digraph G {
0 [labelType="html" label="<br><b>AdaptiveSparkPlan</b><br><br>"];
1 [labelType="html" label="<b>Execute InsertIntoHadoopFsRelationCommand</b><br><br>task commit time total (min, med, max (stageId: taskId))<br>1 ms (0 ms, 0 ms, 1 ms (stage 14158.0: task 15814))<br>number of written files: 5<br>job commit time: 17 ms<br>number of output rows: 538,288<br>number of dynamic part: 0<br>written output: 1264.6 KiB"];
2 [labelType="html" label="<br><b>WriteFiles</b><br><br>"];
subgraph cluster3 {
isCluster="true";
label="WholeStageCodegen (7)\n \nduration: total (min, med, max (stageId: taskId))\n1.1 s (184 ms, 231 ms, 246 ms (stage 14158.0: task 15817))";
4 [labelType="html" label="<b>Sort</b><br><br>sort time total (min, med, max (stageId: taskId))<br>81 ms (10 ms, 13 ms, 30 ms (stage 14158.0: task 15817))<br>peak memory total (min, med, max (stageId: taskId))<br>100.0 MiB (20.0 MiB, 20.0 MiB, 20.0 MiB (stage 14158.0: task 15818))<br>spill size total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 14158.0: task 15818))"];
}
5 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 5<br>partition data size total (min, med, max (stageId: taskId))<br>5.8 MiB (1134.6 KiB, 1175.5 KiB, 1224.6 KiB (driver))<br>number of coalesced partitions: 5"];
6 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 538,288<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>18 ms (2 ms, 2 ms, 6 ms (stage 14153.0: task 15808))<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: 538,288<br>local bytes read total (min, med, max (stageId: taskId))<br>5.4 MiB (1060.1 KiB, 1109.7 KiB, 1168.2 KiB (stage 14158.0: task 15815))<br>fetch wait time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 14158.0: task 15818))<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 14<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>36.8 MiB (4.6 MiB, 4.9 MiB, 12.7 MiB (stage 14153.0: task 15808))<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>5.4 MiB (718.3 KiB, 785.7 KiB, 1762.4 KiB (stage 14153.0: task 15808))"];
7 [labelType="html" label="<br><b>Union</b><br><br>"];
subgraph cluster8 {
isCluster="true";
label="WholeStageCodegen (5)\n \nduration: total (min, med, max (stageId: taskId))\n251 ms (94 ms, 157 ms, 157 ms (stage 14153.0: task 15808))";
9 [labelType="html" label="<br><b>Project</b><br><br>"];
10 [labelType="html" label="<b>Generate</b><br><br>number of output rows: 374,364"];
11 [labelType="html" label="<br><b>Project</b><br><br>"];
12 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 124,788"];
}
13 [labelType="html" label="<b>Window</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 14149.0: task 15802))"];
subgraph cluster14 {
isCluster="true";
label="WholeStageCodegen (4)\n \nduration: total (min, med, max (stageId: taskId))\n365 ms (150 ms, 215 ms, 215 ms (stage 14153.0: task 15808))";
15 [labelType="html" label="<b>Sort</b><br><br>sort time total (min, med, max (stageId: taskId))<br>58 ms (27 ms, 31 ms, 31 ms (stage 14153.0: task 15808))<br>peak memory total (min, med, max (stageId: taskId))<br>36.0 MiB (18.0 MiB, 18.0 MiB, 18.0 MiB (stage 14149.0: task 15802))<br>spill size total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 14149.0: task 15802))"];
