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>2 ms (0 ms, 1 ms, 1 ms (stage 16179.0: task 22352))<br>number of written files: 3<br>job commit time: 10 ms<br>number of output rows: 375,916<br>number of dynamic part: 0<br>written output: 973.0 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))\n599 ms (160 ms, 205 ms, 234 ms (stage 16179.0: task 22354))";
4 [labelType="html" label="<b>Sort</b><br><br>sort time total (min, med, max (stageId: taskId))<br>35 ms (10 ms, 11 ms, 14 ms (stage 16179.0: task 22354))<br>peak memory total (min, med, max (stageId: taskId))<br>60.0 MiB (20.0 MiB, 20.0 MiB, 20.0 MiB (stage 16179.0: task 22353))<br>spill size total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 16179.0: task 22353))"];
}
5 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 3<br>partition data size total (min, med, max (stageId: taskId))<br>3.6 MiB (1105.5 KiB, 1105.8 KiB, 1492.5 KiB (driver))<br>number of coalesced partitions: 3"];
6 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 375,916<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>10 ms (2 ms, 2 ms, 4 ms (stage 16174.0: task 22348))<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: 375,916<br>local bytes read total (min, med, max (stageId: taskId))<br>3.5 MiB (1049.6 KiB, 1056.6 KiB, 1461.9 KiB (stage 16179.0: task 22354))<br>fetch wait time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 16179.0: task 22353))<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 8<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>25.1 MiB (4.7 MiB, 6.7 MiB, 8.7 MiB (stage 16174.0: task 22348))<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>3.5 MiB (653.1 KiB, 924.2 KiB, 1306.3 KiB (stage 16174.0: task 22348))"];
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))\n169 ms (66 ms, 103 ms, 103 ms (stage 16174.0: task 22348))";
9 [labelType="html" label="<br><b>Project</b><br><br>"];
10 [labelType="html" label="<b>Generate</b><br><br>number of output rows: 275,604"];
11 [labelType="html" label="<br><b>Project</b><br><br>"];
12 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 91,868"];
}
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 16174.0: task 22348))"];
subgraph cluster14 {
isCluster="true";
label="WholeStageCodegen (4)\n \nduration: total (min, med, max (stageId: taskId))\n234 ms (97 ms, 137 ms, 137 ms (stage 16174.0: task 22348))";
15 [labelType="html" label="<b>Sort</b><br><br>sort time total (min, med, max (stageId: taskId))<br>14 ms (7 ms, 7 ms, 7 ms (stage 16174.0: task 22348))<br>peak memory total (min, med, max (stageId: taskId))<br>36.0 MiB (18.0 MiB, 18.0 MiB, 18.0 MiB (stage 16174.0: task 22348))<br>spill size total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 16174.0: task 22348))"];
}
16 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 693.8 KiB<br>number of coalesced partitions: 1"];
17 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 45,934<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: 91,868<br>local bytes read total (min, med, max (stageId: taskId))<br>1346.6 KiB (673.3 KiB, 673.3 KiB, 673.3 KiB (stage 16174.0: task 22348))<br>fetch wait time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 16174.0: task 22348))<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: 3.5 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: 673.3 KiB"];
subgraph cluster18 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: 224 ms";
19 [labelType="html" label="<br><b>Project</b><br><br>"];
20 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 45,934"];
}
21 [labelType="html" label="<b>Scan csv </b><br><br>number of output rows: 45,934<br>number of files read: 1<br>metadata time: 0 ms<br>size of files read: 2.7 MiB"];
