如何解决套接字不是由该工厂在 Spark S3 连接中创建的
我正在尝试使用 spark 从 s3 读取数据,但它在不是由此工厂异常创建的 AWS 套接字上引发错误。
Spark 2.3.3 版和 HDP 2.6.5 版
错误详情:
java.lang.IllegalStateException: Socket not created by this factory
at org.apache.http.util.Asserts.check(Asserts.java:34)
at org.apache.http.conn.ssl.SSLSocketFactory.isSecure(SSLSocketFactory.java:435)
at org.apache.http.impl.conn.DefaultClientConnectionOperator.openConnection(DefaultClientConnectionOperator.java:186)
at org.apache.http.impl.conn.ManagedClientConnectionImpl.open(ManagedClientConnectionImpl.java:326)
at org.apache.http.impl.client.DefaultRequestDirector.tryConnect(DefaultRequestDirector.java:610)
at org.apache.http.impl.client.DefaultRequestDirector.execute(DefaultRequestDirector.java:445)
at org.apache.http.impl.client.AbstractHttpClient.doExecute(AbstractHttpClient.java:835)
at org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:83)
at org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:56)
at com.amazonaws.http.AmazonHttpClient.executeOneRequest(AmazonHttpClient.java:728)
at com.amazonaws.http.AmazonHttpClient.executeHelper(AmazonHttpClient.java:489)
at com.amazonaws.http.AmazonHttpClient.execute(AmazonHttpClient.java:310)
at com.amazonaws.services.s3.AmazonS3Client.invoke(AmazonS3Client.java:3785)
at com.amazonaws.services.s3.AmazonS3Client.headBucket(AmazonS3Client.java:1107)
at com.amazonaws.services.s3.AmazonS3Client.doesBucketExist(AmazonS3Client.java:1070)
at org.apache.hadoop.fs.s3a.S3AFileSystem.verifyBucketExists(S3AFileSystem.java:295)
at org.apache.hadoop.fs.s3a.S3AFileSystem.initialize(S3AFileSystem.java:257)
at org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:2796)
at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:99)
at org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:2830)
at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:2812)
at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:390)
at org.apache.hadoop.fs.Path.getFileSystem(Path.java:295)
at org.apache.spark.sql.execution.datasources.DataSource$.org$apache$spark$sql$execution$datasources$DataSource$$checkAndGlobPathIfNecessary(DataSource.scala:709)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$15.apply(DataSource.scala:390)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$15.apply(DataSource.scala:390)
at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241)
at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241)
at scala.collection.immutable.List.foreach(List.scala:381)
at scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:241)
at scala.collection.immutable.List.flatMap(List.scala:344)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:389)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:239)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:227)
at org.apache.spark.sql.DataFrameReader.parquet(DataFrameReader.scala:622)
at org.apache.spark.sql.DataFrameReader.parquet(DataFrameReader.scala:606)
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。