having issues connecting to AWS Postgres from Azure Databricks, I am new to Azure and below is the code I am using to connect to Postgres but somehow its throwing an error
error: org.postgresql.util.PSQLException: The connection attempt failed.
Code:
jdbc_url="jdbc:postgresql://postgreshost:5432/db?user={}&password={}&ssl=true.format(username,password)"
pushdown_query = "(select * from test limit 10) emp_alias"
df = spark.read.jdbc(url=jdbc_url, table="test")
display(df)
2nd method:
df = spark.read \
.format("jdbc") \
.option("url", "jdbc:postgresql://postgreshost:5432/db?user=user&password=password") \
.option("dbtable", "test") \
.load()
Am I missing anything? or should I follow any steps prior to execution?
Log using Scala:
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:450)
at org.postgresql.Driver.connect(Driver.java:252)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:64)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:55)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$.resolveTable(JDBCRDD.scala:56)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCRelation$.getSchema(JDBCRelation.scala:210)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcRelationProvider.createRelation(JdbcRelationProvider.scala:35)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:346)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:298)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:279)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:202)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$$iw$$iw$$iw$$iw$$iw$$iw.<init>(command-3334328075204474:8)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$$iw$$iw$$iw$$iw$$iw.<init>(command-3334328075204474:51)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$$iw$$iw$$iw$$iw.<init>(command-3334328075204474:53)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$$iw$$iw$$iw.<init>(command-3334328075204474:55)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$$iw$$iw.<init>(command-3334328075204474:57)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$$iw.<init>(command-3334328075204474:59)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read.<init>(command-3334328075204474:61)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$.<init>(command-3334328075204474:65)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$.<clinit>(command-3334328075204474)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$eval$.$print$lzycompute(<notebook>:7)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$eval$.$print(<notebook>:6)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$eval.$print(<notebook>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at scala.tools.nsc.interpreter.IMain$ReadEvalPrint.call(IMain.scala:786)
at scala.tools.nsc.interpreter.IMain$Request.loadAndRun(IMain.scala:1047)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:638)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:637)
at scala.reflect.internal.util.ScalaClassLoader$class.asContext(ScalaClassLoader.scala:31)
at scala.reflect.internal.util.AbstractFileClassLoader.asContext(AbstractFileClassLoader.scala:19)
at scala.tools.nsc.interpreter.IMain$WrappedRequest.loadAndRunReq(IMain.scala:637)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:569)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:565)
at com.databricks.backend.daemon.driver.DriverILoop.execute(DriverILoop.scala:199)
at com.databricks.backend.daemon.driver.ScalaDriverLocal$$anonfun$repl$1.apply$mcV$sp(ScalaDriverLocal.scala:189)
at com.databricks.backend.daemon.driver.ScalaDriverLocal$$anonfun$repl$1.apply(ScalaDriverLocal.scala:189)
at com.databricks.backend.daemon.driver.ScalaDriverLocal$$anonfun$repl$1.apply(ScalaDriverLocal.scala:189)
at com.databricks.backend.daemon.driver.DriverLocal$TrapExitInternal$.trapExit(DriverLocal.scala:587)
at com.databricks.backend.daemon.driver.DriverLocal$TrapExit$.apply(DriverLocal.scala:542)
at com.databricks.backend.daemon.driver.ScalaDriverLocal.repl(ScalaDriverLocal.scala:189)
at com.databricks.backend.daemon.driver.DriverLocal$$anonfun$execute$7.apply(DriverLocal.scala:324)
at com.databricks.backend.daemon.driver.DriverLocal$$anonfun$execute$7.apply(DriverLocal.scala:304)
at com.databricks.logging.UsageLogging$$anonfun$withAttributionContext$1.apply(UsageLogging.scala:235)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58)