subgraph cluster22 {
isCluster="true";
label="WholeStageCodegen (6)\n \nduration: total (min, med, max (stageId: taskId))\n593 ms (84 ms, 92 ms, 134 ms (stage 16174.0: task 22351))";
23 [labelType="html" label="<b>Sort</b><br><br>sort time total (min, med, max (stageId: taskId))<br>181 ms (25 ms, 30 ms, 37 ms (stage 16174.0: task 22351))<br>peak memory total (min, med, max (stageId: taskId))<br>112.0 MiB (18.0 MiB, 18.0 MiB, 20.0 MiB (stage 16174.0: task 22351))<br>spill size total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 16174.0: task 22349))"];
}
24 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 3<br>partition data size total (min, med, max (stageId: taskId))<br>3.7 MiB (1131.2 KiB, 1131.2 KiB, 1532.6 KiB (driver))<br>number of coalesced partitions: 3"];
25 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 238,114<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>10 ms (3 ms, 3 ms, 3 ms (stage 16166.0: task 22343))<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: 476,228<br>local bytes read total (min, med, max (stageId: taskId))<br>7.1 MiB (1050.4 KiB, 1102.8 KiB, 1494.5 KiB (stage 16174.0: task 22351))<br>fetch wait time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 16174.0: task 22349))<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 18<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>16.3 MiB (4.9 MiB, 4.9 MiB, 6.5 MiB (stage 16166.0: task 22343))<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>3.6 MiB (1095.9 KiB, 1096.9 KiB, 1454.9 KiB (stage 16166.0: task 22343))"];
subgraph cluster26 {
isCluster="true";
label="WholeStageCodegen (3)\n \nduration: total (min, med, max (stageId: taskId))\n625 ms (90 ms, 107 ms, 122 ms (stage 16164.0: task 22340))";
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>314 ms (46 ms, 48 ms, 68 ms (stage 16164.0: task 22340))<br>peak memory total (min, med, max (stageId: taskId))<br>99.0 MiB (16.3 MiB, 16.3 MiB, 17.0 MiB (stage 16164.0: task 22340))<br>number of output rows: 476,228<br>number of sort fallback tasks: 0<br>avg hash probes per key (min, med, max (stageId: taskId)):<br>(1.3, 1.3, 1.6 (stage 16164.0: task 22340))"];
}
28 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 3<br>partition data size total (min, med, max (stageId: taskId))<br>3.8 MiB (1159.5 KiB, 1159.5 KiB, 1536.2 KiB (driver))<br>number of coalesced partitions: 3"];
29 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 238,232<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>25 ms (2 ms, 2 ms, 3 ms (stage 16162.0: task 22329))<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: 476,464<br>local bytes read total (min, med, max (stageId: taskId))<br>7.2 MiB (1105.1 KiB, 1106.0 KiB, 1476.6 KiB (stage 16164.0: task 22340))<br>fetch wait time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 16164.0: task 22338))<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 60<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>16.4 MiB (1614.9 KiB, 1670.0 KiB, 1718.7 KiB (stage 16162.0: task 22328))<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>3.6 MiB (356.3 KiB, 368.1 KiB, 377.0 KiB (stage 16162.0: task 22328))"];
subgraph cluster30 {
isCluster="true";
label="WholeStageCodegen (2)\n \nduration: total (min, med, max (stageId: taskId))\n1.8 s (133 ms, 188 ms, 192 ms (stage 16162.0: task 22330))";
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>947 ms (83 ms, 98 ms, 100 ms (stage 16162.0: task 22333))<br>peak memory total (min, med, max (stageId: taskId))<br>162.5 MiB (16.3 MiB, 16.3 MiB, 16.3 MiB (stage 16162.0: task 22334))<br>number of output rows: 238,232<br>number of sort fallback tasks: 0<br>avg hash probes per key (min, med, max (stageId: taskId)):<br>(1, 1, 1 (stage 16162.0: task 22334))"];
