You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Michael Armbrust (JIRA)" <ji...@apache.org> on 2015/12/21 22:48:46 UTC

[jira] [Resolved] (SPARK-12374) Improve performance of Range APIs via adding logical/physical operators

     [ https://issues.apache.org/jira/browse/SPARK-12374?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Michael Armbrust resolved SPARK-12374.
--------------------------------------
       Resolution: Fixed
    Fix Version/s: 2.0.0

Issue resolved by pull request 10335
[https://github.com/apache/spark/pull/10335]

> Improve performance of Range APIs via adding logical/physical operators
> -----------------------------------------------------------------------
>
>                 Key: SPARK-12374
>                 URL: https://issues.apache.org/jira/browse/SPARK-12374
>             Project: Spark
>          Issue Type: Improvement
>          Components: SQL
>    Affects Versions: 1.6.0
>            Reporter: Xiao Li
>            Assignee: Apache Spark
>            Priority: Critical
>             Fix For: 2.0.0
>
>
> Creating an actual logical/physical operator for range for matching the performance of RDD Range APIs. 
> Compared with the old Range API, the new version is 3 times faster than the old version. 
> {code}
> scala> val startTime = System.currentTimeMillis; sqlContext.oldRange(0, 1000000000, 1, 15).count(); val endTime = System.currentTimeMillis; val start = new Timestamp(startTime); val end = new Timestamp(endTime); val elapsed = (endTime - startTime)/ 1000.0
> startTime: Long = 1450416394240                                                 
> endTime: Long = 1450416421199
> start: java.sql.Timestamp = 2015-12-17 21:26:34.24
> end: java.sql.Timestamp = 2015-12-17 21:27:01.199
> elapsed: Double = 26.959
> {code}
> {code}
> scala> val startTime = System.currentTimeMillis; sqlContext.range(0, 1000000000, 1, 15).count(); val endTime = System.currentTimeMillis; val start = new Timestamp(startTime); val end = new Timestamp(endTime); val elapsed = (endTime - startTime)/ 1000.0
> startTime: Long = 1450416360107                                                 
> endTime: Long = 1450416368590
> start: java.sql.Timestamp = 2015-12-17 21:26:00.107
> end: java.sql.Timestamp = 2015-12-17 21:26:08.59
> elapsed: Double = 8.483
> {code}



--
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