Develop Reference

AWS Glue Docker ignoring customJdbcDriverClassName and customJdbcDriverS3Path

Attempting to run a very trivial Glue script locally via Docker I can't seem to connect to a mysql database running also in docker.
My docker setup is:
version: '3.7'
services:
glue:
container_name: "dev-glue"
image: amazon/aws-glue-libs:glue_libs_3.0.0_image_01-arm64
ports:
- "4040:4040"
- "18080:18080"
volumes:
- ~/.aws:/home/glue_user/.aws
- /workspace:/home/glue_user/workspace/
environment:
- "AWS_PROFILE=$AWS_PROFILE"
- "AWS_REGION=us-west-2"
- "AWS_DEFAULT_REGION=us-west-2"
- "DISABLE_SSL=true"
stdin_open: true
mysql:
image: mysql:8.0
container_name: 'dev-mysql'
command: --default-authentication-plugin=mysql_native_password
restart: always
environment:
MYSQL_ROOT_PASSWORD: password
volumes:
- mysql-db:/var/lib/mysql
ports:
- '3306:3306'
volumes:
mysql-db:
And according to the documentation found here the following should work without a problem
from awsglue.context import GlueContext
from pyspark.context import SparkContext
from awsglue.context import GlueContext
from awsglue.dynamicframe import DynamicFrame
glueContext = GlueContext(SparkContext.getOrCreate())
def df_mysql(glue_context: GlueContext, schema: str, table: str):
connection = {
"url": f"jdbc:mysql://dev-mysql/{schema}",
"dbtable": table,
"user": "root",
"password": "password",
"customJdbcDriverS3Path": "s3://my-bucket/mysql-connector-java-8.0.17.jar",
"customJdbcDriverClassName": "com.mysql.cj.jdbc.Driver"
}
data_frame: DynamicFrame = glue_context.create_dynamic_frame.from_options(connection_type="mysql", connection_options=connection)
data_frame.printSchema()
df_mysql(glueContext, "my_schema", "my_table")
However this fails with
Traceback (most recent call last):
File "/home/glue_user/workspace/local/local_mysql.py", line 25, in <module>
df_mysql(glueContext, "my_schema", "my_table")
File "/home/glue_user/workspace/local/local_mysql.py", line 19, in df_mysql
data_frame: DynamicFrame = glue_context.create_dynamic_frame.from_options(connection_type="mysql", connection_options=connection)
File "/home/glue_user/aws-glue-libs/PyGlue.zip/awsglue/dynamicframe.py", line 608, in from_options
File "/home/glue_user/aws-glue-libs/PyGlue.zip/awsglue/context.py", line 228, in create_dynamic_frame_from_options
File "/home/glue_user/aws-glue-libs/PyGlue.zip/awsglue/data_source.py", line 36, in getFrame
File "/home/glue_user/spark/python/lib/py4j-0.10.9-src.zip/py4j/java_gateway.py", line 1305, in __call__
File "/home/glue_user/spark/python/pyspark/sql/utils.py", line 111, in deco
return f(*a, **kw)
File "/home/glue_user/spark/python/lib/py4j-0.10.9-src.zip/py4j/protocol.py", line 328, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o45.getDynamicFrame.
: java.lang.ClassNotFoundException: com.mysql.cj.jdbc.Driver
at java.net.URLClassLoader.findClass(URLClassLoader.java:387)
at java.lang.ClassLoader.loadClass(ClassLoader.java:418)
at java.lang.ClassLoader.loadClass(ClassLoader.java:351)
at org.apache.spark.sql.execution.datasources.jdbc.DriverRegistry$.register(DriverRegistry.scala:46)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCOptions.$anonfun$driverClass$1(JDBCOptions.scala:102)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCOptions.$anonfun$driverClass$1$adapted(JDBCOptions.scala:102)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCOptions.<init>(JDBCOptions.scala:102)
at org.apache.spark.sql.jdbc.glue.GlueJDBCOptions.<init>(GlueJDBCOptions.scala:14)
at org.apache.spark.sql.jdbc.glue.GlueJDBCOptions.<init>(GlueJDBCOptions.scala:17)
at org.apache.spark.sql.jdbc.glue.GlueJDBCSource$.createRelation(GlueJDBCSource.scala:29)
at com.amazonaws.services.glue.util.JDBCWrapper.tableDF(JDBCUtils.scala:878)
at com.amazonaws.services.glue.util.NoCondition$.tableDF(JDBCUtils.scala:86)
at com.amazonaws.services.glue.util.NoJDBCPartitioner$.tableDF(JDBCUtils.scala:172)
at com.amazonaws.services.glue.JDBCDataSource.getDynamicFrame(DataSource.scala:967)
at com.amazonaws.services.glue.DataSource.getDynamicFrame(DataSource.scala:99)
at com.amazonaws.services.glue.DataSource.getDynamicFrame$(DataSource.scala:99)
at com.amazonaws.services.glue.SparkSQLDataSource.getDynamicFrame(DataSource.scala:714)
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:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:750)
Whats interesting here is its failing due to java.lang.ClassNotFoundException: com.mysql.cj.jdbc.Driver but if I change the config to use something else, it will fail with the same error message.
Is there some other environment variable or configuration I'm supposed to set in order for this to work?

