[HIVE-9134] Uber JIRA to track HOS performance work

• Type: Improvement
• Status: Open
• Priority: Major
• Resolution: Unresolved
• Affects Version/s: spark-branch
• Component/s: Spark
• Assignee: Xuefu Zhang
• Reporter: Brock Noland
• Created: 16/Dec/14 23:49
• Updated: 17/Dec/14 00:07

Issue Links

• relates to: HIVE-7292 Hive on Spark

Sub-Tasks

• Performance of query 28 from tpc-ds [Spark Branch]: Open
• Performance of SELECT COUNT(*) FROM store_sales WHERE ss_item_sk IS NOT NULL [Spark Branch]: Resolved
• Evaluate hive.rpc.query.plan performance [Spark Branch]: Open
• Improve CombineHiveInputFormat.getSplit performance: Resolved
• Cache Map and Reduce works in RSC [Spark Branch]: Resolved
• Profile query compiler [Spark Branch]: Resolved
• Dynamic Partition Pruning [Spark Branch]: Closed
• Perf enhancement on CombineHiveInputFormat and HiveInputFormat: Resolved
• Investigate CBO [Spark Branch]: Open
• Make vectorization work with Spark [Spark Branch]: Resolved
• Enhance InputSplitShims to extend InputSplitWithLocationInfo [Spark Branch]: Open
• Profile query compiler #2 [Spark Branch]: Resolved
• Avoid redundant clone of JobConf [Spark Branch]: Resolved
• Fix ClassCastException when CBO is enabled for HOS [Spark Branch]: Resolved