[
https://issues.apache.org/jira/browse/PIG-3856?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14296432#comment-14296432
]
Jeff Zhang commented on PIG-3856:
---------------------------------
[~rohini] Quick go through your patch, and have 2 questions :
* Skew join also is impacted (TEZC-Union-6) Is this expected ?
* The new DAG for TEZ-Union-4 is as following :
{code}
v1
/ \
/ \
v2 v3
\ /
\ /
v4
{code}
But I think v4 is not necessary, just group v2 and v3 together as one vertex
group should be enough.
> UnionOptimizer in Tez should optimize the case of replicated join
> -----------------------------------------------------------------
>
> Key: PIG-3856
> URL: https://issues.apache.org/jira/browse/PIG-3856
> Project: Pig
> Issue Type: Sub-task
> Components: tez
> Reporter: Rohini Palaniswamy
> Attachments: PIG-3856-1.patch
>
>
> Replicate join input that was broadcast to union vertex now needs to be
> broadcast to all the union predecessors. So we need to
> - Create edges from the Replicate join input to all the union predecessors
> - Change replicate join input to write to multiple outputs.
> This can be further optimized by using a shared edge which is yet to be
> implemented in Tez (TEZ-391)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
