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>3 ms (0 ms, 1 ms, 2 ms (stage 12927.0: task 17075))<br>number of written files: 3<br>job commit time: 14 ms<br>number of output rows: 488,353<br>number of dynamic part: 0<br>written output: 1333.1 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))\n789 ms (228 ms, 242 ms, 319 ms (stage 12927.0: task 17076))";
4 [labelType="html" label="<b>Sort</b><br><br>sort time total (min, med, max (stageId: taskId))<br>55 ms (15 ms, 16 ms, 24 ms (stage 12927.0: task 17076))<br>peak memory total (min, med, max (stageId: taskId))<br>64.0 MiB (20.0 MiB, 20.0 MiB, 24.0 MiB (stage 12927.0: task 17076))<br>spill size total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 12927.0: task 17075))"];
}
5 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 3<br>partition data size total (min, med, max (stageId: taskId))<br>4.8 MiB (1423.9 KiB, 1452.0 KiB, 1997.2 KiB (driver))<br>number of coalesced partitions: 3"];
6 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 488,353<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>13 ms (2 ms, 2 ms, 5 ms (stage 12922.0: task 17070))<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: 488,353<br>local bytes read total (min, med, max (stageId: taskId))<br>4.6 MiB (1363.3 KiB, 1379.6 KiB, 1950.6 KiB (stage 12927.0: task 17076))<br>fetch wait time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 12927.0: task 17075))<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>33.2 MiB (5.3 MiB, 7.5 MiB, 14.8 MiB (stage 12922.0: task 17070))<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>4.6 MiB (740.9 KiB, 1044.1 KiB, 2.1 MiB (stage 12922.0: task 17070))"];
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))\n267 ms (101 ms, 166 ms, 166 ms (stage 12922.0: task 17070))";
9 [labelType="html" label="<br><b>Project</b><br><br>"];
10 [labelType="html" label="<b>Generate</b><br><br>number of output rows: 438,984"];
11 [labelType="html" label="<br><b>Project</b><br><br>"];
12 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 146,328"];
}
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 12922.0: task 17070))"];
subgraph cluster14 {
isCluster="true";
label="WholeStageCodegen (4)\n \nduration: total (min, med, max (stageId: taskId))\n381 ms (161 ms, 220 ms, 220 ms (stage 12922.0: task 17070))";
15 [labelType="html" label="<b>Sort</b><br><br>sort time total (min, med, max (stageId: taskId))<br>56 ms (28 ms, 28 ms, 28 ms (stage 12922.0: task 17070))<br>peak memory total (min, med, max (stageId: taskId))<br>36.0 MiB (18.0 MiB, 18.0 MiB, 18.0 MiB (stage 12922.0: task 17070))<br>spill size total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 12922.0: task 17070))"];
}
16 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 1<br>partition data size: 1101.0 KiB<br>number of coalesced partitions: 1"];
17 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 73,164<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>6 ms (2 ms, 3 ms, 3 ms (stage 12909.0: task 17048))<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: 146,328<br>local bytes read total (min, med, max (stageId: taskId))<br>2.1 MiB (1056.3 KiB, 1056.3 KiB, 1056.3 KiB (stage 12922.0: task 17070))<br>fetch wait time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 12922.0: task 17070))<br>remote bytes read: 0.0 B<br>merged fetch fallback count: 0<br>local blocks read: 4<br>remote merged chunks fetched: 0<br>remote blocks read: 0<br>data size total (min, med, max (stageId: taskId))<br>6.4 MiB (1631.1 KiB, 4.8 MiB, 4.8 MiB (stage 12909.0: task 17048))<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>1056.3 KiB (263.2 KiB, 793.2 KiB, 793.2 KiB (stage 12909.0: task 17048))"];
subgraph cluster18 {
isCluster="true";