at com.databricks.logging.UsageLogging$class.withAttributionContext(UsageLogging.scala:230)
at com.databricks.backend.daemon.driver.DriverLocal.withAttributionContext(DriverLocal.scala:45)
at com.databricks.logging.UsageLogging$class.withAttributionTags(UsageLogging.scala:268)
at com.databricks.backend.daemon.driver.DriverLocal.withAttributionTags(DriverLocal.scala:45)
at com.databricks.backend.daemon.driver.DriverLocal.execute(DriverLocal.scala:304)
at com.databricks.backend.daemon.driver.DriverWrapper$$anonfun$tryExecutingCommand$2.apply(DriverWrapper.scala:589)
at com.databricks.backend.daemon.driver.DriverWrapper$$anonfun$tryExecutingCommand$2.apply(DriverWrapper.scala:589)
at scala.util.Try$.apply(Try.scala:192)
at com.databricks.backend.daemon.driver.DriverWrapper.tryExecutingCommand(DriverWrapper.scala:584)
at com.databricks.backend.daemon.driver.DriverWrapper.getCommandOutputAndError(DriverWrapper.scala:475)
at com.databricks.backend.daemon.driver.DriverWrapper.executeCommand(DriverWrapper.scala:542)
at com.databricks.backend.daemon.driver.DriverWrapper.runInnerLoop(DriverWrapper.scala:381)
at com.databricks.backend.daemon.driver.DriverWrapper.runInner(DriverWrapper.scala:328)
at com.databricks.backend.daemon.driver.DriverWrapper.run(DriverWrapper.scala:215)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.net.SocketTimeoutException: connect timed out
at java.net.PlainSocketImpl.socketConnect(Native Method)
at java.net.AbstractPlainSocketImpl.doConnect(AbstractPlainSocketImpl.java:350)
at java.net.AbstractPlainSocketImpl.connectToAddress(AbstractPlainSocketImpl.java:206)
at java.net.AbstractPlainSocketImpl.connect(AbstractPlainSocketImpl.java:188)
at java.net.SocksSocketImpl.connect(SocksSocketImpl.java:392)
at java.net.Socket.connect(Socket.java:589)
at org.postgresql.core.PGStream.<init>(PGStream.java:68)
at org.postgresql.core.v3.ConnectionFactoryImpl.openConnectionImpl(ConnectionFactoryImpl.java:144)
at org.postgresql.core.ConnectionFactory.openConnection(ConnectionFactory.java:49)
at org.postgresql.jdbc.PgConnection.<init>(PgConnection.java:194)
at org.postgresql.Driver.makeConnection(Driver.java:450)
at org.postgresql.Driver.connect(Driver.java:252)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:64)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:55)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$.resolveTable(JDBCRDD.scala:56)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCRelation$.getSchema(JDBCRelation.scala:210)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcRelationProvider.createRelation(JdbcRelationProvider.scala:35)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:346)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:298)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:279)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:202)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$$iw$$iw$$iw$$iw$$iw$$iw.<init>(command-3334328075204474:8)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$$iw$$iw$$iw$$iw$$iw.<init>(command-3334328075204474:51)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$$iw$$iw$$iw$$iw.<init>(command-3334328075204474:53)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$$iw$$iw$$iw.<init>(command-3334328075204474:55)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$$iw$$iw.<init>(command-3334328075204474:57)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$$iw.<init>(command-3334328075204474:59)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read.<init>(command-3334328075204474:61)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$.<init>(command-3334328075204474:65)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$read$.<clinit>(command-3334328075204474)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$eval$.$print$lzycompute(<notebook>:7)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$eval$.$print(<notebook>:6)
at lined9bdaa60f31e4f44a370d2ec7ae9793627.$eval.$print(<notebook>)
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 scala.tools.nsc.interpreter.IMain$ReadEvalPrint.call(IMain.scala:786)
at scala.tools.nsc.interpreter.IMain$Request.loadAndRun(IMain.scala:1047)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:638)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:637)
at scala.reflect.internal.util.ScalaClassLoader$class.asContext(ScalaClassLoader.scala:31)
