digraph G {
0 [labelType="html" label="<br><b>AdaptiveSparkPlan</b><br><br>"];
subgraph cluster1 {
isCluster="true";
label="WholeStageCodegen (2)\n \nduration: 0 ms";
2 [labelType="html" label="<b>HashAggregate</b><br><br>time in aggregation build: 0 ms<br>number of output rows: 1"];
}
3 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 2<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 99.0: task 99))<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: 2<br>local bytes read: 115.0 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>32.0 B (0.0 B, 16.0 B, 16.0 B (stage 99.0: task 99))<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>115.0 B (0.0 B, 56.0 B, 59.0 B (stage 99.0: task 98))"];
subgraph cluster4 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n1.1 s (520 ms, 573 ms, 573 ms (stage 99.0: task 98))";
5 [labelType="html" label="<b>HashAggregate</b><br><br>time in aggregation build total (min, med, max (stageId: taskId))<br>1.1 s (519 ms, 572 ms, 572 ms (stage 99.0: task 98))<br>number of output rows: 2"];
6 [labelType="html" label="<br><b>Project</b><br><br>"];
7 [labelType="html" label="<b>ColumnarToRow</b><br><br>number of output rows: 1,189,993<br>number of input batches: 291"];
}
8 [labelType="html" label="<b>Scan parquet </b><br><br>number of files read: 1<br>scan time total (min, med, max (stageId: taskId))<br>1.1 s (519 ms, 571 ms, 571 ms (stage 99.0: task 98))<br>dynamic partition pruning time: 0 ms<br>metadata time: 1 ms<br>size of files read: 47.6 MiB<br>number of output rows: 1,189,993<br>number of partitions read: 1"];
2->0;
3->2;
5->3;
6->5;
7->6;
8->7;
}
9
AdaptiveSparkPlan isFinalPlan=true
HashAggregate(keys=[], functions=[count(1)])
WholeStageCodegen (2)
Exchange SinglePartition, ENSURE_REQUIREMENTS, [plan_id=2539]
HashAggregate(keys=[], functions=[partial_count(1)])
Project
ColumnarToRow
WholeStageCodegen (1)
FileScan parquet [year#11346,month#11347] Batched: true, DataFilters: [], Format: Parquet, Location: InMemoryFileIndex(1 paths)[s3a://rzvde-g11-durnev-pavel/raw_valid/citibike_data], PartitionFilters: [isnotnull(year#11346), isnotnull(month#11347), (year#11346 = 2026), (month#11347 = 2)], PushedFilters: [], ReadSchema: struct<>