You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@spark.apache.org by "weDataSphere (JIRA)" <ji...@apache.org> on 2019/05/01 12:03:00 UTC

[jira] [Created] (SPARK-27615) Merge small files in the read stage

weDataSphere created SPARK-27615:
------------------------------------

             Summary: Merge small files in the read stage
                 Key: SPARK-27615
                 URL: https://issues.apache.org/jira/browse/SPARK-27615
             Project: Spark
          Issue Type: New Feature
          Components: Spark Core
    Affects Versions: 2.4.0
            Reporter: weDataSphere


When Spark reads file paths to form RDDs, the more files there are, the more partitions there will be. RDD partition can improve computing speed to a certain extent, but too much parity will lead to too much Task scheduling speed reduction, and generate more files.

We can reduce the number of partitions by judging whether a file can be merged during Spark reading and, if so, merged reading.



--
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