You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@celeborn.apache.org by zh...@apache.org on 2023/06/21 07:16:38 UTC
[incubator-celeborn] branch main updated: [CELEBORN-704] Print host and port on starting Netty RPC Server
This is an automated email from the ASF dual-hosted git repository.
zhouky pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-celeborn.git
The following commit(s) were added to refs/heads/main by this push:
new 819440755 [CELEBORN-704] Print host and port on starting Netty RPC Server
819440755 is described below
commit 8194407558976f53ab33a6668bfbab1544c80119
Author: Cheng Pan <ch...@apache.org>
AuthorDate: Wed Jun 21 15:16:30 2023 +0800
[CELEBORN-704] Print host and port on starting Netty RPC Server
### What changes were proposed in this pull request?
Print host and port on starting Netty RPC Server
### Why are the changes needed?
Sometimes, the Master/Worker may fail on bootstrap because `BindException: Cannot assign requested address`, but there is no clue which addresses it tried.
```
2023-06-21 14:28:12 [INFO] [main] org.apache.celeborn.service.deploy.worker.Worker#51 - Metrics system enabled.
2023-06-21 14:28:12 [ERROR] [main] org.apache.celeborn.service.deploy.worker.Worker#80 - Initialize worker failed.
java.net.BindException: Cannot assign requested address
at sun.nio.ch.Net.bind0(Native Method) ~[?:1.8.0_372]
at sun.nio.ch.Net.bind(Net.java:461) ~[?:1.8.0_372]
at sun.nio.ch.Net.bind(Net.java:453) ~[?:1.8.0_372]
at sun.nio.ch.ServerSocketChannelImpl.bind(ServerSocketChannelImpl.java:222) ~[?:1.8.0_372]
at io.netty.channel.socket.nio.NioServerSocketChannel.doBind(NioServerSocketChannel.java:141) ~[netty-transport-4.1.93.Final.jar:4.1.93.Final]
at io.netty.channel.AbstractChannel$AbstractUnsafe.bind(AbstractChannel.java:562) ~[netty-transport-4.1.93.Final.jar:4.1.93.Final]
at io.netty.channel.DefaultChannelPipeline$HeadContext.bind(DefaultChannelPipeline.java:1334) ~[netty-transport-4.1.93.Final.jar:4.1.93.Final]
at io.netty.channel.AbstractChannelHandlerContext.invokeBind(AbstractChannelHandlerContext.java:600) ~[netty-transport-4.1.93.Final.jar:4.1.93.Final]
at io.netty.channel.AbstractChannelHandlerContext.bind(AbstractChannelHandlerContext.java:579) ~[netty-transport-4.1.93.Final.jar:4.1.93.Final]
at io.netty.handler.logging.LoggingHandler.bind(LoggingHandler.java:230) ~[netty-handler-4.1.93.Final.jar:4.1.93.Final]
at io.netty.channel.AbstractChannelHandlerContext.invokeBind(AbstractChannelHandlerContext.java:602) ~[netty-transport-4.1.93.Final.jar:4.1.93.Final]
at io.netty.channel.AbstractChannelHandlerContext.bind(AbstractChannelHandlerContext.java:579) ~[netty-transport-4.1.93.Final.jar:4.1.93.Final]
at io.netty.channel.DefaultChannelPipeline.bind(DefaultChannelPipeline.java:973) ~[netty-transport-4.1.93.Final.jar:4.1.93.Final]
at io.netty.channel.AbstractChannel.bind(AbstractChannel.java:260) ~[netty-transport-4.1.93.Final.jar:4.1.93.Final]
at io.netty.bootstrap.AbstractBootstrap$2.run(AbstractBootstrap.java:356) ~[netty-transport-4.1.93.Final.jar:4.1.93.Final]
at io.netty.util.concurrent.AbstractEventExecutor.runTask(AbstractEventExecutor.java:174) ~[netty-common-4.1.93.Final.jar:4.1.93.Final]
at io.netty.util.concurrent.AbstractEventExecutor.safeExecute(AbstractEventExecutor.java:167) ~[netty-common-4.1.93.Final.jar:4.1.93.Final]
at io.netty.util.concurrent.SingleThreadEventExecutor.runAllTasks(SingleThreadEventExecutor.java:470) ~[netty-common-4.1.93.Final.jar:4.1.93.Final]
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:569) ~[netty-transport-4.1.93.Final.jar:4.1.93.Final]
at io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) ~[netty-common-4.1.93.Final.jar:4.1.93.Final]
at io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) ~[netty-common-4.1.93.Final.jar:4.1.93.Final]
at io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) ~[netty-common-4.1.93.Final.jar:4.1.93.Final]
at java.lang.Thread.run(Thread.java:750) ~[?:1.8.0_372]
```
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Manually review.
Closes #1614 from pan3793/CELEBORN-704.
Authored-by: Cheng Pan <ch...@apache.org>
Signed-off-by: zky.zhoukeyong <zk...@alibaba-inc.com>
---
.../main/scala/org/apache/celeborn/common/rpc/netty/NettyRpcEnv.scala | 2 ++
1 file changed, 2 insertions(+)
diff --git a/common/src/main/scala/org/apache/celeborn/common/rpc/netty/NettyRpcEnv.scala b/common/src/main/scala/org/apache/celeborn/common/rpc/netty/NettyRpcEnv.scala
index 1efeb2cbe..6d0eb2bf6 100644
--- a/common/src/main/scala/org/apache/celeborn/common/rpc/netty/NettyRpcEnv.scala
+++ b/common/src/main/scala/org/apache/celeborn/common/rpc/netty/NettyRpcEnv.scala
@@ -355,6 +355,8 @@ private[celeborn] class NettyRpcEnvFactory extends RpcEnvFactory with Logging {
config.advertiseAddress,
config.numUsableCores)
val startNettyRpcEnv: Int => (NettyRpcEnv, Int) = { actualPort =>
+ logInfo(s"Starting RPC Server [${config.name}] on ${config.bindAddress}:$actualPort " +
+ s"with advisor endpoint ${config.advertiseAddress}:$actualPort")
nettyEnv.startServer(config.bindAddress, actualPort)
(nettyEnv, nettyEnv.address.port)
}