[
https://issues.apache.org/jira/browse/FLINK-8458?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16381839#comment-16381839
]
ASF GitHub Bot commented on FLINK-8458:
---------------------------------------
Github user pnowojski commented on a diff in the pull request:
https://github.com/apache/flink/pull/5317#discussion_r171525131
--- Diff:
flink-core/src/main/java/org/apache/flink/configuration/TaskManagerOptions.java
---
@@ -269,15 +269,21 @@
public static final ConfigOption<Integer> NETWORK_BUFFERS_PER_CHANNEL =
key("taskmanager.network.memory.buffers-per-channel")
.defaultValue(2)
- .withDescription("Number of network buffers to use for
each outgoing/incoming channel (subpartition/input channel).");
+ .withDescription("Number of network buffers to use for
each outgoing/incoming channel (subpartition/input channel)." +
+ "In credit-based flow control mode, this
indicates how many credits are exclusive in each input channel. It should be" +
+ " configured at least 2 for good performance. 1
buffer is for receiving in-flight data in the subpartition and 1 buffer is" +
+ " for parallel serialization.");
/**
* Number of extra network buffers to use for each outgoing/incoming
gate (result partition/input gate).
*/
public static final ConfigOption<Integer>
NETWORK_EXTRA_BUFFERS_PER_GATE =
key("taskmanager.network.memory.floating-buffers-per-gate")
.defaultValue(8)
- .withDescription("Number of extra network buffers to
use for each outgoing/incoming gate (result partition/input gate).");
+ .withDescription("Number of extra network buffers to
use for each outgoing/incoming gate (result partition/input gate)." +
+ " In credit-based flow control mode, this
indicates how many floating credits are shared among all the input channels." +
+ " The floating buffers are distributed based on
backlog (real-time output buffers in the subpartition) feedback, and can" +
+ " help relieve back-pressure caused by
unbalanced data distribution among the subpartitions.");
--- End diff --
add: `This value should be increased in case of higher round trip times
between nodes and/or larger number of machines in the cluster.`?
> Add the switch for keeping both the old mode and the new credit-based mode
> --------------------------------------------------------------------------
>
> Key: FLINK-8458
> URL: https://issues.apache.org/jira/browse/FLINK-8458
> Project: Flink
> Issue Type: Sub-task
> Components: Network
> Reporter: zhijiang
> Assignee: zhijiang
> Priority: Major
> Fix For: 1.5.0
>
>
> After the whole feature of credit-based flow control is done, we should add a
> config parameter to switch on/off the new credit-based mode. To do so, we can
> roll back to the old network mode for any expected risks.
> The parameter is defined as
> {{taskmanager.network.credit-based-flow-control.enabled}} and the default
> value is true. This switch may be removed after next release.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
