04e44b37cc
This PR update PySpark to support Python 3 (tested with 3.4). Known issue: unpickle array from Pyrolite is broken in Python 3, those tests are skipped. TODO: ec2/spark-ec2.py is not fully tested with python3. Author: Davies Liu <davies@databricks.com> Author: twneale <twneale@gmail.com> Author: Josh Rosen <joshrosen@databricks.com> Closes #5173 from davies/python3 and squashes the following commits: d7d6323 [Davies Liu] fix tests 6c52a98 [Davies Liu] fix mllib test 99e334f [Davies Liu] update timeout b716610 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 cafd5ec [Davies Liu] adddress comments from @mengxr bf225d7 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 179fc8d [Davies Liu] tuning flaky tests 8c8b957 [Davies Liu] fix ResourceWarning in Python 3 5c57c95 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 4006829 [Davies Liu] fix test 2fc0066 [Davies Liu] add python3 path 71535e9 [Davies Liu] fix xrange and divide 5a55ab4 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 125f12c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 ed498c8 [Davies Liu] fix compatibility with python 3 820e649 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 e8ce8c9 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 ad7c374 [Davies Liu] fix mllib test and warning ef1fc2f [Davies Liu] fix tests 4eee14a [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 20112ff [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 59bb492 [Davies Liu] fix tests 1da268c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 ca0fdd3 [Davies Liu] fix code style 9563a15 [Davies Liu] add imap back for python 2 0b1ec04 [Davies Liu] make python examples work with Python 3 d2fd566 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 a716d34 [Davies Liu] test with python 3.4 f1700e8 [Davies Liu] fix test in python3 671b1db [Davies Liu] fix test in python3 692ff47 [Davies Liu] fix flaky test 7b9699f [Davies Liu] invalidate import cache for Python 3.3+ 9c58497 [Davies Liu] fix kill worker 309bfbf [Davies Liu] keep compatibility 5707476 [Davies Liu] cleanup, fix hash of string in 3.3+ 8662d5b [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 f53e1f0 [Davies Liu] fix tests 70b6b73 [Davies Liu] compile ec2/spark_ec2.py in python 3 a39167e [Davies Liu] support customize class in __main__ 814c77b [Davies Liu] run unittests with python 3 7f4476e [Davies Liu] mllib tests passed d737924 [Davies Liu] pass ml tests 375ea17 [Davies Liu] SQL tests pass 6cc42a9 [Davies Liu] rename 431a8de [Davies Liu] streaming tests pass 78901a7 [Davies Liu] fix hash of serializer in Python 3 24b2f2e [Davies Liu] pass all RDD tests 35f48fe [Davies Liu] run future again 1eebac2 [Davies Liu] fix conflict in ec2/spark_ec2.py 6e3c21d [Davies Liu] make cloudpickle work with Python3 2fb2db3 [Josh Rosen] Guard more changes behind sys.version; still doesn't run 1aa5e8f [twneale] Turned out `pickle.DictionaryType is dict` == True, so swapped it out 7354371 [twneale] buffer --> memoryview I'm not super sure if this a valid change, but the 2.7 docs recommend using memoryview over buffer where possible, so hoping it'll work. b69ccdf [twneale] Uses the pure python pickle._Pickler instead of c-extension _pickle.Pickler. It appears pyspark 2.7 uses the pure python pickler as well, so this shouldn't degrade pickling performance (?). f40d925 [twneale] xrange --> range e104215 [twneale] Replaces 2.7 types.InstsanceType with 3.4 `object`....could be horribly wrong depending on how types.InstanceType is used elsewhere in the package--see http://bugs.python.org/issue8206 79de9d0 [twneale] Replaces python2.7 `file` with 3.4 _io.TextIOWrapper 2adb42d [Josh Rosen] Fix up some import differences between Python 2 and 3 854be27 [Josh Rosen] Run `futurize` on Python code: 7c5b4ce [Josh Rosen] Remove Python 3 check in shell.py.
149 lines
5.5 KiB
Python
149 lines
5.5 KiB
Python
#
|
|
# Licensed to the Apache Software Foundation (ASF) under one or more
|
|
# contributor license agreements. See the NOTICE file distributed with
|
|
# this work for additional information regarding copyright ownership.
|
|
# The ASF licenses this file to You under the Apache License, Version 2.0
|
|
# (the "License"); you may not use this file except in compliance with
|
|
# the License. You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
"""
|
|
Worker that receives input from Piped RDD.
