YuriyGavrilov commented on issue #4406:
URL: https://github.com/apache/seatunnel/issues/4406#issuecomment-1852601049

   I understood how to load data from s3 to local file but receiving an error 
when trying to copy from s3 to s3 with same config to another folder with 
cutting columns option sink_columns = ["a","b"]. So receiving  errors 
   
   ```
   2023-12-12 21:20:20 2023-12-12 18:20:20,797 WARN  
org.apache.seatunnel.engine.server.TaskExecutionService - [localhost]:5801 
[seatunnel-86182] [5.1] Exception in 
org.apache.seatunnel.engine.server.task.TransformSeaTunnelTask@6668d0db
   2023-12-12 21:20:20 java.lang.NoSuchMethodError: 
org.apache.hadoop.util.SemaphoredDelegatingExecutor.<init>(Ljava/util/concurrent/ExecutorService;IZ)V
   2023-12-12 21:20:20     at 
org.apache.hadoop.fs.s3a.S3AFileSystem.create(S3AFileSystem.java:824) 
~[hadoop-aws-3.2.4.jar:?]
   2023-12-12 21:20:20     at 
org.apache.hadoop.fs.FileSystem.create(FileSystem.java:1118) 
~[seatunnel-hadoop3-3.1.4-uber-2.3.1-optional.jar:2.3.1]
   2023-12-12 21:20:20     at 
org.apache.hadoop.fs.FileSystem.create(FileSystem.java:1098) 
~[seatunnel-hadoop3-3.1.4-uber-2.3.1-optional.jar:2.3.1]
   2023-12-12 21:20:20     at 
org.apache.hadoop.fs.FileSystem.create(FileSystem.java:1057) 
~[seatunnel-hadoop3-3.1.4-uber-2.3.1-optional.jar:2.3.1]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.connectors.seatunnel.file.sink.util.FileSystemUtils.getOutputStream(FileSystemUtils.java:108)
 ~[connector-file-s3-2.3.3.jar:2.3.3]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.connectors.seatunnel.file.sink.writer.TextWriteStrategy.getOrCreateOutputStream(TextWriteStrategy.java:138)
 ~[connector-file-s3-2.3.3.jar:2.3.3]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.connectors.seatunnel.file.sink.writer.TextWriteStrategy.write(TextWriteStrategy.java:81)
 ~[connector-file-s3-2.3.3.jar:2.3.3]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.connectors.seatunnel.file.sink.BaseFileSinkWriter.write(BaseFileSinkWriter.java:126)
 ~[connector-file-s3-2.3.3.jar:2.3.3]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.connectors.seatunnel.file.sink.BaseFileSinkWriter.write(BaseFileSinkWriter.java:43)
 ~[connector-file-s3-2.3.3.jar:2.3.3]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.flow.SinkFlowLifeCycle.received(SinkFlowLifeCycle.java:227)
 ~[seatunnel-starter.jar:2.3.3]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.flow.SinkFlowLifeCycle.received(SinkFlowLifeCycle.java:61)
 ~[seatunnel-starter.jar:2.3.3]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.SeaTunnelTransformCollector.collect(SeaTunnelTransformCollector.java:39)
 ~[seatunnel-starter.jar:2.3.3]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.SeaTunnelTransformCollector.collect(SeaTunnelTransformCollector.java:27)
 ~[seatunnel-starter.jar:2.3.3]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.group.queue.IntermediateBlockingQueue.handleRecord(IntermediateBlockingQueue.java:76)
 ~[seatunnel-starter.jar:2.3.3]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.group.queue.IntermediateBlockingQueue.collect(IntermediateBlockingQueue.java:51)
 ~[seatunnel-starter.jar:2.3.3]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.flow.IntermediateQueueFlowLifeCycle.collect(IntermediateQueueFlowLifeCycle.java:52)
 ~[seatunnel-starter.jar:2.3.3]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.TransformSeaTunnelTask.collect(TransformSeaTunnelTask.java:73)
 ~[seatunnel-starter.jar:2.3.3]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.SeaTunnelTask.stateProcess(SeaTunnelTask.java:168)
 ~[seatunnel-starter.jar:2.3.3]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.TransformSeaTunnelTask.call(TransformSeaTunnelTask.java:78)
 ~[seatunnel-starter.jar:2.3.3]
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.TaskExecutionService$BlockingWorker.run(TaskExecutionService.java:613)
 [seatunnel-starter.jar:2.3.3]
   2023-12-12 21:20:20     at 
java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511) 
[?:1.8.0_342]
   2023-12-12 21:20:20     at 
java.util.concurrent.FutureTask.run(FutureTask.java:266) [?:1.8.0_342]
   2023-12-12 21:20:20     at 
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) 
[?:1.8.0_342]
   2023-12-12 21:20:20     at 
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) 
[?:1.8.0_342]
   2023-12-12 21:20:20     at java.lang.Thread.run(Thread.java:750) 
[?:1.8.0_342]
   ```
   
