You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@pig.apache.org by "Rohini Palaniswamy (JIRA)" <ji...@apache.org> on 2014/02/17 08:36:19 UTC
[jira] [Updated] (PIG-3766) Use ONE_TO_ONE edge and IdentityInOut
in skewed join intermediate vertex
[ https://issues.apache.org/jira/browse/PIG-3766?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Rohini Palaniswamy updated PIG-3766:
------------------------------------
Attachment: PIG-3766-1.patch
Changes done:
1) Removed the POLocalRearrange in SampleVertex and replaced it with a POValueOutTez for both orderby and skewedjoin. POValueOutTez takes multiple outputs. So got rid of the POSplit as well in skewed join sample vertex.
2) Replaced the POPackage+POLocalRearrange in the partition vertex of left table (vertex 3) with a POIdentityInOutTez moving the project in POLocalRearrange into the POLocalRearrange in vertex 1. Also made the edge 1-1 between vertex 1 and vertex 3.
> Use ONE_TO_ONE edge and IdentityInOut in skewed join intermediate vertex
> ------------------------------------------------------------------------
>
> Key: PIG-3766
> URL: https://issues.apache.org/jira/browse/PIG-3766
> Project: Pig
> Issue Type: Sub-task
> Components: tez
> Reporter: Rohini Palaniswamy
> Assignee: Rohini Palaniswamy
> Fix For: tez-branch
>
> Attachments: PIG-3766-1.patch
>
>
> From the first vertex (left table load) to the intermediate vertex that does the partitioning of the keys based on the SkewedPartitionerTez, use ONE_TO_ONE Tez edge and unsorted output and input instead of using a shuffle edge. Also replace the POPackage->POForEach->POLocalRearrange in intermediate vertex with POIdentityInOutTez.
--
This message was sent by Atlassian JIRA
(v6.1.5#6160)