我正在使用 Databrics 来运行我的 Spark 应用程序，并且我正在尝试使用它elasticsearch-hadoop来建立与 Elasticsearch 的连接。
在我的 Databricks VPC 和我的 Elasticsearch VPC 之间配置对等连接后，我终于可以让两者相互交谈。它看起来像这样：
%sh
nc -vz [endpoint_to_elasticsearch].es.amazonaws.com 443
> [endpoint_to_elasticsearch].es.amazonaws.com 443 (https) open
这向我表明它们是相连的，太棒了！
但最终的测试还是失败了。这是我尝试运行的内容：
%scala
val df = spark.sql("SELECT * FROM test_data")
df.write
.format("org.elasticsearch.spark.sql")
.option("es.nodes.wan.only","true")
.option("es.port","443")
.option("es.net.ssl","true")
.option("es.nodes", "[endpoint_to_elasticsearch]")
.mode("Overwrite")
.save("test_index/test_type")
df 就是这样：
df:pyspark.sql.dataframe.DataFrame = [field1: string]
+------+
|field1|
+------+
| DS&S|
+------+
但我得到的错误是有害的：
org.elasticsearch.hadoop.EsHadoopIllegalArgumentException: Cannot detect ES version - typically this happens if the network/Elasticsearch cluster is not accessible or when targeting a WAN/Cloud instance without the proper setting 'es.nodes.wan.only'.
at org.elasticsearch.hadoop.rest.InitializationUtils.discoverClusterInfo(InitializationUtils.java:340)
at org.elasticsearch.spark.sql.ElasticsearchRelation.cfg$lzycompute(DefaultSource.scala:225)
at org.elasticsearch.spark.sql.ElasticsearchRelation.cfg(DefaultSource.scala:223)
at org.elasticsearch.spark.sql.ElasticsearchRelation.insert(DefaultSource.scala:603)
at org.elasticsearch.spark.sql.DefaultSource.createRelation(DefaultSource.scala:108)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:45)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:86)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:146)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:134)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$5.apply(SparkPlan.scala:187)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:183)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:134)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:115)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:115)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:710)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:710)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withCustomExecutionEnv$1.apply(SQLExecution.scala:111)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:240)
at org.apache.spark.sql.execution.SQLExecution$.withCustomExecutionEnv(SQLExecution.scala:97)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:170)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:710)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:306)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:292)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:235)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$$iw$$iw$$iw$$iw$$iw$$iw.<init>(command-131822574348522:9)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$$iw$$iw$$iw$$iw$$iw.<init>(command-131822574348522:55)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$$iw$$iw$$iw$$iw.<init>(command-131822574348522:57)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$$iw$$iw$$iw.<init>(command-131822574348522:59)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$$iw$$iw.<init>(command-131822574348522:61)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$$iw.<init>(command-131822574348522:63)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read.<init>(command-131822574348522:65)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$.<init>(command-131822574348522:69)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$.<clinit>(command-131822574348522)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$eval$.$print$lzycompute(<notebook>:7)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$eval$.$print(<notebook>:6)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$eval.$print(<notebook>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at scala.tools.nsc.interpreter.IMain$ReadEvalPrint.call(IMain.scala:793)
at scala.tools.nsc.interpreter.IMain$Request.loadAndRun(IMain.scala:1054)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:645)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:644)
at scala.reflect.internal.util.ScalaClassLoader$class.asContext(ScalaClassLoader.scala:31)
at scala.reflect.internal.util.AbstractFileClassLoader.asContext(AbstractFileClassLoader.scala:19)
at scala.tools.nsc.interpreter.IMain$WrappedRequest.loadAndRunReq(IMain.scala:644)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:576)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:572)
