You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@calcite.apache.org by "Julian Hyde (JIRA)" <ji...@apache.org> on 2017/05/25 00:34:04 UTC

[jira] [Updated] (CALCITE-1806) UnsupportedOperationException accessing Druid through Spark JDBC

     [ https://issues.apache.org/jira/browse/CALCITE-1806?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Julian Hyde updated CALCITE-1806:
---------------------------------
    Description: 
I am interested in querying Druid via Spark.  I realize that there are several mechanisms for doing this, but I was curious about using the JDBC batch offered by the latest release as it is familiar to our analysts and seems like it should be a well supported path going forward.

My first attempt has failed with an UnsupportedOperationException.  I ran spark-shell with the --jars option to add the avatica 1.9.0 jdbc driver jar.

{noformat}
scala> val dw2 = sqlContext.read.format("jdbc").options(Map("url" -> "jdbc:avatica:remote:url=http://jarvis-druid-query002:8082/druid/v2/sql/avatica/", "dbtable" -> "sor_business_events_all", "driver" -> "org.apache.calcite.avatica.remote.Driver", "fetchSize"->"10000")).load()

java.lang.UnsupportedOperationException
	at org.apache.calcite.avatica.AvaticaConnection.prepareStatement(AvaticaConnection.java:275)
	at org.apache.calcite.avatica.AvaticaConnection.prepareStatement(AvaticaConnection.java:121)
	at org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$.resolveTable(JDBCRDD.scala:122)
	at org.apache.spark.sql.execution.datasources.jdbc.JDBCRelation.<init>(JDBCRelation.scala:91)
	at org.apache.spark.sql.execution.datasources.jdbc.DefaultSource.createRelation(DefaultSource.scala:57)
	at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:158)
	at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:119)
	at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:25)
	at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:30)
	at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:32)
	at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:34)
	at $iwC$$iwC$$iwC$$iwC.<init>(<console>:36)
	at $iwC$$iwC$$iwC.<init>(<console>:38)
	at $iwC$$iwC.<init>(<console>:40)
	at $iwC.<init>(<console>:42)
	at <init>(<console>:44)
	at .<init>(<console>:48)
	at .<clinit>(<console>)
	at .<init>(<console>:7)
	at .<clinit>(<console>)
	at $print(<console>)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:606)
	at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1045)
	at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1326)
	at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:821)
	at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:852)
	at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:800)
	at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
	at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
	at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
	at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
	at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
	at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
	at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
	at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
	at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
	at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
	at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
	at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1064)
	at org.apache.spark.repl.Main$.main(Main.scala:31)
	at org.apache.spark.repl.Main.main(Main.scala)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:606)
	at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
	at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
	at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
	at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
	at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala){noformat}

  was:
I am interested in querying Druid via Spark.  I realize that there are several mechanisms for doing this, but I was curious about using the JDBC batch offered by the latest release as it is familiar to our analysts and seems like it should be a well supported path going forward.

My first attempt has failed with an UnsupportedOperationException.  I ran spark-shell with the --jars option to add the avatica 1.9.0 jdbc driver jar.

scala> val dw2 = sqlContext.read.format("jdbc").options(Map("url" -> "jdbc:avatica:remote:url=http://jarvis-druid-query002:8082/druid/v2/sql/avatica/", "dbtable" -> "sor_business_events_all", "driver" -> "org.apache.calcite.avatica.remote.Driver", "fetchSize"->"10000")).load()

