From 1aa549ba9839565274a12c52fa1075b424f138a6 Mon Sep 17 00:00:00 2001 From: Davies Liu Date: Fri, 26 Sep 2014 09:27:42 -0700 Subject: [SPARK-3478] [PySpark] Profile the Python tasks This patch add profiling support for PySpark, it will show the profiling results before the driver exits, here is one example: ``` ============================================================ Profile of RDD ============================================================ 5146507 function calls (5146487 primitive calls) in 71.094 seconds Ordered by: internal time, cumulative time ncalls tottime percall cumtime percall filename:lineno(function) 5144576 68.331 0.000 68.331 0.000 statcounter.py:44(merge) 20 2.735 0.137 71.071 3.554 statcounter.py:33(__init__) 20 0.017 0.001 0.017 0.001 {cPickle.dumps} 1024 0.003 0.000 0.003 0.000 t.py:16() 20 0.001 0.000 0.001 0.000 {reduce} 21 0.001 0.000 0.001 0.000 {cPickle.loads} 20 0.001 0.000 0.001 0.000 copy_reg.py:95(_slotnames) 41 0.001 0.000 0.001 0.000 serializers.py:461(read_int) 40 0.001 0.000 0.002 0.000 serializers.py:179(_batched) 62 0.000 0.000 0.000 0.000 {method 'read' of 'file' objects} 20 0.000 0.000 71.072 3.554 rdd.py:863() 20 0.000 0.000 0.001 0.000 serializers.py:198(load_stream) 40/20 0.000 0.000 71.072 3.554 rdd.py:2093(pipeline_func) 41 0.000 0.000 0.002 0.000 serializers.py:130(load_stream) 40 0.000 0.000 71.072 1.777 rdd.py:304(func) 20 0.000 0.000 71.094 3.555 worker.py:82(process) ``` Also, use can show profile result manually by `sc.show_profiles()` or dump it into disk by `sc.dump_profiles(path)`, such as ```python >>> sc._conf.set("spark.python.profile", "true") >>> rdd = sc.parallelize(range(100)).map(str) >>> rdd.count() 100 >>> sc.show_profiles() ============================================================ Profile of RDD ============================================================ 284 function calls (276 primitive calls) in 0.001 seconds Ordered by: internal time, cumulative time ncalls tottime percall cumtime percall filename:lineno(function) 4 0.000 0.000 0.000 0.000 serializers.py:198(load_stream) 4 0.000 0.000 0.000 0.000 {reduce} 12/4 0.000 0.000 0.001 0.000 rdd.py:2092(pipeline_func) 4 0.000 0.000 0.000 0.000 {cPickle.loads} 4 0.000 0.000 0.000 0.000 {cPickle.dumps} 104 0.000 0.000 0.000 0.000 rdd.py:852() 8 0.000 0.000 0.000 0.000 serializers.py:461(read_int) 12 0.000 0.000 0.000 0.000 rdd.py:303(func) ``` The profiling is disabled by default, can be enabled by "spark.python.profile=true". Also, users can dump the results into disks automatically for future analysis, by "spark.python.profile.dump=path_to_dump" Author: Davies Liu Closes #2351 from davies/profiler and squashes the following commits: 7ef2aa0 [Davies Liu] bugfix, add tests for show_profiles and dump_profiles() 2b0daf2 [Davies Liu] fix docs 7a56c24 [Davies Liu] bugfix cba9463 [Davies Liu] move show_profiles and dump_profiles to SparkContext fb9565b [Davies Liu] Merge branch 'master' of github.com:apache/spark into profiler 116d52a [Davies Liu] Merge branch 'master' of github.com:apache/spark into profiler 09d02c3 [Davies Liu] Merge branch 'master' into profiler c23865c [Davies Liu] Merge branch 'master' into profiler 15d6f18 [Davies Liu] add docs for two configs dadee1a [Davies Liu] add docs string and clear profiles after show or dump 4f8309d [Davies Liu] address comment, add tests 0a5b6eb [Davies Liu] fix Python UDF 4b20494 [Davies Liu] add profile for python --- python/pyspark/worker.py | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'python/pyspark/worker.py') diff --git a/python/pyspark/worker.py b/python/pyspark/worker.py index c1f6e3e4a1..8257dddfee 100644 --- a/python/pyspark/worker.py +++ b/python/pyspark/worker.py @@ -23,6 +23,8 @@ import sys import time import socket import traceback +import cProfile +import pstats from pyspark.accumulators import _accumulatorRegistry from pyspark.broadcast import Broadcast, _broadcastRegistry @@ -90,10 +92,21 @@ def main(infile, outfile): command = pickleSer._read_with_length(infile) if isinstance(command, Broadcast): command = pickleSer.loads(command.value) - (func, deserializer, serializer) = command + (func, stats, deserializer, serializer) = command init_time = time.time() - iterator = deserializer.load_stream(infile) - serializer.dump_stream(func(split_index, iterator), outfile) + + def process(): + iterator = deserializer.load_stream(infile) + serializer.dump_stream(func(split_index, iterator), outfile) + + if stats: + p = cProfile.Profile() + p.runcall(process) + st = pstats.Stats(p) + st.stream = None # make it picklable + stats.add(st.strip_dirs()) + else: + process() except Exception: try: write_int(SpecialLengths.PYTHON_EXCEPTION_THROWN, outfile) -- cgit v1.2.3