hi, all I have installed carbonate succeed following the document “https://cwiki.apache.org/confluence/display/CARBONDATA/“ but when load data into carbonate table throws exception: run command: cc.sql("load data local inpath '../carbondata/sample.csv' into table test_table") errors: org.apache.hadoop.mapreduce.lib.input.InvalidInputException: Input path does not exist: /home/bigdata/bigdata/carbondata/sample.csv at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:321) at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.listStatus(FileInputFormat.java:264) at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.getSplits(FileInputFormat.java:385) at org.apache.spark.rdd.NewHadoopRDD.getPartitions(NewHadoopRDD.scala:120) 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.RDD$$anonfun$take$1.apply(RDD.scala:1307) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111) at org.apache.spark.rdd.RDD.withScope(RDD.scala:316) at org.apache.spark.rdd.RDD.take(RDD.scala:1302) at com.databricks.spark.csv.CarbonCsvRelation.firstLine$lzycompute(CarbonCsvRelation.scala:181) at com.databricks.spark.csv.CarbonCsvRelation.firstLine(CarbonCsvRelation.scala:176) at com.databricks.spark.csv.CarbonCsvRelation.inferSchema(CarbonCsvRelation.scala:144) at com.databricks.spark.csv.CarbonCsvRelation.<init>(CarbonCsvRelation.scala:74) at com.databricks.spark.csv.newapi.DefaultSource.createRelation(DefaultSource.scala:142) at com.databricks.spark.csv.newapi.DefaultSource.createRelation(DefaultSource.scala:44) at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:158) at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:119) at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:109) at org.apache.carbondata.spark.util.GlobalDictionaryUtil$.loadDataFrame(GlobalDictionaryUtil.scala:386) at org.apache.carbondata.spark.util.GlobalDictionaryUtil$.generateGlobalDictionary(GlobalDictionaryUtil.scala:767) at org.apache.spark.sql.execution.command.LoadTable.run(carbonTableSchema.scala:1170) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:58) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:56) at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:70) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55) at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:145) at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:130) at org.apache.carbondata.spark.rdd.CarbonDataFrameRDD.<init>(CarbonDataFrameRDD.scala:23) at org.apache.spark.sql.CarbonContext.sql(CarbonContext.scala:137) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:42) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:47) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:49) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:51) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:53) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:55) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:57) at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:59) at $iwC$$iwC$$iwC$$iwC.<init>(<console>:61) at $iwC$$iwC$$iwC.<init>(<console>:63) at $iwC$$iwC.<init>(<console>:65) at $iwC.<init>(<console>:67) at <init>(<console>:69) at .<init>(<console>:73) at .<clinit>(<console>) at .<init>(<console>:7) at .<clinit>(<console>) at $print(<console>) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065) at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1346) at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840) at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871) at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819) at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857) at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902) at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814) at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657) at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665) at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$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$$process(SparkILoop.scala:945) at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059) at org.apache.spark.repl.carbon.Main$.main(Main.scala:31) at org.apache.spark.repl.carbon.Main.main(Main.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$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) cat /home/bigdata/bigdata/carbondata/sample.csv id,name,city,age 1,david,shenzhen,31 2,eason,shenzhen,27 3,jarry,wuhan,35 ip:taonongyuan.com username:bigdata passwd: Zjw11763 this is private <http://www.baidu.com/link?url=zuB-GJ6ONUu4xqmpd_NsR53R4f-Dwi037YBSX9Xc1DOs3kXtzG5XjyhXo7uAOcC1hfRcTaEnGZQoscjTduMloRYu-KsmdmEUPsq68db0VH3MoYCMd5IamXotlUEffF9b> aly cents server ,you can login to debug….. regards, 仲景武 在 2016年9月27日,上午4:56,Liang Big data <[hidden email]<mailto:[hidden email]>> 写道: Hi zhongjingwu: Can you put these discussions into mailing list : [hidden email]<mailto:[hidden email]> You may get more helps from mailing list. Regards Liang 在 2016年9月26日 下午8:48,仲景武 <[hidden email]<mailto:[hidden email]>>写道: 在 2016年9月26日,下午8:46,仲景武 <[hidden email]<mailto:[hidden email]>> 写道: 在 2016年9月26日,下午8:45,仲景武 <[hidden email]<mailto:[hidden email]>> 写道: @Override public int hashCode() { int hashCode = 1; hashCode = hashCode * 8191 + min_surrogate_key; hashCode = hashCode * 8191 + max_surrogate_key; hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper.hashCode(start_offset); hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper.hashCode(end_offset); hashCode = hashCode * 8191 + chunk_count; hashCode = hashCode * 8191 + ((isSetSegment_id()) ? 131071 : 524287); if (isSetSegment_id()) hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper.hashCode(segment_id); return hashCode; } 我在源码中没有看到 org.apache.thrift.TBaseHelper.hashCode(int) 这样的重载方案啊 无法编译成功啊,什么情况? <FE4BB0D35DD30805BE3BD071450C3118.jpeg> -- Regards Liang |
hi, jingwu,
