Sharing Lecturer:
Lecturer Profile:
The technical director of the Data Center indicator Platform Development Department of Suning Big Data Center, the senior engineer of Baidu Big Data Department and the architect of Yihaodian Search and Precision Department, has been engaged in the research and development of big data, has a deep understanding of big data tools and machine learning, and has rich experience in the field of real-time computing. In-depth knowledge of Storm and Spark Streaming. In 2013, SQL on Stream solution was designed and developed based on the company’s real-time processing platform. I love sharing and technology dissemination, and currently focus on the construction of data analysis platform, aiming at connecting data modeling to data analysis. Based on OLAP technologies such as Druid and MPP, we provide a platform-level data indicator service and create a one-stop solution of “data as a service”.
Share content:
For those who have some basic knowledge of Spark and want to learn more about the internal principles of Spark. This section describes the internal principles of Spark and describes some performance optimization methods based on the operating mechanism of the Spark engine.
1. Core concepts
2. Calculation principle of the Spark engine
3. Spark Shuffle Analysis
4. Optimize Spark performance
Share time: 20:00 — 21:30, December 14, 2018
In-depth analysis of Spark computing Engine
