[
https://issues.apache.org/jira/browse/FLINK-8360?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16366815#comment-16366815
]
ASF GitHub Bot commented on FLINK-8360:
---------------------------------------
Github user StefanRRichter commented on a diff in the pull request:
https://github.com/apache/flink/pull/5239#discussion_r168717401
--- Diff:
flink-runtime/src/test/java/org/apache/flink/runtime/state/TaskStateManagerImplTest.java
---
@@ -148,22 +150,22 @@ public void
testForwardingSubtaskLocalStateBaseDirFromLocalStateStore() throws I
taskLocalStateStore);
LocalRecoveryDirectoryProvider
directoryProviderFromTaskLocalStateStore =
-
taskLocalStateStore.createLocalRecoveryRootDirectoryProvider();
+
taskLocalStateStore.getLocalRecoveryRootDirectoryProvider();
LocalRecoveryDirectoryProvider
directoryProviderFromTaskStateManager =
taskStateManager.createLocalRecoveryRootDirectoryProvider();
for (int i = 0; i < 10; ++i) {
Assert.assertEquals(rootDirs[i %
rootDirs.length],
-
directoryProviderFromTaskLocalStateStore.nextRootDirectory());
+
directoryProviderFromTaskLocalStateStore.rootDirectory(i));
Assert.assertEquals(rootDirs[i %
rootDirs.length],
-
directoryProviderFromTaskStateManager.nextRootDirectory());
+
directoryProviderFromTaskStateManager.rootDirectory(i));
}
- Assert.assertEquals(
-
directoryProviderFromTaskLocalStateStore.getSubtaskSpecificPath(),
-
directoryProviderFromTaskStateManager.getSubtaskSpecificPath());
+// Assert.assertEquals(
+//
directoryProviderFromTaskLocalStateStore.getSubtaskSpecificPath(),
+//
directoryProviderFromTaskStateManager.getSubtaskSpecificPath());
--- End diff --
removed in later commit
> 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
> Priority: Major
> 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
(v7.6.3#76005)