AWS Glue Error: py4j.protocol.Py4JJavaError: An error occurred while calling o89.getCatalogSource. : java.util.NoSuchElementException: None.get

I am running the following glue script to copy certain columns from a postgres table to a bucket in S3.:
import sys
from awsglue.transforms import *
from awsglue.utils import getResolvedOptions
from pyspark.context import SparkContext
from awsglue.context import GlueContext
from awsglue.job import Job
from awsglue import DynamicFrame
def sparkSqlQuery(glueContext, query, mapping, transformation_ctx) -> DynamicFrame:
for alias, frame in mapping.items():
frame.toDF().createOrReplaceTempView(alias)
result = spark.sql(query)
return DynamicFrame.fromDF(result, glueContext, transformation_ctx)
args = getResolvedOptions(sys.argv, ["JOB_NAME"])
sc = SparkContext()
glueContext = GlueContext(sc)
spark = glueContext.spark_session
job = Job(glueContext)
job.init(args["JOB_NAME"], args)
PostgreSQL_node1668126214499 = glueContext.create_dynamic_frame.from_catalog(
database="glue-catalog-ra-db",
table_name="rentalassistance_public_addresses",
transformation_ctx="PostgreSQL_node1668126214499",
)
SqlQuery0 = """
select id, zip, city from myDataSource
"""
SQLQuery_node1668127298659 = sparkSqlQuery(
glueContext,
query=SqlQuery0,
mapping={"p1": PostgreSQL_node1668126214499},
transformation_ctx="SQLQuery_node1668127298659",
)
S3bucket_node3 = glueContext.write_dynamic_frame.from_options(
frame=SQLQuery_node1668127298659,
connection_type="s3",
format="json",
connection_options={
"path": "s3://refined-data.edquity-dev.co/demo_data/",
"partitionKeys": [],
},
transformation_ctx="S3bucket_node3",
)
job.commit()
Unfortunately, I am seeing the following error in my error logs when I try to run this job:
2022-11-11 00:43:45,504 ERROR [main] glue.ProcessLauncher (Logging.scala:logError(73)): Error from Python:Traceback (most recent call last):
File "/tmp/export-public-addresses", line 28, in <module>
transformation_ctx="PostgreSQL_node1668126214499",
File "/opt/amazon/lib/python3.6/site-packages/awsglue/dynamicframe.py", line 787, in from_catalog
return self._glue_context.create_dynamic_frame_from_catalog(db, table_name, redshift_tmp_dir, transformation_ctx, push_down_predicate, additional_options, catalog_id, **kwargs)
File "/opt/amazon/lib/python3.6/site-packages/awsglue/context.py", line 186, in create_dynamic_frame_from_catalog
makeOptions(self._sc, additional_options), catalog_id),
File "/opt/amazon/spark/python/lib/py4j-0.10.9-src.zip/py4j/java_gateway.py", line 1305, in __call__
answer, self.gateway_client, self.target_id, self.name)
File "/opt/amazon/spark/python/lib/pyspark.zip/pyspark/sql/utils.py", line 111, in deco
return f(*a, **kw)
File "/opt/amazon/spark/python/lib/py4j-0.10.9-src.zip/py4j/protocol.py", line 328, in get_return_value
format(target_id, ".", name), value)
py4j.protocol.Py4JJavaError: An error occurred while calling o89.getCatalogSource.
: java.util.NoSuchElementException: None.get
at scala.None$.get(Option.scala:349)
at scala.None$.get(Option.scala:347)
at com.amazonaws.services.glue.util.DataCatalogWrapper.$anonfun$getJDBCConf$1(DataCatalogWrapper.scala:218)
at scala.util.Try$.apply(Try.scala:209)
at com.amazonaws.services.glue.util.DataCatalogWrapper.getJDBCConf(DataCatalogWrapper.scala:209)
at com.amazonaws.services.glue.GlueContext.getGlueNativeJDBCSource(GlueContext.scala:487)
at com.amazonaws.services.glue.GlueContext.getCatalogSource(GlueContext.scala:320)
at com.amazonaws.services.glue.GlueContext.getCatalogSource(GlueContext.scala:185)
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:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:750)
as well as this in another error log:
{
"Event": "GlueETLJobExceptionEvent",
"Timestamp": 1668127425524,
"Failure Reason": "Traceback (most recent call last):\n File \"/tmp/export-public-addresses\", line 28, in <module>\n transformation_ctx=\"PostgreSQL_node1668126214499\",\n File \"/opt/amazon/lib/python3.6/site-packages/awsglue/dynamicframe.py\", line 787, in from_catalog\n return self._glue_context.create_dynamic_frame_from_catalog(db, table_name, redshift_tmp_dir, transformation_ctx, push_down_predicate, additional_options, catalog_id, **kwargs)\n File \"/opt/amazon/lib/python3.6/site-packages/awsglue/context.py\", line 186, in create_dynamic_frame_from_catalog\n makeOptions(self._sc, additional_options), catalog_id),\n File \"/opt/amazon/spark/python/lib/py4j-0.10.9-src.zip/py4j/java_gateway.py\", line 1305, in __call__\n answer, self.gateway_client, self.target_id, self.name)\n File \"/opt/amazon/spark/python/lib/pyspark.zip/pyspark/sql/utils.py\", line 111, in deco\n return f(*a, **kw)\n File \"/opt/amazon/spark/python/lib/py4j-0.10.9-src.zip/py4j/protocol.py\", line 328, in get_return_value\n format(target_id, \".\", name), value)\npy4j.protocol.Py4JJavaError: An error occurred while calling o89.getCatalogSource.\n: java.util.NoSuchElementException: None.get\n\tat scala.None$.get(Option.scala:349)\n\tat scala.None$.get(Option.scala:347)\n\tat com.amazonaws.services.glue.util.DataCatalogWrapper.$anonfun$getJDBCConf$1(DataCatalogWrapper.scala:218)\n\tat scala.util.Try$.apply(Try.scala:209)\n\tat com.amazonaws.services.glue.util.DataCatalogWrapper.getJDBCConf(DataCatalogWrapper.scala:209)\n\tat com.amazonaws.services.glue.GlueContext.getGlueNativeJDBCSource(GlueContext.scala:487)\n\tat com.amazonaws.services.glue.GlueContext.getCatalogSource(GlueContext.scala:320)\n\tat com.amazonaws.services.glue.GlueContext.getCatalogSource(GlueContext.scala:185)\n\tat sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\n\tat sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)\n\tat sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\n\tat java.lang.reflect.Method.invoke(Method.java:498)\n\tat py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\n\tat py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)\n\tat py4j.Gateway.invoke(Gateway.java:282)\n\tat py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\n\tat py4j.commands.CallCommand.execute(CallCommand.java:79)\n\tat py4j.GatewayConnection.run(GatewayConnection.java:238)\n\tat java.lang.Thread.run(Thread.java:750)\n",
"Stack Trace": [
{
"Declaring Class": "get_return_value",
"Method Name": "format(target_id, \".\", name), value)",
"File Name": "/opt/amazon/spark/python/lib/py4j-0.10.9-src.zip/py4j/protocol.py",
"Line Number": 328
},
{
"Declaring Class": "deco",
"Method Name": "return f(*a, **kw)",
"File Name": "/opt/amazon/spark/python/lib/pyspark.zip/pyspark/sql/utils.py",
"Line Number": 111
},
...
I was wondering if anyone has successfully solved this issue in the past?
Thus far I've tried removing the column selector to try and simplify the overall process to 2 steps but that did not really make a difference.
Additioanlly, I've tried increasing memory/node allocation but neither of these made a difference either.
EDIT: Just tried viewing the data through the "data preview" option on glue's studio's visual editor and I see the same error. Seems like its clearly unable to locate the data even though the crawler seems to be working correctly as it pulls in the correct tables.
If I'm understanding this right it looks like an issue with locating the catalog database and table. But I used the visual tool to construct this so I'm not sure why it wouldn't be able to find those crawled tables.