at scala.reflect.internal.util.AbstractFileClassLoader.asContext(AbstractFileClassLoader.scala:19)
at scala.tools.nsc.interpreter.IMain$WrappedRequest.loadAndRunReq(IMain.scala:637)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:569)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:565)
at com.databricks.backend.daemon.driver.DriverILoop.execute(DriverILoop.scala:199)
at com.databricks.backend.daemon.driver.ScalaDriverLocal$$anonfun$repl$1.apply$mcV$sp(ScalaDriverLocal.scala:189)
at com.databricks.backend.daemon.driver.ScalaDriverLocal$$anonfun$repl$1.apply(ScalaDriverLocal.scala:189)
at com.databricks.backend.daemon.driver.ScalaDriverLocal$$anonfun$repl$1.apply(ScalaDriverLocal.scala:189)
at com.databricks.backend.daemon.driver.DriverLocal$TrapExitInternal$.trapExit(DriverLocal.scala:587)
at com.databricks.backend.daemon.driver.DriverLocal$TrapExit$.apply(DriverLocal.scala:542)
at com.databricks.backend.daemon.driver.ScalaDriverLocal.repl(ScalaDriverLocal.scala:189)
at com.databricks.backend.daemon.driver.DriverLocal$$anonfun$execute$7.apply(DriverLocal.scala:324)
at com.databricks.backend.daemon.driver.DriverLocal$$anonfun$execute$7.apply(DriverLocal.scala:304)
at com.databricks.logging.UsageLogging$$anonfun$withAttributionContext$1.apply(UsageLogging.scala:235)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58)
at com.databricks.logging.UsageLogging$class.withAttributionContext(UsageLogging.scala:230)
at com.databricks.backend.daemon.driver.DriverLocal.withAttributionContext(DriverLocal.scala:45)
at com.databricks.logging.UsageLogging$class.withAttributionTags(UsageLogging.scala:268)
at com.databricks.backend.daemon.driver.DriverLocal.withAttributionTags(DriverLocal.scala:45)
at com.databricks.backend.daemon.driver.DriverLocal.execute(DriverLocal.scala:304)
at com.databricks.backend.daemon.driver.DriverWrapper$$anonfun$tryExecutingCommand$2.apply(DriverWrapper.scala:589)
at com.databricks.backend.daemon.driver.DriverWrapper$$anonfun$tryExecutingCommand$2.apply(DriverWrapper.scala:589)
at scala.util.Try$.apply(Try.scala:192)
at com.databricks.backend.daemon.driver.DriverWrapper.tryExecutingCommand(DriverWrapper.scala:584)
at com.databricks.backend.daemon.driver.DriverWrapper.getCommandOutputAndError(DriverWrapper.scala:475)
at com.databricks.backend.daemon.driver.DriverWrapper.executeCommand(DriverWrapper.scala:542)
at com.databricks.backend.daemon.driver.DriverWrapper.runInnerLoop(DriverWrapper.scala:381)
at com.databricks.backend.daemon.driver.DriverWrapper.runInner(DriverWrapper.scala:328)
at com.databricks.backend.daemon.driver.DriverWrapper.run(DriverWrapper.scala:215)
at java.lang.Thread.run(Thread.java:748)
I've never provided the username and password on the connection URL, so I am not sure it works. Usually, it is specified as extra parameters. Checking the Spark Docs, it is specified like this (in Scala):
val jdbcDF = spark.read
.format("jdbc")
.option("url", "jdbc:postgresql:dbserver")
.option("dbtable", "schema.tablename")
.option("user", "username")
.option("password", "password")
.load()
Reference: https://spark.apache.org/docs/latest/sql-data-sources-jdbc.html
Its an internal company issue, nothing to do with the code
Related
When I finished the data processing,I need to save the data back to the Postgre DB.
I can use the same JDBC properties which I used in reading data out. I faced the error . I can insert the data in Data Grip with the same config and that JDBC config is not for read-only. I can use the same config to write via Data Grip.
I cannot insert the data with logic below :
glueContext.write_dynamic_frame.from_options(
frame=DynamicFrame.fromDF(dataFrame, glueContext,"tableName"),
connection_type="postgresql",
connection_options={
"url": jdbcConfig["url"],
"user": jdbcConfig["user"],
"password": jdbcConfig["password"],
"dbtable": "tableName"
}
)
And below is the error I faced(Got from CloudWatch log):
ERROR [Thread-9] postgresql.Driver (Driver.java:connect(233)): Error in url: jdbc:postgresql://cc2-data-analytics-cluster-ndec.cluster-abcdefg.us-west-2.rds.amazonaws.com:5440
2022-04-13 22:36:26,838 INFO [Thread-9] log.GlueLogger (GlueLogger.scala:info(8)): Exception as An error occurred while calling o203.pyWriteDynamicFrame.
: java.lang.Exception: Connection can not be established. Please check your JDBC url, username and password.