Now, Carbon dose not support load data from local, pls put the file into HDFS and test it again. Lionx 2016-10-19 16:55 GMT+08:00 仲景武 <[hidden email]>: > > hi, all > > I have installed carbonate succeed following the document “ > https://cwiki.apache.org/confluence/display/CARBONDATA/“ > > but when load data into carbonate table throws exception: > > > run command: > cc.sql("load data local inpath '../carbondata/sample.csv' into table > test_table") > > errors: > > org.apache.hadoop.mapreduce.lib.input.InvalidInputException: Input path > does not exist: /home/bigdata/bigdata/carbondata/sample.csv > at org.apache.hadoop.mapreduce.lib.input.FileInputFormat. > singleThreadedListStatus(FileInputFormat.java:321) > at org.apache.hadoop.mapreduce.lib.input.FileInputFormat. > listStatus(FileInputFormat.java:264) > at org.apache.hadoop.mapreduce.lib.input.FileInputFormat. > getSplits(FileInputFormat.java:385) > at org.apache.spark.rdd.NewHadoopRDD.getPartitions(NewHadoopRDD.scala:120) > 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.RDD$$anonfun$take$1.apply(RDD.scala:1307) > at org.apache.spark.rdd.RDDOperationScope$.withScope( > RDDOperationScope.scala:150) > at org.apache.spark.rdd.RDDOperationScope$.withScope( > RDDOperationScope.scala:111) > at org.apache.spark.rdd.RDD.withScope(RDD.scala:316) > at org.apache.spark.rdd.RDD.take(RDD.scala:1302) > at com.databricks.spark.csv.CarbonCsvRelation.firstLine$ > lzycompute(CarbonCsvRelation.scala:181) > at com.databricks.spark.csv.CarbonCsvRelation.firstLine( > CarbonCsvRelation.scala:176) > at com.databricks.spark.csv.CarbonCsvRelation.inferSchema( > CarbonCsvRelation.scala:144) > at com.databricks.spark.csv.CarbonCsvRelation.<init>( > CarbonCsvRelation.scala:74) > at com.databricks.spark.csv.newapi.DefaultSource. > createRelation(DefaultSource.scala:142) > at com.databricks.spark.csv.newapi.DefaultSource. > createRelation(DefaultSource.scala:44) > at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply( > ResolvedDataSource.scala:158) > at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:119) > at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:109) > at org.apache.carbondata.spark.util.GlobalDictionaryUtil$.loadDataFrame( > GlobalDictionaryUtil.scala:386) > at org.apache.carbondata.spark.util.GlobalDictionaryUtil$. > generateGlobalDictionary(GlobalDictionaryUtil.scala:767) > at org.apache.spark.sql.execution.command.LoadTable. > run(carbonTableSchema.scala:1170) > at org.apache.spark.sql.execution.ExecutedCommand. > sideEffectResult$lzycompute(commands.scala:58) > at org.apache.spark.sql.execution.ExecutedCommand. > sideEffectResult(commands.scala:56) > at org.apache.spark.sql.execution.ExecutedCommand. > doExecute(commands.scala:70) > at org.apache.spark.sql.execution.SparkPlan$$anonfun$ > execute$5.apply(SparkPlan.scala:132) > at org.apache.spark.sql.execution.SparkPlan$$anonfun$ > execute$5.apply(SparkPlan.scala:130) > at org.apache.spark.rdd.RDDOperationScope$.withScope( > RDDOperationScope.scala:150) > at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) > at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute( > QueryExecution.scala:55) > at org.apache.spark.sql.execution.QueryExecution. > toRdd(QueryExecution.scala:55) > at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:145) > at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:130) > at org.apache.carbondata.spark.rdd.CarbonDataFrameRDD.<init>( > CarbonDataFrameRDD.scala:23) > at org.apache.spark.sql.CarbonContext.sql(CarbonContext.scala:137) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC. > <init>(<console>:42) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.< > init>(<console>:47) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:49) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:51) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:53) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:55) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:57) > at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:59) > at $iwC$$iwC$$iwC$$iwC.<init>(<console>:61) > at $iwC$$iwC$$iwC.<init>(<console>:63) > at $iwC$$iwC.<init>(<console>:65) > at $iwC.<init>(<console>:67) > at <init>(<console>:69) > at .<init>(<console>:73) > at .<clinit>(<console>) > at .<init>(<console>:7) > at .<clinit>(<console>) > at $print(<console>) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at sun.reflect.NativeMethodAccessorImpl.invoke( > NativeMethodAccessorImpl.java:57) > at sun.reflect.DelegatingMethodAccessorImpl.invoke( > DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:606) > at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call( > SparkIMain.scala:1065) > at org.apache.spark.repl.SparkIMain$Request.loadAndRun( > SparkIMain.scala:1346) > at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840) > at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871) > at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819) > at org.apache.spark.repl.SparkILoop.reallyInterpret$1( > SparkILoop.scala:857) > at org.apache.spark.repl.SparkILoop.interpretStartingWith( > SparkILoop.scala:902) > at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814) > at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657) > at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665) > at org.apache.spark.repl.SparkILoop.org$apache$spark$ > repl$SparkILoop$$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$$process(SparkILoop.scala:945) > at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059) > at org.apache.spark.repl.carbon.Main$.main(Main.scala:31) > at org.apache.spark.repl.carbon.Main.main(Main.scala) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at sun.reflect.NativeMethodAccessorImpl.invoke( > NativeMethodAccessorImpl.java:57) > at sun.reflect.DelegatingMethodAccessorImpl.invoke( > DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:606) > at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$ > deploy$SparkSubmit$$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) > > > > > cat /home/bigdata/bigdata/carbondata/sample.csv > > id,name,city,age > 1,david,shenzhen,31 > 2,eason,shenzhen,27 > 3,jarry,wuhan,35 > > > > ip:taonongyuan.com username:bigdata passwd: Zjw11763 > > this is private <http://www.baidu.com/link?url=zuB-GJ6ONUu4xqmpd_NsR53R4f- > Dwi037YBSX9Xc1DOs3kXtzG5XjyhXo7uAOcC1hfRcTaEnGZQoscjTduMloRYu- > KsmdmEUPsq68db0VH3MoYCMd5IamXotlUEffF9b> aly cents server ,you can login > to debug….. > > > > regards, > 仲景武 > > > > > > 在 2016年9月27日,上午4:56,Liang Big data <[hidden email]<mailto: > [hidden email]>> 写道: > > Hi zhongjingwu: > > Can you put these discussions into mailing list : > [hidden email]<mailto:dev@ > carbondata.incubator.apache.org> > You may get more helps from mailing list. > > Regards > Liang > > 在 2016年9月26日 下午8:48,仲景武 <[hidden email]<mailto: > [hidden email]>>写道: > > 在 2016年9月26日,下午8:46,仲景武 <[hidden email]<mailto: > [hidden email]>> 写道: > > > 在 2016年9月26日,下午8:45,仲景武 <[hidden email]<mailto: > [hidden email]>> 写道: > > @Override > public int hashCode() { > int hashCode = 1; > > hashCode = hashCode * 8191 + min_surrogate_key; > > hashCode = hashCode * 8191 + max_surrogate_key; > > hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper. > hashCode(start_offset); > > hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper. > hashCode(end_offset); > > hashCode = hashCode * 8191 + chunk_count; > > hashCode = hashCode * 8191 + ((isSetSegment_id()) ? 131071 : 524287); > if (isSetSegment_id()) > hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper. > hashCode(segment_id); > > return hashCode; > } > > 我在源码中没有看到 org.apache.thrift.TBaseHelper.hashCode(int) 这样的重载方案啊 > 无法编译成功啊,什么情况? > > <FE4BB0D35DD30805BE3BD071450C3118.jpeg> > > > > -- > > Regards > Liang > > |
