[
https://issues.apache.org/jira/browse/TEZ-3708?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16005947#comment-16005947
]
Zhiyuan Yang commented on TEZ-3708:
-----------------------------------
Upload new patch to fix test failure and address [~sseth] comments.
bq. I think this needs to be made configurable. -1 for the default, otherwise a
range between 0.0 and 1.0
A new config knob has been added so that user can specify percentage of task
completion before auto grouping.
bq. TestFairCartesianProductVertexManager - think some more unit tests are
required to exercise corner cases with estimation, etc.
More test has been added to address varies corner cases.
bq. RoundRobinPartitioner - Any concerns with Integer overflow?
Integer overflow can cause problem. Fixed in new patch.
> Improve parallelism and auto grouping of unpartitioned cartesian product
> ------------------------------------------------------------------------
>
> Key: TEZ-3708
> URL: https://issues.apache.org/jira/browse/TEZ-3708
> Project: Apache Tez
> Issue Type: Sub-task
> Reporter: Zhiyuan Yang
> Assignee: Zhiyuan Yang
> Attachments: TEZ-3708.1.patch, TEZ-3708.2.patch, TEZ-3708.3.patch,
> TEZ-3708.4.patch
>
>
> Current unpartitioned cartesian product has a few limitations
> 1. parallelism can be not enough in case of large split and small # src task
> 2. parallelism can be too much in in case of large # src task
> 3. workload is not ideally distributed across the worker. Even with auto
> grouping, grouping by size may not be accurate because same size can means
> different #record and different cartesian product ops.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
