carlosescura commented on PR #7914:
URL: https://github.com/apache/iceberg/pull/7914#issuecomment-2006763129
@lokeshrdy Still doesn't work using Spark `3.5.0`and Iceberg `1.5.0` and
Glue as catalog with the following config:
```
SPARK_SETTINGS = [
(
"spark.jars",
"""
/opt/spark/jars/iceberg-aws-bundle-1.5.0.jar,
/opt/spark/jars/iceberg-spark-runtime-3.5_2.12-1.5.0.jar,
/opt/spark/jars/aws-java-sdk-bundle-1.12.262.jar,
/opt/spark/jars/hadoop-aws-3.3.4.jar
""",
),
("spark.hadoop.fs.s3a.impl", "org.apache.hadoop.fs.s3a.S3AFileSystem"),
("spark.hadoop.com.amazonaws.services.s3.enableV4", "true"),
(
"spark.sql.extensions",
"org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions",
),
(
"spark.sql.catalog.main_catalog",
"org.apache.iceberg.spark.SparkCatalog",
),
(
"spark.sql.catalog.main_catalog.catalog-impl",
"org.apache.iceberg.aws.glue.GlueCatalog",
),
(
"spark.sql.catalog.main_catalog.io-impl",
"org.apache.iceberg.aws.s3.S3FileIO",
),
(
"spark.sql.catalog.main_catalog.warehouse",
ICEBERG_CATALOG_WHAREHOUSE,
),
]
```
I had to add `hadoop-aws-3.3.4.jar` to be able to download some CSVs and
load them as Spark DF.
When calling the `remove_orphan_files` procedure I get the following
exception:
```
py4j.protocol.Py4JJavaError: An error occurred while calling o46.sql.
: java.io.UncheckedIOException:
org.apache.hadoop.fs.UnsupportedFileSystemException: No FileSystem for scheme
"s3"
at
org.apache.iceberg.spark.actions.DeleteOrphanFilesSparkAction.listDirRecursively(DeleteOrphanFilesSparkAction.java:386)
at
org.apache.iceberg.spark.actions.DeleteOrphanFilesSparkAction.listedFileDS(DeleteOrphanFilesSparkAction.java:311)
at
org.apache.iceberg.spark.actions.DeleteOrphanFilesSparkAction.actualFileIdentDS(DeleteOrphanFilesSparkAction.java:296)
at
org.apache.iceberg.spark.actions.DeleteOrphanFilesSparkAction.doExecute(DeleteOrphanFilesSparkAction.java:247)
at
org.apache.iceberg.spark.JobGroupUtils.withJobGroupInfo(JobGroupUtils.java:59)
at
org.apache.iceberg.spark.JobGroupUtils.withJobGroupInfo(JobGroupUtils.java:51)
at
org.apache.iceberg.spark.actions.BaseSparkAction.withJobGroupInfo(BaseSparkAction.java:130)
at
org.apache.iceberg.spark.actions.DeleteOrphanFilesSparkAction.execute(DeleteOrphanFilesSparkAction.java:223)
at
org.apache.iceberg.spark.procedures.RemoveOrphanFilesProcedure.lambda$call$3(RemoveOrphanFilesProcedure.java:185)
at
org.apache.iceberg.spark.procedures.BaseProcedure.execute(BaseProcedure.java:107)
at
org.apache.iceberg.spark.procedures.BaseProcedure.withIcebergTable(BaseProcedure.java:96)
at
org.apache.iceberg.spark.procedures.RemoveOrphanFilesProcedure.call(RemoveOrphanFilesProcedure.java:139)
at
org.apache.spark.sql.execution.datasources.v2.CallExec.run(CallExec.scala:34)
at
org.apache.spark.sql.execution.datasources.v2.V2CommandExec.result$lzycompute(V2CommandExec.scala:43)
at
org.apache.spark.sql.execution.datasources.v2.V2CommandExec.result(V2CommandExec.scala:43)
at
org.apache.spark.sql.execution.datasources.v2.V2CommandExec.executeCollect(V2CommandExec.scala:49)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:107)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:107)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:98)
at
org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:461)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(origin.scala:76)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:461)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:32)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:267)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:263)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:32)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:32)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:437)
at
org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:98)
at
org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:85)
at
org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:83)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:220)
at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:100)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:97)
at
org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:638)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:629)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:659)
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 py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at
py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
at py4j.ClientServerConnection.run(ClientServerConnection.java:106)
at java.lang.Thread.run(Thread.java:750)
Caused by: org.apache.hadoop.fs.UnsupportedFileSystemException: No
FileSystem for scheme "s3"
at
org.apache.hadoop.fs.FileSystem.getFileSystemClass(FileSystem.java:3443)
at
org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:3466)
at org.apache.hadoop.fs.FileSystem.access$300(FileSystem.java:174)
at
org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:3574)
at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:3521)
at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:540)
at org.apache.hadoop.fs.Path.getFileSystem(Path.java:365)
at
org.apache.iceberg.spark.actions.DeleteOrphanFilesSparkAction.listDirRecursively(DeleteOrphanFilesSparkAction.java:356)
... 55 more
```
--
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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
