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 (5)\n \nduration: 228 ms";
3 [labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build: 208 ms<br>peak memory: 17.0 MiB<br>number of output rows: 21,121<br>number of sort fallback tasks: 0<br>avg hash probes per key: 1.5"];
4 [labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build: 192 ms<br>peak memory: 16.3 MiB<br>number of output rows: 21,121<br>number of sort fallback tasks: 0<br>avg hash probes per key: 1"];
5 [labelType="html" label="<br><b>Project</b><br><br>"];
6 [labelType="html" label="<b>SortMergeJoin</b><br><br>number of output rows: 21,121<br>spill size: 0.0 B"];
}
subgraph cluster7 {
isCluster="true";
label="WholeStageCodegen (3)\n \nduration: 253 ms";
8 [labelType="html" label="<b>Sort</b><br><br>sort time: 21 ms<br>peak memory: 16.5 MiB<br>spill size: 0.0 B"];
}
9 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 175.9 KiB<br>number of coalesced partitions: 1"];
10 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 21,121<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>5 ms (1 ms, 1 ms, 1 ms (stage 20849.0: task 27140))<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: 21,121<br>local bytes read: 166.3 KiB<br>fetch wait time: 0 ms<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 3<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>660.0 KiB (20.7 KiB, 319.7 KiB, 319.7 KiB (stage 20849.0: task 27138))<br>local merged bytes read: 0.0 B<br>number of partitions: 10<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>166.3 KiB (6.7 KiB, 79.7 KiB, 79.9 KiB (stage 20849.0: task 27138))"];
subgraph cluster11 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n357 ms (23 ms, 163 ms, 171 ms (stage 20849.0: task 27139))";
12 [labelType="html" label="<br><b>Project</b><br><br>"];
13 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 21,121"];
}
14 [labelType="html" label="<b>Scan csv </b><br><br>number of output rows: 21,121<br>number of files read: 1<br>metadata time: 0 ms<br>size of files read: 8.3 MiB"];
subgraph cluster15 {
isCluster="true";
label="WholeStageCodegen (4)\n \nduration: 226 ms";
16 [labelType="html" label="<b>Sort</b><br><br>sort time: 5 ms<br>peak memory: 16.5 MiB<br>spill size: 0.0 B"];
17 [labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build: 35 ms<br>peak memory: 16.3 MiB<br>number of output rows: 21,121<br>number of sort fallback tasks: 0<br>avg hash probes per key: 1"];
}
18 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 159.0 KiB<br>number of coalesced partitions: 1"];
19 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 21,122<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>4 ms (1 ms, 1 ms, 1 ms (stage 20850.0: task 27143))<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: 21,122<br>local bytes read: 150.8 KiB<br>fetch wait time: 0 ms<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 3<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>660.1 KiB (5.3 KiB, 316.2 KiB, 338.6 KiB (stage 20850.0: task 27142))<br>local merged bytes read: 0.0 B<br>number of partitions: 10<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>150.8 KiB (2.3 KiB, 71.5 KiB, 77.0 KiB (stage 20850.0: task 27142))"];
subgraph cluster20 {
isCluster="true";
label="WholeStageCodegen (2)\n \nduration: total (min, med, max (stageId: taskId))\n281 ms (16 ms, 132 ms, 133 ms (stage 20850.0: task 27141))";
