YoVDO

Configanator - A Data-driven Approach to Improving CDN Performance

Offered By: USENIX via YouTube

Tags

USENIX Symposium on Networked Systems Design and Implementation (NSDI) Courses Algorithmic Design Courses

Course Description

Overview

Explore a conference talk from NSDI '22 that introduces Configanator, a data-driven framework designed to improve Content Delivery Network (CDN) performance. Delve into the challenges of web server configuration in the face of evolving protocols and diverse network conditions. Learn how Configanator leverages connection data to identify network and device characteristics, optimizing configuration parameters for enhanced end-user performance. Discover the framework's impressive results, including 32-67% improvements in tail web performance across various websites and networks. Gain insights into the algorithmic design, workflow, and evaluation setup of Configanator, as well as its potential impact on the future of CDN optimization.

Syllabus

Intro
Web Performance Matters!
Background
Traditional Approaches for Selecting Configurat
Are Traditional Approaches Optimal?
Challenges with Configuration Tuning
Algorithmic Design
Configanator Workflow
Evaluation Setup
Performance Improvements
Related Works
Conclusion + Future Work


Taught by

USENIX

Related Courses

Scaling Memcache at Facebook
USENIX via YouTube
Multi-Person Localization via RF Body Reflections
USENIX via YouTube
Opaque - An Oblivious and Encrypted Distributed Analytics Platform
USENIX via YouTube
Live Video Analytics at Scale with Approximation and Delay-Tolerance
USENIX via YouTube
Clipper - A Low-Latency Online Prediction Serving System
USENIX via YouTube