hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Owen O'Malley (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-491) streaming jobs should allow programs that don't do any IO for a long time
Date Mon, 05 Feb 2007 21:03:06 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-491?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12470351
] 

Owen O'Malley commented on HADOOP-491:
--------------------------------------

This looks good so far, it just needs the default for streaming set. The logic here is that
streaming applications don't have an easy way of reporting to the framework that they are
making progress. So it is far too easy for them to be killed as being dead when they are just
working away. Clearly, disabling the timeout makes it easy to write applications that just
get stuck, but it seems better to allow applications to get stuck rather than killing productive
tasks.

> streaming jobs should allow programs that don't do any IO for a long time
> -------------------------------------------------------------------------
>
>                 Key: HADOOP-491
>                 URL: https://issues.apache.org/jira/browse/HADOOP-491
>             Project: Hadoop
>          Issue Type: New Feature
>          Components: contrib/streaming
>            Reporter: arkady borkovsky
>         Assigned To: Arun C Murthy
>             Fix For: 0.12.0
>
>         Attachments: HADOOP-491_20070205_1.patch, HADOOP-491_20070206_2.patch
>
>
> The jobtracker relies on task to send heartbeats  to know the tasks are still alive.
> There is a 600 seconds timeout preset.
> hadoop streaming also uses input to or output from the program it spawns to indicate
progress, sending appropriate heartbeats.
> Some spawned programs spend longer that 600 seconds without any output while being perfectly
healthy.
> It would be good to enhance the interface between hadoop streaming and the programs it
spawns to track a healthy program in the absense of output.
> There are certain dangers with this protocol: e.g. a task can run a separate thread that
does nothing but send "i'm alive" message.   This would be a user bug to abuse the API in
such way.  

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message