Я создал один стол hivetest, который также создает таблицу в hbase с именем «hbasetest». Теперь я хочу скопировать данные «hbasetest» в другую таблицу hbase (скажем, logdata) с той же схемой. Итак, кто-нибудь может мне помочь, как скопировать данные из «hbasetest» в «logdata» без использования улья.Скопировать данные из одной таблицы hbase в другую
CREATE TABLE hivetest(cookie string, timespent string, pageviews string, visit string, logdate string)
STORED BY 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'
WITH SERDEPROPERTIES ("hbase.columns.mapping" = "m:timespent, m:pageviews, m:visit, m:logdate")
TBLPROPERTIES ("hbase.table.name" = "hbasetest");
Обновленный вопрос:
Я создал таблицу logdata, как это. Но, я получаю следующую ошибку.
create 'logdata', {NAME => ' m', BLOOMFILTER => 'NONE', REPLICATION_SCOPE => '0', VERSIONS => '3', COMPRESSION => 'NONE', MIN_VERSIONS =>'0', TTL => '2147483647', BLOCKSIZE=> '65536', IN_MEMORY => 'false', BLOCKCACHE => 'true'}
13/09/23 12:57:19 INFO mapred.JobClient: Task Id : attempt_201309231115_0025_m_000000_0, Status : FAILED
org.apache.hadoop.hbase.client.RetriesExhaustedWithDetailsException: Failed 755 actions: org.apache.hadoop.hbase.regionserver.NoSuchColumnFamilyException: Column family m does not exist in region logdata,,1379920697845.30fce8bcc99bf9ed321720496a3ec498. in table 'logdata', {NAME => 'm', DATA_BLOCK_ENCODING => 'NONE', BLOOMFILTER => 'NONE', REPLICATION_SCOPE => '0', COMPRESSION => 'NONE', VERSIONS => '3', TTL => '2147483647', MIN_VERSIONS => '0', KEEP_DELETED_CELLS => 'false', BLOCKSIZE => '65536', ENCODE_ON_DISK => 'true', IN_MEMORY => 'false', BLOCKCACHE => 'true'}
at org.apache.hadoop.hbase.regionserver.HRegionServer.multi(HRegionServer.java:3773)
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.hadoop.hbase.ipc.WritableRpcEngine$Server.call(WritableRpcEngine.java:320)
at org.apache.hadoop.hbase.ipc.HBaseServer$Handler.run(HBaseServer.java:1426)
: 755 times, servers with issues: master:60020,
at org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation.processBatchCallback(HConnectionManager.java:1674)
at org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation.processBatch(HConnectionManager.java:1450)
at org.apache.hadoop.hbase.client.HTable.flushCommits(HTable.java:916)
at org.apache.hadoop.hbase.client.HTable.close(HTable.java:953)
at org.apache.hadoop.hbase.mapreduce.TableOutputFormat$TableRecordWriter.close(TableOutputFormat.java:109)
at org.apache.hadoop.mapred.MapTask$NewDirectOutputCollector.close(MapTask.java:651)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:766)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:370)
at org.apache.hadoop.mapred.Child$4.run(Child.java:255)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:415)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1121)
at org.apache.hadoop.mapred.Child.main(Child.java:249)
13/09/23 12:57:29 INFO mapred.JobClient: Task Id : attempt_201309231115_0025_m_000000_1, Status : FAILED
org.apache.hadoop.hbase.client.RetriesExhaustedWithDetailsException: Failed 755 actions: org.apache.hadoop.hbase.regionserver.NoSuchColumnFamilyException: Column family m does not exist in region logdata,,1379920697845.30fce8bcc99bf9ed321720496a3ec498. in table 'logdata', {NAME => 'm', DATA_BLOCK_ENCODING => 'NONE', BLOOMFILTER => 'NONE', REPLICATION_SCOPE => '0', COMPRESSION => 'NONE', VERSIONS => '3', TTL => '2147483647', MIN_VERSIONS => '0', KEEP_DELETED_CELLS => 'false', BLOCKSIZE => '65536', ENCODE_ON_DISK => 'true', IN_MEMORY => 'false', BLOCKCACHE => 'true'}
at org.apache.hadoop.hbase.regionserver.HRegionServer.multi(HRegionServer.java:3773)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.hadoop.hbase.ipc.WritableRpcEngine$Server.call(WritableRpcEngine.java:320)
at org.apache.hadoop.hbase.ipc.HBaseServer$Handler.run(HBaseServer.java:1426)
: 755 times, servers with issues: master:60020,
at org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation.processBatchCallback(HConnectionManager.java:1674)
