xy created HUDI-7772:
------------------------
Summary: HoodieTimelineArchiver##getCommitInstantsToArchive need
skip limiting archiving of instants
Key: HUDI-7772
URL: https://issues.apache.org/jira/browse/HUDI-7772
Project: Apache Hudi
Issue Type: Improvement
Components: archiving
Reporter: xy
Assignee: xy
When user alter table by adding a column then insert new data to the table with
set mdt enable, would error out with follow, from the stack we find that
FileSystemBackedTableMetadata not support it.
org.apache.hudi.exception.HoodieException: Error limiting instant archival
based on metadata table
at
org.apache.hudi.client.HoodieTimelineArchiver.getInstantsToArchive(HoodieTimelineArchiver.java:522)
at
org.apache.hudi.client.HoodieTimelineArchiver.archiveIfRequired(HoodieTimelineArchiver.java:167)
at
org.apache.hudi.client.BaseHoodieTableServiceClient.archive(BaseHoodieTableServiceClient.java:791)
at
org.apache.hudi.client.BaseHoodieWriteClient.archive(BaseHoodieWriteClient.java:890)
at
org.apache.hudi.client.BaseHoodieWriteClient.autoArchiveOnCommit(BaseHoodieWriteClient.java:619)
at
org.apache.hudi.client.BaseHoodieWriteClient.mayBeCleanAndArchive(BaseHoodieWriteClient.java:585)
at
org.apache.hudi.client.BaseHoodieWriteClient.commitStats(BaseHoodieWriteClient.java:248)
at
org.apache.hudi.client.SparkRDDWriteClient.commit(SparkRDDWriteClient.java:104)
at
org.apache.hudi.HoodieSparkSqlWriter$.commitAndPerformPostOperations(HoodieSparkSqlWriter.scala:1020)
at
org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:405)
at
org.apache.spark.sql.hudi.command.InsertIntoHoodieTableCommand$.run(InsertIntoHoodieTableCommand.scala:108)
at
org.apache.spark.sql.hudi.command.InsertIntoHoodieTableCommand.run(InsertIntoHoodieTableCommand.scala:61)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:80)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:78)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:89)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:110)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:110)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:106)
at
org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:481)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:82)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:481)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:30)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:267)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:263)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:457)
at
org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:106)
at
org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:93)
at
org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:91)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:219)
at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
at
org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:618)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:613)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:651)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:83)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:465)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1(SparkSQLCLIDriver.scala:634)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1$adapted(SparkSQLCLIDriver.scala:628)
at
scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at
scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processLine(SparkSQLCLIDriver.scala:628)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:336)
at
org.apache.hadoop.hive.cli.CliDriver.processReader(CliDriver.java:474)
at org.apache.hadoop.hive.cli.CliDriver.processFile(CliDriver.java:490)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:282)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
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:498)
at
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
at
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:968)
at
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203)
at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90)
at
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1070)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1079)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.UnsupportedOperationException
at
org.apache.hudi.metadata.FileSystemBackedTableMetadata.getLatestCompactionTime(FileSystemBackedTableMetadata.java:260)
at
org.apache.hudi.client.HoodieTimelineArchiver.getInstantsToArchive(HoodieTimelineArchiver.java:512)
... 67 more
org.apache.hudi.exception.HoodieException: Error limiting instant archival
based on metadata table
at
org.apache.hudi.client.HoodieTimelineArchiver.getInstantsToArchive(HoodieTimelineArchiver.java:522)
at
org.apache.hudi.client.HoodieTimelineArchiver.archiveIfRequired(HoodieTimelineArchiver.java:167)
at
org.apache.hudi.client.BaseHoodieTableServiceClient.archive(BaseHoodieTableServiceClient.java:791)
at
org.apache.hudi.client.BaseHoodieWriteClient.archive(BaseHoodieWriteClient.java:890)
at
org.apache.hudi.client.BaseHoodieWriteClient.autoArchiveOnCommit(BaseHoodieWriteClient.java:619)
at
org.apache.hudi.client.BaseHoodieWriteClient.mayBeCleanAndArchive(BaseHoodieWriteClient.java:585)
at
org.apache.hudi.client.BaseHoodieWriteClient.commitStats(BaseHoodieWriteClient.java:248)
at
org.apache.hudi.client.SparkRDDWriteClient.commit(SparkRDDWriteClient.java:104)
at
org.apache.hudi.HoodieSparkSqlWriter$.commitAndPerformPostOperations(HoodieSparkSqlWriter.scala:1020)
at
org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:405)
at
org.apache.spark.sql.hudi.command.InsertIntoHoodieTableCommand$.run(InsertIntoHoodieTableCommand.scala:108)
at
org.apache.spark.sql.hudi.command.InsertIntoHoodieTableCommand.run(InsertIntoHoodieTableCommand.scala:61)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:80)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:78)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:89)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:110)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:110)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:106)
at
org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:481)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:82)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:481)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:30)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:267)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:263)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:457)
at
org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:106)
at
org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:93)
at
org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:91)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:219)
at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
at
org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:618)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:613)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:651)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:83)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:465)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1(SparkSQLCLIDriver.scala:634)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1$adapted(SparkSQLCLIDriver.scala:628)
at
scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at
scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processLine(SparkSQLCLIDriver.scala:628)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:336)
at
org.apache.hadoop.hive.cli.CliDriver.processReader(CliDriver.java:474)
at org.apache.hadoop.hive.cli.CliDriver.processFile(CliDriver.java:490)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:282)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
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:498)
at
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
at
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:968)
at
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203)
at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90)
at
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1070)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1079)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.UnsupportedOperationException
at
org.apache.hudi.metadata.FileSystemBackedTableMetadata.getLatestCompactionTime(FileSystemBackedTableMetadata.java:260)
at
org.apache.hudi.client.HoodieTimelineArchiver.getInstantsToArchive(HoodieTimelineArchiver.java:512)
... 67 more
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
