digraph G {
0 [id="node0" labelType="html" label="<b>CollectLimit</b><br><br>shuffle records written: 6,000<br>remote merged reqs duration total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 151.0: task 796))<br>remote merged blocks fetched: 0<br>records read: 0<br>local bytes read total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 151.0: task 796))<br>merged fetch fallback count: 0<br>local blocks read: 0<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>local merged bytes read total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 151.0: task 796))<br>remote reqs duration total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 151.0: task 796))<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>206 ms (0 ms, 0 ms, 188 ms (stage 151.0: task 800))<br>remote merged bytes read total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 151.0: task 796))<br>local merged blocks fetched: 0<br>corrupt merged block chunks: 0<br>fetch wait time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 151.0: task 796))<br>remote bytes read total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 151.0: task 796))<br>remote bytes read to disk total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 151.0: task 796))<br>shuffle bytes written total (min, med, max (stageId: taskId))<br>326.8 KiB (0.0 B, 0.0 B, 54.9 KiB (stage 151.0: task 800))" tooltip="CollectLimit 1000"];
subgraph cluster1 {
isCluster="true";
id="cluster1";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n0 ms (0 ms, 0 ms, 0 ms (stage 151.0: task 796))";
tooltip="WholeStageCodegen (1)";
2 [id="node2" labelType="html" label="<br><b>Project</b><br><br>" tooltip="Project [VendorID#6174L, tpep_pickup_datetime#6175, tpep_dropoff_datetime#6176, trip_distance#6178, RatecodeID#6179L, store_and_fwd_flag#6180, PULocationID#6181L, DOLocationID#6182L, payment_type#6183L, fare_amount#6184, extra#6185, mta_tax#6186, tip_amount#6187, tolls_amount#6188, improvement_surcharge#6189, total_amount#6190, congestion_surcharge#6191, airport_fee#6192, cast(passenger_count#6177L as string) AS passenger_count#6201]"];
3 [id="node3" labelType="html" label="<b>ColumnarToRow</b><br><br>number of output rows: 24,576<br>number of input batches: 6" tooltip="ColumnarToRow"];
}
4 [id="node4" labelType="html" label="<b>Scan parquet </b><br><br>number of files read: 96<br>scan time total (min, med, max (stageId: taskId))<br>3.2 s (0 ms, 0 ms, 1.0 s (stage 151.0: task 803))<br>metadata time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (driver))<br>size of files read total (min, med, max (stageId: taskId))<br>5.9 GiB (0.0 B, 0.0 B, 5.9 GiB (driver))<br>number of output rows: 24,576" tooltip="FileScan parquet [VendorID#6174L,tpep_pickup_datetime#6175,tpep_dropoff_datetime#6176,passenger_count#6177L,trip_distance#6178,RatecodeID#6179L,store_and_fwd_flag#6180,PULocationID#6181L,DOLocationID#6182L,payment_type#6183L,fare_amount#6184,extra#6185,mta_tax#6186,tip_amount#6187,tolls_amount#6188,improvement_surcharge#6189,total_amount#6190,congestion_surcharge#6191,airport_fee#6192] Batched: true, DataFilters: [], Format: Parquet, Location: InMemoryFileIndex(1 paths)[file:/home/jovyan/data/yellow-taxi], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<VendorID:bigint,tpep_pickup_datetime:timestamp_ntz,tpep_dropoff_datetime:timestamp_ntz,pas..."];
2->0;
3->2;
4->3;
}
== Physical Plan ==
CollectLimit (4)
+- * Project (3)
+- * ColumnarToRow (2)
+- Scan parquet (1)
(1) Scan parquet
Output [19]: [VendorID#6174L, tpep_pickup_datetime#6175, tpep_dropoff_datetime#6176, passenger_count#6177L, trip_distance#6178, RatecodeID#6179L, store_and_fwd_flag#6180, PULocationID#6181L, DOLocationID#6182L, payment_type#6183L, fare_amount#6184, extra#6185, mta_tax#6186, tip_amount#6187, tolls_amount#6188, improvement_surcharge#6189, total_amount#6190, congestion_surcharge#6191, airport_fee#6192]
Batched: true
Location: InMemoryFileIndex [file:/home/jovyan/data/yellow-taxi]
ReadSchema: struct<VendorID:bigint,tpep_pickup_datetime:timestamp_ntz,tpep_dropoff_datetime:timestamp_ntz,passenger_count:bigint,trip_distance:double,RatecodeID:bigint,store_and_fwd_flag:string,PULocationID:bigint,DOLocationID:bigint,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 [19]: [VendorID#6174L, tpep_pickup_datetime#6175, tpep_dropoff_datetime#6176, passenger_count#6177L, trip_distance#6178, RatecodeID#6179L, store_and_fwd_flag#6180, PULocationID#6181L, DOLocationID#6182L, payment_type#6183L, fare_amount#6184, extra#6185, mta_tax#6186, tip_amount#6187, tolls_amount#6188, improvement_surcharge#6189, total_amount#6190, congestion_surcharge#6191, airport_fee#6192]
(3) Project [codegen id : 1]
Output [19]: [VendorID#6174L, tpep_pickup_datetime#6175, tpep_dropoff_datetime#6176, trip_distance#6178, RatecodeID#6179L, store_and_fwd_flag#6180, PULocationID#6181L, DOLocationID#6182L, payment_type#6183L, fare_amount#6184, extra#6185, mta_tax#6186, tip_amount#6187, tolls_amount#6188, improvement_surcharge#6189, total_amount#6190, congestion_surcharge#6191, airport_fee#6192, cast(passenger_count#6177L as string) AS passenger_count#6201]
Input [19]: [VendorID#6174L, tpep_pickup_datetime#6175, tpep_dropoff_datetime#6176, passenger_count#6177L, trip_distance#6178, RatecodeID#6179L, store_and_fwd_flag#6180, PULocationID#6181L, DOLocationID#6182L, payment_type#6183L, fare_amount#6184, extra#6185, mta_tax#6186, tip_amount#6187, tolls_amount#6188, improvement_surcharge#6189, total_amount#6190, congestion_surcharge#6191, airport_fee#6192]
(4) CollectLimit
Input [19]: [VendorID#6174L, tpep_pickup_datetime#6175, tpep_dropoff_datetime#6176, trip_distance#6178, RatecodeID#6179L, store_and_fwd_flag#6180, PULocationID#6181L, DOLocationID#6182L, payment_type#6183L, fare_amount#6184, extra#6185, mta_tax#6186, tip_amount#6187, tolls_amount#6188, improvement_surcharge#6189, total_amount#6190, congestion_surcharge#6191, airport_fee#6192, passenger_count#6201]
Arguments: 1000