at com.amazonaws.services.glue.util.JDBCWrapper$$anonfun$12.apply(JDBCUtils.scala:968)
at com.amazonaws.services.glue.util.JDBCWrapper$$anonfun$12.apply(JDBCUtils.scala:964)
at com.amazonaws.services.glue.util.JDBCWrapper$$anonfun$connectWithSSLAttempt$1$$anonfun$apply$8.apply(JDBCUtils.scala:920)
at scala.Option.getOrElse(Option.scala:121)
at com.amazonaws.services.glue.util.JDBCWrapper$$anonfun$connectWithSSLAttempt$1.apply(JDBCUtils.scala:920)
at scala.Option.getOrElse(Option.scala:121)
at com.amazonaws.services.glue.util.JDBCWrapper$.connectWithSSLAttempt(JDBCUtils.scala:920)
at com.amazonaws.services.glue.util.JDBCWrapper$.connectionProperties(JDBCUtils.scala:963)
at com.amazonaws.services.glue.util.JDBCWrapper.connectionProperties$lzycompute(JDBCUtils.scala:734)
at com.amazonaws.services.glue.util.JDBCWrapper.connectionProperties(JDBCUtils.scala:734)
at com.amazonaws.services.glue.util.JDBCWrapper.writeDF(JDBCUtils.scala:883)
at com.amazonaws.services.glue.sinks.PostgresDataSink.writeDynamicFrame(PostgresDataSink.scala:41)
at com.amazonaws.services.glue.DataSink.pyWriteDynamicFrame(DataSink.scala:65)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
INFO [Thread-9] log.GlueLogger (GlueLogger.scala:info(8)): Exception as An error occurred while calling o203.pyWriteDynamicFrame. : java.lang.Exception: Connection can not be established. Please check your JDBC url, username and password. at com.amazonaws.services.glue.util.JDBCWrapper$$anonfun$12.apply(JDBCUtils.scala:968) at com.amazonaws.services.glue.util.JDBCWrapper$$anonfun$12.apply(JDBCUtils.scala:964) at com.amazonaws.services.glue.util.JDBCWrapper$$anonfun$connectWithSSLAttempt$1$$anonfun$apply$8.apply(JDBCUtils.scala:920) at scala.Option.getOrElse(Option.scala:121) at com.amazonaws.services.glue.util.JDBCWrapper$$anonfun$connectWithSSLAttempt$1.apply(JDBCUtils.scala:920) at scala.Option.getOrElse(Option.scala:121) at com.amazonaws.services.glue.util.JDBCWrapper$.connectWithSSLAttempt(JDBCUtils.scala:920) at com.amazonaws.services.glue.util.JDBCWrapper$.connectionProperties(JDBCUtils.scala:963) at com.amazonaws.services.glue.util.JDBCWrapper.connectionProperties$lzycompute(JDBCUtils.scala:734) at com.amazonaws.services.glue.util.JDBCWrapper.connectionProperties(JDBCUtils.scala:734) at com.amazonaws.services.glue.util.JDBCWrapper.writeDF(JDBCUtils.scala:883) at com.amazonaws.services.glue.sinks.PostgresDataSink.writeDynamicFrame(PostgresDataSink.scala:41) at com.amazonaws.services.glue.DataSink.pyWriteDynamicFrame(DataSink.scala:65) 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 tried to use another method but the same error as above method:
dataFrame.select(*igDataDfSchema).write.format("jdbc")\
.option("url", jdbcConfig['url']) \
.option("driver", "org.postgresql.Driver").option("dbtable", "tableName") \
.option("user", jdbcConfig['user']).option("password",jdbcConfig['password']).save()
We are doing pyspark development(cloudera) and inside the pyspark we are using spark SQL engine to migrated Greenplum to hiveSQL. some of the function getting facing as below error. please suggest.
An error occurred while calling o72.insertInto. :
java.lang.AssertionError: assertion failed
at scala.Predef$.assert(Predef.scala:156)
at org.apache.spark.sql.hive.HiveMetastoreCatalog.convertToLogicalRelation(HiveMetastoreCatalog.scala:255)
at org.apache.spark.sql.hive.HiveMetastoreCatalog.convert(HiveMetastoreCatalog.scala:135)
at org.apache.spark.sql.hive.RelationConversions$$anonfun$apply$4.applyOrElse(HiveStrategies.scala:201)
at org.apache.spark.sql.hive.RelationConversions$$anonfun$apply$4.applyOrElse(HiveStrategies.scala:195)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$2.apply(AnalysisHelper.scala:108)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$2.apply(AnalysisHelper.scala:108)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:71)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:107)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperators(AnalysisHelper.scala:73)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:29)
at org.apache.spark.sql.hive.RelationConversions.apply(HiveStrategies.scala:195)
at org.apache.spark.sql.hive.RelationConversions.apply(HiveStrategies.scala:179)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:87)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:84)
at scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:57)
at scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:66)
at scala.collection.mutable.ArrayBuffer.foldLeft(ArrayBuffer.scala:48)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:84)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:76)
at scala.collection.immutable.List.foreach(List.scala:392)
at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:76)
at org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:127)
at org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:121)
at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:106)
at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:105)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:201)
at org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:105)
at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:68)
at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:66)
at org.apache.spark.sql.execution.QueryExecution.org$apache$spark$sql$execution$QueryExecution$$writePlans(QueryExecution.scala:215)
at org.apache.spark.sql.execution.QueryExecution.toString(QueryExecution.scala:230)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:77)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:75)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:684)
at org.apache.spark.sql.DataFrameWriter.insertInto(DataFrameWriter.scala:334)
at org.apache.spark.sql.DataFrameWriter.insertInto(DataFrameWriter.scala:320)
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 am getting strange error while saving dataframe to AWS S3.
