Hi liujun: This issue has been fixed and merged at PR29, please use the latest master code to try it again.
Regards Liang 2016-07-07 13:05 GMT+05:30 刘军 <[email protected]>: > 各位好，我在对一个表进行多次数据导入上，不能正常使用，如下： > scala> cc.sql("create table if not exists tt (id string, name string, city > string, age Int) stored by 'org.apache.carbondata.format'") > > scala> cc.sql(s"load data inpath 'hdfs://127.0.0.1:9000/test/sample.csv' > into table tt") > scala> cc.sql("select * from tt").show > > > 以上几步日志及结果均正常 > scala> cc.sql(s"load data inpath 'hdfs://127.0.0.1:9000/test/sample.csv' > into table tt") > > 此步日志提正常 > scala> cc.sql("select * from tt").show > > 此步出错，希望能得到解决，感谢大家。 > 错误信息如下： > scala> cc.sql("select * from tt").show > INFO 07-07 15:29:12,020 - main Query [SELECT * FROM TT] > INFO 07-07 15:29:12,024 - Parsing command: select * from tt > INFO 07-07 15:29:12,024 - Parse Completed > INFO 07-07 15:29:12,026 - Parsing command: select * from tt > INFO 07-07 15:29:12,027 - Parse Completed > ERROR 07-07 15:29:12,182 - main > java.io.IOException: java.io.FileNotFoundException: File does not exist: > hdfs://127.0.0.1:9000/carbondata/default/tt/Fact/Part0/Segment_0 > at > org.carbondata.hadoop.CarbonInputFormat.getSplits(CarbonInputFormat.java:286) > at > org.carbondata.spark.rdd.CarbonScanRDD.getPartitions(CarbonScanRDD.scala:84) > 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.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.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.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.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.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.sql.execution.SparkPlan.executeTake(SparkPlan.scala:190) > 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:1499) > at > org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499) > at > org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56) > at > org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:2086) > at org.apache.spark.sql.DataFrame.org > $apache$spark$sql$DataFrame$$execute$1(DataFrame.scala:1498) > at org.apache.spark.sql.DataFrame.org > $apache$spark$sql$DataFrame$$collect(DataFrame.scala:1505) > at > org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1375) > at > org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1374) > at > org.apache.spark.sql.DataFrame.withCallback(DataFrame.scala:2099) > at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1374) > at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1456) > at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:170) > at org.apache.spark.sql.DataFrame.show(DataFrame.scala:350) > at org.apache.spark.sql.DataFrame.show(DataFrame.scala:311) > at org.apache.spark.sql.DataFrame.show(DataFrame.scala:319) > at > $line53.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:35) > at > $line53.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:40) > at $line53.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:42) > at $line53.$read$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:44) > at $line53.$read$$iwC$$iwC$$iwC$$iwC.<init>(<console>:46) > at $line53.$read$$iwC$$iwC$$iwC.<init>(<console>:48) > at $line53.$read$$iwC$$iwC.<init>(<console>:50) > at $line53.$read$$iwC.<init>(<console>:52) > at $line53.$read.<init>(<console>:54) > at $line53.$read$.<init>(<console>:58) > at $line53.$read$.<clinit>(<console>) > at $line53.$eval$.<init>(<console>:7) > at $line53.$eval$.<clinit>(<console>) > at $line53.$eval.$print(<console>) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:497) > at > org.apache.spark.repl.SparkIMain$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$.main(Main.scala:31) > at org.apache.spark.repl.Main.main(Main.scala) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:497) > at > org.apache.spark.deploy.SparkSubmit$.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) > Caused by: java.io.FileNotFoundException: File does not exist: hdfs:// > 127.0.0.1:9000/carbondata/default/tt/Fact/Part0/Segment_0 > at > org.apache.hadoop.hdfs.DistributedFileSystem$18.doCall(DistributedFileSystem.java:1122) > at > org.apache.hadoop.hdfs.DistributedFileSystem$18.doCall(DistributedFileSystem.java:1114) > at > org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81) > at > org.apache.hadoop.hdfs.DistributedFileSystem.getFileStatus(DistributedFileSystem.java:1114) > at org.apache.hadoop.fs.FileSystem.resolvePath(FileSystem.java:750) > at > org.apache.hadoop.hdfs.DistributedFileSystem$16.<init>(DistributedFileSystem.java:779) > at > org.apache.hadoop.hdfs.DistributedFileSystem.listLocatedStatus(DistributedFileSystem.java:770) > at > org.apache.hadoop.fs.FileSystem.listLocatedStatus(FileSystem.java:1664) > at > org.carbondata.hadoop.CarbonInputFormat.getFileStatusOfSegments(CarbonInputFormat.java:629) > at > org.carbondata.hadoop.CarbonInputFormat.listStatus(CarbonInputFormat.java:602) > at > org.apache.hadoop.mapreduce.lib.input.FileInputFormat.getSplits(FileInputFormat.java:385) > at > org.carbondata.hadoop.CarbonInputFormat.getSplitsInternal(CarbonInputFormat.java:291) > at > org.carbondata.hadoop.CarbonInputFormat.getSplits(CarbonInputFormat.java:273) > ... 