label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n498 ms (210 ms, 288 ms, 288 ms (stage 12909.0: task 17048))";
19 [labelType="html" label="<br><b>Project</b><br><br>"];
20 [labelType="html" label="<b>Filter</b><br><br>number of output rows: 73,164"];
}
21 [labelType="html" label="<b>Scan csv </b><br><br>number of output rows: 73,164<br>number of files read: 1<br>metadata time: 0 ms<br>size of files read: 5.3 MiB"];
subgraph cluster22 {
isCluster="true";
label="WholeStageCodegen (6)\n \nduration: total (min, med, max (stageId: taskId))\n685 ms (91 ms, 112 ms, 144 ms (stage 12922.0: task 17073))";
23 [labelType="html" label="<b>Sort</b><br><br>sort time total (min, med, max (stageId: taskId))<br>264 ms (33 ms, 42 ms, 61 ms (stage 12918.0: task 17069))<br>peak memory total (min, med, max (stageId: taskId))<br>112.0 MiB (18.0 MiB, 18.0 MiB, 20.0 MiB (stage 12922.0: task 17073))<br>spill size total (min, med, max (stageId: taskId))<br>0.0 B (0.0 B, 0.0 B, 0.0 B (stage 12922.0: task 17072))"];
}
24 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 3<br>partition data size total (min, med, max (stageId: taskId))<br>4.0 MiB (1167.7 KiB, 1233.4 KiB, 1685.9 KiB (driver))<br>number of coalesced partitions: 3"];
25 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 268,861<br>local merged chunks fetched: 0<br>shuffle write time total (min, med, max (stageId: taskId))<br>11 ms (3 ms, 3 ms, 4 ms (stage 12914.0: task 17065))<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: 537,722<br>local bytes read total (min, med, max (stageId: taskId))<br>7.5 MiB (1107.2 KiB, 1162.9 KiB, 1570.3 KiB (stage 12922.0: task 17073))<br>fetch wait time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 12922.0: task 17072))<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>18.5 MiB (5.5 MiB, 5.6 MiB, 7.4 MiB (stage 12914.0: task 17065))<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>3.8 MiB (1152.5 KiB, 1156.4 KiB, 1531.3 KiB (stage 12914.0: task 17065))"];
subgraph cluster26 {
isCluster="true";
label="WholeStageCodegen (3)\n \nduration: total (min, med, max (stageId: taskId))\n766 ms (113 ms, 124 ms, 149 ms (stage 12914.0: task 17065))";
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>420 ms (57 ms, 63 ms, 95 ms (stage 12912.0: task 17062))<br>peak memory total (min, med, max (stageId: taskId))<br>102.0 MiB (16.5 MiB, 16.5 MiB, 18.0 MiB (stage 12914.0: task 17065))<br>number of output rows: 537,722<br>number of sort fallback tasks: 0<br>avg hash probes per key (min, med, max (stageId: taskId)):<br>(1.5, 1.5, 1.5 (stage 12914.0: task 17064))"];
}
28 [labelType="html" label="<b>AQEShuffleRead</b><br><br>number of partitions: 3<br>partition data size total (min, med, max (stageId: taskId))<br>4.0 MiB (1209.5 KiB, 1236.3 KiB, 1624.1 KiB (driver))<br>number of coalesced partitions: 3"];
29 [labelType="html" label="<b>Exchange</b><br><br>shuffle records written: 270,628<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 12910.0: task 17054))<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: 541,256<br>local bytes read total (min, med, max (stageId: taskId))<br>7.6 MiB (1158.8 KiB, 1163.7 KiB, 1546.7 KiB (stage 12914.0: task 17065))<br>fetch wait time total (min, med, max (stageId: taskId))<br>0 ms (0 ms, 0 ms, 0 ms (stage 12914.0: task 17064))<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>18.6 MiB (1883.6 KiB, 1903.8 KiB, 1931.3 KiB (stage 12910.0: task 17050))<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>3.8 MiB (382.4 KiB, 387.3 KiB, 391.9 KiB (stage 12910.0: task 17050))"];
subgraph cluster30 {
isCluster="true";
label="WholeStageCodegen (2)\n \nduration: total (min, med, max (stageId: taskId))\n2.6 s (236 ms, 264 ms, 271 ms (stage 12910.0: task 17050))";