In reply to this post by 仲景武
when run command (thrift sever):
jdbc:hive2://taonongyuan.com<http://taonongyuan.com>:10099/default> load data inpath 'hdfs://name001:9000/carbondata/sample.csv' into table test_table3; throw exception: Driver stacktrace: (state=,code=0) 0: jdbc:hive2://taonongyuan.com<http://taonongyuan.com>:10099/default> load data inpath 'hdfs:///name001:9000/carbondata/sample.csv' into table test_table3; Error: java.lang.IllegalArgumentException: Pathname /name001:9000/carbondata/sample.csv from hdfs:/name001:9000/carbondata/sample.csv is not a valid DFS filename. (state=,code=0) 0: jdbc:hive2://taonongyuan.com<http://taonongyuan.com>:10099/default> load data inpath 'hdfs://name001:9000/carbondata/sample.csv' into table test_table3; Error: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 5.0 failed 4 times, most recent failure: Lost task 0.3 in stage 5.0 (TID 18, data002): java.lang.IllegalArgumentException: Wrong FS: hdfs://name001:9000/user/hive/warehouse/carbon.store/default/test_table3/Metadata/fdd8c8c4-5cdd-4542-aab1-785be20b9f36.dictmeta, expected: file:/// at org.apache.hadoop.fs.FileSystem.checkPath(FileSystem.java:645) at org.apache.hadoop.fs.RawLocalFileSystem.pathToFile(RawLocalFileSystem.java:80) at org.apache.hadoop.fs.RawLocalFileSystem.deprecatedGetFileStatus(RawLocalFileSystem.java:529) at org.apache.hadoop.fs.RawLocalFileSystem.getFileLinkStatusInternal(RawLocalFileSystem.java:747) at org.apache.hadoop.fs.RawLocalFileSystem.getFileStatus(RawLocalFileSystem.java:524) at org.apache.hadoop.fs.FilterFileSystem.getFileStatus(FilterFileSystem.java:409) at org.apache.hadoop.fs.ChecksumFileSystem$ChecksumFSInputChecker.<init>(ChecksumFileSystem.java:140) at org.apache.hadoop.fs.ChecksumFileSystem.open(ChecksumFileSystem.java:341) at org.apache.carbondata.core.datastorage.store.impl.FileFactory.getDataInputStream(FileFactory.java:146) at org.apache.carbondata.core.reader.ThriftReader.open(ThriftReader.java:79) at org.apache.carbondata.core.reader.CarbonDictionaryMetadataReaderImpl.openThriftReader(CarbonDictionaryMetadataReaderImpl.java:181) at org.apache.carbondata.core.reader.CarbonDictionaryMetadataReaderImpl.readLastEntryOfDictionaryMetaChunk(CarbonDictionaryMetadataReaderImpl.java:128) at org.apache.carbondata.core.cache.dictionary.AbstractDictionaryCache.readLastChunkFromDictionaryMetadataFile(AbstractDictionaryCache.java:129) at org.apache.carbondata.core.cache.dictionary.AbstractDictionaryCache.checkAndLoadDictionaryData(AbstractDictionaryCache.java:204) at org.apache.carbondata.core.cache.dictionary.ReverseDictionaryCache.getDictionary(ReverseDictionaryCache.java:181) at org.apache.carbondata.core.cache.dictionary.ReverseDictionaryCache.get(ReverseDictionaryCache.java:69) at org.apache.carbondata.core.cache.dictionary.ReverseDictionaryCache.get(ReverseDictionaryCache.java:40) at org.apache.carbondata.spark.load.CarbonLoaderUtil.getDictionary(CarbonLoaderUtil.java:508) at org.apache.carbondata.spark.load.CarbonLoaderUtil.getDictionary(CarbonLoaderUtil.java:514) at org.apache.carbondata.spark.rdd.CarbonGlobalDictionaryGenerateRDD$$anon$1.<init>(CarbonGlobalDictionaryRDD.scala:362) at org.apache.carbondata.spark.rdd.CarbonGlobalDictionaryGenerateRDD.compute(CarbonGlobalDictionaryRDD.scala:293) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306) at org.apache.spark.rdd.RDD.iterator(RDD.scala:270) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:89) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 在 2016年10月19日,下午4:55,仲景武 <[hidden email]<mailto:[hidden email]>> 写道: hi, all I have installed carbonate succeed following the document “https://cwiki.apache.org/confluence/display/CARBONDATA/“<https://cwiki.apache.org/confluence/display/CARBONDATA/%E2%80%9C> but when load data into carbonate table throws exception: run command: cc.sql("load data local inpath '../carbondata/sample.csv' into table test_table") errors: org.apache.hadoop.mapreduce.lib.input.InvalidInputException: Input path does not exist: /home/bigdata/bigdata/carbondata/sample.csv at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:321) at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.listStatus(FileInputFormat.java:264) at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.getSplits(FileInputFormat.java:385) at org.apache.spark.rdd.NewHadoopRDD.getPartitions(NewHadoopRDD.scala:120) at org.apache.spark.rdd.RDD$$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$$anonfun$partitions$2.apply(RDD.scala:237) at scala.Option.getOrElse(Option.scala:120) at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) at org.apache.spark.rdd.RDD$$anonfun$take$1.apply(RDD.scala:1307) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111) at org.apache.spark.rdd.RDD.withScope(RDD.scala:316) at org.apache.spark.rdd.RDD.take(RDD.scala:1302) at com.databricks.spark.csv.CarbonCsvRelation.firstLine$lzycompute(CarbonCsvRelation.scala:181) at com.databricks.spark.csv.CarbonCsvRelation.firstLine(CarbonCsvRelation.scala:176) at com.databricks.spark.csv.CarbonCsvRelation.inferSchema(CarbonCsvRelation.scala:144) at com.databricks.spark.csv.CarbonCsvRelation.