openinx commented on pull request #3611:
URL: https://github.com/apache/iceberg/pull/3611#issuecomment-983350565
@xingbowu , Could you please verify that whether the oss storage work
fines with different versioned engines ? I tried few engines, there seems be
few issues that we need to address. For example, when I run the spark query to
create tables , it will say ClassNotFound:
```
./bin/spark-sql --jars
/Users/openinx/software/apache-iceberg/spark/v3.1/spark-runtime/build/libs/iceberg-spark-3.1-runtime-0.13.0-SNAPSHOT.jar
\
--conf
spark.sql.extensions=org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions
\
--conf
spark.sql.catalog.spark_catalog=org.apache.iceberg.spark.SparkSessionCatalog \
--conf spark.sql.catalog.spark_catalog.type=hive \
--conf spark.sql.catalog.spark_catalog.uri=thrift://localhost:9031 \
--conf
spark.sql.catalog.spark_catalog.warehouse=oss://iceberg-test/warehouse \
--conf
spark.sql.catalog.spark_catalog.io-impl=org.apache.iceberg.aliyun.oss.OSSFileIO
\
--conf
spark.sql.catalog.spark_catalog.oss.endpoint=oss-cn-hangzhou.aliyuncs.com \
--conf spark.sql.catalog.spark_catalog.access.key.id=****** \
--conf spark.sql.catalog.spark_catalog.access.key.secret=******
spark-sql> CREATE TABLE spark_catalog.default.table (
> id bigint,
> data string,
> catagory string)
> USING iceberg
> LOCATION 'oss://iceberg-test/warehouse'
> PARTITIONED BY (catagory);
21/12/01 14:59:50 ERROR SparkSQLDriver: Failed in [CREATE TABLE
spark_catalog.default.table (
id bigint,
data string,
catagory string)
USING iceberg
LOCATION 'oss://iceberg-test/warehouse'
PARTITIONED BY (catagory)]
java.lang.BootstrapMethodError: java.lang.NoClassDefFoundError:
com/aliyun/oss/OSS
at org.apache.iceberg.aliyun.oss.OSSFileIO.initialize(OSSFileIO.java:94)
at org.apache.iceberg.CatalogUtil.loadFileIO(CatalogUtil.java:273)
at org.apache.iceberg.hive.HiveCatalog.initialize(HiveCatalog.java:88)
at org.apache.iceberg.CatalogUtil.loadCatalog(CatalogUtil.java:193)
at
org.apache.iceberg.CatalogUtil.buildIcebergCatalog(CatalogUtil.java:230)
at
org.apache.iceberg.spark.SparkCatalog.buildIcebergCatalog(SparkCatalog.java:105)
at
org.apache.iceberg.spark.SparkCatalog.initialize(SparkCatalog.java:388)
at
org.apache.iceberg.spark.SparkSessionCatalog.buildSparkCatalog(SparkSessionCatalog.java:70)
at
org.apache.iceberg.spark.SparkSessionCatalog.initialize(SparkSessionCatalog.java:255)
at
org.apache.spark.sql.connector.catalog.Catalogs$.load(Catalogs.scala:61)
at
org.apache.spark.sql.connector.catalog.CatalogManager.loadV2SessionCatalog(CatalogManager.scala:66)
at
org.apache.spark.sql.connector.catalog.CatalogManager.$anonfun$v2SessionCatalog$2(CatalogManager.scala:85)
at scala.collection.mutable.HashMap.getOrElseUpdate(HashMap.scala:86)
at
org.apache.spark.sql.connector.catalog.CatalogManager.$anonfun$v2SessionCatalog$1(CatalogManager.scala:85)
at scala.Option.map(Option.scala:230)
at
org.apache.spark.sql.connector.catalog.CatalogManager.v2SessionCatalog(CatalogManager.scala:84)
at
org.apache.spark.sql.connector.catalog.CatalogManager.catalog(CatalogManager.scala:50)
at
org.apache.spark.sql.connector.catalog.LookupCatalog$CatalogAndIdentifier$.unapply(LookupCatalog.scala:128)
at
org.apache.spark.sql.connector.catalog.LookupCatalog$NonSessionCatalogAndIdentifier$.unapply(LookupCatalog.scala:78)
at
org.apache.spark.sql.catalyst.analysis.ResolveCatalogs$NonSessionCatalogAndTable$.unapply(ResolveCatalogs.scala:220)
at
org.apache.spark.sql.catalyst.analysis.ResolveCatalogs$$anonfun$apply$1.applyOrElse(ResolveCatalogs.scala:143)
at
org.apache.spark.sql.catalyst.analysis.ResolveCatalogs$$anonfun$apply$1.applyOrElse(ResolveCatalogs.scala:34)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$2(AnalysisHelper.scala:108)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:74)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$1(AnalysisHelper.scala:108)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:221)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown(AnalysisHelper.scala:106)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown$(AnalysisHelper.scala:104)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperators(AnalysisHelper.scala:73)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperators$(AnalysisHelper.scala:72)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:29)
at
org.apache.spark.sql.catalyst.analysis.ResolveCatalogs.apply(ResolveCatalogs.scala:34)
at
org.apache.spark.sql.catalyst.analysis.ResolveCatalogs.apply(ResolveCatalogs.scala:29)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$2(RuleExecutor.scala:216)
at
scala.collection.LinearSeqOptimized.foldLeft(LinearSeqOptimized.scala:126)
at
scala.collection.LinearSeqOptimized.foldLeft$(LinearSeqOptimized.scala:122)