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>2.0 s (182 ms, 203 ms, 209 ms (stage 12910.0: task 17054))<br>peak memory total (min, med, max (stageId: taskId))<br>162.5 MiB (16.3 MiB, 16.3 MiB, 16.3 MiB (stage 12910.0: task 17056))<br>number of output rows: 270,628<br>number of sort fallback tasks: 0<br>avg hash probes per key (min, med, max (stageId: taskId)):<br>(1, 1, 1 (stage 12910.0: task 17056))"];
32 [labelType="html" label="<br><b>Project</b><br><br>"];
33 [labelType="html" label="<b>Generate</b><br><br>number of output rows: 1,410,255"];
34 [labelType="html" label="<br><b>Project</b><br><br>"];
35 [labelType="html" label="<b>ColumnarToRow</b><br><br>number of output rows: 201,465<br>number of input batches: 50"];
}
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>73 ms (5 ms, 8 ms, 9 ms (stage 12910.0: task 17057))<br>metadata time: 0 ms<br>size of files read: 12.5 MiB<br>number of output rows: 201,465"];
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_235180, false, Parquet, [path=file:///data/output/cache/parquet/datablock/14_B_PASSAGE_PA_235180], 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#945604 ASC NULLS FIRST, COL_59774853_4110_4672_B6E2_C0D5DE930914#945605 ASC NULLS FIRST], true, 0
WholeStageCodegen (7)
AQEShuffleRead coalesced
Exchange rangepartitioning(COL_E5ADB260_1BF6_449C_8439_0A94CEE6956C#945604 ASC NULLS FIRST, COL_59774853_4110_4672_B6E2_C0D5DE930914#945605 ASC NULLS FIRST, 10), ENSURE_REQUIREMENTS, [plan_id=621160]
Union
Project [COL_DEB05435_3A84_4F8F_8CD2_6BE209A14FA8#945564 AS COL_E5ADB260_1BF6_449C_8439_0A94CEE6956C#945604, col0#945573 AS COL_59774853_4110_4672_B6E2_C0D5DE930914#945605, col1#945574 AS COL_E58DD17C_E55F_4036_9FA9_A5365B045A1A#945606]
Generate stack(3, 01-UF, COL_48FD2AAE_6F4D_4D43_BEE7_8A161203783C#945565, 02-Transport, COL_E0699193_FC70_4F64_BAE6_B2F241857F3B#945566, 03-CCMU, COL_630C2F1A_DB89_4A08_A2D2_179A10CC9FD2#945567), [COL_DEB05435_3A84_4F8F_8CD2_6BE209A14FA8#945564], false, [col0#945573, col1#945574]
Project [COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#945468 AS COL_DEB05435_3A84_4F8F_8CD2_6BE209A14FA8#945564, COL_E82CFB57_01EB_4E90_836D_4D6F4CA131FE#945469 AS COL_48FD2AAE_6F4D_4D43_BEE7_8A161203783C#945565, COL_E1010A22_775B_43B4_B8CA_4603C0801D28#945470 AS COL_E0699193_FC70_4F64_BAE6_B2F241857F3B#945566, COL_6A6D32F5_2B4E_4DF6_A459_B248882F909D#945471 AS COL_630C2F1A_DB89_4A08_A2D2_179A10CC9FD2#945567]
Filter (COL_6B340AEB_6908_4A50_8AD6_FE561D33FBE0#945484 <=> 1)
WholeStageCodegen (5)
Window [row_number() windowspecdefinition(COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#945468, 1 DESC NULLS LAST, specifiedwindowframe(RowFrame, unboundedpreceding$(), currentrow$())) AS COL_6B340AEB_6908_4A50_8AD6_FE561D33FBE0#945484], [COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#945468], [1 DESC NULLS LAST]
Sort [COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#945468 ASC NULLS FIRST, 1 DESC NULLS LAST], false, 0
WholeStageCodegen (4)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#945468, 10), ENSURE_REQUIREMENTS, [plan_id=620885]
Project [Numéro Séjour#945352 AS COL_2AF4FE05_74B1_4A24_9BC1_7612D6ED731D#945468, UF#945353 AS COL_E82CFB57_01EB_4E90_836D_4D6F4CA131FE#945469, str_remove_space(Transport admission#945356, ONLY_ONE) AS COL_E1010A22_775B_43B4_B8CA_4603C0801D28#945470, str_remove_space(str_list_get(str_extract_by_regex(Niveau CCMU#945357, [+\d]+), 0), ALL) AS COL_6A6D32F5_2B4E_4DF6_A459_B248882F909D#945471]
Filter NOT CASE WHEN isnull(StartsWith(Numéro Séjour#945352, #)) THEN false ELSE StartsWith(Numéro Séjour#945352, #) END
WholeStageCodegen (1)