df.coalesce(1).write.mode(SaveMode.Overwrite)
.json(s"s3://myawsacc/results/")
In the same location I was able to insert the data from spark-shell .
and is working...
spark.sparkContext.parallelize(1 to 4).toDF.write.mode(SaveMode.Overwrite)
.format("com.databricks.spark.csv")
.save(s"s3://myawsacc/results/")
My question is why its working in spark-shell and is not working via
spark-submit ? Is there any logic/properties/configuration for this?
Exception in thread "main" java.lang.ExceptionInInitializerError
at com.amazon.ws.emr.hadoop.fs.s3n.S3Credentials.initialize(S3Credentials.java:45)
at com.amazon.ws.emr.hadoop.fs.HadoopConfigurationAWSCredentialsProvider.(HadoopConfigurationAWSCredentialsProvider.java:26)
at com.amazon.ws.emr.hadoop.fs.guice.DefaultAWSCredentialsProviderFactory.getAwsCredentialsProviderChain(DefaultAWSCredentialsProviderFactory.java:44)
at com.amazon.ws.emr.hadoop.fs.guice.DefaultAWSCredentialsProviderFactory.getAwsCredentialsProvider(DefaultAWSCredentialsProviderFactory.java:28)
at com.amazon.ws.emr.hadoop.fs.guice.EmrFSProdModule.getAwsCredentialsProvider(EmrFSProdModule.java:70)
at com.amazon.ws.emr.hadoop.fs.guice.EmrFSProdModule.createS3Configuration(EmrFSProdModule.java:86)
at com.amazon.ws.emr.hadoop.fs.guice.EmrFSProdModule.createAmazonS3LiteClient(EmrFSProdModule.java:80)
at com.amazon.ws.emr.hadoop.fs.guice.EmrFSProdModule.createAmazonS3Lite(EmrFSProdModule.java:120)
at com.amazon.ws.emr.hadoop.fs.guice.EmrFSBaseModule.provideAmazonS3Lite(EmrFSBaseModule.java:99)
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 com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.internal.ProviderMethod.get(ProviderMethod.java:104)
at com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.internal.InternalFactoryToProviderAdapter.get(InternalFactoryToProviderAdapter.java:40)
at com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.internal.ProviderToInternalFactoryAdapter$1.call(ProviderToInternalFactoryAdapter.java:46)
at com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.internal.InjectorImpl.callInContext(InjectorImpl.java:1031)
at com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.internal.ProviderToInternalFactoryAdapter.get(ProviderToInternalFactoryAdapter.java:40)
at com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.Scopes$1$1.get(Scopes.java:65)
at com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.internal.InternalFactoryToProviderAdapter.get(InternalFactoryToProviderAdapter.java:40)
at com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.internal.SingleFieldInjector.inject(SingleFieldInjector.java:53)
at com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.internal.MembersInjectorImpl.injectMembers(MembersInjectorImpl.java:110)
at com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.internal.ConstructorInjector.construct(ConstructorInjector.java:94)
at com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.internal.ConstructorBindingImpl$Factory.get(ConstructorBindingImpl.java:254)
at com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.internal.FactoryProxy.get(FactoryProxy.java:54)
at com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.internal.InjectorImpl$4$1.call(InjectorImpl.java:978)
at com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.internal.InjectorImpl.callInContext(InjectorImpl.java:1024)
at com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.internal.InjectorImpl$4.get(InjectorImpl.java:974)
at com.amazon.ws.emr.hadoop.fs.shaded.com.google.inject.internal.InjectorImpl.getInstance(InjectorImpl.java:1009)
at com.amazon.ws.emr.hadoop.fs.EmrFileSystem.initialize(EmrFileSystem.java:103)
at org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:2717)
at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:93)
at org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:2751)