|
|
"""
|
|
from __future__ import print_function
|
|
import os
|
|
import sys
|
|
import time
|
|
import socket
|
|
import traceback
|
|
|
|
from pyspark.accumulators import _accumulatorRegistry
|
|
from pyspark.broadcast import Broadcast, _broadcastRegistry
|
|
from pyspark.files import SparkFiles
|
|
from pyspark.serializers import write_with_length, write_int, read_long, \
|
|
write_long, read_int, SpecialLengths, UTF8Deserializer, PickleSerializer
|
|
from pyspark import shuffle
|
|
|
|
pickleSer = PickleSerializer()
|
|
utf8_deserializer = UTF8Deserializer()
|
|
|
|
|
|
def report_times(outfile, boot, init, finish):
|
|
write_int(SpecialLengths.TIMING_DATA, outfile)
|
|
write_long(int(1000 * boot), outfile)
|
|
write_long(int(1000 * init), outfile)
|
|
write_long(int(1000 * finish), outfile)
|
|
|
|
|
|
def add_path(path):
|
|
# worker can be used, so donot add path multiple times
|
|
if path not in sys.path:
|
|
# overwrite system packages
|
|
sys.path.insert(1, path)
|
|
|
|
|
|
def main(infile, outfile):
|
|
try:
|
|
boot_time = time.time()
|
|
split_index = read_int(infile)
|
|
if split_index == -1: # for unit tests
|
|
exit(-1)
|
|
|
|
# initialize global state
|
|
shuffle.MemoryBytesSpilled = 0
|
|
shuffle.DiskBytesSpilled = 0
|
|
_accumulatorRegistry.clear()
|
|
|
|
# fetch name of workdir
|
|
spark_files_dir = utf8_deserializer.loads(infile)
|
|
SparkFiles._root_directory = spark_files_dir
|
|
SparkFiles._is_running_on_worker = True
|
|
|
|
# fetch names of includes (*.zip and *.egg files) and construct PYTHONPATH
|
|
add_path(spark_files_dir) # *.py files that were added will be copied here
|
|
num_python_includes = read_int(infile)
|
|
for _ in range(num_python_includes):
|
|
filename = utf8_deserializer.loads(infile)
|
|
add_path(os.path.join(spark_files_dir, filename))
|
|
if sys.version > '3':
|
|
import importlib
|
|
importlib.invalidate_caches()
|
|
|
|
# fetch names and values of broadcast variables
|
|
num_broadcast_variables = read_int(infile)
|
|
for _ in range(num_broadcast_variables):
|
|
bid = read_long(infile)
|
|
if bid >= 0:
|
|
path = utf8_deserializer.loads(infile)
|
|
_broadcastRegistry[bid] = Broadcast(path=path)
|
|
else:
|
|
bid = - bid - 1
|
|
_broadcastRegistry.pop(bid)
|
|
|
|
_accumulatorRegistry.clear()
|
|
command = pickleSer._read_with_length(infile)
|
|
if isinstance(command, Broadcast):
|
|
command = pickleSer.loads(command.value)
|
|
(func, profiler, deserializer, serializer), version = command
|
|
if version != sys.version_info[:2]:
|
|
raise Exception(("Python in worker has different version %s than that in " +
|
|
"driver %s, PySpark cannot run with different minor versions") %
|
|
(sys.version_info[:2], version))
|
|
init_time = time.time()
|
|
|
|
def process():
|
|
iterator = deserializer.load_stream(infile)
|
|
serializer.dump_stream(func(split_index, iterator), outfile)
|
|
|
|
if profiler:
|
|
profiler.profile(process)
|
|
else:
|
|
process()
|
|
except Exception:
|
|
try:
|
|
write_int(SpecialLengths.PYTHON_EXCEPTION_THROWN, outfile)
|
|
write_with_length(traceback.format_exc().encode("utf-8"), outfile)
|
|
except IOError:
|
|
# JVM close the socket
|
|
pass
|
|
except Exception:
|
|
# Write the error to stderr if it happened while serializing
|
|
print("PySpark worker failed with exception:", file=sys.stderr)
|
|
print(traceback.format_exc(), file=sys.stderr)
|
|
exit(-1)
|
|
finish_time = time.time()
|
|
report_times(outfile, boot_time, init_time, finish_time)
|
|
write_long(shuffle.MemoryBytesSpilled, outfile)
|
|
write_long(shuffle.DiskBytesSpilled, outfile)
|
|
|
|
# Mark the beginning of the accumulators section of the output
|
|
write_int(SpecialLengths.END_OF_DATA_SECTION, outfile)
|
|
write_int(len(_accumulatorRegistry), outfile)
|
|
for (aid, accum) in _accumulatorRegistry.items():
|
|
pickleSer._write_with_length((aid, accum._value), outfile)
|
|
|
|
# check end of stream
|
|
if read_int(infile) == SpecialLengths.END_OF_STREAM:
|
|
write_int(SpecialLengths.END_OF_STREAM, outfile)
|
|
else:
|
|
# write a different value to tell JVM to not reuse this worker
|
|
write_int(SpecialLengths.END_OF_DATA_SECTION, outfile)
|
|
exit(-1)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
# Read a local port to connect to from stdin
|
|
java_port = int(sys.stdin.readline())
|
|
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
|
|
sock.connect(("127.0.0.1", java_port))
|
|
sock_file = sock.makefile("a+", 65536)
|
|
main(sock_file, sock_file)
|