[hadoop@slave2 ~]$ cat /opt/incubator-carbondata/sample.csv
id,name,city,age
1,david,shenzhen,31
2,eason,shenzhen,27
3,jarry,wuhan,35
[hadoop@slave2 ~]$
> load data inpath '../sample.csv' into table test_table;
INFO 29-07 16:39:46,087 - main Property file path:
/opt/incubator-carbondata/bin/../../../conf/carbon.properties
INFO 29-07 16:39:46,087 - main ------Using Carbon.properties --------
INFO 29-07 16:39:46,087 - main {}
INFO 29-07 16:39:46,088 - main Query [LOAD DATA INPATH '../SAMPLE.CSV'
INTO TABLE TEST_TABLE]
INFO 29-07 16:39:46,527 - Successfully able to get the table metadata
file lock
INFO 29-07 16:39:46,537 - main Initiating Direct Load for the Table :
(default.test_table)
INFO 29-07 16:39:46,541 - Generate global dictionary from source data
files!
INFO 29-07 16:39:46,569 - [Block Distribution]
INFO 29-07 16:39:46,569 - totalInputSpaceConsumed : 74 ,
defaultParallelism : 6
INFO 29-07 16:39:46,569 - mapreduce.input.fileinputformat.split.maxsize
: 16777216
INFO 29-07 16:39:46,689 - Block broadcast_0 stored as values in memory
(estimated size 232.6 KB, free 232.6 KB)
INFO 29-07 16:39:46,849 - Block broadcast_0_piece0 stored as bytes in
memory (estimated size 19.7 KB, free 252.3 KB)
INFO 29-07 16:39:46,850 - Added broadcast_0_piece0 in memory on
192.168.241.223:41572 (size: 19.7 KB, free: 511.5 MB)
INFO 29-07 16:39:46,856 - Created broadcast 0 from NewHadoopRDD at
CarbonTextFile.scala:45
ERROR 29-07 16:39:46,904 - generate global dictionary failed
ERROR 29-07 16:39:46,904 - main
org.apache.hadoop.mapreduce.lib.input.InvalidInputException: Input path
does not exist: /opt/incubator-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$$anonfun$take$1.apply(RDD.scala:1307)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.take(RDD.scala:1302)
at
com.databricks.spark.csv.CarbonCsvRelation.firstLine$lzycompute(CarbonCsvRelation.scala:175)
at
com.databricks.spark.csv.CarbonCsvRelation.firstLine(CarbonCsvRelation.scala:170)
at
com.databricks.spark.csv.CarbonCsvRelation.inferSchema(CarbonCsvRelation.scala:141)
at
com.databricks.spark.csv.CarbonCsvRelation.<init>(CarbonCsvRelation.scala:71)
at
com.databricks.spark.csv.newapi.DefaultSource.createRelation(DefaultSource.scala:142)
at
com.databricks.spark.csv.newapi.DefaultSource.createRelation(DefaultSource.scala:44)
at
org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:158)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:119)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:109)
at
org.carbondata.spark.util.GlobalDictionaryUtil$.loadDataFrame(GlobalDictionaryUtil.scala:365)
at
org.carbondata.spark.util.GlobalDictionaryUtil$.generateGlobalDictionary(GlobalDictionaryUtil.scala:676)
at
org.apache.spark.sql.execution.command.LoadTable.run(carbonTableSchema.scala:1159)
at
org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:58)
at
org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:56)
at
org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:70)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at
org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:145)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:130)
at
org.carbondata.spark.rdd.CarbonDataFrameRDD.<init>(CarbonDataFrameRDD.scala:23)
at org.apache.spark.sql.CarbonContext.sql(CarbonContext.scala:131)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:63)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:311)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:226)
at
org.apache.spark.sql.hive.cli.CarbonSQLCLIDriver$.main(CarbonSQLCLIDriver.scala:40)
at
org.apache.spark.sql.hive.cli.CarbonSQLCLIDriver.main(CarbonSQLCLIDriver.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$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)
--
金铸
---------------------------------------------------------------------------------------------------
Confidentiality Notice: The information contained in this e-mail and any
accompanying attachment(s)
is intended only for the use of the intended recipient and may be confidential
and/or privileged of
Neusoft Corporation, its subsidiaries and/or its affiliates. If any reader of
this communication is
not the intended recipient, unauthorized use, forwarding, printing, storing,
disclosure or copying
is strictly prohibited, and may be unlawful.If you have received this
communication in error,please
immediately notify the sender by return e-mail, and delete the original message
and all copies from
your system. Thank you.
---------------------------------------------------------------------------------------------------
