[
https://issues.apache.org/jira/browse/TEZ-3274?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15306096#comment-15306096
]
Rohini Palaniswamy commented on TEZ-3274:
-----------------------------------------
bq. Since these tasks also read data from HDFS why would be not want them to
start asap if there is spare capacity.
In the particular issue we had, the other input it is waiting on is not
available for almost two hours as that is from a longer pipeline of the DAG. In
that case the RootInputInitializer vertex just spins idly for the 2 hours. And
since it is 6G containers, it consumes a lot of resources.
> Vertex with MRInput and shuffle input does not respect slow start
> -----------------------------------------------------------------
>
> Key: TEZ-3274
> URL: https://issues.apache.org/jira/browse/TEZ-3274
> Project: Apache Tez
> Issue Type: Bug
> Reporter: Jonathan Eagles
>
> Vertices with shuffle input and MRInput choose RootInputVertexManager (and
> not ShuffleVertexManager) and start containers and tasks immediately. In this
> scenario, resources can be wasted since they do not respect
> tez.shuffle-vertex-manager.min-src-fraction
> tez.shuffle-vertex-manager.max-src-fraction.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