   Next error 
   
   ```
   2023-12-12 21:20:20 2023-12-12 18:20:20,809 ERROR 
org.apache.seatunnel.engine.server.dag.physical.PhysicalVertex - Job 
SeaTunnel_Job (787020937437380609), Pipeline: [(1/1)], task: [pipeline-1 
[Source[0]-S3File-default-identifier]-SourceTask (1/1)] end with state FAILED 
and Exception: java.lang.NoSuchMethodError: 
org.apache.hadoop.util.SemaphoredDelegatingExecutor.<init>(Ljava/util/concurrent/ExecutorService;IZ)V
   2023-12-12 21:20:20     at 
org.apache.hadoop.fs.s3a.S3AFileSystem.create(S3AFileSystem.java:824)
   2023-12-12 21:20:20     at 
org.apache.hadoop.fs.FileSystem.create(FileSystem.java:1118)
   2023-12-12 21:20:20     at 
org.apache.hadoop.fs.FileSystem.create(FileSystem.java:1098)
   2023-12-12 21:20:20     at 
org.apache.hadoop.fs.FileSystem.create(FileSystem.java:1057)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.connectors.seatunnel.file.sink.util.FileSystemUtils.getOutputStream(FileSystemUtils.java:108)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.connectors.seatunnel.file.sink.writer.TextWriteStrategy.getOrCreateOutputStream(TextWriteStrategy.java:138)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.connectors.seatunnel.file.sink.writer.TextWriteStrategy.write(TextWriteStrategy.java:81)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.connectors.seatunnel.file.sink.BaseFileSinkWriter.write(BaseFileSinkWriter.java:126)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.connectors.seatunnel.file.sink.BaseFileSinkWriter.write(BaseFileSinkWriter.java:43)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.flow.SinkFlowLifeCycle.received(SinkFlowLifeCycle.java:227)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.flow.SinkFlowLifeCycle.received(SinkFlowLifeCycle.java:61)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.SeaTunnelTransformCollector.collect(SeaTunnelTransformCollector.java:39)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.SeaTunnelTransformCollector.collect(SeaTunnelTransformCollector.java:27)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.group.queue.IntermediateBlockingQueue.handleRecord(IntermediateBlockingQueue.java:76)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.group.queue.IntermediateBlockingQueue.collect(IntermediateBlockingQueue.java:51)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.flow.IntermediateQueueFlowLifeCycle.collect(IntermediateQueueFlowLifeCycle.java:52)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.TransformSeaTunnelTask.collect(TransformSeaTunnelTask.java:73)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.SeaTunnelTask.stateProcess(SeaTunnelTask.java:168)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.task.TransformSeaTunnelTask.call(TransformSeaTunnelTask.java:78)
   2023-12-12 21:20:20     at 
org.apache.seatunnel.engine.server.TaskExecutionService$BlockingWorker.run(TaskExecutionService.java:613)
   2023-12-12 21:20:20     at 
java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511)
   2023-12-12 21:20:20     at 
java.util.concurrent.FutureTask.run(FutureTask.java:266)
   2023-12-12 21:20:20     at 
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
   2023-12-12 21:20:20     at 
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
   2023-12-12 21:20:20     at java.lang.Thread.run(Thread.java:750)
   2023-12-12 21:20:20 
   2023-12-12 21:20:20 2023-12-12 18:20:20,809 ERROR 
org.apache.seatunnel.engine.server.dag.physical.SubPlan - Task 
TaskGroupLocation{jobId=787020937437380609, pipelineId=1, taskGroupId=50000} 
Failed in Job SeaTunnel_Job (787020937437380609), Pipeline: [(1/1)], Begin to 
cancel other tasks in this pipeline.
   ```
   
   
   
   for this config:
   ```
   2023-12-12 21:20:13     "env" : {
   2023-12-12 21:20:13         "execution.parallelism" : 1,
   2023-12-12 21:20:13         "job.mode" : "BATCH"
   2023-12-12 21:20:13     },
   2023-12-12 21:20:13     "source" : [
   2023-12-12 21:20:13         {
   2023-12-12 21:20:13             "bucket" : "s3a://test",
   2023-12-12 21:20:13             "path" : "/seatunnel/",
   2023-12-12 21:20:13             "secret_key" : "XXXXXX",
   2023-12-12 21:20:13             "file_format_type" : "parquet",
   2023-12-12 21:20:13             "access_key" : "XXXXXXX",
   2023-12-12 21:20:13             "fs.s3a.aws.credentials.provider" : 
"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider",
   2023-12-12 21:20:13             "plugin_name" : "S3File",
   2023-12-12 21:20:13             "fs.s3a.endpoint" : "gateway.storjshare.io"
   2023-12-12 21:20:13         }
   2023-12-12 21:20:13     ],
   2023-12-12 21:20:13     "transform" : [],
   2023-12-12 21:20:13     "sink" : [
   2023-12-12 21:20:13         {
   2023-12-12 21:20:13             "bucket" : "s3a://test",
   2023-12-12 21:20:13             "path" : "/seatunnel2/",
   2023-12-12 21:20:13             "secret_key" : "XXXXX",
   2023-12-12 21:20:13             "access_key" : "XXXXX",
   2023-12-12 21:20:13             "fs.s3a.aws.credentials.provider" : 
"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider",
   2023-12-12 21:20:13             "plugin_name" : "S3File",
   2023-12-12 21:20:13             "fs.s3a.endpoint" : "gateway.storjshare.io",
   2023-12-12 21:20:13             "sink_columns" : [
   2023-12-12 21:20:13                 "a",
   2023-12-12 21:20:13                 "b"
   2023-12-12 21:20:13             ]
   2023-12-12 21:20:13         }
   2023-12-12 21:20:13     ]
   2023-12-12 21:20:13 }
   ```


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to