[
https://issues.apache.org/jira/browse/FLINK-8547?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16352284#comment-16352284
]
ASF GitHub Bot commented on FLINK-8547:
---------------------------------------
Github user pnowojski commented on a diff in the pull request:
https://github.com/apache/flink/pull/5400#discussion_r165930338
--- Diff:
flink-core/src/main/java/org/apache/flink/configuration/TaskManagerOptions.java
---
@@ -184,6 +184,18 @@
key("taskmanager.network.detailed-metrics")
.defaultValue(false);
+ /**
+ * Config parameter defining whether to spill data for channels with
barrier or not in exactly-once
+ * mode based on credit-based flow control.
+ *
+ * @deprecated Will be removed for Flink 1.6 when the old code will be
dropped in favour of
+ * credit-based flow control.
+ */
+ @Deprecated
+ public static final ConfigOption<Boolean>
EXACTLY_ONCE_BLOCKING_DATA_ENABLED =
+ key("taskmanager.exactly-once.blocking.data.enabled")
+ .defaultValue(false);
--- End diff --
I think we would like to enable it by default and leave this config option
just as a safety net in case of bugs/problems.
btw, shouldn't this be tightly coupled with a credit based flow switch?
> Implement CheckpointBarrierHandler not to spill data for exactly-once based
> on credit-based flow control
> --------------------------------------------------------------------------------------------------------
>
> Key: FLINK-8547
> URL: https://issues.apache.org/jira/browse/FLINK-8547
> Project: Flink
> Issue Type: Sub-task
> Components: Network
> Affects Versions: 1.5.0
> Reporter: zhijiang
> Assignee: zhijiang
> Priority: Major
>
> Currently in exactly-once mode, the {{BarrierBuffer}} would block inputs with
> barriers until all inputs have received the barrier for a given checkpoint.
> To avoid back-pressuring the input streams which may cause distributed
> deadlocks, the {{BarrierBuffer}} has to spill the data in disk files to
> recycle the buffers for blocked channels.
>
> Based on credit-based flow control, every channel has exclusive buffers, so
> it is no need to spill data for avoiding deadlock. Then we implement a new
> {{CheckpointBarrierHandler}} for only buffering the data for blocked channels
> for better performance.
>
> And this new {{CheckpointBarrierHandler}} can also be configured to use or
> not in order to rollback the original mode for unexpected risks.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
