Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- File "script_2019-02-06-02-32-43.py", line 197, in <module>
- .parquet("s3://pinfare-glue/cleanedFlights")
- File "/mnt/yarn/usercache/root/appcache/application_1549418793443_0001/container_1549418793443_0001_01_000001/pyspark.zip/pyspark/sql/readwriter.py", line 691, in parquet
- File "/mnt/yarn/usercache/root/appcache/application_1549418793443_0001/container_1549418793443_0001_01_000001/py4j-0.10.4-src.zip/py4j/java_gateway.py", line 1133, in __call__
- File "/mnt/yarn/usercache/root/appcache/application_1549418793443_0001/container_1549418793443_0001_01_000001/pyspark.zip/pyspark/sql/utils.py", line 63, in deco
- File "/mnt/yarn/usercache/root/appcache/application_1549418793443_0001/container_1549418793443_0001_01_000001/py4j-0.10.4-src.zip/py4j/protocol.py", line 319, in get_return_value
- py4j.protocol.Py4JJavaError: An error occurred while calling o246.parquet.
- : org.apache.spark.SparkException: Job aborted.
- at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply$mcV$sp(FileFormatWriter.scala:213)
- at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:166)
- at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:166)
- at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65)
- at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:166)
- at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:145)
- at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
- at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
- at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
- at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
- at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
- at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
- at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:92)
- at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:92)
- at org.apache.spark.sql.execution.datasources.DataSource.writeInFileFormat(DataSource.scala:435)
- at org.apache.spark.sql.execution.datasources.DataSource.write(DataSource.scala:471)
- at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:50)
- at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
- at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
- at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
- at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
- at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
- at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
- at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:92)
- at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:92)
- at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:609)
- at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:233)
- at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:217)
- at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:508)
- 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:280)
- 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.apache.spark.sql.catalyst.errors.package$TreeNodeException: execute, tree:
- Exchange hashpartitioning(countryName#24, querydatetime#213, 200)
- +- *Project [master_key#588, master_querydatetime#589, Id#180, QueryTaskId#181, QueryOriginPlace#182, queryoutbounddate#334, queryinbounddate#375, QueryCabinClass#185, QueryCurrency#186, Agent#187, QuoteAgeInMinutes#188, Price#189, OutboundLegId#190, InboundLegId#191, outdeparture#416, outarrival#457, OutDuration#194, OutJourneyMode#195, OutStops#196, OutCarriers#197, OutOperatingCarriers#198, NumberOutStops#199, NumberOutCarriers#200, NumberOutOperatingCarriers#201, ... 33 more fields]
