You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@kylin.apache.org by "Colin Luo (JIRA)" <ji...@apache.org> on 2019/06/13 10:10:00 UTC
[jira] [Comment Edited] (KYLIN-4038) Lookup tables is empty when
build on ORC tables.
[ https://issues.apache.org/jira/browse/KYLIN-4038?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16862896#comment-16862896 ]
Colin Luo edited comment on KYLIN-4038 at 6/13/19 10:09 AM:
------------------------------------------------------------
KYLIN-3990 maybe a similar problem. I need a solution too.
was (Author: colinluo):
KYLIN-3990 maybe a similar problem.
> Lookup tables is empty when build on ORC tables.
> ------------------------------------------------
>
> Key: KYLIN-4038
> URL: https://issues.apache.org/jira/browse/KYLIN-4038
> Project: Kylin
> Issue Type: Bug
> Affects Versions: v2.6.2
> Environment: HDP 3 cluster.
> Reporter: Alexander
> Assignee: XiaoXiang Yu
> Priority: Blocker
> Attachments: image-2019-06-11-16-12-09-472.png
>
>
> Create tables, simple copy of learn_kylin project.
> {code:java}
> // Create tables
> create table kylin_sales_sida (trans_id bigint,part_dt date,lstg_format_name string,leaf_categ_id bigint,lstg_site_id int,slr_segment_cd smallint,price decimal(19,4),item_count bigint,seller_id bigint,buyer_id bigint,ops_user_id string,ops_region string) stored as orc tblproperties ("orc.compress"="SNAPPY");
> insert into table kylin_sales_sida select * from kylin_sales;
> create table kylin_country_sida (country string,latitude double,longitude double,name string) stored as orc tblproperties ("orc.compress"="SNAPPY");
> insert into table kylin_country_sida select * from kylin_country;
> create table kylin_category_groupings_sida (leaf_categ_id bigint,leaf_categ_name string,site_id int,categ_busn_mgr string,categ_busn_unit string,regn_categ string,user_defined_field1 string,user_defined_field3 string,kylin_groupings_cre_date string,kylin_groupings_upd_date string,kylin_groupings_cre_user string,kylin_groupings_upd_user string,meta_categ_id decimal(10,0),meta_categ_name string,categ_lvl2_id decimal(10,0),categ_lvl3_id decimal(10,0),categ_lvl4_id decimal(10,0),categ_lvl5_id decimal(10,0),categ_lvl6_id decimal(10,0),categ_lvl7_id decimal(10,0),categ_lvl2_name string,categ_lvl3_name string,categ_lvl4_name string,categ_lvl5_name string,categ_lvl6_name string,categ_lvl7_name string,categ_flags decimal(10,0),adult_categ_yn string,domain_id decimal(10,0),user_defined_field5 string,vcs_id decimal(10,0),gcs_id decimal(10,0),move_to decimal(10,0),sap_category_id decimal(10,0),src_id tinyint,bsns_vrtcl_name string) stored as orc tblproperties ("orc.compress"="SNAPPY");
> insert into table kylin_category_groupings_sida select * from kylin_category_groupings;
> create table kylin_cal_dt_sida (cal_dt date,year_beg_dt date,qtr_beg_dt date,month_beg_dt date,week_beg_dt date,age_for_year_id smallint,age_for_qtr_id smallint,age_for_month_id smallint,age_for_week_id smallint,age_for_dt_id smallint,age_for_rtl_year_id smallint,age_for_rtl_qtr_id smallint,age_for_rtl_month_id smallint,age_for_rtl_week_id smallint,age_for_cs_week_id smallint,day_of_cal_id int,day_of_year_id smallint,day_of_qtr_id smallint,day_of_month_id smallint,day_of_week_id int,week_of_year_id tinyint,week_of_cal_id int,month_of_qtr_id tinyint,month_of_year_id tinyint,month_of_cal_id smallint,qtr_of_year_id tinyint,qtr_of_cal_id smallint,year_of_cal_id smallint,year_end_dt string,qtr_end_dt string,month_end_dt string,week_end_dt string,cal_dt_name string,cal_dt_desc string,cal_dt_short_name string,ytd_yn_id tinyint,qtd_yn_id tinyint,mtd_yn_id tinyint,wtd_yn_id tinyint,season_beg_dt string,day_in_year_count smallint,day_in_qtr_count tinyint,day_in_month_count tinyint,day_in_week_count tinyint,rtl_year_beg_dt string,rtl_qtr_beg_dt string,rtl_month_beg_dt string,rtl_week_beg_dt string,cs_week_beg_dt string,cal_date string,day_of_week string,month_id string,prd_desc string,prd_flag string,prd_id string,prd_ind