由于驱动程序和数据库之间缺少连接，Pyspark JDBC到PostgreSQL的连接失败

我们在EMR集群上使用Pyspark来访问和分析PostgreSQL数据库中的数据（可通过JDBC连接器访问

JDBC:postgresql://psqlhost:5432/psqldatabase

）。EMR集群和PostgreSQL实例之间的网络是开放的，因此，当我们通过SSH访问EMR主机时，我们可以成功启动以下作业（在客户端和集群部署模式下）：

我们现在想在EMR集群上更改设置并执行Pyspark命令，该命令来自一个与EMR集群完全连接的独立客户端实例。通过将必要的纱线配置文件复制到客户机，并使用

--master warn

执行Pyspark，已成功设置了该功能

但是，我们在从客户端实例访问PostgreSQL数据库时仍然遇到问题。出于安全原因，客户端计算机无法访问PostgreSQL实例，但EMR集群仍然可以访问该实例。上面的代码片段在

--deploy mode cluster

中正常工作。但是，在

--deploy mode client

中工作时，最后一行产生以下错误：

17/03/27 11:39:21 ERROR Driver: Connection error: 
org.postgresql.util.PSQLException: The connection attempt failed.
    at org.postgresql.core.v3.ConnectionFactoryImpl.openConnectionImpl(ConnectionFactoryImpl.java:275)
    at org.postgresql.core.ConnectionFactory.openConnection(ConnectionFactory.java:49)
    at org.postgresql.jdbc.PgConnection.<init>(PgConnection.java:194)
    at org.postgresql.Driver.makeConnection(Driver.java:431)
    at org.postgresql.Driver.connect(Driver.java:247)
    at org.apache.spark.sql.execution.datasources.jdbc.DriverWrapper.connect(DriverWrapper.scala:45)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:65)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:56)
    at org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$.resolveTable(JDBCRDD.scala:123)
    at org.apache.spark.sql.execution.datasources.jdbc.JDBCRelation.<init>(JDBCRelation.scala:117)
    at org.apache.spark.sql.DataFrameReader.jdbc(DataFrameReader.scala:237)
    at org.apache.spark.sql.DataFrameReader.jdbc(DataFrameReader.scala:159)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
    at py4j.Gateway.invoke(Gateway.java:280)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:128)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:211)
    at java.lang.Thread.run(Thread.java:745)
Caused by: java.net.SocketTimeoutException: connect timed out
    at java.net.PlainSocketImpl.socketConnect(Native Method)
    at java.net.AbstractPlainSocketImpl.doConnect(AbstractPlainSocketImpl.java:350)
    at java.net.AbstractPlainSocketImpl.connectToAddress(AbstractPlainSocketImpl.java:206)
    at java.net.AbstractPlainSocketImpl.connect(AbstractPlainSocketImpl.java:188)
    at java.net.SocksSocketImpl.connect(SocksSocketImpl.java:392)
    at java.net.Socket.connect(Socket.java:589)
    at org.postgresql.core.PGStream.<init>(PGStream.java:62)
    at org.postgresql.core.v3.ConnectionFactoryImpl.openConnectionImpl(ConnectionFactoryImpl.java:144)
    ... 22 more
---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-2-f5f370f4d567> in <module>()
----> 1 products_df = spark.read.jdbc(url=url, table=table, properties=properties)

/opt/spark-2.0.0/python/pyspark/sql/readwriter.pyc in jdbc(self, url, table, column, lowerBound, upperBound, numPartitions, predicates, properties)
    420             jpredicates = utils.toJArray(gateway, gateway.jvm.java.lang.String, predicates)
    421             return self._df(self._jreader.jdbc(url, table, jpredicates, jprop))
--> 422         return self._df(self._jreader.jdbc(url, table, jprop))
    423 
    424 

/opt/spark-2.0.0/python/lib/py4j-0.10.1-src.zip/py4j/java_gateway.py in __call__(self, *args)
    931         answer = self.gateway_client.send_command(command)
    932         return_value = get_return_value(
--> 933             answer, self.gateway_client, self.target_id, self.name)
    934 
    935         for temp_arg in temp_args:

/opt/spark-2.0.0/python/pyspark/sql/utils.pyc in deco(*a, **kw)
     61     def deco(*a, **kw):
     62         try:
---> 63             return f(*a, **kw)
     64         except py4j.protocol.Py4JJavaError as e:
     65             s = e.java_exception.toString()

