service Mesh Migration

Discover how PagerDuty migrated 500+ services to a service mesh with a lean team, achieving 95% completion while avoiding burnout and maintaining system reliability.

• YouTube
• 36 minutes
• Self-Paced
• Free Video

The Computer Wants to Lose Your Data

Explore how computers can fail to save or corrupt data through MySQL and Postgres examples, covering doublewrite buffers, fsyncgate incident, and disk cache safety mechanisms.

• YouTube
• 34 minutes
• Self-Paced
• Free Video

The Bitter and the Sweet of Running a Planet-Scale Build and CI Stack at Google

Discover how Google's SRE team manages a planet-scale Build & CI stack serving 100,000+ users with 98% cache hit rates, resource optimization, and petabyte-scale storage solutions.

• YouTube
• 30 minutes
• Self-Paced
• Free Video