[
https://issues.apache.org/jira/browse/FLINK-16069?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17038976#comment-17038976
]
Till Rohrmann commented on FLINK-16069:
---------------------------------------
Hi [~huwh], do you know what exactly is taking so long. Is the creation of the
{{TaskDeploymentDescriptors}}? If yes, is it the iteration over the input edges?
I think it is not as easy as moving the {{TaskDeploymentDescriptor}} creation
into a future because we are accessing the {{ExecutionGraph}} through the
passed result partitions. This means that in case of a concurrent recovery we
might have a race condition where we read state from an already reset
{{Execution}}, for example.
> Creation of TaskDeploymentDescriptor can block main thread for long time
> ------------------------------------------------------------------------
>
> Key: FLINK-16069
> URL: https://issues.apache.org/jira/browse/FLINK-16069
> Project: Flink
> Issue Type: Improvement
> Components: Runtime / Coordination
> Reporter: huweihua
> Priority: Major
>
> The deploy of tasks will take long time when we submit a high parallelism
> job. And Execution#deploy run in mainThread, so it will block JobMaster
> process other akka messages, such as Heartbeat. The creation of
> TaskDeploymentDescriptor take most of time. We can put the creation in future.
> For example, A job [source(8000)->sink(8000)], the total 16000 tasks from
> SCHEDULED to DEPLOYING took more than 1mins. This caused the heartbeat of
> TaskManager timeout and job never success.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
