Nandor Kollar created PIG-5242: ---------------------------------- Summary: Evaluate DataFrame API for Pig on Spark Key: PIG-5242 URL: https://issues.apache.org/jira/browse/PIG-5242 Project: Pig Issue Type: Improvement Components: spark Reporter: Nandor Kollar Fix For: 0.18.0
Currently, Pig on Spark uses RDD-s. Higher level DataFrame API offers many optimization opportunities like Catalyst optimizer, better serialization (project Tungsten). We should investigate how we can migrate from RDD-s to DataFrames, and does this result in performance improvement. -- This message was sent by Atlassian JIRA (v6.3.15#6346)