USENIX Courses

Blink - Fast Connectivity Recovery Entirely in the Data Plane

Explores programmable switches for rapid rerouting using TCP-induced signals to detect failures. Presents Blink, a data-driven system analyzing TCP flows at line rate to quickly recover connectivity in the data plane.

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

Size-Aware Sharding for Improving Tail Latencies in In-Memory Key-Value Stores

Innovative size-aware sharding technique for in-memory key-value stores, reducing tail latencies and improving throughput by avoiding head-of-line blocking and optimizing request distribution across cores.

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

BLAS-on-Flash - An Efficient Alternative for Large Scale ML Training and Inference

Efficient alternative for large-scale ML tasks using SSD-resident matrices, enabling near in-memory performance on a single workstation. Outperforms distributed systems for complex algorithms like eigensolvers.

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

Chaos Engineering

Explore Netflix's approach to chaos engineering, its impact on system resilience, and lessons learned in building a robust software stack through controlled failure experiments.

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

Debugging Linux Issues with eBPF

Explore eBPF for debugging Linux performance issues, focusing on a real-world case of CPU increase in Kafka after a Debian upgrade. Learn tools and techniques for operational engineers.

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

Serverless Ops - What to Do When the Server Goes Away

Explore the impact of serverless architecture on operations, redefining roles and responsibilities. Learn to adapt, prove value, and navigate the changing landscape of cloud technology.

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

Incident Management at Netflix Velocity

Discover Netflix's approach to handling incidents at high velocity, focusing on preparation, expertise, and continuous learning to ensure quick recovery and unique outage scenarios.

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

Kafka on Kubernetes - From Evaluation to Production at Intuit

Explore Intuit's journey of running Kafka on Kubernetes in AWS, covering evaluation, testing, configuration, and integration with monitoring tools. Learn about challenges faced and solutions implemented.

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

SLO Burn - Reducing Alert Fatigue and Maintenance Cost in Systems of Any Size

Discover strategies to reduce alert fatigue and maintenance costs in systems of any size using Service Level Objectives (SLOs) and symptom-based alerting with Prometheus.

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

Cross Atlantic - Scaling Instagram Infrastructure from US to Europe

Scaling Instagram's infrastructure across continents: challenges, solutions, and disaster recovery strategies for deploying stateful services and partitioning Cassandra databases between US and Europe.

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

Apache Kafka and KSQL in Action - Let's Build a Streaming Data Pipeline

Build real-time streaming data pipelines using Apache Kafka and KSQL. Learn architectural benefits, data integration, filtering, enrichment, and anomaly detection through practical demonstrations.

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

Circonus - Design Failures Case Study

Explore Circonus platform's evolution, including architectural changes and lessons learned from failures in telemetry management and SLO implementation for system reliability.

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

Keep Building Fresh - Shopify's Journey to Kubernetes

Shopify's transition to Kubernetes: challenges, solutions, and benefits of moving from traditional infrastructure to cloud-native. Insights on custom tooling and automation for efficient container orchestration.

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

The Myth of Cloud Agnosticism

Explores the practical challenges of cloud agnosticism, discussing financial, technical, and operational complexities of multi-cloud deployments and migrations between providers.

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

Capacity Planning in Four Parts - Telling the Future without a Crystal Ball

Learn proactive capacity planning techniques to avoid reactive scaling, covering monitoring, future planning, enforcement, re-evaluation, and common pitfall avoidance for SREs and engineers.

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