crp-wrkload-determination - Details for Query 40

Submitted Time: 2026/09/05 08:26:50
Duration: 1 s
Succeeded Jobs: 56 57

Plan Visualization

Show the Stage ID and Task ID that corresponds to the max metric

digraph G { 0 [id="node0" labelType="html" label=" AdaptiveSparkPlan " tooltip="AdaptiveSparkPlan isFinalPlan=true"]; subgraph cluster1 { isCluster="true"; id="cluster1"; label="WholeStageCodegen (5)"; tooltip="WholeStageCodegen (5)"; 2 [id="node2" labelType="html" label=" SerializeFromObject " tooltip="SerializeFromObject [static_invoke(UTF8String.fromString(input[0, java.lang.String, true])) AS value#2097]"]; 3 [id="node3" labelType="html" label=" MapElements " tooltip="MapElements org.apache.spark.sql.delta.commands.VacuumCommand$$$Lambda/0x0000000802109d40@5c492475, obj#2096: java.lang.String"]; 4 [id="node4" labelType="html" label=" DeserializeToObject " tooltip="DeserializeToObject invoke(path#1960.toString()), obj#2095: java.lang.String"]; 5 [id="node5" labelType="html" label=" EmptyRelation " tooltip="EmptyRelation [plan_id=3157]"]; 6 [id="node6" labelType="html" label=" Project " tooltip="Project [path#1960]"]; 7 [id="node7" labelType="html" label=" EmptyRelation " tooltip="EmptyRelation Filter (count#1962L = 1)"]; 8 [id="node8" labelType="html" label=" Filter " tooltip="Filter (count#1962L = 1)"]; 9 [id="node9" labelType="html" label=" EmptyRelation " tooltip="EmptyRelation LogicalQueryStage Aggregate [path#1960], [path#1960, count(1) AS count#1962L], HashAggregate(keys=[path#1960], functions=[count(1)])"]; 10 [id="node10" labelType="html" label=" LogicalQueryStage " tooltip="LogicalQueryStage Aggregate [path#1960], [path#1960, count(1) AS count#1962L], HashAggregate(keys=[path#1960], functions=[count(1)])"]; 11 [id="node11" labelType="html" label=" HashAggregate " tooltip="HashAggregate(keys=[path#1960], functions=[count(1)])"]; } 12 [id="node12" labelType="html" label="Exchange shuffle records written: 0 data size: 0.0 B shuffle write time: 0 ms number of partitions: 200 shuffle bytes written: 0.0 B" tooltip="Exchange hashpartitioning(path#1960, 200), ENSURE_REQUIREMENTS, [plan_id=3109]"]; subgraph cluster13 { isCluster="true"; id="cluster13"; label="WholeStageCodegen (4)\n \nduration: total (min, med, max (stageId: taskId))\n14 ms (0 ms, 0 ms, 1 ms (stage 125.0: task 11777))"; tooltip="WholeStageCodegen (4)"; 14 [id="node14" labelType="html" label="HashAggregate spill size: 0.0 B time in aggregation build total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 125.0: task 11770)) peak memory total (min, med, max (stageId: taskId)) 50.0 MiB (256.0 KiB, 256.0 KiB, 256.0 KiB (stage 125.0: task 11770)) number of output rows: 0 number of sort fallback tasks: 0 avg hash probes per key: 0" tooltip="HashAggregate(keys=[path#1960], functions=[partial_count(1)])"]; 15 [id="node15" labelType="html" label=" SerializeFromObject " tooltip="SerializeFromObject [static_invoke(UTF8String.fromString(invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.commands.VacuumCommand$FileNameAndSize, true])).path()))) AS path#1960]"]; } 16 [id="node16" labelType="html" label=" MapPartitions " tooltip="MapPartitions org.apache.spark.sql.delta.commands.VacuumCommand$$$Lambda/0x00000008020dc000@322e395f, obj#1957: org.apache.spark.sql.delta.commands.VacuumCommand$FileNameAndSize"]; 17 [id="node17" labelType="html" label=" DeserializeToObject " tooltip="DeserializeToObject newInstance(class org.apache.spark.sql.delta.SerializableFileStatus), obj#1954: org.apache.spark.sql.delta.SerializableFileStatus"]; subgraph cluster18 { isCluster="true"; id="cluster18"; label="WholeStageCodegen (3)\n \nduration: total (min, med, max (stageId: taskId))\n204 ms (1 ms, 1 ms, 5 ms (stage 125.0: task 