Spark JDBC error connecting to PostgreSQL

To begin, I have seen a few posts on this, but did not have much luck with any of the fixes.
I currently have the following code:
from pyspark.sql import SparkSession
from pyspark.sql import SQLContext
if __name__ == '__main__':
scSpark = SparkSession.builder.appName("postgres") \
.config("spark.driver.extraClassPath", "C:/Spark/spark-3.0.1-bin-hadoop2.7/jars/postgresql-42.2.18.jar") \
.getOrCreate()
data_file = './data.csv'
sdfData = scSpark.read.csv(data_file, header=True, sep=',').cache()
sdfData.registerTempTable('sales')
scSpark = SparkSession.builder.appName("postgres") \
.config("spark.driver.extraClassPath", "C:/Spark/spark-3.0.1-bin-hadoop2.7/jars/postgresql-42.2.18.jar") \
.getOrCreate()
output = scSpark.sql('SELECT * from sales')
output.write.format('jdbc').options(url='jdbc:postgresql://localhost:5432/spark',driver='com.mysql.cj.jdbc.Driver',dbtable='city_info',user='postgres',password='password').mode('append').save()
When running this code, I get the following error:
Traceback (most recent call last):
File "main.py", line 20, in <module>
output.write.format('jdbc').options(url='jdbc:postgresql://localhost:5432/spark',driver='com.mysql.cj.jdbc.Driver',dbtable='city_info',user='postgres',password='password').mode('append').save()
File "C:\Users\jackt\AppData\Local\Programs\Python\Python38-32\lib\site-packages\pyspark\sql\readwriter.py", line 825, in save
self._jwrite.save()
File "C:\Users\jackt\AppData\Local\Programs\Python\Python38-32\lib\site-packages\py4j\java_gateway.py", line 1304, in __call__
return_value = get_return_value(
File "C:\Users\jackt\AppData\Local\Programs\Python\Python38-32\lib\site-packages\pyspark\sql\utils.py", line 128, in deco
return f(*a, **kw)
File "C:\Users\jackt\AppData\Local\Programs\Python\Python38-32\lib\site-packages\py4j\protocol.py", line 326, in get_return_value
raise Py4JJavaError(
py4j.protocol.Py4JJavaError: An error occurred while calling o49.save.
: java.lang.ClassNotFoundException: com.mysql.cj.jdbc.Driver
at java.net.URLClassLoader.findClass(URLClassLoader.java:382)
at java.lang.ClassLoader.loadClass(ClassLoader.java:418)
at java.lang.ClassLoader.loadClass(ClassLoader.java:351)
at org.apache.spark.sql.execution.datasources.jdbc.DriverRegistry$.register(DriverRegistry.scala:45)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCOptions.$anonfun$driverClass$1(JDBCOptions.scala:99)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCOptions.$anonfun$driverClass$1$adapted(JDBCOptions.scala:99)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCOptions.<init>(JDBCOptions.scala:99)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcOptionsInWrite.<init>(JDBCOptions.scala:194)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcOptionsInWrite.<init>(JDBCOptions.scala:198)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcRelationProvider.createRelation(JdbcRelationProvider.scala:45)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:46)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:90)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:175)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:213)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:210)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:171)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:122)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:121)
at org.apache.spark.sql.DataFrameWriter.$anonfun$runCommand$1(DataFrameWriter.scala:963)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:100)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:160)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:87)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:764)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:963)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:415)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:399)
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:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
I know that the error is java.lang.ClassNotFoundException: com.mysql.cj.jdbc.Driver. However, I manually add it to the classpath when I begin the session, and I ensured that the file had full permissions given to the Users group.

