[HUDI-7805] FileSystemBasedLockProvider need delete lock file auto when occur lock conflict to avoid next write failed

• Type: Improvement
• Status: Open
• Priority: Major
• Resolution: Unresolved
• Component/s: multi-writer
• Labels: pull-request-available
• Assignee: xy
• Reporter: xy
• Created: 28/May/24 12:36
• Updated: 02/Jun/24 06:24

Description

org.apache.hudi.exception.HoodieLockException: Unable to acquire lock, lock object hdfs://aa-region/region04/2211/warehouse/hudi/odsmon_log/.hoodie/lock
at org.apache.hudi.client.transaction.lock.LockManager.lock(LockManager.java:100)
at org.apache.hudi.client.transaction.TransactionManager.beginTransaction(TransactionManager.java:58)
at org.apache.hudi.client.BaseHoodieWriteClient.doInitTable(BaseHoodieWriteClient.java:1258)
at org.apache.hudi.client.BaseHoodieWriteClient.initTable(BaseHoodieWriteClient.java:1301)
at org.apache.hudi.client.SparkRDDWriteClient.upsert(SparkRDDWriteClient.java:139)
at org.apache.hudi.DataSourceUtils.doWriteOperation(DataSourceUtils.java:216)
at org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:396)
at org.apache.spark.sql.hudi.command.InsertIntoHoodieTableCommand$.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$1(SparkSession.scala:618)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:613)
at com.vivo.bigdata.etl.process.EtlProcessMain$.main(EtlProcessMain.scala:367)
at com.vivo.bigdata.etl.process.EtlProcessMain.main(EtlProcessMain.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)

Issue Links

• links to: GitHub Pull Request #11347