- +- BatchEvalPython [getInterval(cast(date_format(outdeparture#416, H, Some(Zulu)) as int), 0, 24, 4), getInterval(cast(date_format(indeparture#498, H, Some(Zulu)) as int), 0, 24, 4)], [master_key#588, master_querydatetime#589, Id#180, QueryTaskId#181, QueryOriginPlace#182, queryoutbounddate#334, queryinbounddate#375, QueryCabinClass#185, QueryCurrency#186, Agent#187, QuoteAgeInMinutes#188, Price#189, OutboundLegId#190, InboundLegId#191, outdeparture#416, outarrival#457, OutDuration#194, OutJourneyMode#195, OutStops#196, OutCarriers#197, OutOperatingCarriers#198, NumberOutStops#199, NumberOutCarriers#200, NumberOutOperatingCarriers#201, ... 21 more fields]
- +- *Sort [key#250 ASC NULLS FIRST, querydatetime#101 ASC NULLS FIRST], true, 0
- +- Exchange rangepartitioning(key#250 ASC NULLS FIRST, querydatetime#101 ASC NULLS FIRST, 200)
- +- *Project [key#250 AS master_key#588, querydatetime#101 AS master_querydatetime#589, Id#180, QueryTaskId#181, QueryOriginPlace#182, queryoutbounddate#334, queryinbounddate#375, QueryCabinClass#185, QueryCurrency#186, Agent#187, QuoteAgeInMinutes#188, Price#189, OutboundLegId#190, InboundLegId#191, outdeparture#416, outarrival#457, OutDuration#194, OutJourneyMode#195, OutStops#196, OutCarriers#197, OutOperatingCarriers#198, NumberOutStops#199, NumberOutCarriers#200, NumberOutOperatingCarriers#201, ... 19 more fields]
- +- *BroadcastHashJoin [key#250, querydatetime#101], [key#590, querydatetime#213], LeftOuter, BuildRight
- :- *Project [key#250, querydatetime#101]
- : +- BroadcastNestedLoopJoin BuildRight, Cross
- : :- Generate explode(pythonUDF0#1633), false, false, [querydatetime#101]
- : : +- BatchEvalPython [generate_date_series(start#94, stop#95)], [start#94, stop#95, pythonUDF0#1633]
- : : +- Scan ExistingRDD[start#94,stop#95]
- : +- BroadcastExchange IdentityBroadcastMode
- : +- *HashAggregate(keys=[key#250], functions=[], output=[key#250])
- : +- *HashAggregate(keys=[key#250], functions=[], output=[key#250])
- : +- *Sample 0.0, 0.001, false, 7736333241016522154
- : +- *GlobalLimit 5000000
- : +- Exchange SinglePartition
- : +- *LocalLimit 5000000
- : +- *Project [concat(outboundlegid#190, -, inboundlegid#191, -, agent#187) AS key#250]
- : +- *SortMergeJoin [querydestinationplace#212], [cast(airportId#38 as int)], Inner
- : :- *Sort [querydestinationplace#212 ASC NULLS FIRST], false, 0
- : : +- Exchange hashpartitioning(querydestinationplace#212, 200)
- : : +- *Project [Agent#187, OutboundLegId#190, InboundLegId#191, querydestinationplace#212]
- : : +- *SortMergeJoin [agent#187], [id#89], Inner
- : : :- *Sort [agent#187 ASC NULLS FIRST], false, 0
- : : : +- Exchange hashpartitioning(agent#187, 200)
- : : : +- *Project [Agent#187, OutboundLegId#190, InboundLegId#191, querydestinationplace#212]
- : : : +- *Filter (isnotnull(agent#187) && isnotnull(querydestinationplace#212))
- : : : +- Scan ExistingRDD[Id#180,QueryTaskId#181,QueryOriginPlace#182,QueryOutboundDate#183,QueryInboundDate#184,QueryCabinClass#185,QueryCurrency#186,Agent#187,QuoteAgeInMinutes#188,Price#189,OutboundLegId#190,InboundLegId#191,OutDeparture#192,OutArrival#193,OutDuration#194,OutJourneyMode#195,OutStops#196,OutCarriers#197,OutOperatingCarriers#198,NumberOutStops#199,NumberOutCarriers#200,NumberOutOperatingCarriers#201,InDeparture#202,InArrival#203,... 10 more fields]
- : : +- *Sort [id#89 ASC NULLS FIRST], false, 0
- : : +- Exchange hashpartitioning(id#89, 200)
- : : +- *Project [cast(id#67L as string) AS id#89]
- : : +- *Filter (isnotnull(id#67L) && isnotnull(cast(id#67L as string)))
- : : +- Scan ExistingRDD[id#67L,name#68,imageurl#69,status#70,optimisedformobile#71,type#72,bookingnumber#73,createdat#74,updatedat#75]
- : +- *Sort [cast(airportId#38 as int) ASC NULLS FIRST], false, 0
- : +- Exchange hashpartitioning(cast(airportId#38 as int), 200)
- : +- *Project [cast(airportId#18L as string) AS airportId#38]