<init>(CarbonCsvRelation.scala:74) at com.databricks.spark.csv.newapi.DefaultSource.createRelation(DefaultSource.scala:142) at com.databricks.spark.csv.newapi.DefaultSource.createRelation(DefaultSource.scala:44) at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:158) at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:119) at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:109) at org.apache.carbondata.spark.util.GlobalDictionaryUtil$.loadDataFrame(GlobalDictionaryUtil.scala:386) at org.apache.carbondata.spark.util.GlobalDictionaryUtil$.generateGlobalDictionary(GlobalDictionaryUtil.scala:767) at org.apache.spark.sql.execution.command.LoadTable.run(carbonTableSchema.scala:1170) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:58) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:56) at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:70) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55) at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:145) at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:130) at org.apache.carbondata.spark.rdd.CarbonDataFrameRDD.<init>(CarbonDataFrameRDD.scala:23) at org.apache.spark.sql.CarbonContext.sql(CarbonContext.scala:137) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:42) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:47) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:49) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:51) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:53) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:55) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:57) at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:59) at $iwC$$iwC$$iwC$$iwC.<init>(<console>:61) at $iwC$$iwC$$iwC.<init>(<console>:63) at $iwC$$iwC.<init>(<console>:65) at $iwC.<init>(<console>:67) at <init>(<console>:69) at .<init>(<console>:73) 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: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.carbon.Main$.main(Main.scala:31) at org.apache.spark.repl.carbon.Main.main(Main.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at org.apache.spark.deploy.SparkSubmit$.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) cat /home/bigdata/bigdata/carbondata/sample.csv id,name,city,age 1,david,shenzhen,31 2,eason,shenzhen,27 3,jarry,wuhan,35 ip:taonongyuan.com username:bigdata passwd: Zjw11763 this is private <http://www.baidu.com/link?url=zuB-GJ6ONUu4xqmpd_NsR53R4f-Dwi037YBSX9Xc1DOs3kXtzG5XjyhXo7uAOcC1hfRcTaEnGZQoscjTduMloRYu-KsmdmEUPsq68db0VH3MoYCMd5IamXotlUEffF9b> aly cents server ,you can login to debug….. regards, 仲景武 在 2016年9月27日,上午4:56,Liang Big data <[hidden email]<mailto:[hidden email]>> 写道: Hi zhongjingwu: Can you put these discussions into mailing list : [hidden email]<mailto:[hidden email]> You may get more helps from mailing list. Regards Liang 在 2016年9月26日 下午8:48,仲景武 <[hidden email]<mailto:[hidden email]>>写道: 在 2016年9月26日,下午8:46,仲景武 <[hidden email]<mailto:[hidden email]>> 写道: 在 2016年9月26日,下午8:45,仲景武 <[hidden email]<mailto:[hidden email]>> 写道: @Override public int hashCode() { int hashCode = 1; hashCode = hashCode * 8191 + min_surrogate_key; hashCode = hashCode * 8191 + max_surrogate_key; hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper.hashCode(start_offset); hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper.hashCode(end_offset); hashCode = hashCode * 8191 + chunk_count; hashCode = hashCode * 8191 + ((isSetSegment_id()) ? 131071 : 524287); if (isSetSegment_id()) hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper.hashCode(segment_id); return hashCode; } 我在源码中没有看到 org.apache.thrift.TBaseHelper.hashCode(int) 这样的重载方案啊 无法编译成功啊,什么情况? <FE4BB0D35DD30805BE3BD071450C3118.jpeg> -- Regards Liang |
when run command (thrift sever): jdbc:hive2://taonongyuan.com<http://taonongyuan.com/>:10099/default> load data inpath 'hdfs://name001:9000/carbondata/sample.csv' into table test_table3; throw exception: Driver stacktrace: (state=,code=0) 0: jdbc:hive2://taonongyuan.com<http://taonongyuan.com/>:10099/default> load data inpath 'hdfs:///name001:9000/carbondata/sample.csv' into table test_table3; Error: java.lang.IllegalArgumentException: Pathname /name001:9000/carbondata/sample.csv from hdfs:/name001:9000/carbondata/sample.csv is not a valid DFS filename. (state=,code=0) 0: jdbc:hive2://taonongyuan.com<http://taonongyuan.com/>:10099/default> load data inpath 'hdfs://name001:9000/carbondata/sample.csv' into table test_table3; Error: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 5.0 failed 4 times, most recent failure: Lost task 0.3 in stage 5.0 (TID 18, data002): java.lang.IllegalArgumentException: Wrong FS: hdfs://name001:9000/user/hive/warehouse/carbon.store/default/test_table3/Metadata/fdd8c8c4-5cdd-4542-aab1-785be20b9f36.dictmeta, expected: file:/// at org.apache.hadoop.fs.FileSystem.checkPath(FileSystem.java:645) at org.apache.hadoop.fs.RawLocalFileSystem.pathToFile(RawLocalFileSystem.java:80) at org.apache.hadoop.fs.RawLocalFileSystem.deprecatedGetFileStatus(RawLocalFileSystem.java:529) at org.apache.hadoop.fs.RawLocalFileSystem.getFileLinkStatusInternal(RawLocalFileSystem.java:747) at org.apache.hadoop.fs.RawLocalFileSystem.getFileStatus(RawLocalFileSystem.java:524) at org.apache.hadoop.fs.FilterFileSystem.getFileStatus(FilterFileSystem.java:409) at org.apache.hadoop.fs.ChecksumFileSystem$ChecksumFSInputChecker.<init>(ChecksumFileSystem.java:140) at org.apache.hadoop.fs.ChecksumFileSystem.open(ChecksumFileSystem.java:341) at org.apache.carbondata.core.datastorage.store.impl.FileFactory.getDataInputStream(FileFactory.java:146) at org.apache.carbondata.core.reader.ThriftReader.open(ThriftReader.java:79) at org.apache.carbondata.core.reader.CarbonDictionaryMetadataReaderImpl.openThriftReader(CarbonDictionaryMetadataReaderImpl.java:181) at org.apache.carbondata.core.reader.CarbonDictionaryMetadataReaderImpl.readLastEntryOfDictionaryMetaChunk(CarbonDictionaryMetadataReaderImpl.java:128) at org.apache.carbondata.core.cache.dictionary.AbstractDictionaryCache.readLastChunkFromDictionaryMetadataFile(AbstractDictionaryCache.java:129) at org.apache.carbondata.core.cache.dictionary.AbstractDictionaryCache.checkAndLoadDictionaryData(AbstractDictionaryCache.java:204) at org.apache.carbondata.core.cache.dictionary.ReverseDictionaryCache.getDictionary(ReverseDictionaryCache.java:181) at org.apache.carbondata.core.cache.dictionary.ReverseDictionaryCache.get(ReverseDictionaryCache.java:69) at org.apache.carbondata.core.cache.dictionary.ReverseDictionaryCache.get(ReverseDictionaryCache.java:40) at org.apache.carbondata.spark.load.CarbonLoaderUtil.getDictionary(CarbonLoaderUtil.java:508) at org.apache.carbondata.spark.load.CarbonLoaderUtil.getDictionary(CarbonLoaderUtil.java:514) at org.apache.carbondata.spark.rdd.CarbonGlobalDictionaryGenerateRDD$$anon$1.