[ https://issues.apache.org/jira/browse/FLINK-7213?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16106672#comment-16106672 ]
ASF GitHub Bot commented on FLINK-7213: --------------------------------------- Github user StefanRRichter commented on the issue: https://github.com/apache/flink/pull/4353 BTW, one alternative I was once considering for the scale down case is merging state handles that are backed by different physical files in one logical state handle, using something based on `MultiStreamStateHandle`. That would require minor changes in how the backends currently iterate the handles and some calculation of virtual offsets near the `StateAssignmentOperation`, mapping the old physical file offsets to the new logical offsets in the stream that gives a consecutive logical view over the files. Then, the whole code would never again deal with this detail. Wonder if this is worth the effort? > Introduce state management by OperatorID in TaskManager > ------------------------------------------------------- > > Key: FLINK-7213 > URL: https://issues.apache.org/jira/browse/FLINK-7213 > Project: Flink > Issue Type: Improvement > Components: State Backends, Checkpointing > Affects Versions: 1.4.0 > Reporter: Stefan Richter > Assignee: Stefan Richter > > Flink-5892 introduced the job manager / checkpoint coordinator part of > managing state on the operator level instead of the task level by introducing > explicit operator_id -> state mappings. However, this explicit mapping was > not introduced in the task manager side, so the explicit mapping is still > converted into a mapping that suits the implicit operator chain order. > We should also introduce explicit operator ids to state management on the > task manager. -- This message was sent by Atlassian JIRA (v6.4.14#64029)