(celeborn) branch main updated: [MINOR] Refine the log for fetch failure and rpc metrics dump

[nicholasjiang]

This is an automated email from the ASF dual-hosted git repository.

nicholasjiang pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/celeborn.git


The following commit(s) were added to refs/heads/main by this push:
     new 6f5ad2dde [MINOR] Refine the log for fetch failure and rpc metrics dump
6f5ad2dde is described below

commit 6f5ad2dde891263d4f84874361a3b957b08ede50
Author: Wang, Fei <fwan...@ebay.com>
AuthorDate: Mon Mar 10 10:56:53 2025 +0800

    [MINOR] Refine the log for fetch failure and rpc metrics dump
    
    ### What changes were proposed in this pull request?
    Minor change for the log, to make the fetch failure message and rpc metrics 
dump much clear.
    
    ### Why are the changes needed?
    As title.
    
    ### Does this PR introduce _any_ user-facing change?
    
    No.
    
    ### How was this patch tested?
    
    GA.
    
    Closes #3136 from turboFei/log_shuffle.
    
    Authored-by: Wang, Fei <fwan...@ebay.com>
    Signed-off-by: SteNicholas <programg...@163.com>
---
 .../main/scala/org/apache/spark/celeborn/ExceptionMakerHelper.scala   | 2 +-
 .../main/scala/org/apache/celeborn/common/rpc/RpcMetricsTracker.scala | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git 
a/client-spark/spark-2/src/main/scala/org/apache/spark/celeborn/ExceptionMakerHelper.scala
 
b/client-spark/spark-2/src/main/scala/org/apache/spark/celeborn/ExceptionMakerHelper.scala
index 6456f3f44..8e4e511b1 100644
--- 
a/client-spark/spark-2/src/main/scala/org/apache/spark/celeborn/ExceptionMakerHelper.scala
+++ 
b/client-spark/spark-2/src/main/scala/org/apache/spark/celeborn/ExceptionMakerHelper.scala
@@ -23,7 +23,7 @@ import org.apache.celeborn.common.util.ExceptionMaker
 
 object ExceptionMakerHelper {
 
-  val FETCH_FAILURE_ERROR_MSG = "Celeborn FetchFailure with shuffle id "
+  val FETCH_FAILURE_ERROR_MSG = "Celeborn FetchFailure with 
appShuffleId/shuffleId: "
 
   val SHUFFLE_FETCH_FAILURE_EXCEPTION_MAKER = new ExceptionMaker() {
     override def makeFetchFailureException(
diff --git 
a/common/src/main/scala/org/apache/celeborn/common/rpc/RpcMetricsTracker.scala 
b/common/src/main/scala/org/apache/celeborn/common/rpc/RpcMetricsTracker.scala
index 5774b7a99..f9fffe306 100644
--- 
a/common/src/main/scala/org/apache/celeborn/common/rpc/RpcMetricsTracker.scala
+++ 
b/common/src/main/scala/org/apache/celeborn/common/rpc/RpcMetricsTracker.scala
@@ -86,7 +86,7 @@ private[celeborn] class RpcMetricsTracker(
       if (slowRpcInterval < 0 || System.currentTimeMillis() - lastLogTime > 
slowRpcInterval &&
         lastSlowLogTime.compareAndSet(lastLogTime, 
System.currentTimeMillis())) {
         logWarning(
-          s"slow rpc detected: currentQueueSize = ${queueLengthFunc()}, 
queueTime=$queueTime processTime=$processTime message=$message")
+          s"slow rpc detected: currentQueueSize = ${queueLengthFunc()}, 
queueTime=$queueTime(ns) processTime=$processTime(ns) message=$message")
       }
 
       val lastTime = lastDumpTime.get
@@ -144,7 +144,7 @@ private[celeborn] class RpcMetricsTracker(
       return
 
     val builder = new StringBuilder();
-    builder.append(s"RPC statistics for $name").append("\n")
+    builder.append(s"RPC statistics for $name (time unit: ns)").append("\n")
     builder.append(s"current queue size = ${queueLengthFunc()}").append("\n")
     builder.append(s"max queue length = ${maxQueueLength.get()}").append("\n")
     histogramMap.entrySet.asScala.foreach(entry => {