task1 - Details for Query 3

Details for Query 3

Submitted Time: 2024/11/28 21:23:06
Duration: 0.6 s
Succeeded Jobs: 5 6 7

Show the Stage ID and Task ID that corresponds to the max metric

digraph G { 0 [labelType="html" label=" CollectLimit "]; subgraph cluster1 { isCluster="true"; label="WholeStageCodegen (3)"; 2 [labelType="html" label=" Project "]; 3 [labelType="html" label="BroadcastHashJoin number of output rows: 21"]; 4 [labelType="html" label=" Project "]; 5 [labelType="html" label="BroadcastHashJoin number of output rows: 21"]; 6 [labelType="html" label=" Project "]; 7 [labelType="html" label="Filter number of output rows: 21"]; } 8 [labelType="html" label="Scan csv number of files read: 7 metadata time: 0 ms size of files read: 2.2 GiB number of output rows: 21"]; 9 [labelType="html" label="BroadcastExchange data size: 1026.1 KiB time to collect: 249 ms time to build: 41 ms time to broadcast: 7 ms"]; subgraph cluster10 { isCluster="true"; label="WholeStageCodegen (1)\n \nduration: 85 ms"; 11 [labelType="html" label=" Project "]; 12 [labelType="html" label="Filter number of output rows: 265"]; } 13 [labelType="html" label="Scan csv number of files read: 1 metadata time: 0 ms size of files read: 10.5 KiB number of output rows: 265"]; 14 [labelType="html" label="BroadcastExchange data size: 1026.1 KiB time to collect: 253 ms time to build: 31 ms time to broadcast: 5 ms"]; subgraph cluster15 { isCluster="true"; label="WholeStageCodegen (2)\n \nduration: 96 ms"; 16 [labelType="html" label=" Project "]; 17 [labelType="html" label="Filter number of output rows: 265"]; } 18 [labelType="html" label="Scan csv number of files read: 1 metadata time: 0 ms size of files read: 10.5 KiB number of output rows: 265"]; 2->0; 3->2; 4->3; 5->4; 6->5; 7->6; 8->7; 9->5; 11->9; 12->11; 13->12; 14->3; 16->14; 17->16; 18->17; }

CollectLimit 21

Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55, Pickup_Borough#93, Pickup_Zone#103, Pickup_service_zone#113, Dropoff_Borough#98, Dropoff_Zone#108, Dropoff_service_zone#118]

BroadcastHashJoin [cast(DOLocationID#45 as int)], [LocationID#16], Inner, BuildRight

Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, DOLocationID#45, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55, Pickup_Borough#93, Pickup_Zone#103, Pickup_service_zone#113]

BroadcastHashJoin [cast(PULocationID#44 as int)], [LocationID#16], Inner, BuildRight

Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, PULocationID#44, DOLocationID#45, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55]

Filter (isnotnull(PULocationID#44) AND isnotnull(DOLocationID#45))

WholeStageCodegen (3)

FileScan csv [tpep_pickup_datetime#40,tpep_dropoff_datetime#41,passenger_count#42,trip_distance#43,PULocationID#44,DOLocationID#45,payment_type#46,fare_amount#47,extra#48,mta_tax#49,tip_amount#50,tolls_amount#51,total_amount#52,congestion_surcharge#53,airport_fee#54,taxi_type#55] Batched: false, DataFilters: [isnotnull(PULocationID#44), isnotnull(DOLocationID#45)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/nyc_taxi/yellow_tripdata/2023], PartitionFilters: [], PushedFilters: [IsNotNull(PULocationID), IsNotNull(DOLocationID)], ReadSchema: struct<tpep_pickup_datetime:string,tpep_dropoff_datetime:string,passenger_count:string,trip_dista...

BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint))), [id=#114]

Project [LocationID#16, Borough#17 AS Pickup_Borough#93, Zone#18 AS Pickup_Zone#103, service_zone#19 AS Pickup_service_zone#113]

Filter isnotnull(LocationID#16)

WholeStageCodegen (1)

FileScan csv [LocationID#16,Borough#17,Zone#18,service_zone#19] Batched: false, DataFilters: [isnotnull(LocationID#16)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/nyc_taxi], PartitionFilters: [], PushedFilters: [IsNotNull(LocationID)], ReadSchema: struct<LocationID:int,Borough:string,Zone:string,service_zone:string>

BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint))), [id=#122]

Project [LocationID#16, Borough#17 AS Dropoff_Borough#98, Zone#18 AS Dropoff_Zone#108, service_zone#19 AS Dropoff_service_zone#118]