11848))"; tooltip="WholeStageCodegen (3)"; 19 [id="node19" labelType="html" label="Filter number of output rows: 0" tooltip="Filter ((modificationTime#1702L < 1787991979546) OR isDir#1701)"]; } 20 [id="node20" labelType="html" label="InMemoryTableScan number of output rows: 0" tooltip="InMemoryTableScan [path#1699, length#1700L, isDir#1701, modificationTime#1702L], [((modificationTime#1702L < 1787991979546) OR isDir#1701)]"]; 21 [id="node21" labelType="html" label=" AdaptiveSparkPlan " tooltip="AdaptiveSparkPlan isFinalPlan=true"]; subgraph cluster22 { isCluster="true"; id="cluster22"; label="WholeStageCodegen (2)\n \nduration: 0 ms"; tooltip="WholeStageCodegen (2)"; 23 [id="node23" labelType="html" label=" SerializeFromObject " tooltip="SerializeFromObject [static_invoke(UTF8String.fromString(invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).path()))) AS path#1699, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).length()) AS length#1700L, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).isDir()) AS isDir#1701, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).modificationTime()) AS modificationTime#1702L]"]; } 24 [id="node24" labelType="html" label=" MapGroups " tooltip="MapGroups org.apache.spark.sql.internal.UDFAdaptors$$$Lambda/0x000000080209d5c0@563ebb8d, invoke(value#1693.toString()), newInstance(class org.apache.spark.sql.delta.SerializableFileStatus), [value#1693], [path#1683, length#1684L, isDir#1685, modificationTime#1686L], obj#1698: org.apache.spark.sql.delta.SerializableFileStatus"]; subgraph cluster25 { isCluster="true"; id="cluster25"; label="WholeStageCodegen (1)\n \nduration: 0 ms"; tooltip="WholeStageCodegen (1)"; 26 [id="node26" labelType="html" label="Sort sort time: 0 ms peak memory: 0.0 B spill size: 0.0 B" tooltip="Sort [value#1693 ASC NULLS FIRST], false, 0"]; } 27 [id="node27" labelType="html" label="Exchange shuffle records written: 0 remote merged reqs duration: 0 ms remote merged blocks fetched: 0 records read: 0 local bytes read: 0.0 B merged fetch fallback count: 0 local blocks read: 0 remote merged chunks fetched: 0 remote blocks read: 0 data size: 0.0 B local merged bytes read: 0.0 B local merged chunks fetched: 0 shuffle write time: 0 ms remote merged bytes read: 0.0 B local merged blocks fetched: 0 corrupt merged block chunks: 0 fetch wait time: 0 ms remote bytes read: 0.0 B number of partitions: 0 remote reqs duration: 0 ms remote bytes read to disk: 0.0 B shuffle bytes written: 0.0 B" tooltip="Exchange hashpartitioning(value#1693, 200), ENSURE_REQUIREMENTS, [plan_id=2018]"]; 28 [id="node28" labelType="html" label=" AppendColumnsWithObject " tooltip="AppendColumnsWithObject org.apache.spark.sql.delta.commands.VacuumCommand$$$Lambda/0x000000080209c000@3c79482b, [static_invoke(UTF8String.fromString(invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).path()))) AS path#1683, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).length()) AS length#1684L, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).isDir()) AS isDir#1685, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).modificationTime()) AS modificationTime#1686L], [static_invoke(UTF8String.fromString(input[0, java.lang.String, true])) AS value#1693]"]; 29 [id="node29" labelType="html" label=" MapElements " tooltip="MapElements org.apache.spark.sql.delta.commands.VacuumCommand$$$Lambda/0x0000000802093950@5e5aa004, obj#1682: org.apache.spark.sql.delta.SerializableFileStatus"]; 30 [id="node30" labelType="html" label="Scan number of output rows: 0" tooltip="Scan[obj#1667]"]; 2->0; 3->2; 4->3; 5->4; 6->5; 7->6; 8->7; 9->8; 10->9; 11->10; 12->11; 14->12; 15->14; 16->15; 17->16; 19->17; 20->19; 21->20; 23->21; 24->23; 26->24; 27->26; 28->27; 29->28; 30->29; }

