Principled Performance Analytics
Explore innovative analytical methods for high-fidelity insights in distributed systems, focusing on performance analytics, statistical approaches, and practical applications in complex services at scale.
Automated Operating System and Environment Certification at LinkedIn - Reducing Toil and Increasing Velocity
Automated OS certification at LinkedIn: Reducing toil, increasing velocity. Discusses project evolution, challenges, and early results in enhancing certification processes across data centers and Azure.
How We Survived - and Thrived - During The Pandemic and Helped Millions of Students Learn Remotely
Discover how McGraw Hill applied 'Upstream Thinking' to thrive during the pandemic, scaling services and implementing SRE principles to support millions of remote learners without compromising security or incurring high costs.
The 'Success' in SRE Is Silent
Strategies for demonstrating ROI in SRE and availability work, addressing challenges and potential regulatory issues to ensure continued investment and positive outcomes.
How the Metrics Backend Works at Datadog
Explore Datadog's metrics backend evolution, scaling challenges, and reliability solutions. Learn about distributed systems, Kafka implementation, and strategies for handling failures at various levels.
Building and Running a Diversity-Focused Pre-Internship Program for SRE
Learn about Meta's innovative pre-internship program for SRE, focusing on diversity and early career development. Gain insights on program structure, curriculum, and outcomes to implement similar initiatives.
Are We There Yet? - Metrics-Driven Prioritization for Your Reliability Roadmap
Metrics-driven framework for prioritizing reliability improvements in SRE teams. Guides leaders in making data-based decisions, highlighting successes, and gaining support for impactful initiatives.
Toward Secure and Convenient Browsing Data Management in the Cloud
Explores a novel Cloud computing Age Browser architecture to address browsing data insecurity and inconvenience issues in modern Web browsers, leveraging cloud storage services.
Scaling Memcache at Facebook
Explore Facebook's scaling of memcached to support billions of requests per second and trillions of items, enabling a rich experience for over a billion users worldwide.
Understanding the Robustness of SSDs under Power Fault
Explores SSD reliability under power faults, revealing surprising failure behaviors in commodity devices. Proposes a testing framework to expose issues and improve storage system robustness.
Never Been KIST - Tor’s Congestion Management Blossoms with Kernel-Informed Socket Transport
Explores Tor's congestion issues, proposing KIST algorithm to improve network performance by optimizing socket management using real-time kernel information, reducing latency and increasing throughput.
GraphX - Graph Processing in a Distributed Dataflow Framework
Explore GraphX, a graph processing framework built on Apache Spark, offering performance comparable to specialized systems while enabling broader computational capabilities and fault tolerance.
Eclipse Attacks on Bitcoin’s Peer-to-Peer Network
Explore eclipse attacks on Bitcoin's P2P network, their impact on mining and consensus, and proposed countermeasures to enhance network security while maintaining decentralization.
Control-Flow Bending - On the Effectiveness of Control-Flow Integrity
Explores Control-Flow Bending attacks on Control-Flow Integrity defenses, revealing vulnerabilities in fine-grained CFI implementations and demonstrating the necessity of shadow stacks for enhanced security against memory corruption.
Named Data Networking
Explore Named Data Networking's potential to replace TCP, its architectural advantages, and data-centric security approach in this insightful presentation by networking experts.
Release Engineering Best Practices at Google
Explore Google's release engineering practices, including bazel usage, branching strategies, and automated systems. Learn about disciplines, philosophies, and techniques for improving release processes.
Efficiently Backing Up Terabytes of Data with PgBackRest
Explore efficient PostgreSQL backup solutions with PgBackRest, featuring checksums, compression, parallel transfer, and more. Learn about its design, features, and practical applications for large-scale databases.
Multi-Person Localization via RF Body Reflections
RF-based indoor localization system that tracks multiple users' positions and gestures through walls, using wireless signal reflections off bodies. Can even locate static users by detecting breathing movements.
Protecting Privacy of BLE Device Users
Explores BLE device privacy vulnerabilities and introduces BLE-Guardian, a system protecting user privacy by controlling device discovery and access without modifying existing devices or protocols.
K-Fingerprinting - A Robust Scalable Website Fingerprinting Technique
Explores k-fingerprinting, a robust website fingerprinting technique using random decision forests, demonstrating high accuracy in identifying visited web pages through encrypted connections.
Applicable and Achievable Formal Verification
Introductory overview of formal verification techniques in industry, focusing on safety-critical systems. Explores tools, applications, and adaptability to existing infrastructures.