Python profile, show_profiles() and dump_profiles(), should throw an error with a better message

Author: HyukjinKwon

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()

python/pyspark/tests.py

@@ -1284,6 +1284,22 @@ 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