21 [labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build total (min, med, max (stageId: taskId))<br>226 ms (5 ms, 109 ms, 112 ms (stage 20850.0: task 27141))<br>peak memory total (min, med, max (stageId: taskId))<br>32.8 MiB (256.0 KiB, 16.3 MiB, 16.3 MiB (stage 20850.0: task 27142))<br>number of output rows: 21,122<br>number of sort fallback tasks: 0<br>avg hash probes per key (min, med, max (stageId: taskId)):<br>(1, 1, 1 (stage 20850.0: task 27142))"];
22 [labelType="html" label="<br><b>Project</b><br><br>"];
23 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 26,044"];
}
24 [labelType="html" label="<b>Scan csv </b><br><br>number of output rows: 26,044<br>number of files read: 1<br>metadata time: 0 ms<br>size of files read: 8.0 MiB"];
1->0;
3->1;
4->3;
5->4;
6->5;
8->6;
9->8;
10->9;
12->10;
13->12;
14->13;
16->6;
17->16;
18->17;
19->18;
21->19;
22->21;
23->22;
24->23;
}
25
AdaptiveSparkPlan isFinalPlan=true
TakeOrderedAndProject(limit=10, orderBy=[COL_1D43C4C0_AE5C_43DC_ABA0_79E72CBFE6D42#1650414L DESC NULLS LAST], output=[COL_1D43C4C0_AE5C_43DC_ABA0_79E72CBFE6D41#1650387,COL_1D43C4C0_AE5C_43DC_ABA0_79E72CBFE6D42#1650414L])
HashAggregate(keys=[COL_1D43C4C0_AE5C_43DC_ABA0_79E72CBFE6D4#1650356], functions=[count(1)])
HashAggregate(keys=[COL_1D43C4C0_AE5C_43DC_ABA0_79E72CBFE6D4#1650356], functions=[partial_count(1)])
Project [RSS_DECOUPAGE_237747_COL_5588E97C_F5A9_4AFC_AD58_2B0A6381409A#1649831 AS COL_1D43C4C0_AE5C_43DC_ABA0_79E72CBFE6D4#1650356]
SortMergeJoin [COL_7948E047_29EE_472A_BFFC_723098878DAD#1649569], [RSS_DECOUPAGE_237747_COL_5588E97C_F5A9_4AFC_AD58_2B0A6381409A#1649831], Inner
WholeStageCodegen (5)
Sort [COL_7948E047_29EE_472A_BFFC_723098878DAD#1649569 ASC NULLS FIRST], false, 0
WholeStageCodegen (3)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_7948E047_29EE_472A_BFFC_723098878DAD#1649569, 10), ENSURE_REQUIREMENTS, [plan_id=1025728]
Project [str_remove_space(NO_ADMIN#1643798, ALL) AS COL_7948E047_29EE_472A_BFFC_723098878DAD#1649569]
Filter isnotnull(str_remove_space(NO_ADMIN#1643798, ALL))
WholeStageCodegen (1)
FileScan csv [NO_ADMIN#1643798] Batched: false, DataFilters: [isnotnull(str_remove_space(NO_ADMIN#1643798, ALL))], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/data/input/depot/csv/tmp/VISUALVALOSEJOU_237544/420780652.2025.1..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<NO_ADMIN:string>
Sort [RSS_DECOUPAGE_237747_COL_5588E97C_F5A9_4AFC_AD58_2B0A6381409A#1649831 ASC NULLS FIRST], false, 0
HashAggregate(keys=[COL_0FDBEAA7_683C_4647_A06F_34AC7E6418C2#1643478], functions=[])
WholeStageCodegen (4)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_0FDBEAA7_683C_4647_A06F_34AC7E6418C2#1643478, 10), ENSURE_REQUIREMENTS, [plan_id=1025753]
HashAggregate(keys=[COL_0FDBEAA7_683C_4647_A06F_34AC7E6418C2#1643478], functions=[])
Project [str_remove_space(str_extract_middle(_c0#1642899, 48, 20), ALL) AS COL_0FDBEAA7_683C_4647_A06F_34AC7E6418C2#1643478]
Filter isnotnull(str_remove_space(str_extract_middle(_c0#1642899, 48, 20), ALL))
WholeStageCodegen (2)
FileScan csv [_c0#1642899] Batched: false, DataFilters: [isnotnull(str_remove_space(str_extract_middle(_c0#1642899, 48, 20), ALL))], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/data/input/depot/csv/tmp/RSS_M12_2025_237542/RSS- 420780652.txt], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<_c0:string>