You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Zhenhua Wang (JIRA)" <ji...@apache.org> on 2017/11/14 09:16:00 UTC
[jira] [Updated] (SPARK-22515) Estimation relation size based on
numRows * rowSize
[ https://issues.apache.org/jira/browse/SPARK-22515?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Zhenhua Wang updated SPARK-22515:
---------------------------------
Description: Currently, relation size is computed as the sum of file size, which is error-prone because storage format like parquet may have a much smaller file size compared to in-memory size. When we choose broadcast join based on file size, there's a risk of OOM. But if the number of rows is available in statistics, we can get a better estimation by `numRows * rowSize`, which helps to alleviate this problem.
> Estimation relation size based on numRows * rowSize
> ---------------------------------------------------
>
> Key: SPARK-22515
> URL: https://issues.apache.org/jira/browse/SPARK-22515
> Project: Spark
> Issue Type: Sub-task
> Components: SQL
> Affects Versions: 2.3.0
> Reporter: Zhenhua Wang
>
> Currently, relation size is computed as the sum of file size, which is error-prone because storage format like parquet may have a much smaller file size compared to in-memory size. When we choose broadcast join based on file size, there's a risk of OOM. But if the number of rows is available in statistics, we can get a better estimation by `numRows * rowSize`, which helps to alleviate this problem.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org