}
16 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 995.9 KiB<br>number of coalesced partitions: 1"];
17 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 62,394<br>local merged chunks fetched: 0<br>shuffle write time: 3 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: 124,788<br>local bytes read total (min, med, max (stageId: taskId))<br>1877.1 KiB (938.6 KiB, 938.6 KiB, 938.6 KiB (stage 14149.0: task 15802))<br>fetch wait time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 14149.0: task 15802))<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: 5.6 MiB<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: 938.6 KiB"];
subgraph cluster18 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: 285 ms";
19 [labelType="html" label="<br><b>Project</b><br><br>"];
20 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 62,394"];
}
21 [labelType="html" label="<b>Scan csv </b><br><br>number of output rows: 62,394<br>number of files read: 1<br>metadata time: 0 ms<br>size of files read: 3.5 MiB"];
subgraph cluster22 {
isCluster="true";
label="WholeStageCodegen (6)\n \nduration: total (min, med, max (stageId: taskId))\n1.2 s (101 ms, 117 ms, 146 ms (stage 14149.0: task 15804))";
23 [labelType="html" label="<b>Sort</b><br><br>sort time total (min, med, max (stageId: taskId))<br>436 ms (37 ms, 42 ms, 64 ms (stage 14149.0: task 15804))<br>peak memory total (min, med, max (stageId: taskId))<br>180.0 MiB (18.0 MiB, 18.0 MiB, 18.0 MiB (stage 14149.0: task 15805))<br>spill size total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 14149.0: task 15805))"];
}
24 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 5<br>partition data size total (min, med, max (stageId: taskId))<br>5.7 MiB (1095.5 KiB, 1205.0 KiB, 1210.5 KiB (driver))<br>number of coalesced partitions: 5"];
25 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 351,106<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>17 ms (3 ms, 3 ms, 3 ms (stage 14145.0: task 15799))<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: 702,212<br>local bytes read total (min, med, max (stageId: taskId))<br>10.8 MiB (1041.8 KiB, 1129.2 KiB, 1150.4 KiB (stage 14149.0: task 15803))<br>fetch wait time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 14149.0: task 15805))<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 50<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>24.1 MiB (4.8 MiB, 4.8 MiB, 4.8 MiB (stage 14145.0: task 15800))<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>5.4 MiB (1103.4 KiB, 1109.9 KiB, 1117.4 KiB (stage 14145.0: task 15800))"];
subgraph cluster26 {
isCluster="true";
label="WholeStageCodegen (3)\n \nduration: total (min, med, max (stageId: taskId))\n1.4 s (87 ms, 172 ms, 173 ms (stage 14143.0: task 15794))";
27 [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>732 ms (45 ms, 85 ms, 94 ms (stage 14143.0: task 15792))<br>peak memory total (min, med, max (stageId: taskId))<br>162.5 MiB (16.3 MiB, 16.3 MiB, 16.3 MiB (stage 14143.0: task 15795))<br>number of output rows: 702,212<br>number of sort fallback tasks: 0<br>avg hash probes per key (min, med, max (stageId: taskId)):<br>(1.3, 1.3, 1.3 (stage 14143.0: task 15795))"];
