update big data error
Posted by yixu2001 on May 22, 2017; 10:22am
URL: http://apache-carbondata-dev-mailing-list-archive.168.s1.nabble.com/update-big-data-error-tp13064.html
dev
V_ORDER_ITEM_PROC_ATTR_CARBON3 (primary key ID) amount of data 7 Billion
update_order_item3 (primary key ID) amount of data 100Million
spark1.6 carbon 1.1 run sql
cc.sql("update e_carbon.V_ORDER_ITEM_PROC_ATTR_CARBON5
A set (a.ORDER_ITEM_ID, a.CLASS_ID )
=(SELECT b.ORDER_ITEM_ID, b.CLASS_ID
from e_carbon.update_order_item3 b
where b.ID=A.ID)").show
Error message
17/05/22 16:14:33 AUDIT deleteExecution$: [HETL032][e_carbon][Thread-1]Delete data operation is failed for e_carbon.v_order_item_proc_attr_carbon5
17/05/22 16:14:33 ERROR deleteExecution$: main Delete data operation is failed due to failure in creating delete delta file for segment : null block : null
17/05/22 16:14:33 ERROR ProjectForUpdateCommand$: main Exception in update operationjava.lang.Exception: Multiple input rows matched for same row.
17/05/22 16:14:33 INFO MapPartitionsRDD: Removing RDD 21 from persistence list
17/05/22 16:14:33 INFO BlockManager: Removing RDD 21
17/05/22 16:14:33 INFO HdfsFileLock: main Deleted the lock file hdfs://ns1/user/e_carbon/private/carbon.store/e_carbon/v_order_item_proc_attr_carbon5/meta.lock
17/05/22 16:14:33 INFO CarbonLockUtil: main Metadata lock has been successfully released
java.lang.RuntimeException: Update operation failed. Multiple input rows matched for same row.
at scala.sys.package$.error(package.scala:27)
at org.apache.spark.sql.execution.command.ProjectForUpdateCommand.run(IUDCommands.scala:236)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:58)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:56)
at org.apache.spark.sql.execution.ExecutedCommand.executeTake(commands.scala:67)
at org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala:165)
at org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:174)
at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1538)
at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1538)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:2125)
at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$execute$1(DataFrame.scala:1537)
at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$collect(DataFrame.scala:1544)
at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1414)
at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1413)
at org.apache.spark.sql.DataFrame.withCallback(DataFrame.scala:2138)
at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1413)
at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1495)
at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:171)
at org.apache.spark.sql.DataFrame.show(DataFrame.scala:394)
at org.apache.spark.sql.DataFrame.show(DataFrame.scala:355)
at org.apache.spark.sql.DataFrame.show(DataFrame.scala:363)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:31)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:36)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:38)
at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:40)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:42)
at $iwC$$iwC$$iwC.<init>(<console>:44)
at $iwC$$iwC.<init>(<console>:46)
at $iwC.<init>(<console>:48)
at <init>(<console>:50)
at .<init>(<console>:54)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1346)
at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
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:1059)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
at org.a
yixu2001