Co-authors: Walaa Eldin Moustafa, Wenye Zhang, Sushant Raikar, Raymond Lam, Ron Hu, Shardul Mahadik, Laura Chen, Khai Tran, Chris Chen, and Nagarathnam Muthusamy Introduction At LinkedIn, our big data compute infrastructure continually grows over time, not only to keep pace with the growth in the number of data applications, or their domains spanning data...

Co-authors: Walaa Eldin Moustafa, Wenye Zhang, Adwait Tumbde, Ratandeep Ratti Introduction Over the years, the popularity of Apache Spark at LinkedIn has grown, and users today continue to leverage its unique features for business-critical tasks. Apache Spark allows users to consume datasets using powerful, yet easy-to-use APIs such as the Dataset interface. The...

In a recent blog post, we touched upon Dali’s new architecture, which is designed to make data and logic seamlessly accessible and shareable across LinkedIn’s diverse environments. Dali achieves this vision by adopting the principles of physical and logical independence. Physical independence refers to enabling users to transparently access data regardless of...