- : +- *Filter (isnotnull(airportId#18L) && isnotnull(cast(airportId#18L as string)))
- : +- Scan ExistingRDD[airportId#18L,cityId#19L,countryId#20L,airportCode#21,airportName#22,cityName#23,countryName#24]
- +- BroadcastExchange HashedRelationBroadcastMode(List(input[34, string, true], input[33, date, true]))
- +- *Project [Id#180, QueryTaskId#181, QueryOriginPlace#182, cast(QueryOutboundDate#183 as date) AS queryoutbounddate#334, cast(QueryInboundDate#184 as date) AS queryinbounddate#375, QueryCabinClass#185, QueryCurrency#186, Agent#187, QuoteAgeInMinutes#188, Price#189, OutboundLegId#190, InboundLegId#191, cast(unix_timestamp(OutDeparture#192, yyyy-MM-dd'T'HH:mm:ss, Some(Zulu)) as timestamp) AS outdeparture#416, cast(unix_timestamp(OutArrival#193, yyyy-MM-dd'T'HH:mm:ss, Some(Zulu)) as timestamp) AS outarrival#457, OutDuration#194, OutJourneyMode#195, OutStops#196, OutCarriers#197, OutOperatingCarriers#198, NumberOutStops#199, NumberOutCarriers#200, NumberOutOperatingCarriers#201, cast(unix_timestamp(InDeparture#202, yyyy-MM-dd'T'HH:mm:ss, Some(Zulu)) as timestamp) AS indeparture#498, cast(unix_timestamp(InArrival#203, yyyy-MM-dd'T'HH:mm:ss, Some(Zulu)) as timestamp) AS inarrival#539, ... 15 more fields]
- +- *Sample 0.0, 0.001, false, 7736333241016522154
- +- *GlobalLimit 5000000
- +- Exchange SinglePartition
- +- *LocalLimit 5000000
- +- *Project [Id#180, QueryTaskId#181, QueryOriginPlace#182, QueryOutboundDate#183, QueryInboundDate#184, QueryCabinClass#185, QueryCurrency#186, Agent#187, QuoteAgeInMinutes#188, Price#189, OutboundLegId#190, InboundLegId#191, OutDeparture#192, OutArrival#193, OutDuration#194, OutJourneyMode#195, OutStops#196, OutCarriers#197, OutOperatingCarriers#198, NumberOutStops#199, NumberOutCarriers#200, NumberOutOperatingCarriers#201, InDeparture#202, InArrival#203, ... 15 more fields]
- +- *SortMergeJoin [querydestinationplace#212], [cast(airportId#38 as int)], Inner
- :- *Sort [querydestinationplace#212 ASC NULLS FIRST], false, 0
- : +- Exchange hashpartitioning(querydestinationplace#212, 200)
- : +- *Project [Id#180, QueryTaskId#181, QueryOriginPlace#182, QueryOutboundDate#183, QueryInboundDate#184, QueryCabinClass#185, QueryCurrency#186, Agent#187, QuoteAgeInMinutes#188, Price#189, OutboundLegId#190, InboundLegId#191, OutDeparture#192, OutArrival#193, OutDuration#194, OutJourneyMode#195, OutStops#196, OutCarriers#197, OutOperatingCarriers#198, NumberOutStops#199, NumberOutCarriers#200, NumberOutOperatingCarriers#201, InDeparture#202, InArrival#203, ... 11 more fields]
- : +- *SortMergeJoin [Agent#187], [id#89], Inner
- : :- *Sort [Agent#187 ASC NULLS FIRST], false, 0
- : : +- Exchange hashpartitioning(Agent#187, 200)
- : : +- *Filter (isnotnull(Agent#187) && isnotnull(querydestinationplace#212))
- : : +- Scan ExistingRDD[Id#180,QueryTaskId#181,QueryOriginPlace#182,QueryOutboundDate#183,QueryInboundDate#184,QueryCabinClass#185,QueryCurrency#186,Agent#187,QuoteAgeInMinutes#188,Price#189,OutboundLegId#190,InboundLegId#191,OutDeparture#192,OutArrival#193,OutDuration#194,OutJourneyMode#195,OutStops#196,OutCarriers#197,OutOperatingCarriers#198,NumberOutStops#199,NumberOutCarriers#200,NumberOutOperatingCarriers#201,InDeparture#202,InArrival#203,... 10 more fields]
- : +- *Sort [id#89 ASC NULLS FIRST], false, 0
- : +- Exchange hashpartitioning(id#89, 200)
- : +- *Project [cast(id#67L as string) AS id#89, name#68]
- : +- *Filter (isnotnull(id#67L) && isnotnull(cast(id#67L as string)))
- : +- Scan ExistingRDD[id#67L,name#68,imageurl#69,status#70,optimisedformobile#71,type#72,bookingnumber#73,createdat#74,updatedat#75]
- +- *Sort [cast(airportId#38 as int) ASC NULLS FIRST], false, 0
- +- Exchange hashpartitioning(cast(airportId#38 as int), 200)
