Facebook-Scale Graph Processing Report by Vikas Jain
Explore Facebook's endeavor in processing one trillion edges in graphs, presented by Vikas Jain. The report covers pros like open-source enhancements and cons like weak experimental evaluations, offering insights into the challenges faced and advancements made in handling massive graphs at Facebook scale.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
One Trillion Edges: Graph Processing at Facebook-Scale (Scriber s Report) Presenter: Vikas Jain (vjain11)
Pros Enhancements are open-source (40%) The Facebook factor (50%) Well Motivated: Reliable Evaluation: Evaluated on real-world workloads (25%) Reliable System: As deployed in production (15%) Work motivated by real-world challenges (10%) Scaled to handle enormous graphs (20%) Support for edge based input (15%) Support for multithreading to optimize resource utilization (15%) Shared operational experience (10%) Serialization of edges and messages to reduce memory (10%)
Cons More of engineering hacks and has marginal novelty (20%) Weak experimental evaluation (55%) No proper evaluation for enhancements (25%) Comparison with Hive for performance (10%) No evaluation of overhead with check-pointing enabled (10%) System performance with failures not discussed or evaluated (10%) Enhancements tightly integrated to Facebook s software stack (20%) Lacks theoretical explanation for design choices. eg. Multithreading, Worker Phases (5%) Some compute model extensions unnecessary, add complexity
Thanks Questions?
