BenjMaq opened a new issue #4207:
URL: https://github.com/apache/hudi/issues/4207
**Describe the problem you faced**
I'm currently using Hudi 0.9.0 and it runs fine. I can insert/delete data
without problems (using Hudi Spark-SQL).
Switching to Hudi 0.10.0 throws
`java.lang.NoSuchMethodError:com.amazonaws.http.AmazonHttpClient.disableStrictHostnameVerification`
**Environment Description**
* Hudi version : 0.10.0
* Spark version : 2.4.4
* Hive version : 2.3.5
* Hadoop version : (`hadoop-aws` 2.7.3)
* Storage (HDFS/S3/GCS..) : S3
* Running on Docker? (yes/no) : No
**Stacktrace**
```
Exception in thread "main"
org.spark_project.guava.util.concurrent.ExecutionError:
java.lang.NoSuchMethodError:
com.amazonaws.http.AmazonHttpClient.disableStrictHostnameVerification()V
at
org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2261)
at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
at
org.spark_project.guava.cache.LocalCache$LocalManualCache.get(LocalCache.java:4789)
at
org.apache.spark.sql.catalyst.catalog.SessionCatalog.getCachedPlan(SessionCatalog.scala:141)
at
org.apache.spark.sql.execution.datasources.FindDataSourceTable.org$apache$spark$sql$execution$datasources$FindDataSourceTable$$readDataSourceTable(DataSourceStrategy.scala:227)
at
org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anonfun$apply$2.applyOrElse(DataSourceStrategy.scala:264)
at
org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anonfun$apply$2.applyOrElse(DataSourceStrategy.scala:255)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$2.apply(AnalysisHelper.scala:108)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$2.apply(AnalysisHelper.scala:108)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:107)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:113)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:113)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:113)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperators(AnalysisHelper.scala:73)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:29)
at
org.apache.spark.sql.execution.datasources.FindDataSourceTable.apply(DataSourceStrategy.scala:255)
at
org.apache.spark.sql.execution.datasources.FindDataSourceTable.apply(DataSourceStrategy.scala:223)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:87)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:84)
at
scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
at scala.collection.immutable.List.foldLeft(List.scala:84)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:84)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:76)
at scala.collection.immutable.List.foreach(List.scala:392)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:76)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:127)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:121)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:106)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:105)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:201)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:105)
at
org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:57)
at
org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:55)
at
org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:47)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:78)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:642)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:694)
at
com.twilio.optimustranformer.OptimusTranformer$$anonfun$main$1$$anonfun$apply$mcV$sp$1.apply(OptimusTranformer.scala:74)
at
com.twilio.optimustranformer.OptimusTranformer$$anonfun$main$1$$anonfun$apply$mcV$sp$1.apply(OptimusTranformer.scala:72)
at
scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
at
com.twilio.optimustranformer.OptimusTranformer$$anonfun$main$1.apply$mcV$sp(OptimusTranformer.scala:71)
at scala.util.control.Breaks.breakable(Breaks.scala:38)
at
com.twilio.optimustranformer.OptimusTranformer$.main(OptimusTranformer.scala:70)
at
com.twilio.optimustranformer.OptimusTranformer.main(OptimusTranformer.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$$runMain(SparkSubmit.scala:845)
at
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:161)
at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:184)
at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:86)
at
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:920)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:929)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.NoSuchMethodError:
com.amazonaws.http.AmazonHttpClient.disableStrictHostnameVerification()V
at
com.amazonaws.services.s3.AmazonS3Client.init(AmazonS3Client.java:444)
at
com.amazonaws.services.s3.AmazonS3Client.<init>(AmazonS3Client.java:391)
at
com.amazonaws.services.s3.AmazonS3Client.<init>(AmazonS3Client.java:371)
at
org.apache.hadoop.fs.s3a.S3AFileSystem.initialize(S3AFileSystem.java:235)
at
org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:2669)
at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:94)
at
org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:2703)
at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:2685)
at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:373)
at org.apache.hadoop.fs.Path.getFileSystem(Path.java:295)
at org.apache.hudi.common.fs.FSUtils.getFs(FSUtils.java:102)
at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:87)
at
org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:316)
at
org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anon$1.call(DataSourceStrategy.scala:242)
at
org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anon$1.call(DataSourceStrategy.scala:227)
at
org.spark_project.guava.cache.LocalCache$LocalManualCache$1.load(LocalCache.java:4792)
at
org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
at
org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
at
org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
at
org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
... 88 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]