- +- *Project [cast(airportId#18L as string) AS airportId#38, countryName#24, cityName#23, airportName#22]
- +- *Filter (isnotnull(airportId#18L) && isnotnull(cast(airportId#18L as string)))
- +- Scan ExistingRDD[airportId#18L,cityId#19L,countryId#20L,airportCode#21,airportName#22,cityName#23,countryName#24]
- at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:56)
- at org.apache.spark.sql.execution.exchange.ShuffleExchange.doExecute(ShuffleExchange.scala:115)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
- at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
- at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
- at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
- at org.apache.spark.sql.execution.SortExec.doExecute(SortExec.scala:101)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
- at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
- at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
- at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
- at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply$mcV$sp(FileFormatWriter.scala:183)
- ... 45 more
- Caused by: org.apache.spark.sql.catalyst.errors.package$TreeNodeException: execute, tree:
- Exchange rangepartitioning(key#250 ASC NULLS FIRST, querydatetime#101 ASC NULLS FIRST, 200)
- +- *Project [key#250 AS master_key#588, querydatetime#101 AS master_querydatetime#589, Id#180, QueryTaskId#181, QueryOriginPlace#182, queryoutbounddate#334, queryinbounddate#375, QueryCabinClass#185, QueryCurrency#186, Agent#187, QuoteAgeInMinutes#188, Price#189, OutboundLegId#190, InboundLegId#191, outdeparture#416, outarrival#457, OutDuration#194, OutJourneyMode#195, OutStops#196, OutCarriers#197, OutOperatingCarriers#198, NumberOutStops#199, NumberOutCarriers#200, NumberOutOperatingCarriers#201, ... 19 more fields]
- +- *BroadcastHashJoin [key#250, querydatetime#101], [key#590, querydatetime#213], LeftOuter, BuildRight
- :- *Project [key#250, querydatetime#101]
- : +- BroadcastNestedLoopJoin BuildRight, Cross
- : :- Generate explode(pythonUDF0#1633), false, false, [querydatetime#101]
- : : +- BatchEvalPython [generate_date_series(start#94, stop#95)], [start#94, stop#95, pythonUDF0#1633]
- : : +- Scan ExistingRDD[start#94,stop#95]
- : +- BroadcastExchange IdentityBroadcastMode
- : +- *HashAggregate(keys=[key#250], functions=[], output=[key#250])
- : +- *HashAggregate(keys=[key#250], functions=[], output=[key#250])
- : +- *Sample 0.0, 0.001, false, 7736333241016522154
- : +- *GlobalLimit 5000000
- : +- Exchange SinglePartition
- : +- *LocalLimit 5000000
- : +- *Project [concat(outboundlegid#190, -, inboundlegid#191, -, agent#187) AS key#250]
- : +- *SortMergeJoin [querydestinationplace#212], [cast(airportId#38 as int)], Inner
- : :- *Sort [querydestinationplace#212 ASC NULLS FIRST], false, 0
- : : +- Exchange hashpartitioning(querydestinationplace#212, 200)
- : : +- *Project [Agent#187, OutboundLegId#190, InboundLegId#191, querydestinationplace#212]
- : : +- *SortMergeJoin [agent#187], [id#89], Inner
- : : :- *Sort [agent#187 ASC NULLS FIRST], false, 0
- : : : +- Exchange hashpartitioning(agent#187, 200)
- : : : +- *Project [Agent#187, OutboundLegId#190, InboundLegId#191, querydestinationplace#212]
- : : : +- *Filter (isnotnull(agent#187) && isnotnull(querydestinationplace#212))
- : : : +- Scan ExistingRDD[Id#180,QueryTaskId#181,QueryOriginPlace#182,QueryOutboundDate#183,QueryInboundDate#184,QueryCabinClass#185,QueryCurrency#186,Agent#187,QuoteAgeInMinutes#188,Price#189,OutboundLegId#190,InboundLegId#191,OutDeparture#192,OutArrival#193,OutDuration#194,OutJourneyMode#195,OutStops#196,OutCarriers#197,OutOperatingCarriers#198,NumberOutStops#199,NumberOutCarriers#200,NumberOutOperatingCarriers#201,InDeparture#202,InArrival#203,... 10 more fields]
