gsudhanshu opened a new issue, #10432:
URL: https://github.com/apache/hudi/issues/10432
My Setup:
My Django application on app server uses pyspark 3.4.2 to connect to
spark-hudi bundle (3.4.2:2_12:0.14.0) on db server
spark config:
```
spark = SparkSession.builder \
.appName("dataHudi") \
.master('spark://db_server:7077') \
.config('spark.driver.bindAddress', '0.0.0.0') \
.config('spark.driver.host', 'app_server') \
.config('spark.driver.port', '37077') \
.config('spark.driver.blockManager.port', '37078') \
.config('spark.executor.host', 'db_server') \
.config("spark.executor.port", "37079") \
.config('spark.fileserver.host', 'db_server') \
.config("spark.fileserver.port", "37080") \
.config('spark.replClassServer.host', 'db_server') \
.config("spark.replClassServer.port", "37081") \
.config('spark.broadcast.host', 'db_server') \
.config("spark.broadcast.port", "37082") \
.config('spark.driver.memory', '7g') \
.config('spark.executor.memory', '4g') \
.config('spark.jars.packages',
'org.apache.hudi:hudi-spark3.4-bundle_2.12:0.14.0') \
.config('spark.serializer',
'org.apache.spark.serializer.KryoSerializer') \
.config('spark.sql.catalog.spark_catalog',
'org.apache.spark.sql.hudi.catalog.HoodieCatalog') \
.config('spark.sql.extensions',
'org.apache.spark.sql.hudi.HoodieSparkSessionExtension') \
.getOrCreate()
```
while writing data from pyspark pandas to hudi, I am getting following errors
Event Error logs:
```
org.apache.hudi.exception.HoodieRemoteException: Failed to create marker
file
/d13b0ab8-8d0d-4743-9f31-b3df2982965f-0_0-2-0_20231229115643749.parquet.marker.CREATE
Connect to 10.0.0.xxx:46131 [/10.0.0.xxx] failed: Connection timed out
(Connection timed out)
at
org.apache.hudi.table.marker.TimelineServerBasedWriteMarkers.executeCreateMarkerRequest(TimelineServerBasedWriteMarkers.java:186)
at
org.apache.hudi.table.marker.TimelineServerBasedWriteMarkers.create(TimelineServerBasedWriteMarkers.java:141)
at
org.apache.hudi.table.marker.WriteMarkers.create(WriteMarkers.java:67)
at
org.apache.hudi.io.storage.row.HoodieRowCreateHandle.createMarkerFile(HoodieRowCreateHandle.java:281)
at
org.apache.hudi.io.storage.row.HoodieRowCreateHandle.<init>(HoodieRowCreateHandle.java:144)
at
org.apache.hudi.table.action.commit.BulkInsertDataInternalWriterHelper.createHandle(BulkInsertDataInternalWriterHelper.java:187)
at
org.apache.hudi.table.action.commit.BulkInsertDataInternalWriterHelper.getRowCreateHandle(BulkInsertDataInternalWriterHelper.java:173)
at
org.apache.hudi.table.action.commit.BulkInsertDataInternalWriterHelper.write(BulkInsertDataInternalWriterHelper.java:121)
at
org.apache.hudi.spark3.internal.HoodieBulkInsertDataInternalWriter.write(HoodieBulkInsertDataInternalWriter.java:62)
at
org.apache.hudi.spark3.internal.HoodieBulkInsertDataInternalWriter.write(HoodieBulkInsertDataInternalWriter.java:38)
at
org.apache.spark.sql.execution.datasources.v2.DataWritingSparkTask$.write(WriteToDataSourceV2Exec.scala:516)
at
org.apache.spark.sql.execution.datasources.v2.WritingSparkTask.$anonfun$run$1(WriteToDataSourceV2Exec.scala:471)
at
org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1563)
at
org.apache.spark.sql.execution.datasources.v2.WritingSparkTask.run(WriteToDataSourceV2Exec.scala:509)
at
org.apache.spark.sql.execution.datasources.v2.WritingSparkTask.run$(WriteToDataSourceV2Exec.scala:448)
at
org.apache.spark.sql.execution.datasources.v2.DataWritingSparkTask$.run(WriteToDataSourceV2Exec.scala:514)
at
org.apache.spark.sql.execution.datasources.v2.V2TableWriteExec.$anonfun$writeWithV2$2(WriteToDataSourceV2Exec.scala:411)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:92)
at
org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:161)
at org.apache.spark.scheduler.Task.run(Task.scala:139)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:554)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1529)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:557)
at
java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
at
java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
at java.base/java.lang.Thread.run(Thread.java:829)
Caused by: org.apache.hudi.org.apache.http.conn.HttpHostConnectException:
Connect to 10.0.0.164:46131 [/10.0.0.164] failed: Connection timed out
(Connection timed out)
at
org.apache.hudi.org.apache.http.impl.conn.DefaultHttpClientConnectionOperator.connect(DefaultHttpClientConnectionOperator.java:151)
at
org.apache.hudi.org.apache.http.impl.conn.PoolingHttpClientConnectionManager.connect(PoolingHttpClientConnectionManager.java:353)
at
org.apache.hudi.org.apache.http.impl.execchain.MainClientExec.establishRoute(MainClientExec.java:380)
at
org.apache.hudi.org.apache.http.impl.execchain.MainClientExec.execute(MainClientExec.java:236)
at
org.apache.hudi.org.apache.http.impl.execchain.ProtocolExec.execute(ProtocolExec.java:184)
at
org.apache.hudi.org.apache.http.impl.execchain.RetryExec.execute(RetryExec.java:88)
at
org.apache.hudi.org.apache.http.impl.execchain.RedirectExec.execute(RedirectExec.java:110)
at
org.apache.hudi.org.apache.http.impl.client.InternalHttpClient.doExecute(InternalHttpClient.java:184)
at
org.apache.hudi.org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:82)
at
org.apache.hudi.org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:107)
at
org.apache.hudi.org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:55)
at
org.apache.hudi.org.apache.http.client.fluent.Request.execute(Request.java:151)
at
org.apache.hudi.table.marker.TimelineServerBasedWriteMarkers.executeRequestToTimelineServer(TimelineServerBasedWriteMarkers.java:232)
at
org.apache.hudi.table.marker.TimelineServerBasedWriteMarkers.executeCreateMarkerRequest(TimelineServerBasedWriteMarkers.java:182)
```
Is there a workaround?
--
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]