class PysparkFlameTest(unittest.TestCase):
def setUp(self):
self.dumpdir = tempfile.mkdtemp()
conf = SparkConf().set("spark.python.profile", "true")
self.sc = SparkContext('local[*]',
'test',
conf=conf,
profiler_cls=FlameProfiler,
environment={'pyspark_flame.interval': 0.25})
def tearDown(self):
self.sc.stop()
shutil.rmtree(self.dumpdir)
def test_pyspark_flame(self):
self.sc.parallelize(range(4)).map(wait_a_bit).sum()
self.sc.dump_profiles(self.dumpdir)
dumps = os.listdir(self.dumpdir)
self.assertEqual(1, len(dumps))
with open(os.path.join(self.dumpdir, dumps[0])) as dumpfile:
for line in dumpfile.readlines():
location, count = line.split(' ')
if 'pyspark_flame_test.py:wait_a_bit:11' in location:
count = int(count)
self.assertIn(count, range(70, 90))
return
else:
self.fail('No wait_a_bit profile line found')
def test_propagate_exception(self):
with self.assertRaises(Exception):
self.sc.parallelize(range(4)).map(crash).sum()
class ProfilerTests(PySparkTestCase):
def setUp(self):
self._old_sys_path = list(sys.path)
class_name = self.__class__.__name__
conf = SparkConf().set("spark.python.profile", "true")
self.sc = SparkContext('local[4]', class_name, conf=conf)
def test_profiler(self):
self.do_computation()
profilers = self.sc.profiler_collector.profilers
self.assertEqual(1, len(profilers))
id, profiler, _ = profilers[0]
stats = profiler.stats()
self.assertTrue(stats is not None)
width, stat_list = stats.get_print_list([])
func_names = [func_name for fname, n, func_name in stat_list]
self.assertTrue("heavy_foo" in func_names)
old_stdout = sys.stdout
sys.stdout = io = StringIO()
self.sc.show_profiles()
self.assertTrue("heavy_foo" in io.getvalue())
sys.stdout = old_stdout
d = tempfile.gettempdir()
self.sc.dump_profiles(d)
self.assertTrue("rdd_%d.pstats" % id in os.listdir(d))
def test_custom_profiler(self):
class TestCustomProfiler(BasicProfiler):
def show(self, id):
self.result = "Custom formatting"
self.sc.profiler_collector.profiler_cls = TestCustomProfiler
self.do_computation()
profilers = self.sc.profiler_collector.profilers
self.assertEqual(1, len(profilers))
_, profiler, _ = profilers[0]
self.assertTrue(isinstance(profiler, TestCustomProfiler))
self.sc.show_profiles()
self.assertEqual("Custom formatting", profiler.result)
def do_computation(self):
def heavy_foo(x):
for i in range(1 << 18):
x = 1
rdd = self.sc.parallelize(range(100))
rdd.foreach(heavy_foo)
class ProfilerTests(PySparkTestCase):
def setUp(self):
self._old_sys_path = list(sys.path)
class_name = self.__class__.__name__
conf = SparkConf().set("spark.python.profile", "true")
self.sc = SparkContext('local[4]', class_name, conf=conf)
def test_profiler(self):
self.do_computation()
profilers = self.sc.profiler_collector.profilers
self.assertEqual(1, len(profilers))
id, profiler, _ = profilers[0]
stats = profiler.stats()
self.assertTrue(stats is not None)
width, stat_list = stats.get_print_list([])
func_names = [func_name for fname, n, func_name in stat_list]
self.assertTrue("heavy_foo" in func_names)
old_stdout = sys.stdout
sys.stdout = io = StringIO()
self.sc.show_profiles()
self.assertTrue("heavy_foo" in io.getvalue())
sys.stdout = old_stdout
d = tempfile.gettempdir()
self.sc.dump_profiles(d)
self.assertTrue("rdd_%d.pstats" % id in os.listdir(d))
def test_custom_profiler(self):
class TestCustomProfiler(BasicProfiler):