string,qtr_desc string,qtr_id string,qtr_ind string,retail_week string,retail_year string,retail_start_date string,retail_wk_end_date string,week_ind string,week_num_desc string,week_beg_date string,week_end_date string,week_in_year_id string,week_id string,week_beg_end_desc_mdy string,week_beg_end_desc_md string,year_id string,year_ind string,cal_dt_mns_1year_dt string,cal_dt_mns_2year_dt string,cal_dt_mns_1qtr_dt string,cal_dt_mns_2qtr_dt string,cal_dt_mns_1month_dt string,cal_dt_mns_2month_dt string,cal_dt_mns_1week_dt string,cal_dt_mns_2week_dt string,curr_cal_dt_mns_1year_yn_id tinyint,curr_cal_dt_mns_2year_yn_id tinyint,curr_cal_dt_mns_1qtr_yn_id tinyint,curr_cal_dt_mns_2qtr_yn_id tinyint,curr_cal_dt_mns_1month_yn_id tinyint,curr_cal_dt_mns_2month_yn_id tinyint,curr_cal_dt_mns_1week_yn_ind tinyint,curr_cal_dt_mns_2week_yn_ind tinyint,rtl_month_of_rtl_year_id string,rtl_qtr_of_rtl_year_id tinyint,rtl_week_of_rtl_year_id tinyint,season_of_year_id tinyint,ytm_yn_id tinyint,ytq_yn_id tinyint,ytw_yn_id tinyint,kylin_cal_dt_cre_date string,kylin_cal_dt_cre_user string,kylin_cal_dt_upd_date string,kylin_cal_dt_upd_user string) stored as orc tblproperties ("orc.compress"="SNAPPY");
> insert into table kylin_cal_dt_sida select * from kylin_cal_dt;
> create table kylin_account_sida (account_id bigint,account_buyer_level int,account_seller_level int,account_country string,account_contact string) stored as orc tblproperties ("orc.compress"="SNAPPY");
> insert into table kylin_account_sida select * from kylin_account;{code}
> Create new project and data model, a manual copy of test cube learn_kylin. Add Lookup tables to HBase.
> Build cube, and notice what the lookup tables builds empty:
> {code:java}
> // Result of Convert Lookup Table to HFile: step
> 2019-06-06 11:12:23,172 DEBUG [Scheduler 1312561281 Job a501b13d-1026-8fbf-5695-80483044f23b-580] common.HadoopCmdOutput:100 : Counters: 39
> File System Counters
> FILE: Number of bytes read=0
> FILE: Number of bytes written=323522
> FILE: Number of read operations=0
> FILE: Number of large read operations=0
> FILE: Number of write operations=0
> HDFS: Number of bytes read=0
> HDFS: Number of bytes written=0
> HDFS: Number of read operations=1
> HDFS: Number of large read operations=0
> HDFS: Number of write operations=0
> Job Counters
> Launched reduce tasks=1
> Total time spent by all reduces in occupied slots (ms)=21696
> Total time spent by all reduce tasks (ms)=3616
> Total vcore-milliseconds taken by all reduce tasks=3616
> Total megabyte-milliseconds taken by all reduce tasks=22216704
> Map-Reduce Framework
> Combine input records=0
> Combine output records=0
> Reduce input groups=0
> Reduce shuffle bytes=0
> Reduce input records=0
> Reduce output records=0
> Spilled Records=0
> Shuffled Maps =0
> Failed Shuffles=0
> Merged Map outputs=0
> GC time elapsed (ms)=71
> CPU time spent (ms)=840
> Physical memory (bytes) snapshot=216272896
> Virtual memory (bytes) snapshot=7290363904
> Total committed heap usage (bytes)=191365120
> Peak Reduce Physical memory (bytes)=216272896
> Peak Reduce Virtual memory (bytes)=7290363904
> Shuffle Errors
> BAD_ID=0
> CONNECTION=0
> IO_ERROR=0
> WRONG_LENGTH=0
> WRONG_MAP=0
> WRONG_REDUCE=0
> File Output Format Counters
> Bytes Written=0
> 2019-06-06 11:12:23,172 DEBUG [Scheduler 1312561281 Job a501b13d-1026-8fbf-5695-80483044f23b-580] common.HadoopCmdOutput:107 : outputFolder is hdfs://********:8020/kylin/kylin_metadata/kylin-a501b13d-1026-8fbf-5695-80483044f23b/DEFAULT.KYLIN_ACCOUNT_SIDA/hfile
> 2019-06-06 11:12:23,173 DEBUG [Scheduler 1312561281 Job a501b13d-1026-8fbf-5695-80483044f23b-580] common.HadoopCmdOutput:112 : Seems no counter found for hdfs
> 2019-06-06 11:12:23,202 INFO [Scheduler 1312561281 Job a501b13d-1026-8fbf-5695-80483044f23b-580] execution.ExecutableManager:453 : job id:a501b13d-1026-8fbf-5695-80483044f23b-05 from RUNNING to SUCCEED
> {code}
> As result any Query with lookup tables data goes to be incorrect. As they are missed.