at com.databricks.backend.daemon.driver.DriverILoop.execute(DriverILoop.scala:215)
at com.databricks.backend.daemon.driver.ScalaDriverLocal$$anonfun$repl$1.apply$mcV$sp(ScalaDriverLocal.scala:197)
at com.databricks.backend.daemon.driver.ScalaDriverLocal$$anonfun$repl$1.apply(ScalaDriverLocal.scala:197)
at com.databricks.backend.daemon.driver.ScalaDriverLocal$$anonfun$repl$1.apply(ScalaDriverLocal.scala:197)
at com.databricks.backend.daemon.driver.DriverLocal$TrapExitInternal$.trapExit(DriverLocal.scala:700)
at com.databricks.backend.daemon.driver.DriverLocal$TrapExit$.apply(DriverLocal.scala:653)
at com.databricks.backend.daemon.driver.ScalaDriverLocal.repl(ScalaDriverLocal.scala:197)
at com.databricks.backend.daemon.driver.DriverLocal$$anonfun$execute$9.apply(DriverLocal.scala:386)
at com.databricks.backend.daemon.driver.DriverLocal$$anonfun$execute$9.apply(DriverLocal.scala:363)
at com.databricks.logging.UsageLogging$$anonfun$withAttributionContext$1.apply(UsageLogging.scala:235)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58)
at com.databricks.logging.UsageLogging$class.withAttributionContext(UsageLogging.scala:230)
at com.databricks.backend.daemon.driver.DriverLocal.withAttributionContext(DriverLocal.scala:49)
at com.databricks.logging.UsageLogging$class.withAttributionTags(UsageLogging.scala:272)
at com.databricks.backend.daemon.driver.DriverLocal.withAttributionTags(DriverLocal.scala:49)
at com.databricks.backend.daemon.driver.DriverLocal.execute(DriverLocal.scala:363)
at com.databricks.backend.daemon.driver.DriverWrapper$$anonfun$tryExecutingCommand$2.apply(DriverWrapper.scala:644)
at com.databricks.backend.daemon.driver.DriverWrapper$$anonfun$tryExecutingCommand$2.apply(DriverWrapper.scala:644)
at scala.util.Try$.apply(Try.scala:192)
at com.databricks.backend.daemon.driver.DriverWrapper.tryExecutingCommand(DriverWrapper.scala:639)
at com.databricks.backend.daemon.driver.DriverWrapper.getCommandOutputAndError(DriverWrapper.scala:485)
at com.databricks.backend.daemon.driver.DriverWrapper.executeCommand(DriverWrapper.scala:597)
at com.databricks.backend.daemon.driver.DriverWrapper.runInnerLoop(DriverWrapper.scala:390)
at com.databricks.backend.daemon.driver.DriverWrapper.runInner(DriverWrapper.scala:337)
at com.databricks.backend.daemon.driver.DriverWrapper.run(DriverWrapper.scala:219)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.elasticsearch.hadoop.rest.EsHadoopInvalidRequest: null
null
at org.elasticsearch.hadoop.rest.RestClient.checkResponse(RestClient.java:477)
at org.elasticsearch.hadoop.rest.RestClient.execute(RestClient.java:434)
at org.elasticsearch.hadoop.rest.RestClient.execute(RestClient.java:428)
at org.elasticsearch.hadoop.rest.RestClient.execute(RestClient.java:388)
at org.elasticsearch.hadoop.rest.RestClient.execute(RestClient.java:392)
at org.elasticsearch.hadoop.rest.RestClient.get(RestClient.java:168)
at org.elasticsearch.hadoop.rest.RestClient.mainInfo(RestClient.java:745)
at org.elasticsearch.hadoop.rest.InitializationUtils.discoverClusterInfo(InitializationUtils.java:330)
at org.elasticsearch.spark.sql.ElasticsearchRelation.cfg$lzycompute(DefaultSource.scala:225)
at org.elasticsearch.spark.sql.ElasticsearchRelation.cfg(DefaultSource.scala:223)
at org.elasticsearch.spark.sql.ElasticsearchRelation.insert(DefaultSource.scala:603)
at org.elasticsearch.spark.sql.DefaultSource.createRelation(DefaultSource.scala:108)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:45)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:86)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:146)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:134)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$5.apply(SparkPlan.scala:187)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:183)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:134)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:115)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:115)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:710)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:710)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withCustomExecutionEnv$1.apply(SQLExecution.scala:111)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:240)
