[
https://issues.apache.org/jira/browse/FLINK-11815?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17219617#comment-17219617
]
Matthias commented on FLINK-11815:
----------------------------------
[~pnowojski] [~trohrmann] Does this issue still need to be kept open
considering that the (only?) subtask is solved? It looks like it is idling for
quite some time...
> Support execution with static resources (Flip-6): E.g. spreading tasks across
> available set of TMs
> --------------------------------------------------------------------------------------------------
>
> Key: FLINK-11815
> URL: https://issues.apache.org/jira/browse/FLINK-11815
> Project: Flink
> Issue Type: Improvement
> Components: Runtime / Coordination
> Affects Versions: 1.6.4, 1.7.2, 1.8.0
> Reporter: Piotr Nowojski
> Priority: Major
>
> FLIP-6 code path changed how tasks are distributed across the cluster which
> is causing problems in some scenarios. This issue intends to improve this.
> Known issues:
> 1. key groups are currently assigned randomly, ignoring their size.
> Previously larger key groups were evenly spread around the available task
> managers
> 2. if task slots are registered before slot request, the code have a tendency
> to group requests together on the same machine because we are using a
> LinkedHashMap
> 3. ???
> CC [[email protected]]
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
