From e678b9f02a2936b35c95e91a5f0ff388b5720261 Mon Sep 17 00:00:00 2001
From: Shivaram Venkataraman <shivaram@cs.berkeley.edu>
Date: Thu, 16 Oct 2014 19:43:33 -0700
Subject: [PATCH] [SPARK-3973] Print call site information for broadcasts

Its hard to debug which broadcast variables refer to what in a big codebase. Printing call site information helps in debugging.

Author: Shivaram Venkataraman <shivaram@cs.berkeley.edu>

Closes #2829 from shivaram/spark-broadcast-print and squashes the following commits:

cd6dbdf [Shivaram Venkataraman] Print call site information for broadcasts
---
 core/src/main/scala/org/apache/spark/SparkContext.scala | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala
index 354116286c..dd3157990e 100644
--- a/core/src/main/scala/org/apache/spark/SparkContext.scala
+++ b/core/src/main/scala/org/apache/spark/SparkContext.scala
@@ -818,6 +818,8 @@ class SparkContext(config: SparkConf) extends Logging {
    */
   def broadcast[T: ClassTag](value: T): Broadcast[T] = {
     val bc = env.broadcastManager.newBroadcast[T](value, isLocal)
+    val callSite = getCallSite
+    logInfo("Created broadcast " + bc.id + " from " + callSite.shortForm)
     cleaner.foreach(_.registerBroadcastForCleanup(bc))
     bc
   }
-- 
GitLab