> (In Build Dimension Dictionary step the same thing, empty lookup data goes into cube calculation)
> If i run fo each tables compact major:
> {code:java}
> // Compact Major on orc tables
> ALTER TABLE DEFAULT.KYLIN_ACCOUNT_SIDA COMPACT 'MAJOR';
> ... ALTER all tables{code}
> After that, a can rerun cube build. The result will be error in MR job:
> {code:java}
> // MR Exception
> 2019-06-07 11:51:54,482 INFO [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] orc.OrcInputFormat:1737 : ORC pushdown predicate: null
> 2019-06-07 11:51:55,052 INFO [ORC_GET_SPLITS #7] impl.OrcCodecPool:56 : Got brand-new codec SNAPPY
> 2019-06-07 11:51:55,263 INFO [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] orc.OrcInputFormat:1855 : FooterCacheHitRatio: 0/1
> 2019-06-07 11:51:55,297 INFO [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] mapreduce.JobSubmitter:202 : number of splits:1
> 2019-06-07 11:51:55,329 INFO [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] mapreduce.JobSubmitter:298 : Submitting tokens for job: job_1559213270190_0372
> 2019-06-07 11:51:55,329 INFO [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] mapreduce.JobSubmitter:299 : Executing with tokens: []
> 2019-06-07 11:51:55,572 INFO [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] impl.YarnClientImpl:306 : Submitted application application_1559213270190_0372
> 2019-06-07 11:51:55,575 INFO [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] mapreduce.Job:1574 : The url to track the job: http://******:8088/proxy/application_1559213270190_0372/
> 2019-06-07 11:51:58,408 INFO [FetcherRunner 833282134-77] threadpool.DefaultFetcherRunner:94 : Job Fetcher: 1 should running, 1 actual running, 0 stopped, 0 ready, 229 already succeed, 61 error, 0 discarded, 1 others
> 2019-06-07 11:52:28,408 INFO [FetcherRunner 833282134-77] threadpool.DefaultFetcherRunner:94 : Job Fetcher: 1 should running, 1 actual running, 0 stopped, 0 ready, 229 already succeed, 61 error, 0 discarded, 1 others
> 2019-06-07 11:52:31,361 INFO [BadQueryDetector] service.BadQueryDetector:147 : Detect bad query.
