[
https://issues.apache.org/jira/browse/KYLIN-5794?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17836097#comment-17836097
]
Zhimin Wu commented on KYLIN-5794:
----------------------------------
fixed by https://issues.apache.org/jira/browse/KYLIN-5846
> Add Spark parquet footer read cache
> -----------------------------------
>
> Key: KYLIN-5794
> URL: https://issues.apache.org/jira/browse/KYLIN-5794
> Project: Kylin
> Issue Type: Improvement
> Reporter: Zhimin Wu
> Priority: Major
>
> *Optimization Proposal*
> In Kylin, the index storage is in Parquet format. When querying, if Spark
> reads Parquet data, it needs to read the Footer information first. In cases
> where there are many columns, reading the Footer can consume a considerable
> amount of time. Therefore, caching the Footer information can improve query
> performance.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