/opt/spark-2.0.0/python/lib/py4j-0.10.1-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    310                 raise Py4JJavaError(
    311                     "An error occurred while calling {0}{1}{2}.\n".
--> 312                     format(target_id, ".", name), value)
    313             else:
    314                 raise Py4JError(

Py4JJavaError: An error occurred while calling o47.jdbc.
: org.postgresql.util.PSQLException: The connection attempt failed.
    at org.postgresql.core.v3.ConnectionFactoryImpl.openConnectionImpl(ConnectionFactoryImpl.java:275)
    at org.postgresql.core.ConnectionFactory.openConnection(ConnectionFactory.java:49)
    at org.postgresql.jdbc.PgConnection.<init>(PgConnection.java:194)
    at org.postgresql.Driver.makeConnection(Driver.java:431)
    at org.postgresql.Driver.connect(Driver.java:247)
    at org.apache.spark.sql.execution.datasources.jdbc.DriverWrapper.connect(DriverWrapper.scala:45)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:65)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:56)
    at org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$.resolveTable(JDBCRDD.scala:123)
    at org.apache.spark.sql.execution.datasources.jdbc.JDBCRelation.<init>(JDBCRelation.scala:117)
    at org.apache.spark.sql.DataFrameReader.jdbc(DataFrameReader.scala:237)
    at org.apache.spark.sql.DataFrameReader.jdbc(DataFrameReader.scala:159)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
    at py4j.Gateway.invoke(Gateway.java:280)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:128)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:211)
    at java.lang.Thread.run(Thread.java:745)
Caused by: java.net.SocketTimeoutException: connect timed out
    at java.net.PlainSocketImpl.socketConnect(Native Method)
    at java.net.AbstractPlainSocketImpl.doConnect(AbstractPlainSocketImpl.java:350)
    at java.net.AbstractPlainSocketImpl.connectToAddress(AbstractPlainSocketImpl.java:206)
    at java.net.AbstractPlainSocketImpl.connect(AbstractPlainSocketImpl.java:188)
    at java.net.SocksSocketImpl.connect(SocksSocketImpl.java:392)
    at java.net.Socket.connect(Socket.java:589)
    at org.postgresql.core.PGStream.<init>(PGStream.java:62)
    at org.postgresql.core.v3.ConnectionFactoryImpl.openConnectionImpl(ConnectionFactoryImpl.java:144)
    ... 22 more

