You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Marco Gaido (JIRA)" <ji...@apache.org> on 2018/09/08 09:05:00 UTC
[jira] [Created] (SPARK-25379) Improve ColumnPruning performance
Marco Gaido created SPARK-25379:
-----------------------------------
Summary: Improve ColumnPruning performance
Key: SPARK-25379
URL: https://issues.apache.org/jira/browse/SPARK-25379
Project: Spark
Issue Type: Sub-task
Components: Optimizer, SQL
Affects Versions: 2.4.0
Reporter: Marco Gaido
The {{--}} operation on {{AttributeSet}} is quite expensive, especially where many columns are involved. {{ColumnPruning}} heavily relies on that operator and this affects its running time. There are 2 optimization which are possible:
- Improve {{--}} performance;
- Replace {{--}} with {{subsetOf}} when possible.
Moreover, when building {{AttributeSet}}s we often do unneeded operations. This also impacts other rules less significantly.
I'll provide more details about the performance improvement achievable in the PR.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org