Details

== Physical Plan ==
AdaptiveSparkPlan (43)
+- == Final Plan ==
   ResultQueryStage (5), Statistics(sizeInBytes=8.0 EiB)
   +- * SerializeFromObject (4)
      +- * MapElements (3)
         +- * DeserializeToObject (2)
            +- * EmptyRelation (1)
               +- Project (unknown)
                  +- EmptyRelation (unknown)
+- == Initial Plan ==
   SerializeFromObject (42)
   +- MapElements (41)
      +- DeserializeToObject (40)
         +- SortMergeJoin LeftAnti (39)
            :- Sort (30)
            :  +- Project (29)
            :     +- Filter (28)
            :        +- HashAggregate (27)
            :           +- Exchange (26)
            :              +- HashAggregate (25)
            :                 +- SerializeFromObject (24)
            :                    +- MapPartitions (23)
            :                       +- DeserializeToObject (22)
            :                          +- Filter (21)
            :                             +- InMemoryTableScan (6)
            :                                   +- InMemoryRelation (7)
            :                                         +- AdaptiveSparkPlan (20)
                                                      +- == Final Plan ==
                                                         ResultQueryStage (16)
                                                         +- * SerializeFromObject (15)
                                                            +- MapGroups (14)
                                                               +- * Sort (13)
                                                                  +- ShuffleQueryStage (12), Statistics(sizeInBytes=0.0 B, rowCount=0)
                                                                     +- Exchange (11)
                                                                        +- AppendColumnsWithObject (10)
                                                                           +- MapElements (9)
                                                                              +- Scan (8)
                                                      +- == Initial Plan ==
                                                         SerializeFromObject (19)
                                                         +- MapGroups (18)
                                                            +- Sort (17)
                                                               +- Exchange (11)
                                                                  +- AppendColumnsWithObject (10)
                                                                     +- MapElements (9)
                                                                        +- Scan (8)
            +- Sort (38)
               +- Exchange (37)
                  +- Project (36)
                     +- Filter (35)
                        +- SerializeFromObject (34)
                           +- MapPartitions (33)
                              +- DeserializeToObject (32)
                                 +- Scan ExistingRDD Delta Table State #0 - hdlfs://065c2b6f-41bb-4a20-b7a2-eb965f9cb071.files.hdl.prod-eu20.hanacloud.ondemand.com:443/crp-workload-determination-service/in/workload-dupl-lock-v3/_delta_log (31)


(1) EmptyRelation [codegen id : 5]
Output [1]: [path#1960]
Arguments: [plan_id=3157]

(2) DeserializeToObject [codegen id : 5]
Input [1]: [path#1960]
Arguments: invoke(path#1960.toString()), obj#2095: java.lang.String

(3) MapElements [codegen id : 5]
Input [1]: [obj#2095]
Arguments: org.apache.spark.sql.delta.commands.VacuumCommand$$$Lambda/0x0000000802109d40@5c492475, obj#2096: java.lang.String

(4) SerializeFromObject [codegen id : 5]
Input [1]: [obj#2096]
Arguments: [static_invoke(UTF8String.fromString(input[0, java.lang.String, true])) AS value#2097]

(5) ResultQueryStage
Output [1]: [value#2097]
Arguments: 3

(6) InMemoryTableScan
Output [4]: [path#1699, length#1700L, isDir#1701, modificationTime#1702L]
Arguments: [path#1699, length#1700L, isDir#1701, modificationTime#1702L], [((modificationTime#1702L < 1787991979546) OR isDir#1701)]

(7) InMemoryRelation
Arguments: [path#1699, length#1700L, isDir#1701, modificationTime#1702L], StorageLevel(disk, memory, deserialized, 1 replicas)

(8) Scan
Output [1]: [obj#1667]
Arguments: obj#1667: org.apache.spark.sql.delta.SerializableFileStatus, MapPartitionsRDD[189] at $anonfun$recordDeltaOperationInternal$1 at DatabricksLogging.scala:128

