USENIX Courses

TAILCHECK - A Lightweight Heap Overflow Detection Mechanism with Page Protection and Tagged Pointers

Innovative heap overflow detection technique using page protection and pointer tagging, offering low-cost security for C/C++ programs with minimal performance impact.

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

Karma - Resource Allocation for Dynamic Demands

Explores Karma, a novel resource allocation algorithm extending max-min fairness for dynamic user demands, ensuring efficiency, strategy-proofness, and fairness in systems with fluctuating resource needs.

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

eZNS - An Elastic Zoned Namespace for Commodity ZNS SSDs

Innovative storage solution enhancing cost-efficiency and performance of SSDs through adaptive zoning, offering improved throughput and reduced latency for applications like RocksDB.

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

Ship Your Critical Section, Not Your Data - Enabling Transparent Delegation with TCLOCKS

Explore transparent delegation in locking protocols with TCLocks, improving application performance without code modifications. Learn about innovative synchronization mechanisms for high-performance systems.

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

Unlocking Unallocated Cloud Capacity for Long, Uninterruptible Workloads

Optimizing cloud resource utilization through predictive analysis of Harvest VMs, enabling efficient execution of long-running workloads at reduced costs while improving job completion times.

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

Resiliency Practices in Managing CDN - Content Delivery Network

Explore Netflix's Open Connect CDN resilience strategies, including stack failures, overload tests, and regional DNS withdrawal exercises to ensure robust content delivery worldwide.

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

Building and Operating a Pretty Big Storage System - My Adventures in Amazon S3

Insights into building and operating Amazon S3, exploring technical challenges, organizational aspects, and personal experiences of working on a massive-scale cloud storage service.

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

Meatbag Systems - How Our Reliability Culture & Practice Evolved over Time

Exploring the evolution of reliability culture through major incidents, emphasizing the human aspect in maintaining production systems and aligning reliability with customer value.

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

Real-Time Adaptive Controls for Resilient Distributed Systems

Explore real-time adaptive controls for resilient distributed systems, focusing on dynamic parameter tuning to enhance service resilience and reduce configuration errors in large-scale production environments.

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

Improving Machine Learning Development Reliability

Explore challenges and solutions for ML development reliability, focusing on unique aspects of the ML lifecycle, monitoring, and scalability in production environments.

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

Move Fast and Learn Things - Principles of Cognition, Teaming, and Coordination

Explore cognitive and coordinative mechanisms for resilient software engineering, drawing from psychology and management theory to enhance SRE practices and organizational effectiveness.

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

Computing Performance 2022 - What's on the Horizon

Explore the future of computing performance with insights on emerging hardware and software technologies, their impact on SRE, and predictions for improved speed and efficiency.

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

A Post Incident Review Review

Explore ANZx's unique post-incident review process, focusing on safety science concepts and avoiding root cause analysis or action items tracking in a regulated industry environment.

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

Advanced Linux Kernel Networking Monitoring

Explore advanced Linux kernel networking monitoring for containers, focusing on troubleshooting techniques and a custom tool for identifying network issues in Kubernetes environments.

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

How We Drained Every Backbone Router Simultaneously

Exploring Meta's 2021 outage: causes, cascading effects, and lessons learned. Insights into network infrastructure, disaster recovery, and future improvements for preventing similar incidents.

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