99 more > java.lang.RuntimeException: Exception occurred in query execution :: > java.io.FileNotFoundException: File does not exist: hdfs:// > 127.0.0.1:9000/carbondata/default/tt/Fact/Part0/Segment_0 > at scala.sys.package$.error(package.scala:27) > at > org.carbondata.spark.rdd.CarbonScanRDD.getPartitions(CarbonScanRDD.scala:95) > 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$$anonfun$partitions$2.apply(RDD.scala:237) > at scala.Option.getOrElse(Option.scala:120) > at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) > at > org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35) > at > org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239) > at > org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237) > at scala.Option.getOrElse(Option.scala:120) > at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) > at > org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35) > at > org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239) > at > org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237) > at scala.Option.getOrElse(Option.scala:120) > at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) > at > org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35) > at > org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239) > at > org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237) > at scala.Option.getOrElse(Option.scala:120) > at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) > at > org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35) > at > org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239) > at > org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237) > at scala.Option.getOrElse(Option.scala:120) > at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) > at > org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35) > at > org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239) > at > org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237) > at scala.Option.getOrElse(Option.scala:120) > at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) > at > org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:190) > at > org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala:165) > at > org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:174) > at > org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499) > at > org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499) > at > org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56) > at > org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:2086) > at org.apache.spark.sql.DataFrame.org > $apache$spark$sql$DataFrame$$execute$1(DataFrame.scala:1498) > at org.apache.spark.sql.DataFrame.org > $apache$spark$sql$DataFrame$$collect(DataFrame.scala:1505) > at > org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1375) > at > org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1374) > at > org.apache.spark.sql.DataFrame.withCallback(DataFrame.scala:2099) > at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1374) > at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1456) > at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:170) > at org.apache.spark.sql.DataFrame.show(DataFrame.scala:350) > at org.apache.spark.sql.DataFrame.show(DataFrame.scala:311) > at org.apache.spark.sql.DataFrame.show(DataFrame.scala:319) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:35) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:40) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:42) > at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:44) > at $iwC$$iwC$$iwC$$iwC.<init>(<console>:46) > at $iwC$$iwC$$iwC.<init>(<console>:48) > at $iwC$$iwC.<init>(<console>:50) > at $iwC.<init>(<console>:52) > at <init>(<console>:54) > at .<init>(<console>:58) > at .<clinit>(<console>) > at .<init>(<console>:7) > at .<clinit>(<console>) > at $print(<console>) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:497) > at > org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065) > at > org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1346) > at > org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840) > at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871) > at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819) > at > org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857) > at > org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902) > at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814) > at > org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657) > at > org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665) > at org.apache.spark.repl.SparkILoop.org > $apache$spark$repl$SparkILoop$$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$$process(SparkILoop.scala:945) > at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059) > at org.apache.spark.repl.Main$.main(Main.scala:31) > at org.apache.spark.repl.Main.main(Main.scala) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:497) > at > org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$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) -- Regards Liang