- : : +- *Sort [id#89 ASC NULLS FIRST], false, 0
- : : +- Exchange hashpartitioning(id#89, 200)
- : : +- *Project [cast(id#67L as string) AS id#89]
- : : +- *Filter (isnotnull(id#67L) && isnotnull(cast(id#67L as string)))
- : : +- Scan ExistingRDD[id#67L,name#68,imageurl#69,status#70,optimisedformobile#71,type#72,bookingnumber#73,createdat#74,updatedat#75]
- : +- *Sort [cast(airportId#38 as int) ASC NULLS FIRST], false, 0
- : +- Exchange hashpartitioning(cast(airportId#38 as int), 200)
- : +- *Project [cast(airportId#18L as string) AS airportId#38]
- : +- *Filter (isnotnull(airportId#18L) && isnotnull(cast(airportId#18L as string)))
- : +- Scan ExistingRDD[airportId#18L,cityId#19L,countryId#20L,airportCode#21,airportName#22,cityName#23,countryName#24]
- +- BroadcastExchange HashedRelationBroadcastMode(List(input[34, string, true], input[33, date, true]))
- +- *Project [Id#180, QueryTaskId#181, QueryOriginPlace#182, cast(QueryOutboundDate#183 as date) AS queryoutbounddate#334, cast(QueryInboundDate#184 as date) AS queryinbounddate#375, QueryCabinClass#185, QueryCurrency#186, Agent#187, QuoteAgeInMinutes#188, Price#189, OutboundLegId#190, InboundLegId#191, cast(unix_timestamp(OutDeparture#192, yyyy-MM-dd'T'HH:mm:ss, Some(Zulu)) as timestamp) AS outdeparture#416, cast(unix_timestamp(OutArrival#193, yyyy-MM-dd'T'HH:mm:ss, Some(Zulu)) as timestamp) AS outarrival#457, OutDuration#194, OutJourneyMode#195, OutStops#196, OutCarriers#197, OutOperatingCarriers#198, NumberOutStops#199, NumberOutCarriers#200, NumberOutOperatingCarriers#201, cast(unix_timestamp(InDeparture#202, yyyy-MM-dd'T'HH:mm:ss, Some(Zulu)) as timestamp) AS indeparture#498, cast(unix_timestamp(InArrival#203, yyyy-MM-dd'T'HH:mm:ss, Some(Zulu)) as timestamp) AS inarrival#539, ... 15 more fields]
- +- *Sample 0.0, 0.001, false, 7736333241016522154
- +- *GlobalLimit 5000000
- +- Exchange SinglePartition
- +- *LocalLimit 5000000
- +- *Project [Id#180, QueryTaskId#181, QueryOriginPlace#182, QueryOutboundDate#183, QueryInboundDate#184, QueryCabinClass#185, QueryCurrency#186, Agent#187, QuoteAgeInMinutes#188, Price#189, OutboundLegId#190, InboundLegId#191, OutDeparture#192, OutArrival#193, OutDuration#194, OutJourneyMode#195, OutStops#196, OutCarriers#197, OutOperatingCarriers#198, NumberOutStops#199, NumberOutCarriers#200, NumberOutOperatingCarriers#201, InDeparture#202, InArrival#203, ... 15 more fields]
- +- *SortMergeJoin [querydestinationplace#212], [cast(airportId#38 as int)], Inner
- :- *Sort [querydestinationplace#212 ASC NULLS FIRST], false, 0
- : +- Exchange hashpartitioning(querydestinationplace#212, 200)
- : +- *Project [Id#180, QueryTaskId#181, QueryOriginPlace#182, QueryOutboundDate#183, QueryInboundDate#184, QueryCabinClass#185, QueryCurrency#186, Agent#187, QuoteAgeInMinutes#188, Price#189, OutboundLegId#190, InboundLegId#191, OutDeparture#192, OutArrival#193, OutDuration#194, OutJourneyMode#195, OutStops#196, OutCarriers#197, OutOperatingCarriers#198, NumberOutStops#199, NumberOutCarriers#200, NumberOutOperatingCarriers#201, InDeparture#202, InArrival#203, ... 11 more fields]
- : +- *SortMergeJoin [Agent#187], [id#89], Inner
- : :- *Sort [Agent#187 ASC NULLS FIRST], false, 0
- : : +- Exchange hashpartitioning(Agent#187, 200)
- : : +- *Filter (isnotnull(Agent#187) && isnotnull(querydestinationplace#212))
- : : +- Scan ExistingRDD[Id#180,QueryTaskId#181,QueryOriginPlace#182,QueryOutboundDate#183,QueryInboundDate#184,QueryCabinClass#185,QueryCurrency#186,Agent#187,QuoteAgeInMinutes#188,Price#189,OutboundLegId#190,InboundLegId#191,OutDeparture#192,OutArrival#193,OutDuration#194,OutJourneyMode#195,OutStops#196,OutCarriers#197,OutOperatingCarriers#198,NumberOutStops#199,NumberOutCarriers#200,NumberOutOperatingCarriers#201,InDeparture#202,InArrival#203,... 10 more fields]