def show(self, id):
self.result = "Custom formatting"
self.sc.profiler_collector.profiler_cls = TestCustomProfiler
self.do_computation()
profilers = self.sc.profiler_collector.profilers
self.assertEqual(1, len(profilers))
_, profiler, _ = profilers[0]
self.assertTrue(isinstance(profiler, TestCustomProfiler))
self.sc.show_profiles()
self.assertEqual("Custom formatting", profiler.result)
def do_computation(self):
def heavy_foo(x):
for i in range(1 << 18):
x = 1
rdd = self.sc.parallelize(range(100))
rdd.foreach(heavy_foo)
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()
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 UDFProfilerTests(unittest.TestCase):
def setUp(self):
self._old_sys_path = list(sys.path)
class_name = self.__class__.__name__
conf = SparkConf().set("spark.python.profile", "true")
self.sc = SparkContext("local[4]", class_name, conf=conf)
self.spark = SparkSession.builder._sparkContext(self.sc).getOrCreate()
def tearDown(self):
self.spark.stop()
sys.path = self._old_sys_path
def test_udf_profiler(self):
self.do_computation()
profilers = self.sc.profiler_collector.profilers
self.assertEqual(3, len(profilers))
old_stdout = sys.stdout
try:
sys.stdout = io = StringIO()
self.sc.show_profiles()
finally:
sys.stdout = old_stdout
d = tempfile.gettempdir()
self.sc.dump_profiles(d)
for i, udf_name in enumerate(["add1", "add2", "add1"]):
id, profiler, _ = profilers[i]
with self.subTest(id=id, udf_name=udf_name):
stats = profiler.stats()
self.assertTrue(stats is not None)
width, stat_list = stats.get_print_list([])
func_names = [func_name for fname, n, func_name in stat_list]
self.assertTrue(udf_name in func_names)
self.assertTrue(udf_name in io.getvalue())
self.assertTrue("udf_%d.pstats" % id in os.listdir(d))
def test_custom_udf_profiler(self):
class TestCustomProfiler(UDFBasicProfiler):
def show(self, id):
self.result = "Custom formatting"
self.sc.profiler_collector.udf_profiler_cls = TestCustomProfiler
self.do_computation()
profilers = self.sc.profiler_collector.profilers
self.assertEqual(3, len(profilers))
_, profiler, _ = profilers[0]
self.assertTrue(isinstance(profiler, TestCustomProfiler))
self.sc.show_profiles()
self.assertEqual("Custom formatting", profiler.result)
def do_computation(self):
@udf
def add1(x):
return x + 1
@udf
def add2(x):
return x + 2
df = self.spark.range(10)
df.select(add1("id"), add2("id"), add1("id")).collect()
from pyspark import SparkContext, SparkConf
import numpy as np
conf = SparkConf()
conf.set('master', 'spark://hadoop-maste:7077')
conf.set('spark.python.profile', 'true')
context = SparkContext(conf=conf)
rdd = context.parallelize(np.arange(10), 3)
print(rdd.collect())
print(context.show_profiles())
context.dump_profiles('/datas/profiles/')
context.stop()
import time
import random
from pyspark_flame import FlameProfiler
from pyspark import SparkConf, SparkContext
def multiply_inefficiently(x):
for i in range(1000):
time.sleep(0.0001 * random.random())
time.sleep(0.0001 * random.random())
return x * 2
conf = SparkConf().set("spark.python.profile", "true")#.set("spark.python.profile.dump", ".")
sc = SparkContext('local', 'test', conf=conf, profiler_cls=FlameProfiler, environment={'pyspark_flame.interval': 0.25})
sc.parallelize(range(1000)).map(multiply_inefficiently).take(10)
sc.show_profiles()
sc.dump_profiles('.')
sc.stop()
