[
https://issues.apache.org/jira/browse/IMPALA-10477?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Wenzhe Zhou updated IMPALA-10477:
---------------------------------
Description:
If an executor node notices that it is somehow unhealthy and repeatedly gets
failures during fragment instance startup, it should report its unhealthy state
to statestore so that the node could be removed from executor group and
coordinators would not schedule new tasks on the unhealthy node.
was:
If an executor node notices that it is somehow unhealthy and got repeated
fragment instance startup failures, it should report its unhealthy state to
statestore so that the node could be removed executor group and coordinator
would not schedule new tasks.
> Mark executor node as down if it repeatedly failed to startup fragment
> instance
> --------------------------------------------------------------------------------
>
> Key: IMPALA-10477
> URL: https://issues.apache.org/jira/browse/IMPALA-10477
> Project: IMPALA
> Issue Type: Sub-task
> Reporter: Wenzhe Zhou
> Assignee: Wenzhe Zhou
> Priority: Major
>
> If an executor node notices that it is somehow unhealthy and repeatedly gets
> failures during fragment instance startup, it should report its unhealthy
> state to statestore so that the node could be removed from executor group and
> coordinators would not schedule new tasks on the unhealthy node.
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