> 2019-06-07 11:52:58,407 INFO [FetcherRunner 833282134-77] threadpool.DefaultFetcherRunner:94 : Job Fetcher: 1 should running, 1 actual running, 0 stopped, 0 ready, 229 already succeed, 61 error, 0 discarded, 1 others
> 2019-06-07 11:53:05,805 DEBUG [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] common.HadoopCmdOutput:100 : Counters: 10
> Job Counters
> Failed map tasks=4
> Killed reduce tasks=1
> Launched map tasks=4
> Other local map tasks=3
> Data-local map tasks=1
> Total time spent by all maps in occupied slots (ms)=136272
> Total time spent by all reduces in occupied slots (ms)=0
> Total time spent by all map tasks (ms)=45424
> Total vcore-milliseconds taken by all map tasks=45424
> Total megabyte-milliseconds taken by all map tasks=139542528
> 2019-06-07 11:53:05,806 DEBUG [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] common.HadoopCmdOutput:107 : outputFolder is hdfs://apachai1.apm.local:8020/kylin/kylin_metadata/kylin-6d0f79da-7902-1b2c-a49e-fa6b6190911c/DEFAULT.KYLIN_ACCOUNT_SIDA/hfile
> 2019-06-07 11:53:05,807 DEBUG [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] common.HadoopCmdOutput:112 : Seems no counter found for hdfs
> 2019-06-07 11:53:05,808 WARN [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] common.HadoopCmdOutput:119 : Job Diagnostics:Task failed task_1559213270190_0372_m_000000
> Job failed as tasks failed. failedMaps:1 failedReduces:0 killedMaps:0 killedReduces: 0
> 2019-06-07 11:53:05,994 WARN [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] common.HadoopCmdOutput:124 : Failure task Diagnostics:
> 2019-06-07 11:53:05,994 WARN [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] common.HadoopCmdOutput:127 : Error: java.lang.ClassCastException: org.apache.hadoop.io.IntWritable cannot be cast to org.apache.hadoop.io.LongWritable
> at org.apache.hadoop.hive.serde2.objectinspector.primitive.WritableLongObjectInspector.getPrimitiveJavaObject(WritableLongObjectInspector.java:46)
> at org.apache.hive.hcatalog.data.HCatRecordSerDe.serializePrimitiveField(HCatRecordSerDe.java:278)
> at org.apache.hive.hcatalog.data.HCatRecordSerDe.serializeField(HCatRecordSerDe.java:199)
> at org.apache.hive.hcatalog.data.LazyHCatRecord.get(LazyHCatRecord.java:53)
> at org.apache.hive.hcatalog.data.LazyHCatRecord.get(LazyHCatRecord.java:97)
> at org.apache.hive.hcatalog.mapreduce.HCatRecordReader.nextKeyValue(HCatRecordReader.java:204)
> at org.apache.hadoop.mapred.MapTask$NewTrackingRecordReader.nextKeyValue(MapTask.java:568)
> at org.apache.hadoop.mapreduce.task.MapContextImpl.nextKeyValue(MapContextImpl.java:80)
> at org.apache.hadoop.mapreduce.lib.map.WrappedMapper$Context.nextKeyValue(WrappedMapper.java:91)
> at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:145)
> at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:799)
> at org.apache.hadoop.mapred.MapTask.run(MapTask.java:347)
> at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:174)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:422)
> at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1730)
> at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:168)
> 2019-06-07 11:53:06,004 INFO [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] execution.ExecutableManager:453 : job id:6d0f79da-7902-1b2c-a49e-fa6b6190911c-05 from RUNNING to ERROR
> 2019-06-07 11:53:06,005 ERROR [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] execution.AbstractExecutable:167 : error running Executable: CubingJob{id=6d0f79da-7902-1b2c-a49e-fa6b6190911c, name=BUILD CUBE - kylin_sales_cube_orc - 20120101000000_20140101000000 - MSK 2019-06-07 11:36:49, state=RUNNING}
> 2019-06-07 11:53:06,008 DEBUG [pool-7-thread-1] cachesync.Broadcaster:116 : Servers in the cluster: [localhost:7070]
> 2019-06-07 11:53:06,009 DEBUG [pool-7-thread-1] cachesync.Broadcaster:126 : Announcing new broadcast to all: BroadcastEvent{entity=execute_output, event=update, cacheKey=6d0f79da-7902-1b2c-a49e-fa6b6190911c}
> 2019-06-07 11:53:06,012 INFO [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] execution.ExecutableManager:453 : job id:6d0f79da-7902-1b2c-a49e-fa6b6190911c from RUNNING to ERROR