FileScan csv [Numéro Séjour#945352,UF#945353,Transport admission#945356,Niveau CCMU#945357] Batched: false, DataFilters: [NOT CASE WHEN isnull(StartsWith(Numéro Séjour#945352, #)) THEN false ELSE StartsWith(Numéro Séjo..., Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/data/input/depot/csv/tmp/02_PASSAGE_PATI_234565/passage_Patient_..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<Numéro Séjour:string,UF:string,Transport admission:string,Niveau CCMU:string>
Sort [COL_DC1A3ABF_ADFC_4208_8B24_35ED54CC87DF#945243 ASC NULLS FIRST, COL_EA9AE57C_DE84_4BBE_9131_053814B337F4#945244 ASC NULLS FIRST], true, 0
WholeStageCodegen (6)
AQEShuffleRead coalesced
Exchange rangepartitioning(COL_DC1A3ABF_ADFC_4208_8B24_35ED54CC87DF#945243 ASC NULLS FIRST, COL_EA9AE57C_DE84_4BBE_9131_053814B337F4#945244 ASC NULLS FIRST, 10), ENSURE_REQUIREMENTS, [plan_id=621058]
HashAggregate(keys=[COL_8D7490B1_ED4B_4A07_9680_ECC66DF49E37#945229, COL_7F6B8B23_E564_4B4E_8794_0FC7CE59D60B#945230, COL_B6440F86_8BD4_4AFD_8640_45556688ABB9#945231], functions=[])
WholeStageCodegen (3)
AQEShuffleRead coalesced
Exchange hashpartitioning(COL_8D7490B1_ED4B_4A07_9680_ECC66DF49E37#945229, COL_7F6B8B23_E564_4B4E_8794_0FC7CE59D60B#945230, COL_B6440F86_8BD4_4AFD_8640_45556688ABB9#945231, 10), ENSURE_REQUIREMENTS, [plan_id=620914]
HashAggregate(keys=[COL_8D7490B1_ED4B_4A07_9680_ECC66DF49E37#945229, COL_7F6B8B23_E564_4B4E_8794_0FC7CE59D60B#945230, COL_B6440F86_8BD4_4AFD_8640_45556688ABB9#945231], functions=[])
Project [COL_BC7CB40E_B2CA_42C4_94A5_B6AA996E14DC#945064 AS COL_8D7490B1_ED4B_4A07_9680_ECC66DF49E37#945229, col0#945129 AS COL_7F6B8B23_E564_4B4E_8794_0FC7CE59D60B#945230, col1#945130 AS COL_B6440F86_8BD4_4AFD_8640_45556688ABB9#945231]
Generate stack(7, 04-Date Naissance, COL_95E23023_63AA_4AB8_A60F_50D45234CFDD#945065, 05-Date Entree, COL_78B23D10_75E8_415E_A3C0_8AB5C826A837#945066, 06-Date Sortie, COL_885784F8_1772_40E3_89B6_6ACE1FAB6407#945067, 07-Fides, COL_32AA235F_1BB1_4047_B8BA_AD2E9197AD1F#945068, 08-Facturable AM, COL_3BBA8558_C3D5_4921_93AE_D7C9E273B39D#945069, 09-Justif Exo, COL_35788C71_38EE_4A08_B685_AAC68457246A#945070, 10-Nature Ass, COL_6EC95BD9_A121_4728_BE4A_49B7EA2976F2#945071), [COL_BC7CB40E_B2CA_42C4_94A5_B6AA996E14DC#945064], false, [col0#945129, col1#945130]
Project [COL_F76265AB_8748_4114_92B4_00E37DE25D34#944556 AS COL_BC7CB40E_B2CA_42C4_94A5_B6AA996E14DC#945064, COL_9262BBED_C393_416D_B38C_8F1458965BA7#944555 AS COL_95E23023_63AA_4AB8_A60F_50D45234CFDD#945065, COL_96E2282E_0771_460E_8BDB_D11261BD9020#944557 AS COL_78B23D10_75E8_415E_A3C0_8AB5C826A837#945066, COL_12028397_66B1_4E3C_BBDB_64537606E7DE#944558 AS COL_885784F8_1772_40E3_89B6_6ACE1FAB6407#945067, COL_0521CAB9_7617_4F31_948E_95DCA16387D7#944553 AS COL_32AA235F_1BB1_4047_B8BA_AD2E9197AD1F#945068, COL_1DACB81E_AFA5_4BB8_83D7_57DE8B8062B7#944554 AS COL_3BBA8558_C3D5_4921_93AE_D7C9E273B39D#945069, COL_4473F770_A575_4100_97F6_8190F900749A#944562 AS COL_35788C71_38EE_4A08_B685_AAC68457246A#945070, COL_715B3479_EAD2_422C_BF5C_7B020197D946#944563 AS COL_6EC95BD9_A121_4728_BE4A_49B7EA2976F2#945071]
ColumnarToRow
WholeStageCodegen (2)
FileScan parquet [COL_0521CAB9_7617_4F31_948E_95DCA16387D7#944553,COL_1DACB81E_AFA5_4BB8_83D7_57DE8B8062B7#944554,COL_9262BBED_C393_416D_B38C_8F1458965BA7#944555,COL_F76265AB_8748_4114_92B4_00E37DE25D34#944556,COL_96E2282E_0771_460E_8BDB_D11261BD9020#944557,COL_12028397_66B1_4E3C_BBDB_64537606E7DE#944558,COL_4473F770_A575_4100_97F6_8190F900749A#944562,COL_715B3479_EAD2_422C_BF5C_7B020197D946#944563] Batched: true, DataFilters: [], Format: Parquet, Location: InMemoryFileIndex(1 paths)[file:/data/output/cache/parquet/datablock/02_A_ELIGIBLE_234754], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<COL_0521CAB9_7617_4F31_948E_95DCA16387D7:string,COL_1DACB81E_AFA5_4BB8_83D7_57DE8B8062B7:s...