<init>(CarbonGlobalDictionaryRDD.scala:362) at org.apache.carbondata.spark.rdd.CarbonGlobalDictionaryGenerateRDD.compute(CarbonGlobalDictionaryRDD.scala:293) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306) at org.apache.spark.rdd.RDD.iterator(RDD.scala:270) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:89) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 在 2016年10月19日,下午4:55,仲景武 <[hidden email]<mailto:[hidden email]>> 写道: hi, all I have installed carbonate succeed following the document “https://cwiki.apache.org/confluence/display/CARBONDATA/“<https://cwiki.apache.org/confluence/display/CARBONDATA/%E2%80%9C> but when load data into carbonate table throws exception: run command: cc.sql("load data local inpath '../carbondata/sample.csv' into table test_table") errors: org.apache.hadoop.mapreduce.lib.input.InvalidInputException: Input path does not exist: /home/bigdata/bigdata/carbondata/sample.csv at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:321) at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.listStatus(FileInputFormat.java:264) at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.getSplits(FileInputFormat.java:385) at org.apache.spark.rdd.NewHadoopRDD.getPartitions(NewHadoopRDD.scala:120) 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.RDD$$anonfun$take$1.apply(RDD.scala:1307) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111) at org.apache.spark.rdd.RDD.withScope(RDD.scala:316) at org.apache.spark.rdd.RDD.take(RDD.scala:1302) at com.databricks.spark.csv.CarbonCsvRelation.firstLine$lzycompute(CarbonCsvRelation.scala:181) at com.databricks.spark.csv.CarbonCsvRelation.firstLine(CarbonCsvRelation.scala:176) at com.databricks.spark.csv.CarbonCsvRelation.inferSchema(CarbonCsvRelation.scala:144) at com.databricks.spark.csv.CarbonCsvRelation.<init>(CarbonCsvRelation.scala:74) at com.databricks.spark.csv.newapi.DefaultSource.createRelation(DefaultSource.scala:142) at com.databricks.spark.csv.newapi.DefaultSource.createRelation(DefaultSource.scala:44) at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:158) at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:119) at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:109) at org.apache.carbondata.spark.util.GlobalDictionaryUtil$.loadDataFrame(GlobalDictionaryUtil.scala:386) at org.apache.carbondata.spark.util.GlobalDictionaryUtil$.generateGlobalDictionary(GlobalDictionaryUtil.scala:767) at org.apache.spark.sql.execution.command.LoadTable.run(carbonTableSchema.scala:1170) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:58) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:56) at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:70) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55) at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:145) at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:130) at org.apache.carbondata.spark.rdd.CarbonDataFrameRDD.<init>(CarbonDataFrameRDD.scala:23) at org.apache.spark.sql.CarbonContext.sql(CarbonContext.scala:137) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:42) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:47) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:49) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:51) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:53) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:55) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:57) at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:59) at $iwC$$iwC$$iwC$$iwC.<init>(<console>:61) at $iwC$$iwC$$iwC.<init>(<console>:63) at $iwC$$iwC.<init>(<console>:65) at $iwC.<init>(<console>:67) at <init>(<console>:69) at .<init>(<console>:73) at .<clinit>(<console>) at .<init>(<console>:7) at .<clinit>(<console>) at $print(<console>) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065) at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1346) at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840) at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871) at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819) at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857) at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902) at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814) at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657) at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665) at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$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$$process(SparkILoop.scala:945) at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059) at org.apache.spark.repl.carbon.Main$.main(Main.scala:31) at org.apache.spark.repl.carbon.Main.main(Main.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$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) cat /home/bigdata/bigdata/carbondata/sample.csv id,name,city,age 1,david,shenzhen,31 2,eason,shenzhen,27 3,jarry,wuhan,35 ip:taonongyuan.com username:bigdata passwd: Zjw11763 this is private <http://www.baidu.com/link?url=zuB-GJ6ONUu4xqmpd_NsR53R4f-Dwi037YBSX9Xc1DOs3kXtzG5XjyhXo7uAOcC1hfRcTaEnGZQoscjTduMloRYu-KsmdmEUPsq68db0VH3MoYCMd5IamXotlUEffF9b> aly cents server ,you can login to debug….. regards, 仲景武 在 2016年9月27日,上午4:56,Liang Big data <[hidden email]<mailto:[hidden email]>> 写道: Hi zhongjingwu: Can you put these discussions into mailing list : [hidden email]<mailto:[hidden email]> You may get more helps from mailing list. Regards Liang 在 2016年9月26日 下午8:48,仲景武 <[hidden email]<mailto:[hidden email]>>写道: 在 2016年9月26日,下午8:46,仲景武 <[hidden email]<mailto:[hidden email]>> 写道: 在 2016年9月26日,下午8:45,仲景武 <[hidden email]<mailto:[hidden email]>> 写道: @Override public int hashCode() { int hashCode = 1; hashCode = hashCode * 8191 + min_surrogate_key; hashCode = hashCode * 8191 + max_surrogate_key; hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper.hashCode(start_offset); hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper.hashCode(end_offset); hashCode = hashCode * 8191 + chunk_count; hashCode = hashCode * 8191 + ((isSetSegment_id()) ? 131071 : 524287); if (isSetSegment_id()) hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper.hashCode(segment_id); return hashCode; } 我在源码中没有看到 org.apache.thrift.TBaseHelper.hashCode(int) 这样的重载方案啊 无法编译成功啊,什么情况? <FE4BB0D35DD30805BE3BD071450C3118.jpeg> -- Regards Liang |
1. please check the file exists or not.
