digraph G {
0 [labelType="html" label="<br><b>AdaptiveSparkPlan</b><br><br>"];
1 [labelType="html" label="<br><b>TakeOrderedAndProject</b><br><br>"];
subgraph cluster2 {
isCluster="true";
label="WholeStageCodegen (2)\n \nduration: 20 ms";
3 [labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build: 1 ms<br>peak memory: 32.2 MiB<br>number of output rows: 2<br>number of sort fallback tasks: 0<br>avg hash probes per key: 1"];
}
4 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 318.0 B<br>number of coalesced partitions: 1"];
5 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 3<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>36 ms (0 ms, 17 ms, 18 ms (stage 6.0: task 8))<br>remote merged bytes read: 0.0 B<br>local merged blocks fetched: 0<br>corrupt merged block chunks: 0<br>remote merged reqs duration: 0 ms<br>remote merged blocks fetched: 0<br>records read: 3<br>local bytes read: 318.0 B<br>fetch wait time: 0 ms<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 2<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>192.0 B (0.0 B, 64.0 B, 128.0 B (stage 6.0: task 8))<br>local merged bytes read: 0.0 B<br>number of partitions: 200<br>remote reqs duration: 0 ms<br>remote bytes read to disk: 0.0 B<br>shuffle bytes written total (min, med, max (stageId: taskId))<br>318.0 B (0.0 B, 106.0 B, 212.0 B (stage 6.0: task 8))"];
subgraph cluster6 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n696 ms (0 ms, 348 ms, 348 ms (stage 6.0: task 7))";
7 [labelType="html" label="<b>HashAggregate</b><br><br>spill size total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 6.0: task 7))<br>time in aggregation build total (min, med, max (stageId: taskId))<br>467 ms (0 ms, 233 ms, 234 ms (stage 6.0: task 7))<br>peak memory total (min, med, max (stageId: taskId))<br>512.0 KiB (0.0 B, 256.0 KiB, 256.0 KiB (stage 6.0: task 7))<br>number of output rows: 3<br>number of sort fallback tasks: 0<br>avg hash probes per key: 0"];
}
8 [labelType="html" label="<b>InMemoryTableScan</b><br><br>number of output rows: 1,219,444"];
subgraph cluster9 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n52.6 s (0 ms, 0 ms, 27.2 s (stage 5.0: task 5))";
10 [labelType="html" label="<br><b>Project</b><br><br>"];
}
11 [labelType="html" label="<b>Scan csv </b><br><br>number of output rows: 1,219,444<br>number of files read: 2<br>metadata time: 0 ms<br>size of files read: 226.6 MiB"];
1->0;
3->1;
4->3;
5->4;
7->5;
8->7;
10->8;
11->10;
}
12
AdaptiveSparkPlan isFinalPlan=true
TakeOrderedAndProject(limit=21, orderBy=[_source_file#156 ASC NULLS FIRST], output=[toprettystring(_source_file)#269,toprettystring(count)#270])
HashAggregate(keys=[_source_file#156], functions=[count(1)])
WholeStageCodegen (2)
AQEShuffleRead coalesced
Exchange hashpartitioning(_source_file#156, 200), ENSURE_REQUIREMENTS, [plan_id=118]
HashAggregate(keys=[_source_file#156], functions=[partial_count(1)])
WholeStageCodegen (1)
InMemoryTableScan [_source_file#156]
Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
WholeStageCodegen (1)
FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
== Physical Plan ==
AdaptiveSparkPlan (16)
+- == Final Plan ==
TakeOrderedAndProject (11)
+- * HashAggregate (10)
+- AQEShuffleRead (9)
+- ShuffleQueryStage (8), Statistics(sizeInBytes=192.0 B, rowCount=3)
+- Exchange (7)
+- * HashAggregate (6)
+- TableCacheQueryStage (5), Statistics(sizeInBytes=322.0 MiB, rowCount=1.22E+6)
+- InMemoryTableScan (1)
+- InMemoryRelation (2)
+- * Project (4)
+- Scan csv (3)
+- == Initial Plan ==
TakeOrderedAndProject (15)
+- HashAggregate (14)
+- Exchange (13)
+- HashAggregate (12)
+- InMemoryTableScan (1)
+- InMemoryRelation (2)
+- * Project (4)
+- Scan csv (3)
(1) InMemoryTableScan
Output [1]: [_source_file#156]
Arguments: [_source_file#156]
(2) InMemoryRelation
Arguments: [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, _source_file#156], CachedRDDBuilder(org.apache.spark.sql.execution.columnar.DefaultCachedBatchSerializer@28f1e8bc,StorageLevel(disk, memory, deserialized, 1 replicas),*(1) Project [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
+- FileScan csv [ride_id#128,rideable_type#129,started_at#130,ended_at#131,start_station_name#132,start_station_id#133,end_station_name#134,end_station_id#135,start_lat#136,start_lng#137,end_lat#138,end_lng#139,member_casual#140,_corrupt_record#141] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(2 paths)[s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:s...
