Я получал исключение BufferOverflowException при попытке выполнить запрос Spark SQL на CSV, хранящемся в S3.
Вот ссылка на CSV и схему данных.
Я на самом деле использую сжатый GZIP CSV в S3.
from pyspark.sql.types import *
schema = StructType([ StructField('is_male', BooleanType(), False), StructField('weight_pounds', DoubleType(), False), ])
df = spark.read.format("minioSelectCSV").schema(schema).load("s3://test/natalityy-1000", compression="gzip")
df.createOrReplaceTempView("natality")
query="SELECT is_male, AVG(weight_pounds) AS avg_weight FROM natality GROUP BY is_male"
df2 = spark.sql(query)
df2.show()
При выполнении приведенного выше фрагмента я получаю исключение BufferOverflowException. Хотя тот же фрагмент работал на CSV с 15 записями. Итак, я уверен, что запрос работает нормально.
Здесь полный журнал исключений:
Py4JJavaError: An error occurred while calling o7064.showString.
: java.nio.BufferOverflowException
at java.nio.HeapByteBuffer.put(HeapByteBuffer.java:189)
at com.amazonaws.services.s3.internal.eventstreaming.MessageDecoder.feed(MessageDecoder.java:38)
at com.amazonaws.services.s3.model.SelectObjectContentEventStream$SelectEventIterator.getNext(SelectObjectContentEventStream.java:207)
at com.amazonaws.services.s3.model.SelectObjectContentEventStream$LazyLoadedIterator.advanceIfNeeded(SelectObjectContentEventStream.java:315)
at com.amazonaws.services.s3.model.SelectObjectContentEventStream$LazyLoadedIterator.hasNext(SelectObjectContentEventStream.java:292)
at com.amazonaws.services.s3.model.SelectObjectContentEventStream$EventStreamEnumeration.getNext(SelectObjectContentEventStream.java:244)
at com.amazonaws.services.s3.model.SelectObjectContentEventStream$LazyLoadedIterator.advanceIfNeeded(SelectObjectContentEventStream.java:315)
at com.amazonaws.services.s3.model.SelectObjectContentEventStream$LazyLoadedIterator.hasNext(SelectObjectContentEventStream.java:292)
at com.amazonaws.services.s3.model.SelectObjectContentEventStream$EventStreamEnumeration.hasMoreElements(SelectObjectContentEventStream.java:273)
at java.io.SequenceInputStream.nextStream(SequenceInputStream.java:109)
at java.io.SequenceInputStream.read(SequenceInputStream.java:211)
at com.amazonaws.internal.SdkFilterInputStream.read(SdkFilterInputStream.java:90)
at com.amazonaws.internal.SdkFilterInputStream.read(SdkFilterInputStream.java:90)
at sun.nio.cs.StreamDecoder.readBytes(StreamDecoder.java:284)
at sun.nio.cs.StreamDecoder.implRead(StreamDecoder.java:326)
at sun.nio.cs.StreamDecoder.read(StreamDecoder.java:178)
at java.io.InputStreamReader.read(InputStreamReader.java:184)
at java.io.BufferedReader.fill(BufferedReader.java:161)
at java.io.BufferedReader.readLine(BufferedReader.java:324)
at java.io.BufferedReader.readLine(BufferedReader.java:389)
at io.minio.spark.select.SelectCSVRelation.getRows(SelectCSVRelation.scala:86)
at io.minio.spark.select.SelectCSVRelation.tokenRDD(SelectCSVRelation.scala:96)
at io.minio.spark.select.SelectCSVRelation.buildScan(SelectCSVRelation.scala:119)
at org.apache.spark.sql.execution.datasources.DataSourceStrategy$$anonfun$10.apply(DataSourceStrategy.scala:293)
at org.apache.spark.sql.execution.datasources.DataSourceStrategy$$anonfun$10.apply(DataSourceStrategy.scala:293)
at org.apache.spark.sql.execution.datasources.DataSourceStrategy$$anonfun$pruneFilterProject$1.apply(DataSourceStrategy.scala:338)
at org.apache.spark.sql.execution.datasources.DataSourceStrategy$$anonfun$pruneFilterProject$1.apply(DataSourceStrategy.scala:337)
at org.apache.spark.sql.execution.datasources.DataSourceStrategy.pruneFilterProjectRaw(DataSourceStrategy.scala:393)
at org.apache.spark.sql.execution.datasources.DataSourceStrategy.pruneFilterProject(DataSourceStrategy.scala:333)
at org.apache.spark.sql.execution.datasources.DataSourceStrategy.apply(DataSourceStrategy.scala:289)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$1.apply(QueryPlanner.scala:63)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$1.apply(QueryPlanner.scala:63)