2. if 1 is right, remove the "hdfs://name001:9000/" out of you path, and try again. |
In reply to this post by 仲景武
try hdfs://name001:9000/carbondata/sample.csv
Instead of hdfs:///name001:9000/carbondata/sample.csv 发自我的 iPhone > 在 2016年10月20日,上午10:52,仲景武 <[hidden email]> 写道: > > > when run command (thrift sever): > > jdbc:hive2://taonongyuan.com<http://taonongyuan.com/>:10099/default> load data inpath 'hdfs://name001:9000/carbondata/sample.csv' into table test_table3; > > > throw exception: > > Driver stacktrace: (state=,code=0) > 0: jdbc:hive2://taonongyuan.com<http://taonongyuan.com/>:10099/default> load data inpath 'hdfs:///name001:9000/carbondata/sample.csv' into table test_table3; > Error: java.lang.IllegalArgumentException: Pathname /name001:9000/carbondata/sample.csv from hdfs:/name001:9000/carbondata/sample.csv is not a valid DFS filename. (state=,code=0) > 0: jdbc:hive2://taonongyuan.com<http://taonongyuan.com/>:10099/default> load data inpath 'hdfs://name001:9000/carbondata/sample.csv' into table test_table3; > Error: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 5.0 failed 4 times, most recent failure: Lost task 0.3 in stage 5.0 (TID 18, data002): java.lang.IllegalArgumentException: Wrong FS: hdfs://name001:9000/user/hive/warehouse/carbon.store/default/test_table3/Metadata/fdd8c8c4-5cdd-4542-aab1-785be20b9f36.dictmeta, expected: file:/// > at org.apache.hadoop.fs.FileSystem.checkPath(FileSystem.java:645) > at org.apache.hadoop.fs.RawLocalFileSystem.pathToFile(RawLocalFileSystem.java:80) > at org.apache.hadoop.fs.RawLocalFileSystem.deprecatedGetFileStatus(RawLocalFileSystem.java:529) > at org.apache.hadoop.fs.RawLocalFileSystem.getFileLinkStatusInternal(RawLocalFileSystem.java:747) > at org.apache.hadoop.fs.RawLocalFileSystem.getFileStatus(RawLocalFileSystem.java:524) > at org.apache.hadoop.fs.FilterFileSystem.getFileStatus(FilterFileSystem.java:409) > at org.apache.hadoop.fs.ChecksumFileSystem$ChecksumFSInputChecker.<init>(ChecksumFileSystem.java:140) > at org.apache.hadoop.fs.ChecksumFileSystem.open(ChecksumFileSystem.java:341) > at org.apache.carbondata.core.datastorage.store.impl.FileFactory.getDataInputStream(FileFactory.java:146) > at org.apache.carbondata.core.reader.ThriftReader.open(ThriftReader.java:79) > at org.apache.carbondata.core.reader.CarbonDictionaryMetadataReaderImpl.openThriftReader(CarbonDictionaryMetadataReaderImpl.java:181) > at org.apache.carbondata.core.reader.CarbonDictionaryMetadataReaderImpl.readLastEntryOfDictionaryMetaChunk(CarbonDictionaryMetadataReaderImpl.java:128) > at org.apache.carbondata.core.cache.dictionary.AbstractDictionaryCache.readLastChunkFromDictionaryMetadataFile(AbstractDictionaryCache.java:129) > at org.apache.carbondata.core.cache.dictionary.AbstractDictionaryCache.checkAndLoadDictionaryData(AbstractDictionaryCache.java:204) > at org.apache.carbondata.core.cache.dictionary.ReverseDictionaryCache.getDictionary(ReverseDictionaryCache.java:181) > at org.apache.carbondata.core.cache.dictionary.ReverseDictionaryCache.get(ReverseDictionaryCache.java:69) > at org.apache.carbondata.core.cache.dictionary.ReverseDictionaryCache.get(ReverseDictionaryCache.java:40) > at org.apache.carbondata.spark.load.CarbonLoaderUtil.getDictionary(CarbonLoaderUtil.java:508) > at org.apache.carbondata.spark.load.CarbonLoaderUtil.getDictionary(CarbonLoaderUtil.java:514) > at org.apache.carbondata.spark.rdd.CarbonGlobalDictionaryGenerateRDD$$anon$1.<init>(CarbonGlobalDictionaryRDD.scala:362) > at org.apache.carbondata.spark.rdd.CarbonGlobalDictionaryGenerateRDD.compute(CarbonGlobalDictionaryRDD.scala:293) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:270) > at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) > at org.apache.spark.scheduler.Task.run(Task.scala:89) > at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227) > at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:745) > > > > 在 2016年10月19日,下午4:55,仲景武 <[hidden email]<mailto:[hidden email]>> 写道: > > > hi, all > > I have installed carbonate succeed following the document “https://cwiki.apache.org/confluence/display/CARBONDATA/“<https://cwiki.apache.org/confluence/display/CARBONDATA/%E2%80%9C> > > but when load data into carbonate table throws exception: > > > run command: > cc.sql("load data local inpath '../carbondata/sample.csv' into table test_table") > > errors: > > org.apache.hadoop.mapreduce.lib.input.InvalidInputException: Input path does not exist: /home/bigdata/bigdata/carbondata/sample.csv > at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:321) > at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.listStatus(FileInputFormat.java:264) > at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.getSplits(FileInputFormat.java:385) > at org.apache.spark.rdd.NewHadoopRDD.getPartitions(NewHadoopRDD.scala:120) > at org.apache.spark.rdd.RDD$$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$$anonfun$partitions$2.apply(RDD.scala:237) > at scala.Option.getOrElse(Option.scala:120) > at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) > at org.apache.spark.rdd.RDD$$anonfun$take$1.apply(RDD.scala:1307) > at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) > at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111) > at org.apache.spark.rdd.RDD.withScope(RDD.scala:316) > at org.apache.spark.rdd.RDD.take(RDD.scala:1302) > at com.databricks.spark.csv.CarbonCsvRelation.firstLine$lzycompute(CarbonCsvRelation.scala:181) > at com.databricks.spark.csv.CarbonCsvRelation.firstLine(CarbonCsvRelation.scala:176) > at com.databricks.spark.csv.CarbonCsvRelation.inferSchema(CarbonCsvRelation.scala:144) > at com.databricks.spark.csv.CarbonCsvRelation.<init>(CarbonCsvRelation.scala:74) > at com.databricks.spark.csv.newapi.DefaultSource.createRelation(DefaultSource.scala:142) > at com.databricks.spark.csv.newapi.DefaultSource.createRelation(DefaultSource.scala:44) > at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:158) > at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:119) > at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:109) > at org.apache.carbondata.spark.util.GlobalDictionaryUtil$.loadDataFrame(GlobalDictionaryUtil.scala:386) > at org.apache.carbondata.spark.util.GlobalDictionaryUtil$.generateGlobalDictionary(GlobalDictionaryUtil.scala:767) > at org.apache.spark.sql.execution.command.LoadTable.run(carbonTableSchema.scala:1170) > at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:58) > at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:56) > at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:70) > at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) > at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) > at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) > at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) > at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55) > at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55) > at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:145) > at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:130) > at org.apache.carbondata.spark.rdd.CarbonDataFrameRDD.