}
28 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 5<br>partition data size total (min, med, max (stageId: taskId))<br>5.7 MiB (1146.8 KiB, 1163.7 KiB, 1174.9 KiB (driver))<br>number of coalesced partitions: 5"];
29 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 351,106<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>26 ms (2 ms, 2 ms, 3 ms (stage 14141.0: task 15785))<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: 702,212<br>local bytes read total (min, med, max (stageId: taskId))<br>10.9 MiB (1106.0 KiB, 1112.1 KiB, 1121.2 KiB (stage 14143.0: task 15795))<br>fetch wait time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 14143.0: task 15795))<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 100<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>24.1 MiB (2.4 MiB, 2.4 MiB, 2.5 MiB (stage 14141.0: task 15782))<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>5.4 MiB (549.0 KiB, 557.9 KiB, 569.2 KiB (stage 14141.0: task 15782))"];
subgraph cluster30 {
isCluster="true";
label="WholeStageCodegen (2)\n \nduration: total (min, med, max (stageId: taskId))\n21.6 s (2.1 s, 2.2 s, 2.2 s (stage 14141.0: task 15782))";
31 [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>21.2 s (2.1 s, 2.1 s, 2.2 s (stage 14141.0: task 15782))<br>peak memory total (min, med, max (stageId: taskId))<br>162.5 MiB (16.3 MiB, 16.3 MiB, 16.3 MiB (stage 14141.0: task 15790))<br>number of output rows: 351,106<br>number of sort fallback tasks: 0<br>avg hash probes per key (min, med, max (stageId: taskId)):<br>(1, 1, 1 (stage 14141.0: task 15790))"];
32 [labelType="html" label="<br><b>Project</b><br><br>"];
33 [labelType="html" label="<b>Generate</b><br><br>number of output rows: 2,450,945"];
34 [labelType="html" label="<br><b>Project</b><br><br>"];
35 [labelType="html" label="<b>ColumnarToRow</b><br><br>number of output rows: 350,135<br>number of input batches: 90"];
}
36 [labelType="html" label="<b>Scan parquet </b><br><br>number of files read: 10<br>scan time total (min, med, max (stageId: taskId))<br>71 ms (4 ms, 7 ms, 9 ms (stage 14141.0: task 15783))<br>metadata time: 0 ms<br>size of files read: 23.0 MiB<br>number of output rows: 350,135"];
1->0;
2->1;
4->2;
5->4;
6->5;
7->6;
9->7;
10->9;
11->10;
12->11;
13->12;
15->13;
16->15;
17->16;
19->17;
20->19;
21->20;
23->7;
24->23;
25->24;
27->25;
28->27;
29->28;
31->29;
32->31;
33->32;
34->33;
35->34;
36->35;
}
37
AdaptiveSparkPlan isFinalPlan=true
Execute InsertIntoHadoopFsRelationCommand file:/data/output/cache/parquet/datablock/14_B_PASSAGE_PA_213400, false, Parquet, [path=file:///data/output/cache/parquet/datablock/14_B_PASSAGE_PA_213400], Overwrite, [COL_E5ADB260_1BF6_449C_8439_0A94CEE6956C, COL_59774853_4110_4672_B6E2_C0D5DE930914, COL_E58DD17C_E55F_4036_9FA9_A5365B045A1A]
WriteFiles
Sort [COL_E5ADB260_1BF6_449C_8439_0A94CEE6956C#1214662 ASC NULLS FIRST, COL_59774853_4110_4672_B6E2_C0D5DE930914#1214663 ASC NULLS FIRST], true, 0
WholeStageCodegen (7)
AQEShuffleRead coalesced