32 [labelType="html" label="<br><b>Project</b><br><br>"];
33 [labelType="html" label="<b>Generate</b><br><br>number of output rows: 1,174,215"];
34 [labelType="html" label="<br><b>Project</b><br><br>"];
35 [labelType="html" label="<b>ColumnarToRow</b><br><br>number of output rows: 167,745<br>number of input batches: 49"];
}
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>63 ms (4 ms, 7 ms, 8 ms (stage 16162.0: task 22329))<br>metadata time: 0 ms<br>size of files read: 11.5 MiB<br>number of output rows: 167,745"];
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_176405, false, Parquet, [path=file:///data/output/cache/parquet/datablock/14_B_PASSAGE_PA_176405], 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#1261142 ASC NULLS FIRST, COL_59774853_4110_4672_B6E2_C0D5DE930914#1261143 ASC NULLS FIRST], true, 0
WholeStageCodegen (7)
AQEShuffleRead coalesced
Exchange rangepartitioning(COL_E5ADB260_1BF6_449C_8439_0A94CEE6956C#1261142 ASC NULLS FIRST, COL_59774853_4110_4672_B6E2_C0D5DE930914#1261143 ASC NULLS FIRST, 10), ENSURE_REQUIREMENTS, [plan_id=712059]
Union
Project [COL_DEB05435_3A84_4F8F_8CD2_6BE209A14FA8#1261102 AS COL_E5ADB260_1BF6_449C_8439_0A94CEE6956C#1261142, col0#1261111 AS COL_59774853_4110_4672_B6E2_C0D5DE930914#1261143, col1#1261112 AS COL_E58DD17C_E55F_4036_9FA9_A5365B045A1A#1261144]
Generate stack(3, 01-UF, COL_48FD2AAE_6F4D_4D43_BEE7_8A161203783C#1261103, 02-Transport, COL_E0699193_FC70_4F64_BAE6_B2F241857F3B#1261104, 03-CCMU, COL_630C2F1A_DB89_4A08_A2D2_179A10CC9FD2#1261105), [COL_DEB05435_3A84_4F8F_8CD2_6BE209A14FA8#1261102], false, [col0#1261111, col1#1261112]
Project [COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#1260610 AS COL_DEB05435_3A84_4F8F_8CD2_6BE209A14FA8#1261102, COL_E82CFB57_01EB_4E90_836D_4D6F4CA131FE#1260611 AS COL_48FD2AAE_6F4D_4D43_BEE7_8A161203783C#1261103, COL_E1010A22_775B_43B4_B8CA_4603C0801D28#1260612 AS COL_E0699193_FC70_4F64_BAE6_B2F241857F3B#1261104, COL_6A6D32F5_2B4E_4DF6_A459_B248882F909D#1260613 AS COL_630C2F1A_DB89_4A08_A2D2_179A10CC9FD2#1261105]
Filter (COL_6B340AEB_6908_4A50_8AD6_FE561D33FBE0#1260626 <=> 1)
WholeStageCodegen (5)
Window [row_number() windowspecdefinition(COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#1260610, 1 DESC NULLS LAST, specifiedwindowframe(RowFrame, unboundedpreceding$(), currentrow$())) AS COL_6B340AEB_6908_4A50_8AD6_FE561D33FBE0#1260626], [COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#1260610], [1 DESC NULLS LAST]
Sort [COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#1260610 ASC NULLS FIRST, 1 DESC NULLS LAST], false, 0
WholeStageCodegen (4)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#1260610, 10), ENSURE_REQUIREMENTS, [plan_id=711786]
Project [Numéro Séjour#1260494 AS COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#1260610, UF#1260495 AS COL_E82CFB57_01EB_4E90_836D_4D6F4CA131FE#1260611, str_remove_space(Transport admission#1260498, ONLY_ONE) AS COL_E1010A22_775B_43B4_B8CA_4603C0801D28#1260612, str_remove_space(str_list_get(str_extract_by_regex(Niveau CCMU#1260499, [+\d]+), 0), ALL) AS COL_6A6D32F5_2B4E_4DF6_A459_B248882F909D#1260613]
Filter NOT CASE WHEN isnull(StartsWith(Numéro Séjour#1260494, #)) THEN false ELSE StartsWith(Numéro Séjour#1260494, #) END
WholeStageCodegen (1)
