[jira] [Issue Comment Deleted] (TEZ-2646) Add scheduling casual dependency for attempts

["Bikas Saha (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/TEZ-2646?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Bikas Saha updated TEZ-2646:
----------------------------
    Comment: was deleted

(was: {color:green}+1 overall{color}.  Here are the results of testing the latest attachment
  http://issues.apache.org/jira/secure/attachment/12748206/TEZ-2646.1.patch
  against master revision 4f66cb4.

    {color:green}+1 @author{color}.  The patch does not contain any @author tags.

    {color:green}+1 tests included{color}.  The patch appears to include 7 new or modified test files.

    {color:green}+1 javac{color}.  The applied patch does not increase the total number of javac compiler warnings.

    {color:green}+1 javadoc{color}.  There were no new javadoc warning messages.

    {color:green}+1 findbugs{color}.  The patch does not introduce any new Findbugs (version 3.0.1) warnings.

    {color:green}+1 release audit{color}.  The applied patch does not increase the total number of release audit warnings.

    {color:green}+1 core tests{color}.  The patch passed unit tests in .

Test results: https://builds.apache.org/job/PreCommit-TEZ-Build/946//testReport/
Console output: https://builds.apache.org/job/PreCommit-TEZ-Build/946//console

This message is automatically generated.)

> Add scheduling casual dependency for attempts
> ---------------------------------------------
>
>                 Key: TEZ-2646
>                 URL: https://issues.apache.org/jira/browse/TEZ-2646
>             Project: Apache Tez
>          Issue Type: Sub-task
>            Reporter: Bikas Saha
>            Assignee: Bikas Saha
>         Attachments: TEZ-2646.1.patch
>
>
> When a task gets scheduled then we dont know what caused it. Some possibilities are
> 1) initial scheduling by the vertex manager - causality determined by VM. E.g. dynamic partition pruning VM in Hive can point causality to the attempt that sent it the stats needed to complete the partition pruning logic.
> 2) re-scheduling due to own previous version failure - causality points to the previous version that just failed
> 3) re-scheduling because read error reported by consumer - causality points to the consumer attempt that reported the error and caused the scheduling.
> This causality relationship can be used to stitch together scheduling dependencies in the execution timeline of the DAG.



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