reef-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Julia (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (REEF-1407) Catching exceptions in group communication are implemented incorrectly
Date Wed, 08 Jun 2016 07:19:20 GMT

    [ https://issues.apache.org/jira/browse/REEF-1407?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15320167#comment-15320167
] 

Julia commented on REEF-1407:
-----------------------------

Shall we let each task to send notification to the driver and waiting until all received or
we only need the notification message from master? If it is each task, then we might have
to introduce one more task sate. 

Close event is used to handle failure cases. Here we are talking about successful case. We
can leverage Task/Driver message to achieve it. We still need to consider the scenarios in
which during the notification, before task completion, some Evaluators or task failed. 

If mater task can communicate with  mappers without going through the driver, that would be
better.  

> Catching exceptions in group communication are implemented incorrectly
> ----------------------------------------------------------------------
>
>                 Key: REEF-1407
>                 URL: https://issues.apache.org/jira/browse/REEF-1407
>             Project: REEF
>          Issue Type: Bug
>            Reporter: Julia
>            Assignee: Dhruv Mahajan
>              Labels: FT
>
> Currently when a task fails, other tasks in the group are stuck in reading data by a
blocking call. We should be able to try and throw an exception and propagate the exception
to Task so that the task can handle it in a proper way. 



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message