[
https://issues.apache.org/jira/browse/TEZ-3334?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15985532#comment-15985532
]
Kuhu Shukla commented on TEZ-3334:
----------------------------------
[~sseth],
bq. 1) The deletion setup in the AM along with config parameters
Does this point relate to the following patch review comments, or am I missing
something here?
{quote}
A) The config TEZ_AM_SHUFFLE_AUXILIARY_SERVICE_ID - Does this belong to
TezConfiguration or TezRuntimeConfiguration? (On a kind of related note: Is the
config per AM or per dag, when session mode is in use)
B) TEZ_AM_DAG_DELETE_ENABLED - The property is not really used. Could be
renamed to something like tez.dag.cleanup.after.dag.completion
C) TEZ_AM_DELETION_TRACKER_CLASS - Not sure why this is needed. Can
cleanupEnabled=true mean set up the default class. false=Don't set it up or
setup a NoOp implementation of the interface
{quote}
Appreciate it if you can shed some more light on it. Thanks!
> Tez Custom Shuffle Handler
> --------------------------
>
> Key: TEZ-3334
> URL: https://issues.apache.org/jira/browse/TEZ-3334
> Project: Apache Tez
> Issue Type: New Feature
> Reporter: Jonathan Eagles
> Attachments: TEZ-3334.1.patch
>
>
> For conditions where auto-parallelism is reduced (e.g. TEZ-3222), a custom
> shuffle handler could help reduce the number of fetches and could more
> efficiently fetch data. In particular if a reducer is fetching 100 pieces
> serially from the same mapper it could do this in one fetch call.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