- : +- *Sort [id#89 ASC NULLS FIRST], false, 0
- : +- Exchange hashpartitioning(id#89, 200)
- : +- *Project [cast(id#67L as string) AS id#89, name#68]
- : +- *Filter (isnotnull(id#67L) && isnotnull(cast(id#67L as string)))
- : +- Scan ExistingRDD[id#67L,name#68,imageurl#69,status#70,optimisedformobile#71,type#72,bookingnumber#73,createdat#74,updatedat#75]
- +- *Sort [cast(airportId#38 as int) ASC NULLS FIRST], false, 0
- +- Exchange hashpartitioning(cast(airportId#38 as int), 200)
- +- *Project [cast(airportId#18L as string) AS airportId#38, countryName#24, cityName#23, airportName#22]
- +- *Filter (isnotnull(airportId#18L) && isnotnull(cast(airportId#18L as string)))
- +- Scan ExistingRDD[airportId#18L,cityId#19L,countryId#20L,airportCode#21,airportName#22,cityName#23,countryName#24]
- at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:56)
- at org.apache.spark.sql.execution.exchange.ShuffleExchange.doExecute(ShuffleExchange.scala:115)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
- at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
- at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
- at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
- at org.apache.spark.sql.execution.InputAdapter.inputRDDs(WholeStageCodegenExec.scala:252)
- at org.apache.spark.sql.execution.SortExec.inputRDDs(SortExec.scala:121)
- at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:386)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
- at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
- at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
- at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
- at org.apache.spark.sql.execution.python.BatchEvalPythonExec.doExecute(BatchEvalPythonExec.scala:83)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
- at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
- at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
- at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
- at org.apache.spark.sql.execution.InputAdapter.inputRDDs(WholeStageCodegenExec.scala:252)
- at org.apache.spark.sql.execution.ProjectExec.inputRDDs(basicPhysicalOperators.scala:42)
- at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:386)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
- at org.apache.spark.rdd.RDDOperationScope$.wi
- thScope(RDDOperationScope.scala:151)
- at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
- at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
- at org.apache.spark.sql.execution.exchange.ShuffleExchange.prepareShuffleDependency(ShuffleExchange.scala:88)
- at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:124)
- at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:115)
- at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)
- ... 60 more
- Caused by: java.util.concurrent.TimeoutException: Futures timed out after [300 seconds]
- at scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:219)
- at scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223)
- at org.apache.spark.util.ThreadUtils$.awaitResult(ThreadUtils.scala:201)
- at org.apache.spark.sql.execution.exchange.BroadcastExchangeExec.doExecuteBroadcast(BroadcastExchangeExec.scala:123)
- at org.apache.spark.sql.execution.InputAdapter.doExecuteBroadcast(WholeStageCodegenExec.scala:248)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeBroadcast$1.apply(SparkPlan.scala:127)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeBroadcast$1.apply(SparkPlan.scala:127)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
- at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
- at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
- at org.apache.spark.sql.execution.SparkPlan.executeBroadcast(SparkPlan.scala:126)
