digraph G {
0 [id="node0" labelType="html" label="<b>CollectLimit</b><br><br>shuffle records written: 2,000<br>remote merged reqs duration: 0 ms<br>remote merged blocks fetched: 0<br>records read: 1,000<br>local bytes read: 50.1 KiB<br>merged fetch fallback count: 0<br>local blocks read: 1<br>remote merged chunks fetched: 0<br>remote blocks read: 1<br>local merged bytes read: 0.0 B<br>remote reqs duration: 5 ms<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>2 ms (0 ms, 1 ms, 1 ms (stage 142.0: task 758))<br>remote merged bytes read: 0.0 B<br>local merged blocks fetched: 0<br>corrupt merged block chunks: 0<br>fetch wait time: 0 ms<br>remote bytes read: 51.0 KiB<br>remote bytes read to disk: 0.0 B<br>shuffle bytes written total (min, med, max (stageId: taskId))<br>101.1 KiB (50.1 KiB, 51.0 KiB, 51.0 KiB (stage 142.0: task 759))" tooltip="CollectLimit 1000"];
subgraph cluster1 {
isCluster="true";
id="cluster1";
label="WholeStageCodegen (1)\n \nduration: 0 ms";
tooltip="WholeStageCodegen (1)";
2 [id="node2" labelType="html" label="<b>ColumnarToRow</b><br><br>number of output rows: 8,192<br>number of input batches: 2" tooltip="ColumnarToRow"];
}
3 [id="node3" labelType="html" label="<b>Scan parquet </b><br><br>number of files read: 1<br>scan time total (min, med, max (stageId: taskId))<br>190 ms (95 ms, 95 ms, 95 ms (stage 142.0: task 758))<br>metadata time: 0 ms<br>size of files read: 57.1 MiB<br>number of output rows: 8,192" tooltip="FileScan parquet [VendorID#6040,tpep_pickup_datetime#6041,tpep_dropoff_datetime#6042,trip_distance#6044,RatecodeID#6045L,store_and_fwd_flag#6046,PULocationID#6047,DOLocationID#6048,payment_type#6049L,fare_amount#6050,extra#6051,mta_tax#6052,tip_amount#6053,tolls_amount#6054,improvement_surcharge#6055,total_amount#6056,congestion_surcharge#6057,Airport_fee#6058] Batched: true, DataFilters: [], Format: Parquet, Location: InMemoryFileIndex(1 paths)[file:/home/jovyan/data/yellow-taxi/yellow_tripdata_2024-06.parquet], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<VendorID:int,tpep_pickup_datetime:timestamp_ntz,tpep_dropoff_datetime:timestamp_ntz,trip_d..."];
2->0;
3->2;
}
== Physical Plan ==
CollectLimit (3)
+- * ColumnarToRow (2)
+- Scan parquet (1)
(1) Scan parquet
Output [18]: [VendorID#6040, tpep_pickup_datetime#6041, tpep_dropoff_datetime#6042, trip_distance#6044, RatecodeID#6045L, store_and_fwd_flag#6046, PULocationID#6047, DOLocationID#6048, payment_type#6049L, fare_amount#6050, extra#6051, mta_tax#6052, tip_amount#6053, tolls_amount#6054, improvement_surcharge#6055, total_amount#6056, congestion_surcharge#6057, Airport_fee#6058]
Batched: true
Location: InMemoryFileIndex [file:/home/jovyan/data/yellow-taxi/yellow_tripdata_2024-06.parquet]
ReadSchema: struct<VendorID:int,tpep_pickup_datetime:timestamp_ntz,tpep_dropoff_datetime:timestamp_ntz,trip_distance:double,RatecodeID:bigint,store_and_fwd_flag:string,PULocationID:int,DOLocationID:int,payment_type:bigint,fare_amount:double,extra:double,mta_tax:double,tip_amount:double,tolls_amount:double,improvement_surcharge:double,total_amount:double,congestion_surcharge:double,Airport_fee:double>
(2) ColumnarToRow [codegen id : 1]
Input [18]: [VendorID#6040, tpep_pickup_datetime#6041, tpep_dropoff_datetime#6042, trip_distance#6044, RatecodeID#6045L, store_and_fwd_flag#6046, PULocationID#6047, DOLocationID#6048, payment_type#6049L, fare_amount#6050, extra#6051, mta_tax#6052, tip_amount#6053, tolls_amount#6054, improvement_surcharge#6055, total_amount#6056, congestion_surcharge#6057, Airport_fee#6058]
(3) CollectLimit
Input [18]: [VendorID#6040, tpep_pickup_datetime#6041, tpep_dropoff_datetime#6042, trip_distance#6044, RatecodeID#6045L, store_and_fwd_flag#6046, PULocationID#6047, DOLocationID#6048, payment_type#6049L, fare_amount#6050, extra#6051, mta_tax#6052, tip_amount#6053, tolls_amount#6054, improvement_surcharge#6055, total_amount#6056, congestion_surcharge#6057, Airport_fee#6058]
Arguments: 1000