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

Posted to issues@carbondata.apache.org by "Weizhong (JIRA)" <ji...@apache.org> on 2017/03/29 08:25:41 UTC

[jira] [Created] (CARBONDATA-830) Incorrect schedule for NewCarbonDataLoadRDD

Weizhong created CARBONDATA-830:
-----------------------------------

             Summary: Incorrect schedule for NewCarbonDataLoadRDD
                 Key: CARBONDATA-830
                 URL: https://issues.apache.org/jira/browse/CARBONDATA-830
             Project: CarbonData
          Issue Type: Bug
          Components: spark-integration
    Affects Versions: 1.0.0-incubating
         Environment: Spark 2.1 + Carbon 1.0.0
            Reporter: Weizhong
            Assignee: Weizhong
            Priority: Minor


Currently NewCarbonDataLoadRDD's getPreferredLocations will return all locs rather than 1, then on Spark may pick the same node for two tasks, so one node is getting over loaded with the task and one has no task to do, and impacting the performance despite of any failure.



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)