at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:2733)
at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:377)
at org.apache.hadoop.fs.Path.getFileSystem(Path.java:295)
at org.apache.spark.sql.execution.datasources.DataSource.writeInFileFormat(DataSource.scala:394)
at org.apache.spark.sql.execution.datasources.DataSource.write(DataSource.scala:471)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:50)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:92)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:92)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:609)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:233)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:217)
at org.apache.spark.sql.DataFrameWriter.json(DataFrameWriter.scala:487)
at com.org.ComparatorUtil$.writeLogNError(ComparatorUtil.scala:245)
at com.org.ComparatorUtil$.writeToJson(ComparatorUtil.scala:161)
at com.org.comparator.SnowFlakeTableComparator$.mainExecutor(SnowFlakeTableComparator.scala:98)
at com.org.executor.myclass$$anonfun$main$4$$anonfun$apply$1.apply(myclass.scala:232)
at com.org.executor.myclass$$anonfun$main$4$$anonfun$apply$1.apply(myclass.scala:153)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
at com.org.executor.myclass$$anonfun$main$4.apply(myclass.scala:153)
at com.org.executor.myclass$$anonfun$main$4.apply(myclass.scala:134)
at scala.collection.immutable.List.foreach(List.scala:381)
at com.org.executor.myclass$.main(myclass.scala:134)
at com.org.executor.myclass.main(myclass.scala)
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 org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:775)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:119)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.IllegalArgumentException: URI is not absolute
at java.net.URI.toURL(URI.java:1088)
at org.apache.hadoop.fs.http.AbstractHttpFileSystem.open(AbstractHttpFileSystem.java:60)
at org.apache.hadoop.fs.http.HttpFileSystem.open(HttpFileSystem.java:23)
at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:773)
at org.apache.hadoop.fs.FsUrlConnection.connect(FsUrlConnection.java:50)
at org.apache.hadoop.fs.FsUrlConnection.getInputStream(FsUrlConnection.java:59)
at java.net.URL.openStream(URL.java:1045)
at com.amazon.ws.emr.hadoop.fs.shaded.com.fasterxml.jackson.core.JsonFactory._optimizedStreamFromURL(JsonFactory.java:1479)
at com.amazon.ws.emr.hadoop.fs.shaded.com.fasterxml.jackson.core.JsonFactory.createParser(JsonFactory.java:779)
at com.amazon.ws.emr.hadoop.fs.shaded.com.fasterxml.jackson.databind.ObjectMapper.readValue(ObjectMapper.java:2679)
at com.amazon.ws.emr.hadoop.fs.util.PlatformInfo.getClusterIdFromConfigurationEndpoint(PlatformInfo.java:39)
at com.amazon.ws.emr.hadoop.fs.util.PlatformInfo.getJobFlowId(PlatformInfo.java:53)
at com.amazon.ws.emr.hadoop.fs.util.EmrFsUtils.getJobFlowId(EmrFsUtils.java:384)
at com.amazon.ws.emr.hadoop.fs.util.EmrFsUtils.(EmrFsUtils.java:60)
... 77 more
import java.net.URI
import spark.implicits._
spark.sparkContext.parallelize(1 to 4).toDF
.coalesce(1)
.write.mode(SaveMode.Overwrite)
.json(new URI("s3://myawsacc/results/").toString)
spark.sparkContext.parallelize(1 to 4).toDF
.coalesce(1)
.write.mode(SaveMode.Overwrite)
.json(URI.create("s3://myawsacc/results/").toString)
is working fine for me.
seems like spark-shell implcitly applying new URI or URI.create and hence its was working fine.
I want to execute spark2 job in my cloudera cluster (cdh) kerberos enabled.
I enabled kerberos in cludera cluster 15.0.1 with MIT kerberos .
When I want to send an email, I hit the following error:
ERROR spark.SparkContext: Error initializing SparkContext.
org.apache.spark.SparkException: Yarn application has already ended! It might have been killed or unable to launch app lication master.
