From 7c7266208a3be984ac1ce53747dc0c3640f4ecac Mon Sep 17 00:00:00 2001
From: hyukjinkwon <gurwls223@gmail.com>
Date: Mon, 18 Sep 2017 13:20:11 +0900
Subject: [PATCH] [SPARK-22043][PYTHON] Improves error message for
 show_profiles and dump_profiles

## What changes were proposed in this pull request?

This PR proposes to improve error message from:

```
>>> sc.show_profiles()
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File ".../spark/python/pyspark/context.py", line 1000, in show_profiles
    self.profiler_collector.show_profiles()
AttributeError: 'NoneType' object has no attribute 'show_profiles'
>>> sc.dump_profiles("/tmp/abc")
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File ".../spark/python/pyspark/context.py", line 1005, in dump_profiles
    self.profiler_collector.dump_profiles(path)
AttributeError: 'NoneType' object has no attribute 'dump_profiles'
```

to

```
>>> sc.show_profiles()
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File ".../spark/python/pyspark/context.py", line 1003, in show_profiles
    raise RuntimeError("'spark.python.profile' configuration must be set "
RuntimeError: 'spark.python.profile' configuration must be set to 'true' to enable Python profile.
>>> sc.dump_profiles("/tmp/abc")
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File ".../spark/python/pyspark/context.py", line 1012, in dump_profiles
    raise RuntimeError("'spark.python.profile' configuration must be set "
RuntimeError: 'spark.python.profile' configuration must be set to 'true' to enable Python profile.
```

## How was this patch tested?

Unit tests added in `python/pyspark/tests.py` and manual tests.

Author: hyukjinkwon <gurwls223@gmail.com>

Closes #19260 from HyukjinKwon/profile-errors.
---
 python/pyspark/context.py | 12 ++++++++++--
 python/pyspark/tests.py   | 16 ++++++++++++++++
 2 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/python/pyspark/context.py b/python/pyspark/context.py
index a7046043e0376..a33f6dcf31fc0 100644
--- a/python/pyspark/context.py
+++ b/python/pyspark/context.py
@@ -997,12 +997,20 @@ def runJob(self, rdd, partitionFunc, partitions=None, allowLocal=False):
 
     def show_profiles(self):
         """ Print the profile stats to stdout """
-        self.profiler_collector.show_profiles()
+        if self.profiler_collector is not None:
+            self.profiler_collector.show_profiles()
+        else:
+            raise RuntimeError("'spark.python.profile' configuration must be set "
+                               "to 'true' to enable Python profile.")
 
     def dump_profiles(self, path):
         """ Dump the profile stats into directory `path`
         """
-        self.profiler_collector.dump_profiles(path)
+        if self.profiler_collector is not None:
+            self.profiler_collector.dump_profiles(path)
+        else:
+            raise RuntimeError("'spark.python.profile' configuration must be set "
+                               "to 'true' to enable Python profile.")
 
     def getConf(self):
         conf = SparkConf()
diff --git a/python/pyspark/tests.py b/python/pyspark/tests.py
index 3c108ec92ccc9..da99872da2f0e 100644
--- a/python/pyspark/tests.py
+++ b/python/pyspark/tests.py
@@ -1296,6 +1296,22 @@ def heavy_foo(x):
         rdd.foreach(heavy_foo)
 
 
+class ProfilerTests2(unittest.TestCase):
+    def test_profiler_disabled(self):
+        sc = SparkContext(conf=SparkConf().set("spark.python.profile", "false"))
+        try:
+            self.assertRaisesRegexp(
+                RuntimeError,
+                "'spark.python.profile' configuration must be set",
+                lambda: sc.show_profiles())
+            self.assertRaisesRegexp(
+                RuntimeError,
+                "'spark.python.profile' configuration must be set",
+                lambda: sc.dump_profiles("/tmp/abc"))
+        finally:
+            sc.stop()
+
+
 class InputFormatTests(ReusedPySparkTestCase):
 
     @classmethod