digraph G {
0 [labelType="html" label="<br><b>AdaptiveSparkPlan</b><br><br>"];
subgraph cluster1 {
isCluster="true";
label="WholeStageCodegen (2)\n \nduration: 3 ms";
2 [labelType="html" label="<b>HashAggregate</b><br><br>time in aggregation build: 3 ms<br>number of output rows: 1"];
}
3 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 74<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>28 ms (0 ms, 0 ms, 0 ms (stage 140.0: task 336))<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: 74<br>local bytes read: 4.3 KiB<br>fetch wait time: 0 ms<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 74<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>1184.0 B (0.0 B, 16.0 B, 16.0 B (stage 140.0: task 323))<br>local merged bytes read: 0.0 B<br>number of partitions: 1<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>4.3 KiB (0.0 B, 59.0 B, 59.0 B (stage 140.0: task 323))"];
subgraph cluster4 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n1.5 m (304 ms, 1.1 s, 3.7 s (stage 140.0: task 357))";
5 [labelType="html" label="<b>HashAggregate</b><br><br>time in aggregation build total (min, med, max (stageId: taskId))<br>1.5 m (303 ms, 1.1 s, 3.7 s (stage 140.0: task 357))<br>number of output rows: 74"];
}
6 [labelType="html" label="<b>Scan csv </b><br><br>number of output rows: 48,408,771<br>number of files read: 55<br>metadata time: 1 ms<br>size of files read: 8.8 GiB"];
2->0;
3->2;
5->3;
6->5;
}
7
AdaptiveSparkPlan isFinalPlan=true
HashAggregate(keys=[], functions=[count(1)])
WholeStageCodegen (2)
Exchange SinglePartition, ENSURE_REQUIREMENTS, [plan_id=2070]
HashAggregate(keys=[], functions=[partial_count(1)])
WholeStageCodegen (1)
FileScan csv [] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(55 paths)[s3a://rzvde-g8-kirsanov-dmitry/raw/citibike_data/202502/202502-citibi..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<>