在Hive 中建立Phoenix 外表，进行关联和where条件查询时候Undefined column. columnName=user
Query ID = hadoop_20190508174141_0127402b-038c-4fc8-86d1-9470a9944e39
Total jobs = 1
Launching Job 1 out of 1
Number of reduce tasks determined at compile time: 1
In order to change the average load for a reducer (in bytes):
set hive.exec.reducers.bytes.per.reducer=
In order to limit the maximum number of reducers:
set hive.exec.reducers.max=
In order to set a constant number of reducers:
set mapreduce.job.reduces=
java.lang.RuntimeException: org.apache.phoenix.schema.ColumnNotFoundException: ERROR 504 (42703): Undefined column. columnName=user
at org.apache.phoenix.hive.mapreduce.PhoenixInputFormat.getQueryPlan(PhoenixInputFormat.java:266)
at org.apache.phoenix.hive.mapreduce.PhoenixInputFormat.getSplits(PhoenixInputFormat.java:131)
at org.apache.hadoop.hive.ql.io.HiveInputFormat.addSplitsForGroup(HiveInputFormat.java:320)
at org.apache.hadoop.hive.ql.io.HiveInputFormat.getSplits(HiveInputFormat.java:432)
at org.apache.hadoop.hive.ql.io.CombineHiveInputFormat.getCombineSplits(CombineHiveInputFormat.java:370)
at org.apache.hadoop.hive.ql.io.CombineHiveInputFormat.getSplits(CombineHiveInputFormat.java:547)
at org.apache.hadoop.mapreduce.JobSubmitter.writeOldSplits(JobSubmitter.java:332)
at org.apache.hadoop.mapreduce.JobSubmitter.writeSplits(JobSubmitter.java:324)
at org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:200)
at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1307)
at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1304)
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:1917)
at org.apache.hadoop.mapreduce.Job.submit(Job.java:1304)
at org.apache.hadoop.mapred.JobClient$1.run(JobClient.java:578)
at org.apache.hadoop.mapred.JobClient$1.run(JobClient.java:573)
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:1917)
at org.apache.hadoop.mapred.JobClient.submitJobInternal(JobClient.java:573)
at org.apache.hadoop.mapred.JobClient.submitJob(JobClient.java:564)
at org.apache.hadoop.hive.ql.exec.mr.ExecDriver.execute(ExecDriver.java:436)
at org.apache.hadoop.hive.ql.exec.mr.MapRedTask.execute(MapRedTask.java:142)
at org.apache.hadoop.hive.ql.exec.Task.executeTask(Task.java:214)
at org.apache.hadoop.hive.ql.exec.TaskRunner.runSequential(TaskRunner.java:99)
at org.apache.hadoop.hive.ql.Driver.launchTask(Driver.java:2052)
at org.apache.hadoop.hive.ql.Driver.execute(Driver.java:1748)
at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1501)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1285)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1275)
at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:226)
at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:175)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:389)
at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:781)
at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:699)
at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:634)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at org.apache.hadoop.util.RunJar.run(RunJar.java:221)
at org.apache.hadoop.util.RunJar.main(RunJar.java:136)
Caused by: org.apache.phoenix.schema.ColumnNotFoundException: ERROR 504 (42703): Undefined column. columnName=user
at org.apache.phoenix.schema.PTableImpl.getColumnForColumnName(PTableImpl.java:828)
at org.apache.phoenix.compile.FromCompiler$SingleTableColumnResolver.resolveColumn(FromCompiler.java:477)
at org.apache.phoenix.compile.TupleProjectionCompiler$ColumnRefVisitor.visit(TupleProjectionCompiler.java:207)
at org.apache.phoenix.compile.TupleProjectionCompiler$ColumnRefVisitor.visit(TupleProjectionCompiler.java:193)
at org.apache.phoenix.parse.ColumnParseNode.accept(ColumnParseNode.java:56)
at org.apache.phoenix.compile.TupleProjectionCompiler.createProjectedTable(TupleProjectionCompiler.java:109)
at org.apache.phoenix.compile.QueryCompiler.compileSingleFlatQuery(QueryCompiler.java:528)
at org.apache.phoenix.compile.QueryCompiler.compileSingleQuery(QueryCompiler.java:507)
at org.apache.phoenix.compile.QueryCompiler.compileSelect(QueryCompiler.java:202)
at org.apache.phoenix.compile.QueryCompiler.compile(QueryCompiler.java:157)
at org.apache.phoenix.jdbc.PhoenixStatement$ExecutableSelectStatement.compilePlan(PhoenixStatement.java:476)
at org.apache.phoenix.jdbc.PhoenixStatement$ExecutableSelectStatement.compilePlan(PhoenixStatement.java:442)
at org.apache.phoenix.jdbc.PhoenixStatement.compileQuery(PhoenixStatement.java:1679)
at org.apache.phoenix.jdbc.PhoenixStatement.compileQuery(PhoenixStatement.java:1672)
at org.apache.phoenix.jdbc.PhoenixStatement.optimizeQuery(PhoenixStatement.java:1666)
at org.apache.phoenix.hive.mapreduce.PhoenixInputFormat.getQueryPlan(PhoenixInputFormat.java:260)
... 42 more
Job Submission failed with exception 'java.lang.RuntimeException(org.apache.phoenix.schema.ColumnNotFoundException: ERROR 504 (42703): Undefined column. columnName=user)'
FAILED: Execution Error, return code 1 from org.apache.hadoop.hive.ql.exec.mr.MapRedTask
最近在用Phoenix，建立外表关联后，进行 select count from user 正常执行。但是一旦关联一个hive表或者加一个where一个条件进行出现如上异常 在国内网站查询一圈，大家只认为是一个bug，并没有bug的解决方案。使用google 输入 phoenix hive external undefined column 后发现大部分也只是mapping 配置错了。
最后在官方的jira 中发现了该bug已经记录 https://issues.apache.org/jira/browse/PHOENIX-4804 并提供了 git link 来修复该问题，查看了解决方法比较简单，需要重新打包 core 包。https://github.com/apache/phoenix/pull/407/commits/66715753fc346392c01fb5e6ff4b561fb486370d
ps: 重新打包方法 请看我另外一篇文章