digraph G {
0 [labelType="html" label="<br><b>AdaptiveSparkPlan</b><br><br>"];
subgraph cluster1 {
isCluster="true";
label="WholeStageCodegen (7)\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: 1<br>local merged chunks fetched: 0<br>shuffle write time: 0 ms<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: 1<br>local bytes read: 59.0 B<br>fetch wait time: 0 ms<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 1<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size: 16.0 B<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: 59.0 B"];
subgraph cluster4 {
isCluster="true";
label="WholeStageCodegen (6)\n \nduration: 131 ms";
5 [labelType="html" label="<b>HashAggregate</b><br><br>spill size: 0.0 B<br>time in aggregation build: 131 ms<br>peak memory: 0.0 B<br>number of output rows: 1<br>number of sort fallback tasks: 0<br>avg hash probes per key: 0"];
6 [labelType="html" label="<br><b>Project</b><br><br>"];
7 [labelType="html" label="<b>SortMergeJoin</b><br><br>number of output rows: 41,179<br>spill size: 0.0 B"];
}
subgraph cluster8 {
isCluster="true";
label="WholeStageCodegen (3)\n \nduration: 225 ms";
9 [labelType="html" label="<b>Sort</b><br><br>sort time: 11 ms<br>peak memory: 17.0 MiB<br>spill size: 0.0 B"];
}
10 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 361.3 KiB<br>number of coalesced partitions: 1"];
11 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 41,179<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>6 ms (2 ms, 4 ms, 4 ms (stage 1196.0: task 1625))<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: 41,179<br>local bytes read: 343.6 KiB<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>1286.8 KiB (195.8 KiB, 1091.1 KiB, 1091.1 KiB (stage 1196.0: task 1621))<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>343.6 KiB (53.3 KiB, 290.3 KiB, 290.3 KiB (stage 1196.0: task 1621))"];
subgraph cluster12 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n8.6 s (2 ms, 7 ms, 6.9 s (stage 1196.0: task 1621))";
13 [labelType="html" label="<br><b>Project</b><br><br>"];
14 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 41,179"];
15 [labelType="html" label="<b>ColumnarToRow</b><br><br>number of output rows: 2,996,009<br>number of input batches: 732"];
}
16 [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 (1 ms, 6 ms, 883 ms (stage 1196.0: task 1621))<br>metadata time: 0 ms<br>size of files read: 150.9 MiB<br>number of output rows: 2,996,009"];
subgraph cluster17 {
isCluster="true";
label="WholeStageCodegen (5)\n \nduration: 0 ms";
18 [labelType="html" label="<br><b>Project</b><br><br>"];
19 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 83,244"];
}
20 [labelType="html" label="<b>Window</b><br><br>spill size: 0.0 B"];
subgraph cluster21 {
isCluster="true";
label="WholeStageCodegen (4)\n \nduration: 0 ms";
22 [labelType="html" label="<b>Sort</b><br><br>sort time: 11 ms<br>peak memory: 20.0 MiB<br>spill size: 0.0 B"];
}
23 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 780.9 KiB<br>number of coalesced partitions: 1"];
24 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 93,005<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>5 ms (2 ms, 2 ms, 2 ms (stage 1197.0: task 1627))<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: 93,005<br>local bytes read: 736.8 KiB<br>fetch wait time: 0 ms<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 2<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>2.8 MiB (1195.3 KiB, 1711.1 KiB, 1711.1 KiB (stage 1197.0: task 1627))<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>736.8 KiB (308.6 KiB, 428.2 KiB, 428.2 KiB (stage 1197.0: task 1627))"];
subgraph cluster25 {
isCluster="true";
label="WholeStageCodegen (2)\n \nduration: total (min, med, max (stageId: taskId))\n265 ms (112 ms, 153 ms, 153 ms (stage 1197.0: task 1627))";
26 [labelType="html" label="<br><b>Project</b><br><br>"];
27 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 93,005"];
}
