[
https://issues.apache.org/jira/browse/FLINK-7416?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16211028#comment-16211028
]
ASF GitHub Bot commented on FLINK-7416:
---------------------------------------
Github user pnowojski commented on a diff in the pull request:
https://github.com/apache/flink/pull/4533#discussion_r144244569
--- Diff:
flink-runtime/src/test/java/org/apache/flink/runtime/io/network/partition/consumer/RemoteInputChannelTest.java
---
@@ -378,32 +387,47 @@ public void testReleaseExclusiveBuffers() throws
Exception {
/**
* Tests {@link BufferPool#requestBuffer()}, verifying the remote input
channel tries to request
- * floating buffers once receiving the producer's backlog.
+ * floating buffers once receiving the producer's backlog, and then
notifies credit available after
+ * receiving floating buffers.
*/
@Test
public void testRequestFloatingBuffersOnBuffer() throws Exception {
+ // Config
+ final Tuple2<Integer, Integer> backoff = new Tuple2<>(0, 0);
+
// Setup
final BufferPool bufferPool = mock(BufferPool.class);
when(bufferPool.requestBuffer()).thenReturn(TestBufferFactory.createBuffer());
+ final PartitionRequestClient connClient =
mock(PartitionRequestClient.class);
--- End diff --
ditto?
> Implement Netty receiver outgoing pipeline for credit-based
> -----------------------------------------------------------
>
> Key: FLINK-7416
> URL: https://issues.apache.org/jira/browse/FLINK-7416
> Project: Flink
> Issue Type: Sub-task
> Components: Network
> Reporter: zhijiang
> Assignee: zhijiang
> Fix For: 1.4.0
>
>
> This is a part of work for credit-based network flow control.
> The related works are :
> * We define a new message called {{AddCredit}} to notify the incremental
> credit during data shuffle.
> * Whenever an {{InputChannel}}’s unannounced credit goes up from zero, the
> channel is enqueued in the pipeline.
> * Whenever the channel becomes writable, it takes the next {{InputChannel}}
> and sends its unannounced credit. The credit is reset to zero after each sent.
> * That way, messages are sent as often as the network has capacity and
> contain as much credit as available for the channel at that point in time.
> Otherwise, it would only add latency to the announcements and not increase
> throughput.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
