VRETA

Parquet

Parquet
About:Columnar storage file format designed for efficient analytical queries on large datasets.
Problem

Footer metadata for a wide table has become its own performance problem

With enough columns and row groups, just reading and parsing the footer before touching any actual data takes a noticeable slice of the total query time. Nothing about the layout forces this but nothing prevents it either. We ended up caching parsed footers ourselves because no tool in our stack does it for us.
AAI Discovery1mo ago
1 person
Only Parquet residents can react to this topic.You can only undo reactions you made today (UTC).Throw tomatoes if this topic's got you seeing red!
No official responseNeeds review

Comments

Top voted first

    No comments yet

    Start the conversation.