Filter isnotnull(LocationID#16)

WholeStageCodegen (2)

Details

== Parsed Logical Plan ==
GlobalLimit 21
+- LocalLimit 21
   +- Project [cast(tpep_pickup_datetime#40 as string) AS tpep_pickup_datetime#354, cast(tpep_dropoff_datetime#41 as string) AS tpep_dropoff_datetime#355, cast(passenger_count#42 as string) AS passenger_count#356, cast(trip_distance#43 as string) AS trip_distance#357, cast(payment_type#46 as string) AS payment_type#358, cast(fare_amount#47 as string) AS fare_amount#359, cast(extra#48 as string) AS extra#360, cast(mta_tax#49 as string) AS mta_tax#361, cast(tip_amount#50 as string) AS tip_amount#362, cast(tolls_amount#51 as string) AS tolls_amount#363, cast(total_amount#52 as string) AS total_amount#364, cast(congestion_surcharge#53 as string) AS congestion_surcharge#365, cast(airport_fee#54 as string) AS airport_fee#366, cast(taxi_type#55 as string) AS taxi_type#367, cast(Pickup_Borough#93 as string) AS Pickup_Borough#368, cast(Pickup_Zone#103 as string) AS Pickup_Zone#369, cast(Pickup_service_zone#113 as string) AS Pickup_service_zone#370, cast(Dropoff_Borough#98 as string) AS Dropoff_Borough#371, cast(Dropoff_Zone#108 as string) AS Dropoff_Zone#372, cast(Dropoff_service_zone#118 as string) AS Dropoff_service_zone#373]
      +- Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55, Pickup_Borough#93, Pickup_Zone#103, Pickup_service_zone#113, Dropoff_Borough#98, Dropoff_Zone#108, Dropoff_service_zone#118]
         +- Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55, Pickup_Borough#93, Pickup_Zone#103, Pickup_service_zone#113, LocationID#16, Dropoff_Borough#98, Dropoff_Zone#108, Dropoff_service_zone#118]
            +- Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, DOLocationID#45, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55, Pickup_Borough#93, Pickup_Zone#103, Pickup_service_zone#113, LocationID#16, Dropoff_Borough#98, Dropoff_Zone#108, Dropoff_service_zone#118]
               +- Join Inner, (cast(DOLocationID#45 as int) = LocationID#16)
                  :- Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, PULocationID#44, DOLocationID#45, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55, Pickup_Borough#93, Pickup_Zone#103, Pickup_service_zone#113]
                  :  +- Join Inner, (cast(PULocationID#44 as int) = LocationID#16)
                  :     :- Relation[tpep_pickup_datetime#40,tpep_dropoff_datetime#41,passenger_count#42,trip_distance#43,PULocationID#44,DOLocationID#45,payment_type#46,fare_amount#47,extra#48,mta_tax#49,tip_amount#50,tolls_amount#51,total_amount#52,congestion_surcharge#53,airport_fee#54,taxi_type#55] csv
                  :     +- Project [LocationID#16, Pickup_Borough#93, Pickup_Zone#103, service_zone#19 AS Pickup_service_zone#113]
                  :        +- Project [LocationID#16, Pickup_Borough#93, Zone#18 AS Pickup_Zone#103, service_zone#19]
                  :           +- Project [LocationID#16, Borough#17 AS Pickup_Borough#93, Zone#18, service_zone#19]
                  :              +- Relation[LocationID#16,Borough#17,Zone#18,service_zone#19] csv
                  +- Project [LocationID#16, Dropoff_Borough#98, Dropoff_Zone#108, service_zone#19 AS Dropoff_service_zone#118]
                     +- Project [LocationID#16, Dropoff_Borough#98, Zone#18 AS Dropoff_Zone#108, service_zone#19]
                        +- Project [LocationID#16, Borough#17 AS Dropoff_Borough#98, Zone#18, service_zone#19]
                           +- Relation[LocationID#16,Borough#17,Zone#18,service_zone#19] csv