at org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation.processBatch(HConnectionManager.java:1450)
at org.apache.hadoop.hbase.client.HTable.flushCommits(HTable.java:916)
at org.apache.hadoop.hbase.client.HTable.close(HTable.java:953)
at org.apache.hadoop.hbase.mapreduce.TableOutputFormat$TableRecordWriter.close(TableOutputFormat.java:109)
at org.apache.hadoop.mapred.MapTask$NewDirectOutputCollector.close(MapTask.java:651)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:766)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:370)
at org.apache.hadoop.mapred.Child$4.run(Child.java:255)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:415)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1121)
at org.apache.hadoop.mapred.Child.main(Child.java:249)
13/09/23 12:57:38 INFO mapred.JobClient: Task Id : attempt_201309231115_0025_m_000000_2, Status : FAILED
org.apache.hadoop.hbase.client.RetriesExhaustedWithDetailsException: Failed 755 actions: org.apache.hadoop.hbase.regionserver.NoSuchColumnFamilyException: Column family m does not exist in region logdata,,1379920697845.30fce8bcc99bf9ed321720496a3ec498. in table 'logdata', {NAME => 'm', DATA_BLOCK_ENCODING => 'NONE', BLOOMFILTER => 'NONE', REPLICATION_SCOPE => '0', COMPRESSION => 'NONE', VERSIONS => '3', TTL => '2147483647', MIN_VERSIONS => '0', KEEP_DELETED_CELLS => 'false', BLOCKSIZE => '65536', ENCODE_ON_DISK => 'true', IN_MEMORY => 'false', BLOCKCACHE => 'true'}
at org.apache.hadoop.hbase.regionserver.HRegionServer.multi(HRegionServer.java:3773)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.hadoop.hbase.ipc.WritableRpcEngine$Server.call(WritableRpcEngine.java:320)
at org.apache.hadoop.hbase.ipc.HBaseServer$Handler.run(HBaseServer.java:1426)
: 755 times, servers with issues: master:60020,
at org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation.processBatchCallback(HConnectionManager.java:1674)
at org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation.processBatch(HConnectionManager.java:1450)
at org.apache.hadoop.hbase.client.HTable.flushCommits(HTable.java:916)
at org.apache.hadoop.hbase.client.HTable.close(HTable.java:953)
at org.apache.hadoop.hbase.mapreduce.TableOutputFormat$TableRecordWriter.close(TableOutputFormat.java:109)
at org.apache.hadoop.mapred.MapTask$NewDirectOutputCollector.close(MapTask.java:651)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:766)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:370)
at org.apache.hadoop.mapred.Child$4.run(Child.java:255)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:415)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1121)
at org.apache.hadoop.mapred.Child.main(Child.java:249)
13/09/23 12:57:53 INFO mapred.JobClient: Job complete: job_201309231115_0025
13/09/23 12:57:53 INFO mapred.JobClient: Counters: 7
13/09/23 12:57:53 INFO mapred.JobClient: Job Counters
13/09/23 12:57:53 INFO mapred.JobClient: SLOTS_MILLIS_MAPS=34605
13/09/23 12:57:53 INFO mapred.JobClient: Total time spent by all reduces waiting after reserving slots (ms)=0
13/09/23 12:57:53 INFO mapred.JobClient: Total time spent by all maps waiting after reserving slots (ms)=0
13/09/23 12:57:53 INFO mapred.JobClient: Rack-local map tasks=4
13/09/23 12:57:53 INFO mapred.JobClient: Launched map tasks=4
13/09/23 12:57:53 INFO mapred.JobClient: SLOTS_MILLIS_REDUCES=0
13/09/23 12:57:53 INFO mapred.JobClient: Failed map tasks=1
Прежде всего, чемx tariq. Но, теперь я получаю ошибку, которую я редактировал в своем вопросе. Не могли бы вы рассказать мне, что создает проблему? – Naresh
Не могли бы вы показать мне вывод ** описать «logdata» ** ?? – Tariq
Фактически данные не копировались. Когда я выполнил команду «hbase org.apache.hadoop.hbase.mapreduce.CopyTable --new.name = logdata hbasetest». Это дало мне ошибку, которую я обновил в своем вопросе. Кроме того, нужно ли создавать таблицу перед копированием данных? Эта команда не создается сама по себе. – Naresh