Change the driver parameter when saving the DataFrame into database. You need to use org.postgresql.Driver for Postgresql:
output.write.format('jdbc').options(
url='jdbc:postgresql://localhost:5432/spark',
driver='org.postgresql.Driver',
dbtable='city_info',
user='postgres',
password='password'
).mode('append').save()

Wrong JDBC driver
com.mysql.cj.jdbc.Driver is for MySQL, not for Postgres. These are two different, competing database server products.
For accessing Postgres, you have a choice of JDBC driver vendors:
PostgreSQL JDBC Driver from postgresql.org
PGJDBC-NG from impossibl, for JDBC 4.2 and later.
Commercial vendors, such as OpenLink Software

Error when running simple pyspark code with cloudera CDH5.13

I am running simple code as below. Actually I am just starting to practice spark with cloudera cdh. My goal is to read 'orders' table and then print it as RDD
from pyspark import SparkContext, SparkConf
if __name__ == "__main__":
# create Spark context with Spark configuration
conf = SparkConf().setAppName("Spark Count")
sc = SparkContext(conf=conf)
data = sc.textFile("hdfs://user/cloudera/orders")
print data.collect()
But I am getting below Error
[cloudera#quickstart ~]$ spark-submit spark_ex.py Traceback (most
recent call last): File "/home/cloudera/spark_ex.py", line 7, in
print data.collect() File "/usr/lib/spark/python/lib/pyspark.zip/pyspark/rdd.py", line 771, in
collect File
"/usr/lib/spark/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py",
line 813, in call File
"/usr/lib/spark/python/lib/py4j-0.9-src.zip/py4j/protocol.py", line
308, in get_return_value py4j.protocol.Py4JJavaError: An error
occurred while calling
z:org.apache.spark.api.python.PythonRDD.collectAndServe. :
java.net.ConnectException: Call From quickstart.cloudera/10.0.2.15 to
user:8020 failed on connection exception: java.net.ConnectException:
Connection refused; For more details see:
http://wiki.apache.org/hadoop/ConnectionRefused at
sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at
sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:57)
at
sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:526)
at org.apache.hadoop.net.NetUtils.wrapWithMessage(NetUtils.java:791)
at org.apache.hadoop.net.NetUtils.wrapException(NetUtils.java:731)
at org.apache.hadoop.ipc.Client.call(Client.java:1508) at
org.apache.hadoop.ipc.Client.call(Client.java:1441) at
org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:230)
at com.sun.proxy.$Proxy21.getFileInfo(Unknown Source) at
org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.getFileInfo(ClientNamenodeProtocolTranslatorPB.java:786)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606) at
org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:260)
at
org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:104)
at com.sun.proxy.$Proxy22.getFileInfo(Unknown Source) at
org.apache.hadoop.hdfs.DFSClient.getFileInfo(DFSClient.java:2131) at
org.apache.hadoop.hdfs.DistributedFileSystem$20.doCall(DistributedFileSystem.java:1265)
at
org.apache.hadoop.hdfs.DistributedFileSystem$20.doCall(DistributedFileSystem.java:1261)
at
org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
at
org.apache.hadoop.hdfs.DistributedFileSystem.getFileStatus(DistributedFileSystem.java:1261)
at org.apache.hadoop.fs.Globber.getFileStatus(Globber.java:64) at
org.apache.hadoop.fs.Globber.doGlob(Globber.java:272) at
org.apache.hadoop.fs.Globber.glob(Globber.java:151) at
org.apache.hadoop.fs.FileSystem.globStatus(FileSystem.java:1734) at
org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:259)
at
org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:229)
at
org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:315)
at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:202)
at
org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at
org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120) at
org.apache.spark.rdd.RDD.partitions(RDD.scala:237) at
org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at
org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at
org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120) at
org.apache.spark.rdd.RDD.partitions(RDD.scala:237) at
org.apache.spark.SparkContext.runJob(SparkContext.scala:1959) at
org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:927) at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316) at
org.apache.spark.rdd.RDD.collect(RDD.scala:926) at
org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:405)
at
org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606) at
py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231) at
py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381) at
py4j.Gateway.invoke(Gateway.java:259) at
py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79) at
py4j.GatewayConnection.run(GatewayConnection.java:209) at
java.lang.Thread.run(Thread.java:745) Caused by:
java.net.ConnectException: Connection refused at
sun.nio.ch.SocketChannelImpl.checkConnect(Native Method) at
sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:739)
at
org.apache.hadoop.net.SocketIOWithTimeout.connect(SocketIOWithTimeout.java:206)
at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:530) at
org.apache.hadoop.net.NetUtils.connect(NetUtils.java:494) at
org.apache.hadoop.ipc.Client$Connection.setupConnection(Client.java:648)
at
org.apache.hadoop.ipc.Client$Connection.setupIOstreams(Client.java:744)
at
org.apache.hadoop.ipc.Client$Connection.access$3000(Client.java:396)
at org.apache.hadoop.ipc.Client.getConnection(Client.java:1557) at
org.apache.hadoop.ipc.Client.call(Client.java:1480) ... 52 more
Can anyone please Thanks

