pnowojski commented on a change in pull request #11541: [FLINK-15416][network]
add task manager netty client retry mechenism
URL: https://github.com/apache/flink/pull/11541#discussion_r400970930
##########
File path:
flink-runtime/src/main/java/org/apache/flink/runtime/io/network/netty/PartitionRequestClientFactory.java
##########
@@ -81,14 +92,36 @@ NettyPartitionRequestClient
createPartitionRequestClient(ConnectionID connection
Object old = clients.putIfAbsent(connectionId,
connectingChannel);
if (old == null) {
-
nettyClient.connect(connectionId.getAddress()).addListener(connectingChannel);
-
- client =
connectingChannel.waitForChannel();
-
- clients.replace(connectionId,
connectingChannel, client);
+ int count = 0;
+ ChannelException exception = null;
+ do {
+ try {
+ exception = null;
+ connectingChannel.error
= null;
+ LOG.info("Connecting to
{} at {} attempt", connectionId.getAddress(), count);
+
nettyClient.connect(connectionId.getAddress()).addListener(connectingChannel);
+
+ client =
connectingChannel.waitForChannel();
+
+
clients.replace(connectionId, connectingChannel, client);
+ } catch (ChannelException e) {
+ LOG.error("Failed {}
times to connect to {}", count, connectionId.getAddress(), e);
+ exception = e;
+ }
+ count++;
+ } while (count <= retryNumber);
+
+ if (exception != null) {
+ throw exception;
+ }
}
else if (old instanceof ConnectingChannel) {
- client = ((ConnectingChannel)
old).waitForChannel();
+
+ try {
+ client = ((ConnectingChannel)
old).waitForChannel();
+ } catch (IOException e) {
+ LOG.info("Continue to
waitForChannel until the original thread has completed or failed");
+ }
Review comment:
What do you mean by this change/log message?
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