17/03/27 11:39:21错误驱动程序：连接错误：
org.postgresql.util.PSQLException:连接尝试失败。
位于org.postgresql.core.v3.ConnectionFactoryImpl.openConnectionImpl（ConnectionFactoryImpl.java:275）
位于org.postgresql.core.ConnectionFactory.openConnection（ConnectionFactory.java:49）
位于org.postgresql.jdbc.PgConnection.（PgConnection.java:194）
位于org.postgresql.Driver.makeConnection（Driver.java:431）
位于org.postgresql.Driver.connect（Driver.java:247）
位于org.apache.spark.sql.execution.datasources.jdbc.DriverWrapper.connect（DriverWrapper.scala:45）
位于org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply（JdbcUtils.scala:65）
位于org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply（JdbcUtils.scala:56）
位于org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$.resolveTable（JDBCRDD.scala:123）
位于org.apache.spark.sql.execution.datasources.jdbc.jdbcreation.（jdbcreation.scala:117）
位于org.apache.spark.sql.DataFrameReader.jdbc（DataFrameReader.scala:237）
位于org.apache.spark.sql.DataFrameReader.jdbc（DataFrameReader.scala:159）
在sun.reflect.NativeMethodAccessorImpl.invoke0（本机方法）处
位于sun.reflect.NativeMethodAccessorImpl.invoke（NativeMethodAccessorImpl.java:62）
在sun.reflect.DelegatingMethodAccessorImpl.invoke（DelegatingMethodAccessorImpl.java:43）中
位于java.lang.reflect.Method.invoke（Method.java:498）
位于py4j.reflection.MethodInvoker.invoke（MethodInvoker.java:237）
位于py4j.reflection.ReflectionEngine.invoke（ReflectionEngine.java:357）
在py4j.Gateway.invoke处（Gateway.java:280）
位于py4j.commands.AbstractCommand.invokeMethod（AbstractCommand.java:128）
在py4j.commands.CallCommand.execute（CallCommand.java:79）
在py4j.GatewayConnection.run处（GatewayConnection.java:211）
运行（Thread.java:745）
原因：java.net.SocketTimeoutException:连接超时
位于java.net.PlainSocketImpl.socketConnect（本机方法）
位于java.net.AbstractPlainSocketImpl.doConnect（AbstractPlainSocketImpl.java:350）
位于java.net.AbstractPlainSocketImpl.connectToAddress（AbstractPlainSocketImpl.java:206）
位于java.net.AbstractPlainSocketImpl.connect（AbstractPlainSocketImpl.java:188）
位于java.net.socksocketimpl.connect（socksocketimpl.java:392）
位于java.net.Socket.connect（Socket.java:589）
位于org.postgresql.core.PGStream（PGStream.java:62）
位于org.postgresql.core.v3.ConnectionFactoryImpl.openConnectionImpl（ConnectionFactoryImpl.java:144）
... 还有22个
---------------------------------------------------------------------------
Py4JJavaError回溯（最近一次调用）
在（）
---->1 products_df=spark.read.jdbc（url=url，table=table，properties=properties）
/jdbc中的opt/spark-2.0.0/python/pyspark/sql/readwriter.pyc（self、url、表、列、lowerBound、上限、numPartitions、谓词、属性）
420 jpredicates=utils.toJArray（网关，gateway.jvm.java.lang.String，谓词）
421返回self.\u df（self.\u jreader.jdbc（url，table，jpredicates，jprop））
-->422返回self.\u df（self.\u jreader.jdbc（url，table，jprop））
423
424
/opt/spark-2.0.0/python/lib/py4j-0.10.1-src.zip/py4j/java_gateway.py in____调用（self，*args）
931 answer=self.gateway\u client.send\u命令（command）
932返回值=获取返回值(
-->933应答，self.gateway_客户端，self.target_id，self.name）
934
935对于临时参数中的临时参数：
/装饰中的opt/spark-2.0.0/python/pyspark/sql/utils.pyc（*a，**kw）
61 def装饰（*a，**千瓦）：
62尝试：
--->63返回f（*a，**kw）
64除py4j.protocol.Py4JJavaError外的其他错误为e:
65 s=e.java_exception.toString（）
/get_return_value中的opt/spark-2.0.0/python/lib/py4j-0.10.1-src.zip/py4j/protocol.py（答案、网关_客户端、目标_id、名称）
310 raise Py4JJavaError(
311“调用{0}{1}{2}时出错。\n”。
-->312格式（目标id，“.”，名称），值）
313其他：
314升起Py4JError(
Py4JJavaError:调用o47.jdbc时出错。
：org.postgresql.util.PSQLException:连接尝试失败。
位于org.postgresql.core.v3.ConnectionFactoryImpl.openConnectionImpl（ConnectionFactoryImpl.java:275）
位于org.postgresql.core.ConnectionFactory.openConnection（ConnectionFactory.java:49）
位于org.postgresql.jdbc.PgConnection.（PgConnection.java:194）
位于org.postgresql.Driver.makeConnection（Driver.java:431）
位于org.postgresql.Driver.connect（Driver.java:24
17/03/27 11:39:21 ERROR Driver: Connection error: 
org.postgresql.util.PSQLException: The connection attempt failed.
    at org.postgresql.core.v3.ConnectionFactoryImpl.openConnectionImpl(ConnectionFactoryImpl.java:275)
    at org.postgresql.core.ConnectionFactory.openConnection(ConnectionFactory.java:49)
    at org.postgresql.jdbc.PgConnection.<init>(PgConnection.java:194)
    at org.postgresql.Driver.makeConnection(Driver.java:431)
    at org.postgresql.Driver.connect(Driver.java:247)
    at org.apache.spark.sql.execution.datasources.jdbc.DriverWrapper.connect(DriverWrapper.scala:45)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:65)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:56)
    at org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$.resolveTable(JDBCRDD.scala:123)
    at org.apache.spark.sql.execution.datasources.jdbc.JDBCRelation.<init>(JDBCRelation.scala:117)
    at org.apache.spark.sql.DataFrameReader.jdbc(DataFrameReader.scala:237)
    at org.apache.spark.sql.DataFrameReader.jdbc(DataFrameReader.scala:159)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
    at py4j.Gateway.invoke(Gateway.java:280)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:128)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:211)
    at java.lang.Thread.run(Thread.java:745)
Caused by: java.net.SocketTimeoutException: connect timed out
    at java.net.PlainSocketImpl.socketConnect(Native Method)
    at java.net.AbstractPlainSocketImpl.doConnect(AbstractPlainSocketImpl.java:350)
    at java.net.AbstractPlainSocketImpl.connectToAddress(AbstractPlainSocketImpl.java:206)
    at java.net.AbstractPlainSocketImpl.connect(AbstractPlainSocketImpl.java:188)
    at java.net.SocksSocketImpl.connect(SocksSocketImpl.java:392)
    at java.net.Socket.connect(Socket.java:589)
    at org.postgresql.core.PGStream.<init>(PGStream.java:62)
    at org.postgresql.core.v3.ConnectionFactoryImpl.openConnectionImpl(ConnectionFactoryImpl.java:144)
    ... 22 more
---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-2-f5f370f4d567> in <module>()
----> 1 products_df = spark.read.jdbc(url=url, table=table, properties=properties)