at org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend.waitForApplication(YarnClientSchedulerBackend .scala:85)
at org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend.start(YarnClientSchedulerBackend.scala:62)
at org.apache.spark.scheduler.TaskSchedulerImpl.start(TaskSchedulerImpl.scala:165)
at org.apache.spark.SparkContext.<init>(SparkContext.scala:512)
at org.apache.spark.SparkContext$.getOrCreate(SparkContext.scala:2511)
at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:909)
at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:901)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.sql.SparkSession$Builder.getOrCreate(SparkSession.scala:901)
at org.apache.spark.repl.Main$.createSparkSession(Main.scala:97)
at $line3.$read$$iw$$iw.<init>(<console>:15)
at $line3.$read$$iw.<init>(<console>:42)
at $line3.$read.<init>(<console>:44)
at $line3.$read$.<init>(<console>:48)
at $line3.$read$.<clinit>(<console>)
at $line3.$eval$.$print$lzycompute(<console>:7)
at $line3.$eval$.$print(<console>:6)
at $line3.$eval.$print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at scala.tools.nsc.interpreter.IMain$ReadEvalPrint.call(IMain.scala:786)
at scala.tools.nsc.interpreter.IMain$Request.loadAndRun(IMain.scala:1047)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:638)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:637)
at scala.reflect.internal.util.ScalaClassLoader$class.asContext(ScalaClassLoader.scala:31)
at scala.reflect.internal.util.AbstractFileClassLoader.asContext(AbstractFileClassLoader.scala:19)
at scala.tools.nsc.interpreter.IMain$WrappedRequest.loadAndRunReq(IMain.scala:637)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:569)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:565)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:807)
at scala.tools.nsc.interpreter.ILoop.command(ILoop.scala:681)
at scala.tools.nsc.interpreter.ILoop.processLine(ILoop.scala:395)
at org.apache.spark.repl.SparkILoop$$anonfun$initializeSpark$1.apply$mcV$sp(SparkILoop.scala:38)
at org.apache.spark.repl.SparkILoop$$anonfun$initializeSpark$1.apply(SparkILoop.scala:37)
at org.apache.spark.repl.SparkILoop$$anonfun$initializeSpark$1.apply(SparkILoop.scala:37)
at scala.tools.nsc.interpreter.IMain.beQuietDuring(IMain.scala:214)
at org.apache.spark.repl.SparkILoop.initializeSpark(SparkILoop.scala:37)
at org.apache.spark.repl.SparkILoop.loadFiles(SparkILoop.scala:98)
at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply$mcZ$sp(ILoop.scala:920)
at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply(ILoop.scala:909)
at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply(ILoop.scala:909)
at scala.reflect.internal.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:97)
at scala.tools.nsc.interpreter.ILoop.process(ILoop.scala:909)
at org.apache.spark.repl.Main$.doMain(Main.scala:70)
at org.apache.spark.repl.Main$.main(Main.scala:53)
at org.apache.spark.repl.Main.main(Main.scala)
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 org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:755)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:119)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
18/09/05 11:59:33 WARN cluster.YarnSchedulerBackend$YarnSchedulerEndpoint: Attempted to request executors before the A M has registered!
18/09/05 11:59:33 ERROR util.Utils: Uncaught exception in thread main
java.lang.NullPointerException
at org.apache.spark.network.shuffle.ExternalShuffleClient.close(ExternalShuffleClient.java:141)
at org.apache.spark.storage.BlockManager.stop(BlockManager.scala:1485)
at org.apache.spark.SparkEnv.stop(SparkEnv.scala:90)
at org.apache.spark.SparkContext$$anonfun$stop$11.apply$mcV$sp(SparkContext.scala:1939)
at org.apache.spark.util.Utils$.tryLogNonFatalError(Utils.scala:1317)
at org.apache.spark.SparkContext.stop(SparkContext.scala:1938)
at org.apache.spark.SparkContext.<init>(SparkContext.scala:590)
at org.apache.spark.SparkContext$.getOrCreate(SparkContext.scala:2511)
at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:909)
at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:901)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.sql.SparkSession$Builder.getOrCreate(SparkSession.scala:901)
at org.apache.spark.repl.Main$.createSparkSession(Main.scala:97)
at $line3.$read$$iw$$iw.<init>(<console>:15)
at $line3.$read$$iw.<init>(<console>:42)
at $line3.$read.<init>(<console>:44)
at $line3.$read$.<init>(<console>:48)
at $line3.$read$.<clinit>(<console>)
at $line3.$eval$.$print$lzycompute(<console>:7)
at $line3.$eval$.$print(<console>:6)
at $line3.$eval.$print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at scala.tools.nsc.interpreter.IMain$ReadEvalPrint.call(IMain.scala:786)
at scala.tools.nsc.interpreter.IMain$Request.loadAndRun(IMain.scala:1047)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:638)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:637)
at scala.reflect.internal.util.ScalaClassLoader$class.asContext(ScalaClassLoader.scala:31)
at scala.reflect.internal.util.AbstractFileClassLoader.asContext(AbstractFileClassLoader.scala:19)
at scala.tools.nsc.interpreter.IMain$WrappedRequest.loadAndRunReq(IMain.scala:637)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:569)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:565)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:807)
at scala.tools.nsc.interpreter.ILoop.command(ILoop.scala:681)
at scala.tools.nsc.interpreter.ILoop.processLine(ILoop.scala:395)
at org.apache.spark.repl.SparkILoop$$anonfun$initializeSpark$1.apply$mcV$sp(SparkILoop.scala:38)
at org.apache.spark.repl.SparkILoop$$anonfun$initializeSpark$1.apply(SparkILoop.scala:37)
at org.apache.spark.repl.SparkILoop$$anonfun$initializeSpark$1.apply(SparkILoop.scala:37)
at scala.tools.nsc.interpreter.IMain.beQuietDuring(IMain.scala:214)
at org.apache.spark.repl.SparkILoop.initializeSpark(SparkILoop.scala:37)
at org.apache.spark.repl.SparkILoop.loadFiles(SparkILoop.scala:98)
at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply$mcZ$sp(ILoop.scala:920)
at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply(ILoop.scala:909)
at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply(ILoop.scala:909)
at scala.reflect.internal.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:97)
at scala.tools.nsc.interpreter.ILoop.process(ILoop.scala:909)
at org.apache.spark.repl.Main$.doMain(Main.scala:70)
at org.apache.spark.repl.Main$.main(Main.scala:53)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:755)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:119)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
org.apache.spark.SparkException: Yarn application has already ended! It might have been killed or unable to launch app lication master.