java.lang.UnsupportedOperationException
	at org.apache.calcite.avatica.AvaticaConnection.prepareStatement(AvaticaConnection.java:275)
	at org.apache.calcite.avatica.AvaticaConnection.prepareStatement(AvaticaConnection.java:121)
	at org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$.resolveTable(JDBCRDD.scala:122)
	at org.apache.spark.sql.execution.datasources.jdbc.JDBCRelation.<init>(JDBCRelation.scala:91)
	at org.apache.spark.sql.execution.datasources.jdbc.DefaultSource.createRelation(DefaultSource.scala:57)
	at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:158)
	at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:119)
	at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:25)
	at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:30)
	at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:32)
	at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:34)
	at $iwC$$iwC$$iwC$$iwC.<init>(<console>:36)
	at $iwC$$iwC$$iwC.<init>(<console>:38)
	at $iwC$$iwC.<init>(<console>:40)
	at $iwC.<init>(<console>:42)
	at <init>(<console>:44)
	at .<init>(<console>:48)
	at .<clinit>(<console>)
	at .<init>(<console>:7)
	at .<clinit>(<console>)
	at $print(<console>)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:606)
	at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1045)
	at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1326)
	at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:821)
	at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:852)
	at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:800)
	at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
	at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
	at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
	at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
	at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
	at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
	at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
	at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
	at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
	at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
	at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
	at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1064)
	at org.apache.spark.repl.Main$.main(Main.scala:31)
	at org.apache.spark.repl.Main.main(Main.scala)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:606)
	at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
	at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
	at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
	at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
	at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)


> UnsupportedOperationException accessing Druid through Spark JDBC
> ----------------------------------------------------------------
>
>                 Key: CALCITE-1806
>                 URL: https://issues.apache.org/jira/browse/CALCITE-1806
>             Project: Calcite
>          Issue Type: Bug
>          Components: avatica
>    Affects Versions: avatica-1.9.0
>         Environment: Spark 1.6, scala 10, CDH 5.7
>            Reporter: Benjamin Vogan
>
> I am interested in querying Druid via Spark.  I realize that there are several mechanisms for doing this, but I was curious about using the JDBC batch offered by the latest release as it is familiar to our analysts and seems like it should be a well supported path going forward.
> My first attempt has failed with an UnsupportedOperationException.  I ran spark-shell with the --jars option to add the avatica 1.9.0 jdbc driver jar.
> {noformat}
> scala> val dw2 = sqlContext.read.format("jdbc").options(Map("url" -> "jdbc:avatica:remote:url=http://jarvis-druid-query002:8082/druid/v2/sql/avatica/", "dbtable" -> "sor_business_events_all", "driver" -> "org.apache.calcite.avatica.remote.Driver", "fetchSize"->"10000")).load()
> java.lang.UnsupportedOperationException
> 	at org.apache.calcite.avatica.AvaticaConnection.prepareStatement(AvaticaConnection.java:275)
> 	at org.apache.calcite.avatica.AvaticaConnection.prepareStatement(AvaticaConnection.java:121)
> 	at org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$.resolveTable(JDBCRDD.scala:122)
> 	at org.apache.spark.sql.execution.datasources.jdbc.JDBCRelation.<init>(JDBCRelation.scala:91)
> 	at org.apache.spark.sql.execution.datasources.jdbc.DefaultSource.createRelation(DefaultSource.scala:57)
> 	at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:158)
> 	at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:119)
> 	at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:25)
> 	at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:30)
> 	at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:32)
> 	at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:34)
> 	at $iwC$$iwC$$iwC$$iwC.<init>(<console>:36)
> 	at $iwC$$iwC$$iwC.<init>(<console>:38)
> 	at $iwC$$iwC.<init>(<console>:40)
> 	at $iwC.<init>(<console>:42)
> 	at <init>(<console>:44)
> 	at .<init>(<console>:48)
> 	at .<clinit>(<console>)
> 	at .<init>(<console>:7)
> 	at .<clinit>(<console>)
> 	at $print(<console>)
> 	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> 	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> 	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> 	at java.lang.reflect.Method.invoke(Method.java:606)
> 	at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1045)
> 	at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1326)
> 	at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:821)
> 	at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:852)
> 	at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:800)
> 	at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
> 	at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
> 	at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
> 	at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
> 	at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
> 	at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
> 	at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
> 	at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
> 	at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
> 	at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
> 	at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
> 	at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1064)
> 	at org.apache.spark.repl.Main$.main(Main.scala:31)
> 	at org.apache.spark.repl.Main.main(Main.scala)
> 	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> 	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> 	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> 	at java.lang.reflect.Method.invoke(Method.java:606)
> 	at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
> 	at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
> 	at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
> 	at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
> 	at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala){noformat}



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)