Updated: (HADOOP-654) jobs fail with some hardware/system failures on a small number of nodes

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view
|

Updated: (HADOOP-654) jobs fail with some hardware/system failures on a small number of nodes

Hudson (Jira)

     [ https://issues.apache.org/jira/browse/HADOOP-654?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Doug Cutting updated HADOOP-654:
--------------------------------

    Resolution: Fixed
        Status: Resolved  (was: Patch Available)

I just committed this.  Thanks, Arun!

> jobs fail with some hardware/system failures on a small number of nodes
> -----------------------------------------------------------------------
>
>                 Key: HADOOP-654
>                 URL: https://issues.apache.org/jira/browse/HADOOP-654
>             Project: Hadoop
>          Issue Type: Bug
>          Components: mapred
>    Affects Versions: 0.7.2
>            Reporter: Yoram Arnon
>         Assigned To: Arun C Murthy
>            Priority: Minor
>             Fix For: 0.12.0
>
>         Attachments: HADOOP-654_20070208_1.patch, HADOOP-654_20070209_2.patch, HADOOP-654_20070220_3.patch, HADOOP-654_20070221_4.patch
>
>
> occasionally, such as when the OS is out of some resource, a node fails only partly. The node is up and running, the task tracker is running and sending heartbeats, but every task fails because the tasktracker can't fork tasks or something.
> In these cases, that task tracker keeps getting assigned tasks to execute, and they all fail.
> A couple of nodes like that and jobs start failing badly.
> The job tracker should avoid assigning tasks to tasktrackers that are misbehaving.
> simple approach: avoid tasktrackers that report many more failures than average (say 3X). Simply use the info sent by the TT.
> better but harder: track TT failures over time and:
>  1. avoid those that exhibit a high failure *rate*
>  2. tell them to shut down

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