[HIVE-11276] Optimization around job submission and adding jars [Spark Branch]

• Type: Sub-task
• Status: Resolved
• Priority: Major
• Resolution: Not A Problem
• Affects Version/s: 1.1.0
• Component/s: Spark
• Assignee: Chengxiang Li
• Reporter: Xuefu Zhang
• Created: 16/Jul/15 04:51
• Updated: 17/Jul/15 13:11
• Resolved: 17/Jul/15 12:57

Description

It seems that Hive on Spark has some room for performance improvement on job submission. Specifically, we are calling refreshLocalResources() for every job submission despite there is are no changes in the jar list. Since Hive on Spark is reusing the containers in the whole user session, we might be able to optimize that.

We do need to take into consideration the case of dynamic allocation, in which new executors might be added.

This task is some R&D in this area.