turboFei commented on code in PR #3147:
URL: https://github.com/apache/celeborn/pull/3147#discussion_r2099189084
##########
common/src/main/scala/org/apache/celeborn/common/CelebornConf.scala:
##########
@@ -6033,6 +6034,14 @@ object CelebornConf extends Logging {
.booleanConf
.createWithDefault(false)
+ val PARTITION_CONNECTION_EXCEPTION_ENABLED: ConfigEntry[Boolean] =
+ buildConf("celeborn.client.partitionConnectionException.enabled")
+ .categories("client")
+ .version("0.6.0")
+ .doc("Whether to enable partition connection exception on failure.")
Review Comment:
"celeborn.client.flink.partitionConnectionException.enabled"
```
If enabled,
`org.apache.flink.runtime.io.network.partition.consumer.PartitionConnectionException`
would be thrown when RemoteBufferStreamReader finds that the current exception
is about connection failure,
then Flink can be aware of the lost Celeborn server side nodes and be able
to re-compute affected data.
```
cc @RexXiong
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