/opt/spark-2.0.0/python/pyspark/sql/readwriter.pyc in jdbc(self, url, table, column, lowerBound, upperBound, numPartitions, predicates, properties)
    420             jpredicates = utils.toJArray(gateway, gateway.jvm.java.lang.String, predicates)
    421             return self._df(self._jreader.jdbc(url, table, jpredicates, jprop))
--> 422         return self._df(self._jreader.jdbc(url, table, jprop))
    423 
    424 

/opt/spark-2.0.0/python/lib/py4j-0.10.1-src.zip/py4j/java_gateway.py in __call__(self, *args)
    931         answer = self.gateway_client.send_command(command)
    932         return_value = get_return_value(
--> 933             answer, self.gateway_client, self.target_id, self.name)
    934 
    935         for temp_arg in temp_args:

/opt/spark-2.0.0/python/pyspark/sql/utils.pyc in deco(*a, **kw)
     61     def deco(*a, **kw):
     62         try:
---> 63             return f(*a, **kw)
     64         except py4j.protocol.Py4JJavaError as e:
     65             s = e.java_exception.toString()

/opt/spark-2.0.0/python/lib/py4j-0.10.1-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    310                 raise Py4JJavaError(
    311                     "An error occurred while calling {0}{1}{2}.\n".
--> 312                     format(target_id, ".", name), value)
    313             else:
    314                 raise Py4JError(

Py4JJavaError: An error occurred while calling o47.jdbc.
: org.postgresql.util.PSQLException: The connection attempt failed.
    at org.postgresql.core.v3.ConnectionFactoryImpl.openConnectionImpl(ConnectionFactoryImpl.java:275)
    at org.postgresql.core.ConnectionFactory.openConnection(ConnectionFactory.java:49)
    at org.postgresql.jdbc.PgConnection.<init>(PgConnection.java:194)
    at org.postgresql.Driver.makeConnection(Driver.java:431)
    at org.postgresql.Driver.connect(Driver.java:247)
    at org.apache.spark.sql.execution.datasources.jdbc.DriverWrapper.connect(DriverWrapper.scala:45)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:65)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply(JdbcUtils.scala:56)
    at org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$.resolveTable(JDBCRDD.scala:123)
    at org.apache.spark.sql.execution.datasources.jdbc.JDBCRelation.<init>(JDBCRelation.scala:117)
    at org.apache.spark.sql.DataFrameReader.jdbc(DataFrameReader.scala:237)
    at org.apache.spark.sql.DataFrameReader.jdbc(DataFrameReader.scala:159)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
    at py4j.Gateway.invoke(Gateway.java:280)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:128)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:211)
    at java.lang.Thread.run(Thread.java:745)
Caused by: java.net.SocketTimeoutException: connect timed out
    at java.net.PlainSocketImpl.socketConnect(Native Method)
    at java.net.AbstractPlainSocketImpl.doConnect(AbstractPlainSocketImpl.java:350)
    at java.net.AbstractPlainSocketImpl.connectToAddress(AbstractPlainSocketImpl.java:206)
    at java.net.AbstractPlainSocketImpl.connect(AbstractPlainSocketImpl.java:188)
    at java.net.SocksSocketImpl.connect(SocksSocketImpl.java:392)
    at java.net.Socket.connect(Socket.java:589)
    at org.postgresql.core.PGStream.<init>(PGStream.java:62)
    at org.postgresql.core.v3.ConnectionFactoryImpl.openConnectionImpl(ConnectionFactoryImpl.java:144)
    ... 22 more

from sshtunnel import SSHTunnelForwarder

url = 'jdbc:postgresql://localhost:5432,psqlhost:5432/psqldatabase'
table = 'mytable'

properties = {
    'user': 'user',
    'password': 'password',
    'driver': 'org.postgresql.Driver'
}

with SSHTunnelForwarder(
    ('emrhost', 22),
    remote_bind_address=('psqlhost', 5432),
    local_bind_address=('localhost', 5432)
    ):
    products_df = spark.read.jdbc(url=url, table=table, properties=properties)