- at org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.prepareBroadcast(BroadcastHashJoinExec.scala:98)
- at org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.codegenOuter(BroadcastHashJoinExec.scala:242)
- at org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.doConsume(BroadcastHashJoinExec.scala:83)
- at org.apache.spark.sql.execution.CodegenSupport$class.consume(WholeStageCodegenExec.scala:155)
- at org.apache.spark.sql.execution.ProjectExec.consume(basicPhysicalOperators.scala:36)
- at org.apache.spark.sql.execution.ProjectExec.doConsume(basicPhysicalOperators.scala:68)
- at org.apache.spark.sql.execution.CodegenSupport$class.consume(WholeStageCodegenExec.scala:155)
- at org.apache.spark.sql.execution.InputAdapter.consume(WholeStageCodegenExec.scala:235)
- at org.apache.spark.sql.execution.InputAdapter.doProduce(WholeStageCodegenExec.scala:263)
- at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:85)
- at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:80)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
- at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
- at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
- at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:80)
- at org.apache.spark.sql.execution.InputAdapter.produce(WholeStageCodegenExec.scala:235)
- at org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:46)
- at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:85)
- at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:80)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
- at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
- at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
- at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:80)
- at org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:36)
- at org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.doProduce(BroadcastHashJoinExec.scala:77)
- at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:85)
- at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:80)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
- at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
- at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
- at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:80)
- at org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.produce(BroadcastHashJoinExec.scala:38)
- at org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:46)
- at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:85)
- at org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:80)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
- at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
- at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
- at org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:80)
- at org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:36)
- at org.apache.spark.sql.execution.WholeStageCodegenExec.doCodeGen(WholeStageCodegenExec.scala:331)
- at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:372)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
- at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
- at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
- at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
- at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
- at org.apache.spark.sql.execution.exchange.ShuffleExchange.prepareShuffleDependency(ShuffleExchange.scala:88)
- at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:124)
- at org.apache.spark.sql.execution.exchange.ShuffleExchange$$anonfun$doExecute$1.apply(ShuffleExchange.scala:115)
- at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)
- ... 96 more
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement