[
https://issues.apache.org/jira/browse/FLINK-8360?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16322293#comment-16322293
]
ASF GitHub Bot commented on FLINK-8360:
---------------------------------------
Github user pnowojski commented on a diff in the pull request:
https://github.com/apache/flink/pull/5239#discussion_r160912998
--- Diff:
flink-runtime/src/main/java/org/apache/flink/runtime/taskexecutor/TaskExecutor.java
---
@@ -380,6 +390,20 @@ public void postStop() throws Exception {
ResultPartitionConsumableNotifier
resultPartitionConsumableNotifier =
jobManagerConnection.getResultPartitionConsumableNotifier();
PartitionProducerStateChecker partitionStateChecker =
jobManagerConnection.getPartitionStateChecker();
+ final TaskLocalStateStore localStateStore =
localStateStoresManager.localStateStoreForTask(
+ jobId,
+ taskInformation.getJobVertexId(),
+ tdd.getSubtaskIndex());
+
+ final JobManagerTaskRestore taskRestore =
tdd.getTaskRestore();
--- End diff --
nit: could you while you are at it and expand this abbreviated `tdd` name?
I am not sure how _test driven development_ could give me a `TaskRestore` :(
This can be done on top if you do not want to bother with pushing rename to
the bottom.
> Implement task-local state recovery
> -----------------------------------
>
> Key: FLINK-8360
> URL: https://issues.apache.org/jira/browse/FLINK-8360
> Project: Flink
> Issue Type: New Feature
> Components: State Backends, Checkpointing
> Reporter: Stefan Richter
> Assignee: Stefan Richter
> Fix For: 1.5.0
>
>
> This issue tracks the development of recovery from task-local state. The main
> idea is to have a secondary, local copy of the checkpointed state, while
> there is still a primary copy in DFS that we report to the checkpoint
> coordinator.
> Recovery can attempt to restore from the secondary local copy, if available,
> to save network bandwidth. This requires that the assignment from tasks to
> slots is as sticky is possible.
> For starters, we will implement this feature for all managed keyed states and
> can easily enhance it to all other state types (e.g. operator state) later.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