> 2019-06-07 11:53:06,012 DEBUG [pool-7-thread-1] cachesync.Broadcaster:116 : Servers in the cluster: [localhost:7070]
> 2019-06-07 11:53:06,012 DEBUG [http-nio-7070-exec-1] cachesync.Broadcaster:246 : Broadcasting UPDATE, execute_output, 6d0f79da-7902-1b2c-a49e-fa6b6190911c
> 2019-06-07 11:53:06,012 DEBUG [Scheduler 1312561281 Job 6d0f79da-7902-1b2c-a49e-fa6b6190911c-580] execution.AbstractExecutable:318 : no need to send email, user list is empty
> 2019-06-07 11:53:06,012 DEBUG [pool-7-thread-1] cachesync.Broadcaster:126 : Announcing new broadcast to all: BroadcastEvent{entity=execute_output, event=update, cacheKey=6d0f79da-7902-1b2c-a49e-fa6b6190911c}
> 2019-06-07 11:53:06,013 DEBUG [http-nio-7070-exec-1] cachesync.Broadcaster:280 : Done broadcasting UPDATE, execute_output, 6d0f79da-7902-1b2c-a49e-fa6b6190911c
> 2019-06-07 11:53:06,014 ERROR [pool-11-thread-10] threadpool.DefaultScheduler:116 : ExecuteException job:6d0f79da-7902-1b2c-a49e-fa6b6190911c
> org.apache.kylin.job.exception.ExecuteException: org.apache.kylin.job.exception.ExecuteException: org.apache.kylin.engine.mr.exception.MapReduceException: Counters: 10
> Job Counters
> Failed map tasks=4
> Killed reduce tasks=1
> Launched map tasks=4
> Other local map tasks=3
> Data-local map tasks=1
> Total time spent by all maps in occupied slots (ms)=136272
> Total time spent by all reduces in occupied slots (ms)=0
> Total time spent by all map tasks (ms)=45424
> Total vcore-milliseconds taken by all map tasks=45424
> Total megabyte-milliseconds taken by all map tasks=139542528
> Job Diagnostics:Task failed task_1559213270190_0372_m_000000
> Job failed as tasks failed. failedMaps:1 failedReduces:0 killedMaps:0 killedReduces: 0
> Failure task Diagnostics:
> Error: java.lang.ClassCastException: org.apache.hadoop.io.IntWritable cannot be cast to org.apache.hadoop.io.LongWritable
> at org.apache.hadoop.hive.serde2.objectinspector.primitive.WritableLongObjectInspector.getPrimitiveJavaObject(WritableLongObjectInspector.java:46)
> at org.apache.hive.hcatalog.data.HCatRecordSerDe.serializePrimitiveField(HCatRecordSerDe.java:278)
> at org.apache.hive.hcatalog.data.HCatRecordSerDe.serializeField(HCatRecordSerDe.java:199)
> at org.apache.hive.hcatalog.data.LazyHCatRecord.get(LazyHCatRecord.java:53)
> at org.apache.hive.hcatalog.data.LazyHCatRecord.get(LazyHCatRecord.java:97)
> at org.apache.hive.hcatalog.mapreduce.HCatRecordReader.nextKeyValue(HCatRecordReader.java:204)
> at org.apache.hadoop.mapred.MapTask$NewTrackingRecordReader.nextKeyValue(MapTask.java:568)
> at org.apache.hadoop.mapreduce.task.MapContextImpl.nextKeyValue(MapContextImpl.java:80)
> at org.apache.hadoop.mapreduce.lib.map.WrappedMapper$Context.nextKeyValue(WrappedMapper.java:91)
> at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:145)
> at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:799)
> at org.apache.hadoop.mapred.MapTask.run(MapTask.java:347)
> at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:174)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:422)
> at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1730)
> at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:168)
> at org.apache.kylin.job.execution.AbstractExecutable.execute(AbstractExecutable.java:180)
> at org.apache.kylin.job.impl.threadpool.DefaultScheduler$JobRunner.run(DefaultScheduler.java:114)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: org.apache.kylin.job.exception.ExecuteException: org.apache.kylin.engine.mr.exception.MapReduceException: Counters: 10
> Job Counters
> Failed map tasks=4
> Killed reduce tasks=1
> Launched map tasks=4
> Other local map tasks=3
> Data-local map tasks=1
> Total time spent by all maps in occupied slots (ms)=136272
> Total time spent by all reduces in occupied slots (ms)=0
> Total time spent by all map tasks (ms)=45424
> Total vcore-milliseconds taken by all map tasks=45424
> Total megabyte-milliseconds taken by all map tasks=139542528
> Job Diagnostics:Task failed task_1559213270190_0372_m_000000
> Job failed as tasks failed. failedMaps:1 failedReduces:0 killedMaps:0 killedReduces: 0
> Failure task Diagnostics:
