[
https://issues.apache.org/jira/browse/TEZ-4338?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
László Bodor updated TEZ-4338:
------------------------------
Summary: Tez should consider node information to realize OUTPUT_LOST as
early as possible - upstream(mapper) problems (was: Tez should consider node
information for computing failure fraction - upstream(mapper) problems)
> Tez should consider node information to realize OUTPUT_LOST as early as
> possible - upstream(mapper) problems
> ------------------------------------------------------------------------------------------------------------
>
> Key: TEZ-4338
> URL: https://issues.apache.org/jira/browse/TEZ-4338
> Project: Apache Tez
> Issue Type: Improvement
> Reporter: László Bodor
> Assignee: László Bodor
> Priority: Major
>
> Finally, I decided to split TEZ-4139 into 2 different tasks, because handling
> upstream problems doesn't need lots of changes to the tez event itself
> (downstream host).
> So, from TEZ-4139, this ticket is intended to handle downstream failures as:
> collect all reported upstream mapper task attempts for a vertex, and if it's
> beyond a certain amount for the same source(map) host, blame mapper task
> immediately => blame mapper task attempt as soon as possible if read error is
> likely because of upstream node failure (somewhat similar goal to TEZ-3910,
> but currently TEZ-3910 is about to give the power of failure downstream task
> completely to AM)
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