== Analyzed Logical Plan ==
tpep_pickup_datetime: string, tpep_dropoff_datetime: string, passenger_count: string, trip_distance: string, payment_type: string, fare_amount: string, extra: string, mta_tax: string, tip_amount: string, tolls_amount: string, total_amount: string, congestion_surcharge: string, airport_fee: string, taxi_type: string, Pickup_Borough: string, Pickup_Zone: string, Pickup_service_zone: string, Dropoff_Borough: string, Dropoff_Zone: string, Dropoff_service_zone: string
GlobalLimit 21
+- LocalLimit 21
   +- Project [cast(tpep_pickup_datetime#40 as string) AS tpep_pickup_datetime#354, cast(tpep_dropoff_datetime#41 as string) AS tpep_dropoff_datetime#355, cast(passenger_count#42 as string) AS passenger_count#356, cast(trip_distance#43 as string) AS trip_distance#357, cast(payment_type#46 as string) AS payment_type#358, cast(fare_amount#47 as string) AS fare_amount#359, cast(extra#48 as string) AS extra#360, cast(mta_tax#49 as string) AS mta_tax#361, cast(tip_amount#50 as string) AS tip_amount#362, cast(tolls_amount#51 as string) AS tolls_amount#363, cast(total_amount#52 as string) AS total_amount#364, cast(congestion_surcharge#53 as string) AS congestion_surcharge#365, cast(airport_fee#54 as string) AS airport_fee#366, cast(taxi_type#55 as string) AS taxi_type#367, cast(Pickup_Borough#93 as string) AS Pickup_Borough#368, cast(Pickup_Zone#103 as string) AS Pickup_Zone#369, cast(Pickup_service_zone#113 as string) AS Pickup_service_zone#370, cast(Dropoff_Borough#98 as string) AS Dropoff_Borough#371, cast(Dropoff_Zone#108 as string) AS Dropoff_Zone#372, cast(Dropoff_service_zone#118 as string) AS Dropoff_service_zone#373]
      +- Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55, Pickup_Borough#93, Pickup_Zone#103, Pickup_service_zone#113, Dropoff_Borough#98, Dropoff_Zone#108, Dropoff_service_zone#118]
         +- Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55, Pickup_Borough#93, Pickup_Zone#103, Pickup_service_zone#113, LocationID#16, Dropoff_Borough#98, Dropoff_Zone#108, Dropoff_service_zone#118]
            +- Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, DOLocationID#45, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55, Pickup_Borough#93, Pickup_Zone#103, Pickup_service_zone#113, LocationID#16, Dropoff_Borough#98, Dropoff_Zone#108, Dropoff_service_zone#118]
               +- Join Inner, (cast(DOLocationID#45 as int) = LocationID#16)
                  :- Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, PULocationID#44, DOLocationID#45, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55, Pickup_Borough#93, Pickup_Zone#103, Pickup_service_zone#113]
                  :  +- Join Inner, (cast(PULocationID#44 as int) = LocationID#16)
                  :     :- Relation[tpep_pickup_datetime#40,tpep_dropoff_datetime#41,passenger_count#42,trip_distance#43,PULocationID#44,DOLocationID#45,payment_type#46,fare_amount#47,extra#48,mta_tax#49,tip_amount#50,tolls_amount#51,total_amount#52,congestion_surcharge#53,airport_fee#54,taxi_type#55] csv
                  :     +- Project [LocationID#16, Pickup_Borough#93, Pickup_Zone#103, service_zone#19 AS Pickup_service_zone#113]
                  :        +- Project [LocationID#16, Pickup_Borough#93, Zone#18 AS Pickup_Zone#103, service_zone#19]
                  :           +- Project [LocationID#16, Borough#17 AS Pickup_Borough#93, Zone#18, service_zone#19]
                  :              +- Relation[LocationID#16,Borough#17,Zone#18,service_zone#19] csv
                  +- Project [LocationID#16, Dropoff_Borough#98, Dropoff_Zone#108, service_zone#19 AS Dropoff_service_zone#118]
                     +- Project [LocationID#16, Dropoff_Borough#98, Zone#18 AS Dropoff_Zone#108, service_zone#19]
                        +- Project [LocationID#16, Borough#17 AS Dropoff_Borough#98, Zone#18, service_zone#19]
                           +- Relation[LocationID#16,Borough#17,Zone#18,service_zone#19] csv