> Error: java.lang.ClassCastException: org.apache.hadoop.io.IntWritable cannot be cast to org.apache.hadoop.io.LongWritable
> at org.apache.hadoop.hive.serde2.objectinspector.primitive.WritableLongObjectInspector.getPrimitiveJavaObject(WritableLongObjectInspector.java:46)
> at org.apache.hive.hcatalog.data.HCatRecordSerDe.serializePrimitiveField(HCatRecordSerDe.java:278)
> at org.apache.hive.hcatalog.data.HCatRecordSerDe.serializeField(HCatRecordSerDe.java:199)
> at org.apache.hive.hcatalog.data.LazyHCatRecord.get(LazyHCatRecord.java:53)
> at org.apache.hive.hcatalog.data.LazyHCatRecord.get(LazyHCatRecord.java:97)
> at org.apache.hive.hcatalog.mapreduce.HCatRecordReader.nextKeyValue(HCatRecordReader.java:204)
> at org.apache.hadoop.mapred.MapTask$NewTrackingRecordReader.nextKeyValue(MapTask.java:568)
> at org.apache.hadoop.mapreduce.task.MapContextImpl.nextKeyValue(MapContextImpl.java:80)
> at org.apache.hadoop.mapreduce.lib.map.WrappedMapper$Context.nextKeyValue(WrappedMapper.java:91)
> at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:145)
> at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:799)
> at org.apache.hadoop.mapred.MapTask.run(MapTask.java:347)
> at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:174)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:422)
> at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1730)
> at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:168)
> at org.apache.kylin.job.execution.AbstractExecutable.execute(AbstractExecutable.java:180)
> at org.apache.kylin.job.execution.DefaultChainedExecutable.doWork(DefaultChainedExecutable.java:70)
> at org.apache.kylin.job.execution.AbstractExecutable.execute(AbstractExecutable.java:165)
> ... 4 more
> Caused by: org.apache.kylin.engine.mr.exception.MapReduceException: Counters: 10
> Job Counters
> Failed map tasks=4
> Killed reduce tasks=1
> Launched map tasks=4
> Other local map tasks=3
> Data-local map tasks=1
> Total time spent by all maps in occupied slots (ms)=136272
> Total time spent by all reduces in occupied slots (ms)=0
> Total time spent by all map tasks (ms)=45424
> Total vcore-milliseconds taken by all map tasks=45424
> Total megabyte-milliseconds taken by all map tasks=139542528
> Job Diagnostics:Task failed task_1559213270190_0372_m_000000
> Job failed as tasks failed. failedMaps:1 failedReduces:0 killedMaps:0 killedReduces: 0
> Failure task Diagnostics:
> Error: java.lang.ClassCastException: org.apache.hadoop.io.IntWritable cannot be cast to org.apache.hadoop.io.LongWritable
> at org.apache.hadoop.hive.serde2.objectinspector.primitive.WritableLongObjectInspector.getPrimitiveJavaObject(WritableLongObjectInspector.java:46)
> at org.apache.hive.hcatalog.data.HCatRecordSerDe.serializePrimitiveField(HCatRecordSerDe.java:278)
> at org.apache.hive.hcatalog.data.HCatRecordSerDe.serializeField(HCatRecordSerDe.java:199)
> at org.apache.hive.hcatalog.data.LazyHCatRecord.get(LazyHCatRecord.java:53)
> at org.apache.hive.hcatalog.data.LazyHCatRecord.get(LazyHCatRecord.java:97)
> at org.apache.hive.hcatalog.mapreduce.HCatRecordReader.nextKeyValue(HCatRecordReader.java:204)
> at org.apache.hadoop.mapred.MapTask$NewTrackingRecordReader.nextKeyValue(MapTask.java:568)
> at org.apache.hadoop.mapreduce.task.MapContextImpl.nextKeyValue(MapContextImpl.java:80)
> at org.apache.hadoop.mapreduce.lib.map.WrappedMapper$Context.nextKeyValue(WrappedMapper.java:91)
> at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:145)
> at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:799)
> at org.apache.hadoop.mapred.MapTask.run(MapTask.java:347)
> at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:174)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:422)
> at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1730)
> at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:168)
> at org.apache.kylin.engine.mr.common.MapReduceExecutable.doWork(MapReduceExecutable.java:173)
> at org.apache.kylin.job.execution.AbstractExecutable.execute(AbstractExecutable.java:165)
> ... 6 more
> {code}
> Looks like the problem ib HCatalog that used by Kylin to access Hive tables... Please help, with solution finding...
>
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)