版权声明:原创作品请注明出处,谢谢。 https://blog.csdn.net/a2099948768/article/details/79580634
代码如下:
#! /usr/bin/python
# -*- coding: utf8 -*-
#author:yukang
import pyspark
from pyspark import SparkContext as sc
from pyspark import SparkConf
import os
conf = SparkConf().setAppName('test').setMaster('local[*]')
sc = sc.getOrCreate(conf)
报错如下:
解决方案:
解决方案网上找了一大推,但是都不能解决我的问题。
那么只能自己看源码解决了。
看报错:
首先进入getOrCreate()方法中,这个方法是实例化一个SparkContext,并将其注册为singleton对象。
跳转SparkContext()类中中,__init__初始化。
跳转_ensure_initialized()方法中,主要检查SparkContext是否被初始化。
最后跳转launch_gateway()中,主要错误在这里面。这里主要启动 jvm 网关。
首先看报错文件的源码,源码我都给与了中文备注,源码如下:
import atexit
import os
import sys
import select
import signal
import shlex
import socket
import platform
from subprocess import Popen, PIPE
if sys.version >= '3':
xrange = range
from py4j.java_gateway import java_import, JavaGateway, GatewayClient
from pyspark.find_spark_home import _find_spark_home
from pyspark.serializers import read_int
def launch_gateway(conf=None):
"""
launch jvm gateway
启动 jvm 网关
:param conf: spark configuration passed to spark-submit
:return:
"""
if "PYSPARK_GATEWAY_PORT" in os.environ:
gateway_port = int(os.environ["PYSPARK_GATEWAY_PORT"])
else:
SPARK_HOME = _find_spark_home()
# Launch the Py4j gateway using Spark's run command so that we pick up the
#使用Spark的run命令我们就可以启动Py4j网关
# proper classpath and settings from spark-env.sh
# spark-env.sh 类的路径和设置
on_windows = platform.system() == "Windows"
script = "./bin/spark-submit.cmd" if on_windows else "./bin/spark-submit"
command = [os.path.join(SPARK_HOME, script)]
if conf:
for k, v in conf.getAll():
command += ['--conf', '%s=%s' % (k, v)]
submit_args = os.environ.get("PYSPARK_SUBMIT_ARGS", "pyspark-shell")
if os.environ.get("SPARK_TESTING"):
submit_args = ' '.join([
"--conf spark.ui.enabled=false",
submit_args
])
command = command + shlex.split(submit_args)
# Start a socket that will be used by PythonGatewayServer to communicate its port to us
# 启动一个套接字,它将由python-ongatewayserver用于将其端口与我们通信
callback_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
callback_socket.bind(('127.0.0.1', 0))
callback_socket.listen(1)
callback_host, callback_port = callback_socket.getsockname()
env = dict(os.environ)
env['_PYSPARK_DRIVER_CALLBACK_HOST'] = callback_host
env['_PYSPARK_DRIVER_CALLBACK_PORT'] = str(callback_port)
# Launch the Java gateway. 启动Java网关。
# We open a pipe to stdin so that the Java gateway can die when the pipe is broken
# 我们打开一个管道到stdin,这样Java网关就会在管道被破坏时死亡
if not on_windows:
# Don't send ctrl-c / SIGINT to the Java gateway:
# 不要向Java网关发送ctrl-c/SIGINT:
def preexec_func():
signal.signal(signal.SIGINT, signal.SIG_IGN)
proc = Popen(command, stdin=PIPE, preexec_fn=preexec_func, env=env)
else:
# preexec_fn not supported on Windows
# 在Windows上不支持preexec fn
proc = Popen(command, stdin=PIPE, env=env)
gateway_port = None
# We use select() here in order to avoid blocking indefinitely if the subprocess dies
# before connecting
# 我们使用select()来避免在连接之前终止子进程
while gateway_port is None and proc.poll() is None:
timeout = 1 # (seconds)
readable, _, _ = select.select([callback_socket], [], [], timeout)
if callback_socket in readable:
gateway_connection = callback_socket.accept()[0]
# Determine which ephemeral port the server started on:
# 确定服务器启动的临时窗口
gateway_port = read_int(gateway_connection.makefile(mode="rb"))
gateway_connection.close()
callback_socket.close()
if gateway_port is None:
raise Exception("Java gateway process exited before sending the driver its port number")
# In Windows, ensure the Java child processes do not linger after Python has exited.
# In UNIX-based systems, the child process can kill itself on broken pipe (i.e. when
# the parent process' stdin sends an EOF). In Windows, however, this is not possible
# because java.lang.Process reads directly from the parent process' stdin, contending
# with any opportunity to read an EOF from the parent. Note that this is only best
# effort and will not take effect if the python process is violently terminated.
if on_windows:
# In Windows, the child process here is "spark-submit.cmd", not the JVM itself
# (because the UNIX "exec" command is not available). This means we cannot simply
# call proc.kill(), which kills only the "spark-submit.cmd" process but not the
# JVMs. Instead, we use "taskkill" with the tree-kill option "/t" to terminate all
# child processes in the tree (http://technet.microsoft.com/en-us/library/bb491009.aspx)
def killChild():
Popen(["cmd", "/c", "taskkill", "/f", "/t", "/pid", str(proc.pid)])
atexit.register(killChild)
# Connect to the gateway
gateway = JavaGateway(GatewayClient(port=gateway_port), auto_convert=True)
# Import the classes used by PySpark
java_import(gateway.jvm, "org.apache.spark.SparkConf")
java_import(gateway.jvm, "org.apache.spark.api.java.*")
java_import(gateway.jvm, "org.apache.spark.api.python.*")
java_import(gateway.jvm, "org.apache.spark.ml.python.*")
java_import(gateway.jvm, "org.apache.spark.mllib.api.python.*")
# TODO(davies): move into sql
java_import(gateway.jvm, "org.apache.spark.sql.*")
java_import(gateway.jvm, "org.apache.spark.sql.api.python.*")
java_import(gateway.jvm, "org.apache.spark.sql.hive.*")
java_import(gateway.jvm, "scala.Tuple2")
return gateway
可以很清楚的看到报错由 87行 自定义错误引发。
那么怎么解决。
方法:
导入os模块,然后代码中添加,=号后面的地址主要看你JDK的地址,按个人地址为主,我的地址只做参考:
os.environ ['JAVA_HOME'] = 'D:\jdk1.8'
完美解决问题。