at scala.collection.immutable.List.foldLeft(List.scala:89)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1(RuleExecutor.scala:213)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1$adapted(RuleExecutor.scala:205)
at scala.collection.immutable.List.foreach(List.scala:392)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:205)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:196)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:190)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:155)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$executeAndTrack$1(RuleExecutor.scala:183)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:88)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.executeAndTrack(RuleExecutor.scala:183)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.$anonfun$executeAndCheck$1(Analyzer.scala:174)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:228)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:173)
at
org.apache.spark.sql.execution.QueryExecution.$anonfun$analyzed$1(QueryExecution.scala:73)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111)
at
org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$1(QueryExecution.scala:143)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at
org.apache.spark.sql.execution.QueryExecution.executePhase(QueryExecution.scala:143)
at
org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:73)
at
org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:71)
at
org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:63)
at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:98)
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:650)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:67)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:381)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1(SparkSQLCLIDriver.scala:500)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1$adapted(SparkSQLCLIDriver.scala:494)
at scala.collection.Iterator.foreach(Iterator.scala:941)
at scala.collection.Iterator.foreach$(Iterator.scala:941)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1429)
at scala.collection.IterableLike.foreach(IterableLike.scala:74)
at scala.collection.IterableLike.foreach$(IterableLike.scala:73)
at scala.collection.AbstractIterable.foreach(Iterable.scala:56)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processLine(SparkSQLCLIDriver.scala:494)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:284)
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:951)
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:1039)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1048)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.NoClassDefFoundError: com/aliyun/oss/OSS
... 91 more
Caused by: java.lang.ClassNotFoundException: com.aliyun.oss.OSS
at java.net.URLClassLoader.findClass(URLClassLoader.java:382)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
... 91 more
java.lang.BootstrapMethodError: java.lang.NoClassDefFoundError:
com/aliyun/oss/OSS
at org.apache.iceberg.aliyun.oss.OSSFileIO.initialize(OSSFileIO.java:94)
at org.apache.iceberg.CatalogUtil.loadFileIO(CatalogUtil.java:273)
at org.apache.iceberg.hive.HiveCatalog.initialize(HiveCatalog.java:88)
at org.apache.iceberg.CatalogUtil.loadCatalog(CatalogUtil.java:193)
at
org.apache.iceberg.CatalogUtil.buildIcebergCatalog(CatalogUtil.java:230)
at
org.apache.iceberg.spark.SparkCatalog.buildIcebergCatalog(SparkCatalog.java:105)
at
org.apache.iceberg.spark.SparkCatalog.initialize(SparkCatalog.java:388)
at
org.apache.iceberg.spark.SparkSessionCatalog.buildSparkCatalog(SparkSessionCatalog.java:70)
at
org.apache.iceberg.spark.SparkSessionCatalog.initialize(SparkSessionCatalog.java:255)
at
org.apache.spark.sql.connector.catalog.Catalogs$.load(Catalogs.scala:61)
at
org.apache.spark.sql.connector.catalog.CatalogManager.loadV2SessionCatalog(CatalogManager.scala:66)
at
org.apache.spark.sql.connector.catalog.CatalogManager.$anonfun$v2SessionCatalog$2(CatalogManager.scala:85)
at scala.collection.mutable.HashMap.getOrElseUpdate(HashMap.scala:86)
at
org.apache.spark.sql.connector.catalog.CatalogManager.$anonfun$v2SessionCatalog$1(CatalogManager.scala:85)
at scala.Option.map(Option.scala:230)
at
org.apache.spark.sql.connector.catalog.CatalogManager.v2SessionCatalog(CatalogManager.scala:84)
at
org.apache.spark.sql.connector.catalog.CatalogManager.catalog(CatalogManager.scala:50)
at
org.apache.spark.sql.connector.catalog.LookupCatalog$CatalogAndIdentifier$.unapply(LookupCatalog.scala:128)
at
org.apache.spark.sql.connector.catalog.LookupCatalog$NonSessionCatalogAndIdentifier$.unapply(LookupCatalog.scala:78)
at
