经过一些研究，我可以使用pyspark连接到redshift，并且可以将表数据读取到spark数据框中。现在，我正在尝试将该数据帧插入另一个具有相同结构的redshift表中。
这是我用来连接s3 / redshift并从spark_df变量中读取数据的代码。
from pyspark.sql import SQLContext
from pyspark import SparkConf, SparkContext
sc = SparkContext(conf=SparkConf().setAppName("MyApp").setMaster("local"))
hadoop_conf=sc._jsc.hadoopConfiguration()
hadoop_conf.set("fs.s3n.impl", "org.apache.hadoop.fs.s3native.NativeS3FileSystem")
hadoop_conf.set("fs.s3n.awsAccessKeyId", "XXXXXXXXXXXXXXXX")
hadoop_conf.set("fs.s3n.awsSecretAccessKey", "XXXXXXXXXXXXXXXXX")
sql_context = SQLContext(sc)
df = sql_context.read.json("events_20191101_000000000050_00.json")
print(df.count())
# Read data from a table
spark_df = sql_context.read \
.format("com.databricks.spark.redshift") \
.option("url", "jdbc:redshift://redshift-cluster-1.XXXXXXXXXXXXXXXXXXXXXXXXXXX") \
.option("dbtable", "public.events_20190310") \
.option("tempdir", "s3n://big-query-to-rs/rs_temp_data") \
.load()
print("loaded into spark df")
print("spdf ", spark_df)
print(spark_df.count())
print("----------------------------------------------------")
#print(spark_df.first())
#print(spark_df.second())
# Write back to a table
spark_df.write \
.format("com.databricks.spark.redshift") \
.option("url", "jdbc:redshift://redshift-cluster-1.XXXXXXXXXXXXXXXXXXXXXXXXXXX") \
.option("dbtable", "public.events_20000101") \
.option("tempdir", "s3n://big-query-to-rs/rs_temp_data") \
.mode("overwrite") \
.save()
使用spark_df将spark_df.write数据帧插入redshift时，会出现以下错误。
line 38, in <module>
.mode("overwrite") \
File "/home/ubuntu/spark-2.3.0-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/sql/readwriter.py", line 701, in save
File "/home/ubuntu/spark-2.3.0-bin-hadoop2.7/python/lib/py4j-0.10.6-src.zip/py4j/java_gateway.py", line 1160, in __call__
File "/home/ubuntu/spark-2.3.0-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/sql/utils.py", line 63, in deco
File "/home/ubuntu/spark-2.3.0-bin-hadoop2.7/python/lib/py4j-0.10.6-src.zip/py4j/protocol.py", line 320, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o44.save.
: java.io.IOException: s3n://big-query-to-rs : 400 : Bad Request
at org.apache.hadoop.fs.s3native.Jets3tNativeFileSystemStore.processException(Jets3tNativeFileSystemStore.java:453)
at org.apache.hadoop.fs.s3native.Jets3tNativeFileSystemStore.processException(Jets3tNativeFileSystemStore.java:427)
at org.apache.hadoop.fs.s3native.Jets3tNativeFileSystemStore.handleException(Jets3tNativeFileSystemStore.java:411)
at org.apache.hadoop.fs.s3native.Jets3tNativeFileSystemStore.retrieveMetadata(Jets3tNativeFileSystemStore.java:181)
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.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:191)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102)
at org.apache.hadoop.fs.s3native.$Proxy20.retrieveMetadata(Unknown Source)
at org.apache.hadoop.fs.s3native.NativeS3FileSystem.getFileStatus(NativeS3FileSystem.java:476)
at org.apache.hadoop.fs.FileSystem.exists(FileSystem.java:1426)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:92)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:104)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:122)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:654)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:654)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:654)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:273)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:267)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:225)
at com.databricks.spark.redshift.RedshiftWriter.unloadData(RedshiftWriter.scala:278)
at com.databricks.spark.redshift.RedshiftWriter.saveToRedshift(RedshiftWriter.scala:346)
at com.databricks.spark.redshift.DefaultSource.createRelation(DefaultSource.scala:106)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:46)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:86)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:654)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:654)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:654)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:273)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:267)
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 py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.jets3t.service.impl.rest.HttpException: 400 Bad Request
at org.jets3t.service.impl.rest.httpclient.RestStorageService.performRequest(RestStorageService.java:425)
at org.jets3t.service.impl.rest.httpclient.RestStorageService.performRequest(RestStorageService.java:279)
at org.jets3t.service.impl.rest.httpclient.RestStorageService.performRestHead(RestStorageService.java:1052)
at org.jets3t.service.impl.rest.httpclient.RestStorageService.getObjectImpl(RestStorageService.java:2264)
at org.jets3t.service.impl.rest.httpclient.RestStorageService.getObjectDetailsImpl(RestStorageService.java:2193)
at org.jets3t.service.StorageService.getObjectDetails(StorageService.java:1120)
at org.jets3t.service.StorageService.getObjectDetails(StorageService.java:575)
at org.apache.hadoop.fs.s3native.Jets3tNativeFileSystemStore.retrieveMetadata(Jets3tNativeFileSystemStore.java:174)
... 60 more
2019-12-19 06:26:31 INFO SparkContext:54 - Invoking stop() from shutdown hook
2019-12-19 06:26:31 INFO AbstractConnector:318 - Stopped Spark@145d5bb9{HTTP/1.1,[http/1.1]}{0.0.0.0:4041}
2019-12-19 06:26:31 INFO SparkUI:54 - Stopped Spark web UI at http://ip-172-30-1-193.ap-south-1.compute.internal:4041
我尝试了不同的模式（append，overwrite，“忽略”，“错误”），但没有一个将加载的数据插入spark数据帧并给出各自的错误。
任何潜在客户均受到高度赞赏。非常感谢。
仅供参考：spark_df大约有500万行数据（约10gb）。