[
https://issues.apache.org/jira/browse/FLINK-8523?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16346480#comment-16346480
]
ASF GitHub Bot commented on FLINK-8523:
---------------------------------------
Github user zhijiangW commented on a diff in the pull request:
https://github.com/apache/flink/pull/5381#discussion_r164990652
--- Diff:
flink-runtime/src/main/java/org/apache/flink/runtime/io/network/partition/consumer/UnionInputGate.java
---
@@ -138,6 +148,24 @@ public void requestPartitions() throws IOException,
InterruptedException {
}
}
+ @Override
+ public void blockInputChannel(int channelIndex) {
+ InputGate inputGate = indexToInputGateMap.get(channelIndex);
+ if (inputGate == null) {
+ throw new IllegalStateException("Could not find input
gate from the channel index " + channelIndex);
+ }
+
+ int indexOffset = inputGateToIndexOffsetMap.get(inputGate);
+ inputGate.blockInputChannel(channelIndex - indexOffset);
--- End diff --
alright
> Stop assigning floating buffers for blocked input channels in exactly-once
> mode
> -------------------------------------------------------------------------------
>
> Key: FLINK-8523
> URL: https://issues.apache.org/jira/browse/FLINK-8523
> Project: Flink
> Issue Type: Sub-task
> Components: Network
> Affects Versions: 1.5.0
> Reporter: zhijiang
> Assignee: zhijiang
> Priority: Major
>
> In exactly-once mode, the input channel is set blocked state when reading
> barrier from it. And the blocked state will be released after barrier
> alignment or cancelled.
>
> In credit-based network flow control, we should avoid assigning floating
> buffers for blocked input channels because the buffers after barrier will not
> be processed by operator until alignment.
> To do so, we can fully make use of floating buffers and speed up barrier
> alignment in some extent.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