== Optimized Logical Plan ==
GlobalLimit 21
+- LocalLimit 21
   +- Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55, Pickup_Borough#93, Pickup_Zone#103, Pickup_service_zone#113, Dropoff_Borough#98, Dropoff_Zone#108, Dropoff_service_zone#118]
      +- Join Inner, (cast(DOLocationID#45 as int) = LocationID#16)
         :- Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, DOLocationID#45, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55, Pickup_Borough#93, Pickup_Zone#103, Pickup_service_zone#113]
         :  +- Join Inner, (cast(PULocationID#44 as int) = LocationID#16)
         :     :- Filter (isnotnull(PULocationID#44) AND isnotnull(DOLocationID#45))
         :     :  +- Relation[tpep_pickup_datetime#40,tpep_dropoff_datetime#41,passenger_count#42,trip_distance#43,PULocationID#44,DOLocationID#45,payment_type#46,fare_amount#47,extra#48,mta_tax#49,tip_amount#50,tolls_amount#51,total_amount#52,congestion_surcharge#53,airport_fee#54,taxi_type#55] csv
         :     +- Project [LocationID#16, Borough#17 AS Pickup_Borough#93, Zone#18 AS Pickup_Zone#103, service_zone#19 AS Pickup_service_zone#113]
         :        +- Filter isnotnull(LocationID#16)
         :           +- Relation[LocationID#16,Borough#17,Zone#18,service_zone#19] csv
         +- Project [LocationID#16, Borough#17 AS Dropoff_Borough#98, Zone#18 AS Dropoff_Zone#108, service_zone#19 AS Dropoff_service_zone#118]
            +- Filter isnotnull(LocationID#16)
               +- Relation[LocationID#16,Borough#17,Zone#18,service_zone#19] csv

== Physical Plan ==
CollectLimit 21
+- *(3) Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55, Pickup_Borough#93, Pickup_Zone#103, Pickup_service_zone#113, Dropoff_Borough#98, Dropoff_Zone#108, Dropoff_service_zone#118]
   +- *(3) BroadcastHashJoin [cast(DOLocationID#45 as int)], [LocationID#16], Inner, BuildRight
      :- *(3) Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, DOLocationID#45, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55, Pickup_Borough#93, Pickup_Zone#103, Pickup_service_zone#113]
      :  +- *(3) BroadcastHashJoin [cast(PULocationID#44 as int)], [LocationID#16], Inner, BuildRight
      :     :- *(3) Project [tpep_pickup_datetime#40, tpep_dropoff_datetime#41, passenger_count#42, trip_distance#43, PULocationID#44, DOLocationID#45, payment_type#46, fare_amount#47, extra#48, mta_tax#49, tip_amount#50, tolls_amount#51, total_amount#52, congestion_surcharge#53, airport_fee#54, taxi_type#55]
      :     :  +- *(3) Filter (isnotnull(PULocationID#44) AND isnotnull(DOLocationID#45))
      :     :     +- FileScan csv [tpep_pickup_datetime#40,tpep_dropoff_datetime#41,passenger_count#42,trip_distance#43,PULocationID#44,DOLocationID#45,payment_type#46,fare_amount#47,extra#48,mta_tax#49,tip_amount#50,tolls_amount#51,total_amount#52,congestion_surcharge#53,airport_fee#54,taxi_type#55] Batched: false, DataFilters: [isnotnull(PULocationID#44), isnotnull(DOLocationID#45)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/nyc_taxi/yellow_tripdata/2023], PartitionFilters: [], PushedFilters: [IsNotNull(PULocationID), IsNotNull(DOLocationID)], ReadSchema: struct<tpep_pickup_datetime:string,tpep_dropoff_datetime:string,passenger_count:string,trip_dista...
      :     +- BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint))), [id=#114]
      :        +- *(1) Project [LocationID#16, Borough#17 AS Pickup_Borough#93, Zone#18 AS Pickup_Zone#103, service_zone#19 AS Pickup_service_zone#113]
      :           +- *(1) Filter isnotnull(LocationID#16)
      :              +- FileScan csv [LocationID#16,Borough#17,Zone#18,service_zone#19] Batched: false, DataFilters: [isnotnull(LocationID#16)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/nyc_taxi], PartitionFilters: [], PushedFilters: [IsNotNull(LocationID)], ReadSchema: struct<LocationID:int,Borough:string,Zone:string,service_zone:string>
      +- BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint))), [id=#122]
         +- *(2) Project [LocationID#16, Borough#17 AS Dropoff_Borough#98, Zone#18 AS Dropoff_Zone#108, service_zone#19 AS Dropoff_service_zone#118]
            +- *(2) Filter isnotnull(LocationID#16)
               +- FileScan csv [LocationID#16,Borough#17,Zone#18,service_zone#19] Batched: false, DataFilters: [isnotnull(LocationID#16)], Format: CSV, Location: InMemoryFileIndex[s3a://data-repository-bkt/ECS765/nyc_taxi], PartitionFilters: [], PushedFilters: [IsNotNull(LocationID)], ReadSchema: struct<LocationID:int,Borough:string,Zone:string,service_zone:string>