,None)
(3) Scan csv
Output [14]: [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141]
Batched: false
Location: InMemoryFileIndex [s3a://rzvde-g11-durnev-pavel/raw/citibike_data/202602/202602-citibike-tripdata-part00.csv, ... 1 entries]
ReadSchema: struct<ride_id:string,rideable_type:string,started_at:string,ended_at:string,start_station_name:string,start_station_id:string,end_station_name:string,end_station_id:string,start_lat:string,start_lng:string,end_lat:string,end_lng:string,member_casual:string,_corrupt_record:string>
(4) Project [codegen id : 1]
Output [15]: [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141, regexp_extract(input_file_name(), [^/]+$, 0) AS _source_file#156]
Input [14]: [ride_id#128, rideable_type#129, started_at#130, ended_at#131, start_station_name#132, start_station_id#133, end_station_name#134, end_station_id#135, start_lat#136, start_lng#137, end_lat#138, end_lng#139, member_casual#140, _corrupt_record#141]
(5) TableCacheQueryStage
Output [1]: [_source_file#156]
Arguments: 0
(6) HashAggregate [codegen id : 1]
Input [1]: [_source_file#156]
Keys [1]: [_source_file#156]
Functions [1]: [partial_count(1)]
Aggregate Attributes [1]: [count#498L]
Results [2]: [_source_file#156, count#499L]
(7) Exchange
Input [2]: [_source_file#156, count#499L]
Arguments: hashpartitioning(_source_file#156, 200), ENSURE_REQUIREMENTS, [plan_id=118]
(8) ShuffleQueryStage
Output [2]: [_source_file#156, count#499L]
Arguments: 1
(9) AQEShuffleRead
Input [2]: [_source_file#156, count#499L]
Arguments: coalesced
(10) HashAggregate [codegen id : 2]
Input [2]: [_source_file#156, count#499L]
Keys [1]: [_source_file#156]
Functions [1]: [count(1)]
Aggregate Attributes [1]: [count(1)#263L]
Results [2]: [_source_file#156, count(1)#263L AS count#264L]
(11) TakeOrderedAndProject
Input [2]: [_source_file#156, count#264L]
Arguments: 21, [_source_file#156 ASC NULLS FIRST], [toprettystring(_source_file#156, Some(UTC)) AS toprettystring(_source_file)#269, toprettystring(count#264L, Some(UTC)) AS toprettystring(count)#270]
(12) HashAggregate
Input [1]: [_source_file#156]
Keys [1]: [_source_file#156]
Functions [1]: [partial_count(1)]
Aggregate Attributes [1]: [count#498L]
Results [2]: [_source_file#156, count#499L]
(13) Exchange
Input [2]: [_source_file#156, count#499L]
Arguments: hashpartitioning(_source_file#156, 200), ENSURE_REQUIREMENTS, [plan_id=83]
(14) HashAggregate
Input [2]: [_source_file#156, count#499L]
Keys [1]: [_source_file#156]
Functions [1]: [count(1)]
Aggregate Attributes [1]: [count(1)#263L]
Results [2]: [_source_file#156, count(1)#263L AS count#264L]
(15) TakeOrderedAndProject
Input [2]: [_source_file#156, count#264L]
Arguments: 21, [_source_file#156 ASC NULLS FIRST], [toprettystring(_source_file#156, Some(UTC)) AS toprettystring(_source_file)#269, toprettystring(count#264L, Some(UTC)) AS toprettystring(count)#270]
(16) AdaptiveSparkPlan
Output [2]: [toprettystring(_source_file)#269, toprettystring(count)#270]
Arguments: isFinalPlan=true