FileScan csv [Numéro Séjour#1260494,UF#1260495,Transport admission#1260498,Niveau CCMU#1260499] Batched: false, DataFilters: [NOT CASE WHEN isnull(StartsWith(Numéro Séjour#1260494, #)) THEN false ELSE StartsWith(Numéro Séj..., Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/data/input/depot/csv/tmp/02_PASSAGE_PATI_175675/passage_patient_..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<Numéro Séjour:string,UF:string,Transport admission:string,Niveau CCMU:string>
Sort [COL_DC1A3ABF_ADFC_4208_8B24_35ED54CC87DF#1261042 ASC NULLS FIRST, COL_EA9AE57C_DE84_4BBE_9131_053814B337F4#1261043 ASC NULLS FIRST], true, 0
WholeStageCodegen (6)
AQEShuffleRead coalesced
Exchange rangepartitioning(COL_DC1A3ABF_ADFC_4208_8B24_35ED54CC87DF#1261042 ASC NULLS FIRST, COL_EA9AE57C_DE84_4BBE_9131_053814B337F4#1261043 ASC NULLS FIRST, 10), ENSURE_REQUIREMENTS, [plan_id=711912]
HashAggregate(keys=[COL_8D7490B1_ED4B_4A07_9680_ECC66DF49E37#1261036, COL_7F6B8B23_E564_4B4E_8794_0FC7CE59D60B#1261037, COL_B6440F86_8BD4_4AFD_8640_45556688ABB9#1261038], functions=[])
WholeStageCodegen (3)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_8D7490B1_ED4B_4A07_9680_ECC66DF49E37#1261036, COL_7F6B8B23_E564_4B4E_8794_0FC7CE59D60B#1261037, COL_B6440F86_8BD4_4AFD_8640_45556688ABB9#1261038, 10), ENSURE_REQUIREMENTS, [plan_id=711815]
HashAggregate(keys=[COL_8D7490B1_ED4B_4A07_9680_ECC66DF49E37#1261036, COL_7F6B8B23_E564_4B4E_8794_0FC7CE59D60B#1261037, COL_B6440F86_8BD4_4AFD_8640_45556688ABB9#1261038], functions=[])
Project [COL_BC7CB40E_B2CA_42C4_94A5_B6AA996E14DC#1260997 AS COL_8D7490B1_ED4B_4A07_9680_ECC66DF49E37#1261036, col0#1261014 AS COL_7F6B8B23_E564_4B4E_8794_0FC7CE59D60B#1261037, col1#1261015 AS COL_B6440F86_8BD4_4AFD_8640_45556688ABB9#1261038]
Generate stack(7, 04-Date Naissance, COL_95E23023_63AA_4AB8_A60F_50D45234CFDD#1260998, 05-Date Entree, COL_78B23D10_75E8_415E_A3C0_8AB5C826A837#1260999, 06-Date Sortie, COL_885784F8_1772_40E3_89B6_6ACE1FAB6407#1261000, 07-Fides, COL_32AA235F_1BB1_4047_B8BA_AD2E9197AD1F#1261001, 08-Facturable AM, COL_3BBA8558_C3D5_4921_93AE_D7C9E273B39D#1261002, 09-Justif Exo, COL_35788C71_38EE_4A08_B685_AAC68457246A#1261003, 10-Nature Ass, COL_6EC95BD9_A121_4728_BE4A_49B7EA2976F2#1261004), [COL_BC7CB40E_B2CA_42C4_94A5_B6AA996E14DC#1260997], false, [col0#1261014, col1#1261015]
Project [COL_F76265AB_8748_4114_92B4_00E37DE25D34#1260675 AS COL_BC7CB40E_B2CA_42C4_94A5_B6AA996E14DC#1260997, COL_9262BBED_C393_416D_B38C_8F1458965BA7#1260674 AS COL_95E23023_63AA_4AB8_A60F_50D45234CFDD#1260998, COL_96E2282E_0771_460E_8BDB_D11261BD9020#1260676 AS COL_78B23D10_75E8_415E_A3C0_8AB5C826A837#1260999, COL_12028397_66B1_4E3C_BBDB_64537606E7DE#1260677 AS COL_885784F8_1772_40E3_89B6_6ACE1FAB6407#1261000, COL_0521CAB9_7617_4F31_948E_95DCA16387D7#1260672 AS COL_32AA235F_1BB1_4047_B8BA_AD2E9197AD1F#1261001, COL_1DACB81E_AFA5_4BB8_83D7_57DE8B8062B7#1260673 AS COL_3BBA8558_C3D5_4921_93AE_D7C9E273B39D#1261002, COL_4473F770_A575_4100_97F6_8190F900749A#1260681 AS COL_35788C71_38EE_4A08_B685_AAC68457246A#1261003, COL_715B3479_EAD2_422C_BF5C_7B020197D946#1260682 AS COL_6EC95BD9_A121_4728_BE4A_49B7EA2976F2#1261004]
ColumnarToRow
WholeStageCodegen (2)
FileScan parquet [COL_0521CAB9_7617_4F31_948E_95DCA16387D7#1260672,COL_1DACB81E_AFA5_4BB8_83D7_57DE8B8062B7#1260673,COL_9262BBED_C393_416D_B38C_8F1458965BA7#1260674,COL_F76265AB_8748_4114_92B4_00E37DE25D34#1260675,COL_96E2282E_0771_460E_8BDB_D11261BD9020#1260676,COL_12028397_66B1_4E3C_BBDB_64537606E7DE#1260677,COL_4473F770_A575_4100_97F6_8190F900749A#1260681,COL_715B3479_EAD2_422C_BF5C_7B020197D946#1260682] Batched: true, DataFilters: [], Format: Parquet, Location: InMemoryFileIndex(1 paths)[file:/data/output/cache/parquet/datablock/02_A_ELIGIBLE_176076], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<COL_0521CAB9_7617_4F31_948E_95DCA16387D7:string,COL_1DACB81E_AFA5_4BB8_83D7_57DE8B8062B7:s...