28 [labelType="html" label="<b>Scan csv </b><br><br>number of output rows: 93,005<br>number of files read: 1<br>metadata time: 0 ms<br>size of files read: 6.4 MiB"];
2->0;
3->2;
5->3;
6->5;
7->6;
9->7;
10->9;
11->10;
13->11;
14->13;
15->14;
16->15;
18->7;
19->18;
20->19;
22->20;
23->22;
24->23;
26->24;
27->26;
28->27;
}
29
AdaptiveSparkPlan isFinalPlan=true
HashAggregate(keys=[], functions=[count(1)])
WholeStageCodegen (7)
Exchange SinglePartition, ENSURE_REQUIREMENTS, [plan_id=30333]
HashAggregate(keys=[], functions=[partial_count(1)])
Project
SortMergeJoin [COL_136DCAA3_2545_47C9_A61E_86ED7914066D#108272], [00_C_PASSAGE_PA_345648_COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#108565], LeftOuter
WholeStageCodegen (6)
Sort [COL_136DCAA3_2545_47C9_A61E_86ED7914066D#108272 ASC NULLS FIRST], false, 0
WholeStageCodegen (3)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_136DCAA3_2545_47C9_A61E_86ED7914066D#108272, 10), ENSURE_REQUIREMENTS, [plan_id=29947]
Project [COL_1CCAED33_3E69_435E_B522_DAE3B9E63F9D#108168 AS COL_136DCAA3_2545_47C9_A61E_86ED7914066D#108272]
Filter (str_if_with_rule((((str_remove_space(str_if_with_rule(((COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#108165 <=> B) OR (COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#108165 <=> C)), str_extract_middle(COL_B706A975_F287_4DC9_B631_A35735FE936F#108162, 78, 5), null), ONLY_ONE) <=> SAS) OR (str_remove_space(str_if_with_rule(((COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#108165 <=> B) OR (COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#108165 <=> C)), str_extract_middle(COL_B706A975_F287_4DC9_B631_A35735FE936F#108162, 78, 5), null), ONLY_ONE) <=> SUF)) OR (str_remove_space(str_if_with_rule(((COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#108165 <=> B) OR (COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#108165 <=> C)), str_extract_middle(COL_B706A975_F287_4DC9_B631_A35735FE936F#108162, 78, 5), null), ONLY_ONE) <=> SUN)), 1, 0) <=> 1)
ColumnarToRow
WholeStageCodegen (1)
FileScan parquet [COL_B706A975_F287_4DC9_B631_A35735FE936F#108162,COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38#108165,COL_1CCAED33_3E69_435E_B522_DAE3B9E63F9D#108168] Batched: true, DataFilters: [(str_if_with_rule((((str_remove_space(str_if_with_rule(((COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F3..., Format: Parquet, Location: InMemoryFileIndex(1 paths)[file:/data/output/cache/parquet/datablock/00_A_LIGNES_RSF_345253], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<COL_B706A975_F287_4DC9_B631_A35735FE936F:string,COL_1ADA21FB_DB08_4A1F_986E_E8E363B14F38:s...
Project [COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#108106 AS 00_C_PASSAGE_PA_345648_COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#108565]
Filter (COL_6B340AEB_6908_4A50_8AD6_FE561D33FBE0#108122 <=> 1)
WholeStageCodegen (5)
Window [row_number() windowspecdefinition(COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#108106, 1 DESC NULLS LAST, specifiedwindowframe(RowFrame, unboundedpreceding$(), currentrow$())) AS COL_6B340AEB_6908_4A50_8AD6_FE561D33FBE0#108122], [COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#108106], [1 DESC NULLS LAST]
Sort [COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#108106 ASC NULLS FIRST, 1 DESC NULLS LAST], false, 0
WholeStageCodegen (4)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#108106, 10), ENSURE_REQUIREMENTS, [plan_id=29963]
Project [Numéro Séjour#107985 AS COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#108106]
Filter (NOT CASE WHEN isnull(StartsWith(Numéro Séjour#107985, #)) THEN false ELSE StartsWith(Numéro Séjour#107985, #) END AND isnotnull(Numéro Séjour#107985))
WholeStageCodegen (2)
FileScan csv [Numéro Séjour#107985] Batched: false, DataFilters: [NOT CASE WHEN isnull(StartsWith(Numéro Séjour#107985, #)) THEN false ELSE StartsWith(Numéro Séjo..., Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/data/input/depot/csv/tmp/02_PASSAGE_PATI_344985/passage_pationt_..., PartitionFilters: [], PushedFilters: [IsNotNull(Numéro Séjour)], ReadSchema: struct<Numéro Séjour:string>