<init>(CarbonDataFrameRDD.scala:23) > at org.apache.spark.sql.CarbonContext.sql(CarbonContext.scala:137) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:42) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:47) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:49) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:51) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:53) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:55) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:57) > at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:59) > at $iwC$$iwC$$iwC$$iwC.<init>(<console>:61) > at $iwC$$iwC$$iwC.<init>(<console>:63) > at $iwC$$iwC.<init>(<console>:65) > at $iwC.<init>(<console>:67) > at <init>(<console>:69) > at .<init>(<console>:73) > 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: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.carbon.Main$.main(Main.scala:31) > at org.apache.spark.repl.carbon.Main.main(Main.scala) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) > at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:606) > at org.apache.spark.deploy.SparkSubmit$.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) > > > > > cat /home/bigdata/bigdata/carbondata/sample.csv > > id,name,city,age > 1,david,shenzhen,31 > 2,eason,shenzhen,27 > 3,jarry,wuhan,35 > > > > ip:taonongyuan.com username:bigdata passwd: Zjw11763 > > this is private <http://www.baidu.com/link?url=zuB-GJ6ONUu4xqmpd_NsR53R4f-Dwi037YBSX9Xc1DOs3kXtzG5XjyhXo7uAOcC1hfRcTaEnGZQoscjTduMloRYu-KsmdmEUPsq68db0VH3MoYCMd5IamXotlUEffF9b> aly cents server ,you can login to debug….. > > > > regards, > 仲景武 > > > > > > 在 2016年9月27日,上午4:56,Liang Big data <[hidden email]<mailto:[hidden email]>> 写道: > > Hi zhongjingwu: > > Can you put these discussions into mailing list : [hidden email]<mailto:[hidden email]> > You may get more helps from mailing list. > > Regards > Liang > > 在 2016年9月26日 下午8:48,仲景武 <[hidden email]<mailto:[hidden email]>>写道: > > 在 2016年9月26日,下午8:46,仲景武 <[hidden email]<mailto:[hidden email]>> 写道: > > > 在 2016年9月26日,下午8:45,仲景武 <[hidden email]<mailto:[hidden email]>> 写道: > > @Override > public int hashCode() { > int hashCode = 1; > > hashCode = hashCode * 8191 + min_surrogate_key; > > hashCode = hashCode * 8191 + max_surrogate_key; > > hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper.hashCode(start_offset); > > hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper.hashCode(end_offset); > > hashCode = hashCode * 8191 + chunk_count; > > hashCode = hashCode * 8191 + ((isSetSegment_id()) ? 131071 : 524287); > if (isSetSegment_id()) > hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper.hashCode(segment_id); > > return hashCode; > } > > 我在源码中没有看到 org.apache.thrift.TBaseHelper.hashCode(int) 这样的重载方案啊 无法编译成功啊,什么情况? > > <FE4BB0D35DD30805BE3BD071450C3118.jpeg> > > > > -- > > Regards > Liang > > > |
sorry, it can’t run….
0: jdbc:hive2://taonongyuan.com<http://taonongyuan.com>:10099/default> load data inpath 'hdfs:///name001:9000/carbondata/sample.csv' into table test_table3; Error: java.lang.IllegalArgumentException: Pathname /name001:9000/carbondata/sample.csv from hdfs:/name001:9000/carbondata/sample.csv is not a valid DFS filename. (state=,code=0) 0: jdbc:hive2://taonongyuan.com<http://taonongyuan.com>:10099/default> load data inpath 'hdfs:///name001:9000/carbondata/sample.csv' into table test_table3; Error: java.lang.IllegalArgumentException: Pathname /name001:9000/carbondata/sample.csv from hdfs:/name001:9000/carbondata/sample.csv is not a valid DFS filename. (state=,code=0) 0: jdbc:hive2://taonongyuan.com<http://taonongyuan.com>:10099/default> load data inpath '/carbondata/sample.csv' into table test_table3; Error: org.apache.carbondata.processing.etl.DataLoadingException: The input file does not exist: hdfs://name001:9000hdfs://name001:9000/opt/data/carbondata/sample.csv (state=,code=0) 0: jdbc:hive2://taonongyuan.com<http://taonongyuan.com>:10099/default> 在 2016年10月20日,下午8:19,foryou2030 <[hidden email]<mailto:[hidden email]>> 写道: try hdfs://name001:9000/carbondata/sample.csv Instead of hdfs:///name001:9000/carbondata/sample.csv 发自我的 iPhone 在 2016年10月20日,上午10:52,仲景武 <[hidden email]> 写道: when run command (thrift sever): jdbc:hive2://taonongyuan.com<http://taonongyuan.com/>:10099/default> load data inpath 'hdfs://name001:9000/carbondata/sample.csv' into table test_table3; throw exception: Driver stacktrace: (state=,code=0) 0: jdbc:hive2://taonongyuan.com<http://taonongyuan.com/>:10099/default> load data inpath 'hdfs:///name001:9000/carbondata/sample.csv' into table test_table3; Error: java.lang.IllegalArgumentException: Pathname /name001:9000/carbondata/sample.csv from hdfs:/name001:9000/carbondata/sample.csv is not a valid DFS filename. (state=,code=0) 0: jdbc:hive2://taonongyuan.com<http://taonongyuan.com/>:10099/default> load data inpath 'hdfs://name001:9000/carbondata/sample.csv' into table test_table3; Error: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 5.0 failed 4 times, most recent failure: Lost task 0.3 in stage 5.0 (TID 18, data002): java.lang.IllegalArgumentException: Wrong FS: hdfs://name001:9000/user/hive/warehouse/carbon.store/default/test_table3/Metadata/fdd8c8c4-5cdd-4542-aab1-785be20b9f36.dictmeta, expected: file:/// at org.apache.hadoop.fs.FileSystem.checkPath(FileSystem.java:645) at org.apache.hadoop.fs.RawLocalFileSystem.pathToFile(RawLocalFileSystem.java:80) at org.apache.hadoop.fs.RawLocalFileSystem.deprecatedGetFileStatus(RawLocalFileSystem.java:529) at org.apache.hadoop.fs.RawLocalFileSystem.getFileLinkStatusInternal(RawLocalFileSystem.java:747) at org.apache.hadoop.fs.RawLocalFileSystem.getFileStatus(RawLocalFileSystem.java:524) at org.apache.hadoop.fs.FilterFileSystem.getFileStatus(FilterFileSystem.java:409) at org.apache.hadoop.fs.ChecksumFileSystem$ChecksumFSInputChecker.<init>(ChecksumFileSystem.java:140) at org.apache.hadoop.fs.ChecksumFileSystem.open(ChecksumFileSystem.java:341) at org.apache.carbondata.core.datastorage.store.impl.FileFactory.getDataInputStream(FileFactory.java:146) at org.apache.carbondata.core.reader.ThriftReader.open(ThriftReader.java:79) at org.apache.carbondata.core.reader.CarbonDictionaryMetadataReaderImpl.openThriftReader(CarbonDictionaryMetadataReaderImpl.java:181) at org.apache.carbondata.core.reader.CarbonDictionaryMetadataReaderImpl.readLastEntryOfDictionaryMetaChunk(CarbonDictionaryMetadataReaderImpl.java:128) at org.apache.carbondata.core.cache.dictionary.AbstractDictionaryCache.readLastChunkFromDictionaryMetadataFile(AbstractDictionaryCache.java:129) at org.apache.carbondata.core.cache.dictionary.AbstractDictionaryCache.checkAndLoadDictionaryData(AbstractDictionaryCache.java:204) at org.apache.carbondata.core.cache.dictionary.ReverseDictionaryCache.getDictionary(ReverseDictionaryCache.java:181) at org.apache.carbondata.core.cache.dictionary.ReverseDictionaryCache.get(ReverseDictionaryCache.java:69) at org.apache.carbondata.core.cache.dictionary.ReverseDictionaryCache.get(ReverseDictionaryCache.java:40) at org.apache.carbondata.spark.load.CarbonLoaderUtil.getDictionary(CarbonLoaderUtil.java:508) at org.apache.carbondata.spark.load.CarbonLoaderUtil.getDictionary(CarbonLoaderUtil.java:514) at org.apache.carbondata.spark.rdd.CarbonGlobalDictionaryGenerateRDD$$anon$1.