[DRILL-4601] Partitioning based on the parquet statistics

• Type: Improvement
• Status: Resolved
• Priority: Major
• Resolution: Duplicate
• Fix Version/s: 1.9.0
• Component/s: Query Planning & Optimization
• Labels: parquet partitioning planning statistics
• Flags: Patch
• Assignee: Unassigned
• Reporter: Miroslav Holubec
• Created: 13/Apr/16 08:27
• Updated: 24/Jan/17 09:17
• Resolved: 24/Jan/17 09:17

Description

It can really help performance to extend current partitioning idea implemented in DRILL-3333 even further.
Currently partitioning is based on statistics, when min value equals to max value for whole file. Based on this, files are removed from scan in planning phase. Problem is, that it leads to many small parquet files, which is not fine in HDFS world. Also only few columns are partitioned.

I would like to extend this idea to use all statistics for all columns. So if value should equal to constant, remove all files from plan which have statistics off. This will really help performance for scans over many parquet files.

I have initial patch ready, currently just to give an idea. (it changes metadata v2, which is not fine).

Issue Links

• duplicates: DRILL-1950 Implement filter pushdown for Parquet