Exchange rangepartitioning(COL_E5ADB260_1BF6_449C_8439_0A94CEE6956C#1214662 ASC NULLS FIRST, COL_59774853_4110_4672_B6E2_C0D5DE930914#1214663 ASC NULLS FIRST, 10), ENSURE_REQUIREMENTS, [plan_id=735017]
Union
Project [COL_DEB05435_3A84_4F8F_8CD2_6BE209A14FA8#1214622 AS COL_E5ADB260_1BF6_449C_8439_0A94CEE6956C#1214662, col0#1214631 AS COL_59774853_4110_4672_B6E2_C0D5DE930914#1214663, col1#1214632 AS COL_E58DD17C_E55F_4036_9FA9_A5365B045A1A#1214664]
Generate stack(3, 01-UF, COL_48FD2AAE_6F4D_4D43_BEE7_8A161203783C#1214623, 02-Transport, COL_E0699193_FC70_4F64_BAE6_B2F241857F3B#1214624, 03-CCMU, COL_630C2F1A_DB89_4A08_A2D2_179A10CC9FD2#1214625), [COL_DEB05435_3A84_4F8F_8CD2_6BE209A14FA8#1214622], false, [col0#1214631, col1#1214632]
Project [COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#1214135 AS COL_DEB05435_3A84_4F8F_8CD2_6BE209A14FA8#1214622, COL_E82CFB57_01EB_4E90_836D_4D6F4CA131FE#1214136 AS COL_48FD2AAE_6F4D_4D43_BEE7_8A161203783C#1214623, COL_E1010A22_775B_43B4_B8CA_4603C0801D28#1214137 AS COL_E0699193_FC70_4F64_BAE6_B2F241857F3B#1214624, COL_6A6D32F5_2B4E_4DF6_A459_B248882F909D#1214138 AS COL_630C2F1A_DB89_4A08_A2D2_179A10CC9FD2#1214625]
Filter (COL_6B340AEB_6908_4A50_8AD6_FE561D33FBE0#1214151 <=> 1)
WholeStageCodegen (5)
Window [row_number() windowspecdefinition(COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#1214135, 1 DESC NULLS LAST, specifiedwindowframe(RowFrame, unboundedpreceding$(), currentrow$())) AS COL_6B340AEB_6908_4A50_8AD6_FE561D33FBE0#1214151], [COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#1214135], [1 DESC NULLS LAST]
Sort [COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#1214135 ASC NULLS FIRST, 1 DESC NULLS LAST], false, 0
WholeStageCodegen (4)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#1214135, 10), ENSURE_REQUIREMENTS, [plan_id=734742]
Project [Numéro Séjour#1214023 AS COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#1214135, UF#1214024 AS COL_E82CFB57_01EB_4E90_836D_4D6F4CA131FE#1214136, str_remove_space(Transport admission#1214028, ONLY_ONE) AS COL_E1010A22_775B_43B4_B8CA_4603C0801D28#1214137, str_remove_space(str_list_get(str_extract_by_regex(Niveau CCMU#1214025, [+\d]+), 0), ALL) AS COL_6A6D32F5_2B4E_4DF6_A459_B248882F909D#1214138]
Filter NOT CASE WHEN isnull(StartsWith(Numéro Séjour#1214023, #)) THEN false ELSE StartsWith(Numéro Séjour#1214023, #) END
WholeStageCodegen (1)
FileScan csv [Numéro Séjour#1214023,UF#1214024,Niveau CCMU#1214025,Transport admission#1214028] Batched: false, DataFilters: [NOT CASE WHEN isnull(StartsWith(Numéro Séjour#1214023, #)) THEN false ELSE StartsWith(Numéro Séj..., Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/data/input/depot/csv/tmp/02_PASSAGE_PATI_212789/passage_Patient_..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<Numéro Séjour:string,UF:string,Niveau CCMU:string,Transport admission:string>
Sort [COL_DC1A3ABF_ADFC_4208_8B24_35ED54CC87DF#1214562 ASC NULLS FIRST, COL_EA9AE57C_DE84_4BBE_9131_053814B337F4#1214563 ASC NULLS FIRST], true, 0
WholeStageCodegen (6)
AQEShuffleRead coalesced