org.apache.spark.sql.catalyst.analysis.ResolveCatalogs$NonSessionCatalogAndTable$.unapply(ResolveCatalogs.scala:220)
at
org.apache.spark.sql.catalyst.analysis.ResolveCatalogs$$anonfun$apply$1.applyOrElse(ResolveCatalogs.scala:143)
at
org.apache.spark.sql.catalyst.analysis.ResolveCatalogs$$anonfun$apply$1.applyOrElse(ResolveCatalogs.scala:34)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$2(AnalysisHelper.scala:108)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:74)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$1(AnalysisHelper.scala:108)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:221)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown(AnalysisHelper.scala:106)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown$(AnalysisHelper.scala:104)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperators(AnalysisHelper.scala:73)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperators$(AnalysisHelper.scala:72)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:29)
at
org.apache.spark.sql.catalyst.analysis.ResolveCatalogs.apply(ResolveCatalogs.scala:34)
at
org.apache.spark.sql.catalyst.analysis.ResolveCatalogs.apply(ResolveCatalogs.scala:29)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$2(RuleExecutor.scala:216)
at
scala.collection.LinearSeqOptimized.foldLeft(LinearSeqOptimized.scala:126)
at
scala.collection.LinearSeqOptimized.foldLeft$(LinearSeqOptimized.scala:122)
at scala.collection.immutable.List.foldLeft(List.scala:89)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1(RuleExecutor.scala:213)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1$adapted(RuleExecutor.scala:205)
at scala.collection.immutable.List.foreach(List.scala:392)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:205)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:196)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:190)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:155)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$executeAndTrack$1(RuleExecutor.scala:183)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:88)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.executeAndTrack(RuleExecutor.scala:183)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.$anonfun$executeAndCheck$1(Analyzer.scala:174)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:228)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:173)
at
org.apache.spark.sql.execution.QueryExecution.$anonfun$analyzed$1(QueryExecution.scala:73)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111)
at
org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$1(QueryExecution.scala:143)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at
org.apache.spark.sql.execution.QueryExecution.executePhase(QueryExecution.scala:143)
at
org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:73)
at
org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:71)
at
org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:63)
at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:98)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
at
org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:618)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:613)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:67)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:381)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1(SparkSQLCLIDriver.scala:500)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1$adapted(SparkSQLCLIDriver.scala:494)
at scala.collection.Iterator.foreach(Iterator.scala:941)
at scala.collection.Iterator.foreach$(Iterator.scala:941)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1429)
at scala.collection.IterableLike.foreach(IterableLike.scala:74)
at scala.collection.IterableLike.foreach$(IterableLike.scala:73)
at scala.collection.AbstractIterable.foreach(Iterable.scala:56)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processLine(SparkSQLCLIDriver.scala:494)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:284)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
at
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:951)
at
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203)
at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90)
at
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1039)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1048)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.NoClassDefFoundError: com/aliyun/oss/OSS
... 91 more
Caused by: java.lang.ClassNotFoundException: com.aliyun.oss.OSS
at java.net.URLClassLoader.findClass(URLClassLoader.java:382)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
... 91 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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
