[ https://issues.apache.org/jira/browse/SPARK-31629?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Hyukjin Kwon updated SPARK-31629: --------------------------------- Priority: Major (was: Critical) > "py4j.protocol.Py4JJavaError: An error occurred while calling o90.save" in > pyspark 2.3.1 > ---------------------------------------------------------------------------------------- > > Key: SPARK-31629 > URL: https://issues.apache.org/jira/browse/SPARK-31629 > Project: Spark > Issue Type: Bug > Components: PySpark > Affects Versions: 2.3.1 > Environment: Ubuntu19.10 > > anaconda3-python3.6.10 > > scala 2.11.8 > > apache-hive-3.0.0-bin > > hadoop-2.7.7 > > spark-2.3.1-bin-hadoop2.7 > > java version "1.8.0_131" > > Mysql Server version: 8.0.19-0ubuntu0.19.10.3 (Ubuntu) > > driver:mysql-connector-java-8.0.20.jar > > [Driver > link|[https://mvnrepository.com/artifact/mysql/mysql-connector-java/8.0.20]] > > Reporter: appleyuchi > Priority: Major > Fix For: 1.4.1, 1.5.0 > > Original Estimate: 168h > Remaining Estimate: 168h > > I have search the forum, > SPARK-8365 > mentioned the same issue in spark 1.4.0 > SPARK-8368 > fix it in spark 1.4.1 1.5.0 > > However,in spark 2.3.1,this bug occur again > Please help me ,thanks~!!! > #---------------------------------------------------------------------- > test.py > [https://paste.ubuntu.com/p/HJfbcQ2zq3/] > > running method is: > ①spark-submit --master yarn --deploy-mode cluster test.py > ②pyspark --master yarn( and then paste the code above) > each method can replicate this error. > > then I got: > Traceback (most recent call last): > File "test.py", line 45, in <module> > password="appleyuchi").mode('append').save() > File > "/home/appleyuchi/bigdata/hadoop_tmp/nm-local-dir/usercache/appleyuchi/appcache/application_1588504345289_0003/container_1588504345289_0003_01_000001/pyspark.zip/pyspark/sql/readwriter.py", > line 703, in save > File > "/home/appleyuchi/bigdata/hadoop_tmp/nm-local-dir/usercache/appleyuchi/appcache/application_1588504345289_0003/container_1588504345289_0003_01_000001/py4j-0.10.7-src.zip/py4j/java_gateway.py", > line 1257, in __call__ > File > "/home/appleyuchi/bigdata/hadoop_tmp/nm-local-dir/usercache/appleyuchi/appcache/application_1588504345289_0003/container_1588504345289_0003_01_000001/pyspark.zip/pyspark/sql/utils.py", > line 63, in deco > File > "/home/appleyuchi/bigdata/hadoop_tmp/nm-local-dir/usercache/appleyuchi/appcache/application_1588504345289_0003/container_1588504345289_0003_01_000001/py4j-0.10.7-src.zip/py4j/protocol.py", > line 328, in get_return_value > {color:#FF0000}*py4j.protocol.Py4JJavaError: An error occurred while calling > o90.save.*{color} > : java.sql.SQLSyntaxErrorException: Unknown database > 'leaf'*{color:#FF0000}(I'm sure this database exists){color}* > at > com.mysql.cj.jdbc.exceptions.SQLError.createSQLException(SQLError.java:120) > at com.mysql.cj.jdbc.exceptions.SQLError.createSQLException(SQLError.java:97) > at > com.mysql.cj.jdbc.exceptions.SQLExceptionsMapping.translateException(SQLExceptionsMapping.java:122) > at com.mysql.cj.jdbc.ConnectionImpl.createNewIO(ConnectionImpl.java:836) > at com.mysql.cj.jdbc.ConnectionImpl.<init>(ConnectionImpl.java:456) > at com.mysql.cj.jdbc.ConnectionImpl.getInstance(ConnectionImpl.java:246) > at > com.mysql.cj.jdbc.NonRegisteringDriver.connect(NonRegisteringDriver.java:197) > at > org.apache.spark.sql.execution.datasources.jdbc.DriverWrapper.connect(DriverWrapper.scala:45) > at > org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:63) > at > org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$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 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) -- This message was sent by Atlassian Jira (v8.3.4#803005) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org