AT&T's Migration of Billions of Events Processing From Hadoop
OVERVIEW
EXPERIENCE | In Person |
---|---|
TYPE | Breakout |
TRACK | Data Engineering and Streaming |
INDUSTRY | Media and Entertainment |
TECHNOLOGIES | Apache Spark, ETL, Orchestration |
SKILL LEVEL | Intermediate |
DURATION | 40 min |
DOWNLOAD SESSION SLIDES |
AT&T's strategic migration of Hadoop MapReduce jobs to Databricks for one of their network applications has resulted in significant cost and time efficiencies, setting a benchmark in big data processing and analytics. This presentation outlines the comprehensive approach and industry best practices employed by AT&T in this migration. The transition involved converting Hadoop MapReduce jobs to Spark jobs, which are natively supported by the Databricks Platform, leading to improved performance and scalability. This move resulted in a substantial 30% reduction in compute costs and more than halved the execution time, thereby enhancing AT&T's operational efficiency and productivity. The successful migration exemplifies the transformative potential of cloud-native platforms and underlines the value of adopting industry best practices in big data management and processing.
SESSION SPEAKERS
Praveen Vemulapalli
/Director- Technology
AT&T
Akshay Sharma
/Senior Solutions Consultant
Databricks