Error While writing pyspark dataframe to MySQL database

I am getting the following error:
"Caused by: java.lang.NoSuchMethodException: org.apache.spark.sql.execution.datasources.jdbc.DriverWrapper.<init>()" while writing pyspark dataframe to mysql database
spark-submit command:
spark-submit --deploy-mode client --master yarn --conf spark.pyspark.python=/usr/bin/python3 --packages mysql:mysql-connector-java:8.0.12 s3://aramark-files/test_pyspark.py
And I am writing using:
df.write.jdbc(url="jdbc:mysql://dbhost/dbname", table="tablename", mode="append", properties={"user":"dbuser", "password": "s3cret"})
Below is the error I am getting after executing the above spark-submit command:
Traceback (most recent call last):
File "/mnt/tmp/spark-8bb457ce-fc88-4384-af58-9e52e2d6e21a/test_pyspark.py", line 51, in <module>
df.write.jdbc(jdbcUrl, where, mode='append', properties=dbProperties)
File "/usr/lib/spark/python/lib/pyspark.zip/pyspark/sql/readwriter.py", line 942, in jdbc
File "/usr/lib/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__
File "/usr/lib/spark/python/lib/pyspark.zip/pyspark/sql/utils.py", line 63, in deco
File "/usr/lib/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py", line 328, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o79.jdbc.
: java.lang.InstantiationException: org.apache.spark.sql.execution.datasources.jdbc.DriverWrapper
at java.lang.Class.newInstance(Class.java:427)
at org.apache.spark.sql.execution.datasources.jdbc.DriverRegistry$.register(DriverRegistry.scala:53)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:55)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:54)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcRelationProvider.createRelation(JdbcRelationProvider.scala:63)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:45)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:86)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:654)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:654)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:654)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:273)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:267)
at org.apache.spark.sql.DataFrameWriter.jdbc(DataFrameWriter.scala:499)
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:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.NoSuchMethodException: org.apache.spark.sql.execution.datasources.jdbc.DriverWrapper.<init>()
at java.lang.Class.getConstructor0(Class.java:3082)
at java.lang.Class.newInstance(Class.java:412)
... 34 more

I ran across the same problem in the Scala API. I'm reading from and writing to an Oracle 12c database, and both the DataFrameReader and the DataFrameWriter require the "driver" property to be set, in my case to "oracle.jdbc.OracleDriver", or else the former blows up with "No suitable driver" and the latter blows up with NoSuchMethodException.
I would therefore suggest you try
df.write.jdbc(url="jdbc:mysql://dbhost/dbname", table="tablename", mode="append", properties={"user":"dbuser", "password": "s3cret", "driver": "com.mysql.cj.jdbc.Driver" })
Where I've substituted the MySQL driver class name from the docs.