at org.apache.spark.sql.execution.SQLExecution$.withCustomExecutionEnv(SQLExecution.scala:97)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:170)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:710)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:306)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:292)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:235)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$$iw$$iw$$iw$$iw$$iw$$iw.<init>(command-131822574348522:9)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$$iw$$iw$$iw$$iw$$iw.<init>(command-131822574348522:55)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$$iw$$iw$$iw$$iw.<init>(command-131822574348522:57)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$$iw$$iw$$iw.<init>(command-131822574348522:59)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$$iw$$iw.<init>(command-131822574348522:61)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$$iw.<init>(command-131822574348522:63)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read.<init>(command-131822574348522:65)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$.<init>(command-131822574348522:69)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$read$.<clinit>(command-131822574348522)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$eval$.$print$lzycompute(<notebook>:7)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$eval$.$print(<notebook>:6)
at linef15e9c33e51e4c34a4649c4ec822a09d31.$eval.$print(<notebook>)
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 scala.tools.nsc.interpreter.IMain$ReadEvalPrint.call(IMain.scala:793)
at scala.tools.nsc.interpreter.IMain$Request.loadAndRun(IMain.scala:1054)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:645)
at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:644)
at scala.reflect.internal.util.ScalaClassLoader$class.asContext(ScalaClassLoader.scala:31)
at scala.reflect.internal.util.AbstractFileClassLoader.asContext(AbstractFileClassLoader.scala:19)
at scala.tools.nsc.interpreter.IMain$WrappedRequest.loadAndRunReq(IMain.scala:644)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:576)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:572)
at com.databricks.backend.daemon.driver.DriverILoop.execute(DriverILoop.scala:215)
at com.databricks.backend.daemon.driver.ScalaDriverLocal$$anonfun$repl$1.apply$mcV$sp(ScalaDriverLocal.scala:197)
at com.databricks.backend.daemon.driver.ScalaDriverLocal$$anonfun$repl$1.apply(ScalaDriverLocal.scala:197)
at com.databricks.backend.daemon.driver.ScalaDriverLocal$$anonfun$repl$1.apply(ScalaDriverLocal.scala:197)
at com.databricks.backend.daemon.driver.DriverLocal$TrapExitInternal$.trapExit(DriverLocal.scala:700)
at com.databricks.backend.daemon.driver.DriverLocal$TrapExit$.apply(DriverLocal.scala:653)
at com.databricks.backend.daemon.driver.ScalaDriverLocal.repl(ScalaDriverLocal.scala:197)
at com.databricks.backend.daemon.driver.DriverLocal$$anonfun$execute$9.apply(DriverLocal.scala:386)
at com.databricks.backend.daemon.driver.DriverLocal$$anonfun$execute$9.apply(DriverLocal.scala:363)
at com.databricks.logging.UsageLogging$$anonfun$withAttributionContext$1.apply(UsageLogging.scala:235)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58)
at com.databricks.logging.UsageLogging$class.withAttributionContext(UsageLogging.scala:230)
at com.databricks.backend.daemon.driver.DriverLocal.withAttributionContext(DriverLocal.scala:49)
at com.databricks.logging.UsageLogging$class.withAttributionTags(UsageLogging.scala:272)
at com.databricks.backend.daemon.driver.DriverLocal.withAttributionTags(DriverLocal.scala:49)
at com.databricks.backend.daemon.driver.DriverLocal.execute(DriverLocal.scala:363)
at com.databricks.backend.daemon.driver.DriverWrapper$$anonfun$tryExecutingCommand$2.apply(DriverWrapper.scala:644)
at com.databricks.backend.daemon.driver.DriverWrapper$$anonfun$tryExecutingCommand$2.apply(DriverWrapper.scala:644)
at scala.util.Try$.apply(Try.scala:192)
at com.databricks.backend.daemon.driver.DriverWrapper.tryExecutingCommand(DriverWrapper.scala:639)
at com.databricks.backend.daemon.driver.DriverWrapper.getCommandOutputAndError(DriverWrapper.scala:485)
at com.databricks.backend.daemon.driver.DriverWrapper.executeCommand(DriverWrapper.scala:597)
at com.databricks.backend.daemon.driver.DriverWrapper.runInnerLoop(DriverWrapper.scala:390)
at com.databricks.backend.daemon.driver.DriverWrapper.runInner(DriverWrapper.scala:337)
at com.databricks.backend.daemon.driver.DriverWrapper.run(DriverWrapper.scala:219)
at java.lang.Thread.run(Thread.java:748)
起初我认为这与版本错误有关，但我正在努力寻找不匹配的地方。
我在跑：
AWS 弹性搜索 - 7.1
Databricks - 6.1（包括 Apache Spark 2.4.4、Scala 2.11）
elasticsearch-hadoop - elasticsearch_spark_20_2_11_7_5_2.jar
我错过了什么？