[HIVE-11363] Prewarm Hive on Spark containers [Spark Branch]

• Type: Sub-task
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 1.1.0
• Fix Version/s: spark-branch, 1.3.0, 2.0.0
• Component/s: Spark
• Assignee: Xuefu Zhang
• Reporter: Xuefu Zhang
• Created: 23/Jul/15 23:35
• Updated: 05/Sep/17 06:41
• Resolved: 30/Jul/15 19:51

Description

When Hive job is launched by Oozie, a Hive session is created and job script is executed. Session is closed when Hive job is completed. Thus, Hive session is not shared among Hive jobs either in an Oozie workflow or across workflows. Since the parallelism of a Hive job executed on Spark is impacted by the available executors, such Hive jobs will suffer the executor ramp-up overhead. The idea here is to wait a bit so that enough executors can come up before a job can be executed.

Issue Links

• is related to: HIVE-12951 Reduce Spark executor prewarm timeout to 5s
• relates to: HIVE-11434 Followup for HIVE-10166: reuse existing configurations for prewarming Spark executors