You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Yang Wang (JIRA)" <ji...@apache.org> on 2016/09/14 15:08:20 UTC
[jira] [Updated] (SPARK-17537) Improve performance for reading
parquet schema
[ https://issues.apache.org/jira/browse/SPARK-17537?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Yang Wang updated SPARK-17537:
------------------------------
Description: spark.read.parquet would issue a spark jobs to read parquet schema. When spark.sql.parquet.mergeSchema are set to false (the default value), there is often only one file to read, so there is no need to issue a spark job to do it. In this case, we can read it from driver directly instead of issuing a spark job. This could reduce the infer schema latency from several hundreds milliseconds to around around ten milliseconds in my environment. (was: spark.read.parquet would issue a spark jobs to read parquet schema. When spark.sql.parquet.mergeSchema are set to false (the default value), there is often only one file to read, so there is no need to issue a spark job to do it. In this case, we can read it from driver directly rather issuing a spark job. This could reduce the infer schema latency from several hundreds milliseconds to around around ten milliseconds in my environment.)
> Improve performance for reading parquet schema
> ----------------------------------------------
>
> Key: SPARK-17537
> URL: https://issues.apache.org/jira/browse/SPARK-17537
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Affects Versions: 1.6.2, 2.0.0
> Reporter: Yang Wang
> Priority: Minor
>
> spark.read.parquet would issue a spark jobs to read parquet schema. When spark.sql.parquet.mergeSchema are set to false (the default value), there is often only one file to read, so there is no need to issue a spark job to do it. In this case, we can read it from driver directly instead of issuing a spark job. This could reduce the infer schema latency from several hundreds milliseconds to around around ten milliseconds in my environment.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org