[SPARK-24206] Improve DataSource benchmark code for read and pushdown

• Type: Improvement
• Status: Resolved
• Priority: Minor
• Resolution: Fixed
• Affects Version/s: 2.3.0
• Fix Version/s: 2.4.0
• Component/s: SQL
• Assignee: Takeshi Yamamuro
• Reporter: Takeshi Yamamuro
• Created: 08/May/18 04:58
• Updated: 17/Jul/18 18:34
• Resolved: 23/May/18 20:02

Description

I improved the DataSource code for read and pushdown in the parquet v1.10.0 upgrade activity: https://github.com/apache/spark/pull/21070

Based on the code, we need to brush up the benchmark code and results in the master.

Issue Links

• duplicates: SPARK-24071 Micro-benchmark of Parquet Filter Pushdown
• links to: [Github] Pull Request #21266 (maropu)
• links to: [Github] Pull Request #21288 (maropu)
• links to: [Github] Pull Request #21625 (maropu)