at org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend.waitForApplication(YarnClientSchedulerBackend.scala :85)
at org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend.start(YarnClientSchedulerBackend.scala:62)
at org.apache.spark.scheduler.TaskSchedulerImpl.start(TaskSchedulerImpl.scala:165)
at org.apache.spark.SparkContext.<init>(SparkContext.scala:512)
at org.apache.spark.SparkContext$.getOrCreate(SparkContext.scala:2511)
at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:909)
at org.apache.spark.sql.SparkSession$Builder$$anonfun$6.apply(SparkSession.scala:901)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.sql.SparkSession$Builder.getOrCreate(SparkSession.scala:901)
at org.apache.spark.repl.Main$.createSparkSession(Main.scala:97)
... 47 elided
<console>:14: error: not found: value spark
import spark.implicits._
^
<console>:14: error: not found: value spark
import spark.sql
^
Welcome to
____ __
/ __/__ ___ _____/ /__
_\ \/ _ \/ _ `/ __/ '_/
/___/ .__/\_,_/_/ /_/\_\ version 2.2.0.cloudera2
/_/
Using Scala version 2.11.8 (Java HotSpot(TM) 64-Bit Server VM, Java 1.8.0_144)
Type in expressions to have them evaluated.
Type :help for more information.
scala>
please help me.
I'm trying to connect to hbase from Pyspark using SHC API by referring the below link.
https://community.hortonworks.com/questions/143802/read-hbase-with-pyspark-from-jupyter-notebook.html
Sample code:
spark = SparkSession.builder.appName("Hbase Read").getOrCreate()
data_source_format = 'org.apache.spark.sql.execution.datasources.hbase'
catalog = ''.join("""{
"table":{"namespace":"default", "name":"table"},
"rowkey":"key",
"columns":{
"firstcol":{"cf":"rowkey", "col":"key", "type":"string"},
"secondcol":{"cf":"cf", "col":"col1", "type":"int"}
}
}""".split())
df = spark.read \
.options(catalog=catalog) \
.format(data_source_format) \
.load()
df.show()
Spark-submit:
spark-submit --packages com.hortonworks:shc:1.1.1-2.1-s_2.11 --repositories http://repo.hortonworks.com/content/groups/public/ TestHbaseRead.py
i'm getting this error.
Error log:
: java.lang.ClassNotFoundException: Failed to find data source: org.apache.spark.sql.execution.datasources.hbase. Please find packages at http://spark.apache.org/third-party-projects.html
at org.apache.spark.sql.execution.datasources.DataSource$.lookupDataSource(DataSource.scala:635)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:190)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:164)
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:214)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.ClassNotFoundException: org.apache.spark.sql.execution.datasources.hbase.DefaultSource
at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$23$$anonfun$apply$15.apply(DataSource.scala:618)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$23$$anonfun$apply$15.apply(DataSource.scala:618)
at scala.util.Try$.apply(Try.scala:192)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$23.apply(DataSource.scala:618)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$23.apply(DataSource.scala:618)
at scala.util.Try.orElse(Try.scala:84)
at org.apache.spark.sql.execution.datasources.DataSource$.lookupDataSource(DataSource.scala:618)
... 13 more