From 31d435ecfdc24a788a6e38f4e82767bc275a3283 Mon Sep 17 00:00:00 2001
From: KaiXinXiaoLei <huleilei1@huawei.com>
Date: Mon, 9 Feb 2015 20:58:58 -0800
Subject: [PATCH] Add a config option to print DAG.

Add a config option "spark.rddDebug.enable" to check whether to print DAG info. When "spark.rddDebug.enable" is true, it will print information about DAG in the log.

Author: KaiXinXiaoLei <huleilei1@huawei.com>

Closes #4257 from KaiXinXiaoLei/DAGprint and squashes the following commits:

d9fe42e [KaiXinXiaoLei] change  log info
c27ee76 [KaiXinXiaoLei] change log info
83c2b32 [KaiXinXiaoLei] change config option
adcb14f [KaiXinXiaoLei] change the file.
f4e7b9e [KaiXinXiaoLei] add a option to print DAG
---
 core/src/main/scala/org/apache/spark/SparkContext.scala | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala
index 71bdbc9b38..8d3c3d000a 100644
--- a/core/src/main/scala/org/apache/spark/SparkContext.scala
+++ b/core/src/main/scala/org/apache/spark/SparkContext.scala
@@ -1420,6 +1420,9 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli
     val callSite = getCallSite
     val cleanedFunc = clean(func)
     logInfo("Starting job: " + callSite.shortForm)
+    if (conf.getBoolean("spark.logLineage", false)) {
+      logInfo("RDD's recursive dependencies:\n" + rdd.toDebugString)
+    }
     dagScheduler.runJob(rdd, cleanedFunc, partitions, callSite, allowLocal,
       resultHandler, localProperties.get)
     progressBar.foreach(_.finishAll())
-- 
GitLab