<init>(CarbonGlobalDictionaryRDD.scala:362) at org.apache.carbondata.spark.rdd.CarbonGlobalDictionaryGenerateRDD.compute(CarbonGlobalDictionaryRDD.scala:293) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306) at org.apache.spark.rdd.RDD.iterator(RDD.scala:270) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:89) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 在 2016年10月19日,下午4:55,仲景武 <[hidden email]<mailto:[hidden email]>> 写道: hi, all I have installed carbonate succeed following the document “https://cwiki.apache.org/confluence/display/CARBONDATA/“<https://cwiki.apache.org/confluence/display/CARBONDATA/%E2%80%9C> but when load data into carbonate table throws exception: run command: cc.sql("load data local inpath '../carbondata/sample.csv' into table test_table") errors: org.apache.hadoop.mapreduce.lib.input.InvalidInputException: Input path does not exist: /home/bigdata/bigdata/carbondata/sample.csv at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:321) at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.listStatus(FileInputFormat.java:264) at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.getSplits(FileInputFormat.java:385) at org.apache.spark.rdd.NewHadoopRDD.getPartitions(NewHadoopRDD.scala:120) 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.RDD$$anonfun$take$1.apply(RDD.scala:1307) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111) at org.apache.spark.rdd.RDD.withScope(RDD.scala:316) at org.apache.spark.rdd.RDD.take(RDD.scala:1302) at com.databricks.spark.csv.CarbonCsvRelation.firstLine$lzycompute(CarbonCsvRelation.scala:181) at com.databricks.spark.csv.CarbonCsvRelation.firstLine(CarbonCsvRelation.scala:176) at com.databricks.spark.csv.CarbonCsvRelation.inferSchema(CarbonCsvRelation.scala:144) at com.databricks.spark.csv.CarbonCsvRelation.<init>(CarbonCsvRelation.scala:74) at com.databricks.spark.csv.newapi.DefaultSource.createRelation(DefaultSource.scala:142) at com.databricks.spark.csv.newapi.DefaultSource.createRelation(DefaultSource.scala:44) at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:158) at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:119) at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:109) at org.apache.carbondata.spark.util.GlobalDictionaryUtil$.loadDataFrame(GlobalDictionaryUtil.scala:386) at org.apache.carbondata.spark.util.GlobalDictionaryUtil$.generateGlobalDictionary(GlobalDictionaryUtil.scala:767) at org.apache.spark.sql.execution.command.LoadTable.run(carbonTableSchema.scala:1170) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:58) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:56) at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:70) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55) at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:145) at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:130) at org.apache.carbondata.spark.rdd.CarbonDataFrameRDD.<init>(CarbonDataFrameRDD.scala:23) at org.apache.spark.sql.CarbonContext.sql(CarbonContext.scala:137) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:42) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:47) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:49) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:51) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:53) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:55) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:57) at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:59) at $iwC$$iwC$$iwC$$iwC.<init>(<console>:61) at $iwC$$iwC$$iwC.<init>(<console>:63) at $iwC$$iwC.<init>(<console>:65) at $iwC.<init>(<console>:67) at <init>(<console>:69) at .<init>(<console>:73) at .<clinit>(<console>) at .<init>(<console>:7) at .<clinit>(<console>) at $print(<console>) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065) at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1346) at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840) at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871) at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819) at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857) at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902) at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814) at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657) at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665) at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$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$$process(SparkILoop.scala:945) at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059) at org.apache.spark.repl.carbon.Main$.main(Main.scala:31) at org.apache.spark.repl.carbon.Main.main(Main.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$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) cat /home/bigdata/bigdata/carbondata/sample.csv id,name,city,age 1,david,shenzhen,31 2,eason,shenzhen,27 3,jarry,wuhan,35 ip:taonongyuan.com username:bigdata passwd: Zjw11763 this is private <http://www.baidu.com/link?url=zuB-GJ6ONUu4xqmpd_NsR53R4f-Dwi037YBSX9Xc1DOs3kXtzG5XjyhXo7uAOcC1hfRcTaEnGZQoscjTduMloRYu-KsmdmEUPsq68db0VH3MoYCMd5IamXotlUEffF9b> aly cents server ,you can login to debug….. regards, 仲景武 在 2016年9月27日,上午4:56,Liang Big data <[hidden email]<mailto:[hidden email]>> 写道: Hi zhongjingwu: Can you put these discussions into mailing list : [hidden email]<mailto:[hidden email]> You may get more helps from mailing list. Regards Liang 在 2016年9月26日 下午8:48,仲景武 <[hidden email]<mailto:[hidden email]>>写道: 在 2016年9月26日,下午8:46,仲景武 <[hidden email]<mailto:[hidden email]>> 写道: 在 2016年9月26日,下午8:45,仲景武 <[hidden email]<mailto:[hidden email]>> 写道: @Override public int hashCode() { int hashCode = 1; hashCode = hashCode * 8191 + min_surrogate_key; hashCode = hashCode * 8191 + max_surrogate_key; hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper.hashCode(start_offset); hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper.hashCode(end_offset); hashCode = hashCode * 8191 + chunk_count; hashCode = hashCode * 8191 + ((isSetSegment_id()) ? 131071 : 524287); if (isSetSegment_id()) hashCode = hashCode * 8191 + org.apache.thrift.TBaseHelper.hashCode(segment_id); return hashCode; } 我在源码中没有看到 org.apache.thrift.TBaseHelper.hashCode(int) 这样的重载方案啊 无法编译成功啊,什么情况? <FE4BB0D35DD30805BE3BD071450C3118.jpeg> -- Regards Liang |
Free forum by Nabble | Edit this page |