at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:439)
at org.apache.spark.sql.catalyst.planning.QueryPlanner.plan(QueryPlanner.scala:93)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2$$anonfun$apply$2.apply(QueryPlanner.scala:78)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2$$anonfun$apply$2.apply(QueryPlanner.scala:75)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:157)
at scala.collection.AbstractIterator.foldLeft(Iterator.scala:1336)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2.apply(QueryPlanner.scala:75)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2.apply(QueryPlanner.scala:67)
at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
at org.apache.spark.sql.catalyst.planning.QueryPlanner.plan(QueryPlanner.scala:93)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2$$anonfun$apply$2.apply(QueryPlanner.scala:78)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2$$anonfun$apply$2.apply(QueryPlanner.scala:75)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:157)
at scala.collection.AbstractIterator.foldLeft(Iterator.scala:1336)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2.apply(QueryPlanner.scala:75)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2.apply(QueryPlanner.scala:67)
at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
at org.apache.spark.sql.catalyst.planning.QueryPlanner.plan(QueryPlanner.scala:93)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2$$anonfun$apply$2.apply(QueryPlanner.scala:78)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2$$anonfun$apply$2.apply(QueryPlanner.scala:75)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:157)
at scala.collection.AbstractIterator.foldLeft(Iterator.scala:1336)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2.apply(QueryPlanner.scala:75)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2.apply(QueryPlanner.scala:67)
at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
at org.apache.spark.sql.catalyst.planning.QueryPlanner.plan(QueryPlanner.scala:93)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2$$anonfun$apply$2.apply(QueryPlanner.scala:78)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2$$anonfun$apply$2.apply(QueryPlanner.scala:75)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:157)
at scala.collection.AbstractIterator.foldLeft(Iterator.scala:1336)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2.apply(QueryPlanner.scala:75)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2.apply(QueryPlanner.scala:67)
at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
at org.apache.spark.sql.catalyst.planning.QueryPlanner.plan(QueryPlanner.scala:93)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2$$anonfun$apply$2.apply(QueryPlanner.scala:78)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2$$anonfun$apply$2.apply(QueryPlanner.scala:75)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:157)
at scala.collection.AbstractIterator.foldLeft(Iterator.scala:1336)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2.apply(QueryPlanner.scala:75)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$2.apply(QueryPlanner.scala:67)
at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:434)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
at org.apache.spark.sql.catalyst.planning.QueryPlanner.plan(QueryPlanner.scala:93)
at org.apache.spark.sql.execution.QueryExecution.sparkPlan$lzycompute(QueryExecution.scala:72)
at org.apache.spark.sql.execution.QueryExecution.sparkPlan(QueryExecution.scala:68)
at org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:77)
at org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:77)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3248)
at org.apache.spark.sql.Dataset.head(Dataset.scala:2484)
at org.apache.spark.sql.Dataset.take(Dataset.scala:2698)
at org.apache.spark.sql.Dataset.showString(Dataset.scala:254)
at sun.reflect.GeneratedMethodAccessor79.invoke(Unknown Source)
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)