Exchange rangepartitioning(COL_DC1A3ABF_ADFC_4208_8B24_35ED54CC87DF#1214562 ASC NULLS FIRST, COL_EA9AE57C_DE84_4BBE_9131_053814B337F4#1214563 ASC NULLS FIRST, 10), ENSURE_REQUIREMENTS, [plan_id=734915]
HashAggregate(keys=[COL_8D7490B1_ED4B_4A07_9680_ECC66DF49E37#1214556, COL_7F6B8B23_E564_4B4E_8794_0FC7CE59D60B#1214557, COL_B6440F86_8BD4_4AFD_8640_45556688ABB9#1214558], functions=[])
WholeStageCodegen (3)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_8D7490B1_ED4B_4A07_9680_ECC66DF49E37#1214556, COL_7F6B8B23_E564_4B4E_8794_0FC7CE59D60B#1214557, COL_B6440F86_8BD4_4AFD_8640_45556688ABB9#1214558, 10), ENSURE_REQUIREMENTS, [plan_id=734771]
HashAggregate(keys=[COL_8D7490B1_ED4B_4A07_9680_ECC66DF49E37#1214556, COL_7F6B8B23_E564_4B4E_8794_0FC7CE59D60B#1214557, COL_B6440F86_8BD4_4AFD_8640_45556688ABB9#1214558], functions=[])
Project [COL_BC7CB40E_B2CA_42C4_94A5_B6AA996E14DC#1214517 AS COL_8D7490B1_ED4B_4A07_9680_ECC66DF49E37#1214556, col0#1214534 AS COL_7F6B8B23_E564_4B4E_8794_0FC7CE59D60B#1214557, col1#1214535 AS COL_B6440F86_8BD4_4AFD_8640_45556688ABB9#1214558]
Generate stack(7, 04-Date Naissance, COL_95E23023_63AA_4AB8_A60F_50D45234CFDD#1214518, 05-Date Entree, COL_78B23D10_75E8_415E_A3C0_8AB5C826A837#1214519, 06-Date Sortie, COL_885784F8_1772_40E3_89B6_6ACE1FAB6407#1214520, 07-Fides, COL_32AA235F_1BB1_4047_B8BA_AD2E9197AD1F#1214521, 08-Facturable AM, COL_3BBA8558_C3D5_4921_93AE_D7C9E273B39D#1214522, 09-Justif Exo, COL_35788C71_38EE_4A08_B685_AAC68457246A#1214523, 10-Nature Ass, COL_6EC95BD9_A121_4728_BE4A_49B7EA2976F2#1214524), [COL_BC7CB40E_B2CA_42C4_94A5_B6AA996E14DC#1214517], false, [col0#1214534, col1#1214535]
Project [COL_F76265AB_8748_4114_92B4_00E37DE25D34#1214199 AS COL_BC7CB40E_B2CA_42C4_94A5_B6AA996E14DC#1214517, COL_9262BBED_C393_416D_B38C_8F1458965BA7#1214198 AS COL_95E23023_63AA_4AB8_A60F_50D45234CFDD#1214518, COL_96E2282E_0771_460E_8BDB_D11261BD9020#1214200 AS COL_78B23D10_75E8_415E_A3C0_8AB5C826A837#1214519, COL_12028397_66B1_4E3C_BBDB_64537606E7DE#1214201 AS COL_885784F8_1772_40E3_89B6_6ACE1FAB6407#1214520, COL_0521CAB9_7617_4F31_948E_95DCA16387D7#1214196 AS COL_32AA235F_1BB1_4047_B8BA_AD2E9197AD1F#1214521, COL_1DACB81E_AFA5_4BB8_83D7_57DE8B8062B7#1214197 AS COL_3BBA8558_C3D5_4921_93AE_D7C9E273B39D#1214522, COL_4473F770_A575_4100_97F6_8190F900749A#1214205 AS COL_35788C71_38EE_4A08_B685_AAC68457246A#1214523, COL_715B3479_EAD2_422C_BF5C_7B020197D946#1214206 AS COL_6EC95BD9_A121_4728_BE4A_49B7EA2976F2#1214524]
ColumnarToRow
WholeStageCodegen (2)
FileScan parquet [COL_0521CAB9_7617_4F31_948E_95DCA16387D7#1214196,COL_1DACB81E_AFA5_4BB8_83D7_57DE8B8062B7#1214197,COL_9262BBED_C393_416D_B38C_8F1458965BA7#1214198,COL_F76265AB_8748_4114_92B4_00E37DE25D34#1214199,COL_96E2282E_0771_460E_8BDB_D11261BD9020#1214200,COL_12028397_66B1_4E3C_BBDB_64537606E7DE#1214201,COL_4473F770_A575_4100_97F6_8190F900749A#1214205,COL_715B3479_EAD2_422C_BF5C_7B020197D946#1214206] Batched: true, DataFilters: [], Format: Parquet, Location: InMemoryFileIndex(1 paths)[file:/data/output/cache/parquet/datablock/02_A_ELIGIBLE_212978], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<COL_0521CAB9_7617_4F31_948E_95DCA16387D7:string,COL_1DACB81E_AFA5_4BB8_83D7_57DE8B8062B7:s...