4
移動我有一個8小時的工作（火花2.0.0）寫入，使用標準方法將結果寫入出來實木複合地板：阿帕奇星火S3未能拼花文件從臨時文件夾
processed_images_df.write.format("parquet").save(s3_output_path)
它執行10000任務並將結果寫入_temporary文件夾，在最後一步（完成所有任務之後），它將複製_temporary文件夾中的parquet文件，但在複製大約2-3000個文件後失敗，首先我認爲這是是一個暫時的S3失敗，但我重新運行3次，並得到相同的錯誤）：
org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelationCommand.scala:149)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand$$anonfun$run$1.apply(InsertIntoHadoopFsRelationCommand.scala:115)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand$$anonfun$run$1.apply(InsertIntoHadoopFsRelationCommand.scala:115)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:115)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:60)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:58)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:86)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:86)
at org.apache.spark.sql.execution.datasources.DataSource.write(DataSource.scala:487)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:211)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:194)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:128)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:211)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.http.NoHttpResponseException: s3-bucket.s3.amazonaws.com:443 failed to respond
at org.apache.http.impl.conn.DefaultHttpResponseParser.parseHead(DefaultHttpResponseParser.java:143)
at org.apache.http.impl.conn.DefaultHttpResponseParser.parseHead(DefaultHttpResponseParser.java:57)
at org.apache.http.impl.io.AbstractMessageParser.parse(AbstractMessageParser.java:261)
at org.apache.http.impl.AbstractHttpClientConnection.receiveResponseHeader(AbstractHttpClientConnection.java:283)
at org.apache.http.impl.conn.DefaultClientConnection.receiveResponseHeader(DefaultClientConnection.java:259)
at org.apache.http.impl.conn.AbstractClientConnAdapter.receiveResponseHeader(AbstractClientConnAdapter.java:232)
at org.apache.http.protocol.HttpRequestExecutor.doReceiveResponse(HttpRequestExecutor.java:272)
at org.apache.http.protocol.HttpRequestExecutor.execute(HttpRequestExecutor.java:124)
at org.apache.http.impl.client.DefaultRequestDirector.tryExecute(DefaultRequestDirector.java:686)
at org.apache.http.impl.client.DefaultRequestDirector.execute(DefaultRequestDirector.java:488)
at org.apache.http.impl.client.AbstractHttpClient.doExecute(AbstractHttpClient.java:884)
at org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:82)
at org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:55)
at org.jets3t.service.impl.rest.httpclient.RestStorageService.performRequest(RestStorageService.java:326)
at org.jets3t.service.impl.rest.httpclient.RestStorageService.performRequest(RestStorageService.java:277)
at org.jets3t.service.impl.rest.httpclient.RestStorageService.performRestPut(RestStorageService.java:1143)
at org.jets3t.service.impl.rest.httpclient.RestStorageService.copyObjectImpl(RestStorageService.java:2117)
at org.jets3t.service.StorageService.copyObject(StorageService.java:898)
at org.jets3t.service.StorageService.copyObject(StorageService.java:943)
at org.apache.hadoop.fs.s3native.Jets3tNativeFileSystemStore.copy(Jets3tNativeFileSystemStore.java:320)
at sun.reflect.GeneratedMethodAccessor40.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:190)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:103)
at org.apache.hadoop.fs.s3native.$Proxy20.copy(Unknown Source)
at org.apache.hadoop.fs.s3native.NativeS3FileSystem.rename(NativeS3FileSystem.java:645)
at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.mergePaths(FileOutputCommitter.java:345)
at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.mergePaths(FileOutputCommitter.java:362)
at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.commitJob(FileOutputCommitter.java:310)
at org.apache.parquet.hadoop.ParquetOutputCommitter.commitJob(ParquetOutputCommitter.java:46)
at org.apache.spark.sql.execution.datasources.BaseWriterContainer.commitJob(WriterContainer.scala:222)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelationCommand.scala:144)
... 29 more
男人你是生命的救星... – will
我花了半天的時間尋找這條線以上！萬分感謝！ – FacePalm
查看更多信息：https：//docs.databricks.com/spark/latest/faq/append-slow-with-spark-2.0.0.html –