(9) MapElements
Input [1]: [obj#1667]
Arguments: org.apache.spark.sql.delta.commands.VacuumCommand$$$Lambda/0x0000000802093950@5e5aa004, obj#1682: org.apache.spark.sql.delta.SerializableFileStatus

(10) AppendColumnsWithObject
Input [1]: [obj#1682]
Arguments: org.apache.spark.sql.delta.commands.VacuumCommand$$$Lambda/0x000000080209c000@3c79482b, [static_invoke(UTF8String.fromString(invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).path()))) AS path#1683, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).length()) AS length#1684L, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).isDir()) AS isDir#1685, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).modificationTime()) AS modificationTime#1686L], [static_invoke(UTF8String.fromString(input[0, java.lang.String, true])) AS value#1693]

(11) Exchange
Input [5]: [path#1683, length#1684L, isDir#1685, modificationTime#1686L, value#1693]
Arguments: hashpartitioning(value#1693, 200), ENSURE_REQUIREMENTS, [plan_id=2018]

(12) ShuffleQueryStage
Output [5]: [path#1683, length#1684L, isDir#1685, modificationTime#1686L, value#1693]
Arguments: 0

(13) Sort [codegen id : 1]
Input [5]: [path#1683, length#1684L, isDir#1685, modificationTime#1686L, value#1693]
Arguments: [value#1693 ASC NULLS FIRST], false, 0

(14) MapGroups
Input [5]: [path#1683, length#1684L, isDir#1685, modificationTime#1686L, value#1693]
Arguments: org.apache.spark.sql.internal.UDFAdaptors$$$Lambda/0x000000080209d5c0@563ebb8d, invoke(value#1693.toString()), newInstance(class org.apache.spark.sql.delta.SerializableFileStatus), [value#1693], [path#1683, length#1684L, isDir#1685, modificationTime#1686L], obj#1698: org.apache.spark.sql.delta.SerializableFileStatus

(15) SerializeFromObject [codegen id : 2]
Input [1]: [obj#1698]
Arguments: [static_invoke(UTF8String.fromString(invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).path()))) AS path#1699, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).length()) AS length#1700L, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).isDir()) AS isDir#1701, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).modificationTime()) AS modificationTime#1702L]

(16) ResultQueryStage
Output [4]: [path#1699, length#1700L, isDir#1701, modificationTime#1702L]
Arguments: 1

(17) Sort
Input [5]: [path#1683, length#1684L, isDir#1685, modificationTime#1686L, value#1693]
Arguments: [value#1693 ASC NULLS FIRST], false, 0

(18) MapGroups
Input [5]: [path#1683, length#1684L, isDir#1685, modificationTime#1686L, value#1693]
Arguments: org.apache.spark.sql.internal.UDFAdaptors$$$Lambda/0x000000080209d5c0@563ebb8d, invoke(value#1693.toString()), newInstance(class org.apache.spark.sql.delta.SerializableFileStatus), [value#1693], [path#1683, length#1684L, isDir#1685, modificationTime#1686L], obj#1698: org.apache.spark.sql.delta.SerializableFileStatus

(19) SerializeFromObject
Input [1]: [obj#1698]
Arguments: [static_invoke(UTF8String.fromString(invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).path()))) AS path#1699, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).length()) AS length#1700L, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).isDir()) AS isDir#1701, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).modificationTime()) AS modificationTime#1702L]

(20) AdaptiveSparkPlan
Output [4]: [path#1699, length#1700L, isDir#1701, modificationTime#1702L]
Arguments: isFinalPlan=true

(21) Filter
Input [4]: [path#1699, length#1700L, isDir#1701, modificationTime#1702L]
Condition : ((modificationTime#1702L < 1787991979546) OR isDir#1701)

(22) DeserializeToObject
Input [4]: [path#1699, length#1700L, isDir#1701, modificationTime#1702L]
Arguments: newInstance(class org.apache.spark.sql.delta.SerializableFileStatus), obj#1954: org.apache.spark.sql.delta.SerializableFileStatus

(23) MapPartitions
Input [1]: [obj#1954]
Arguments: org.apache.spark.sql.delta.commands.VacuumCommand$$$Lambda/0x00000008020dc000@322e395f, obj#1957: org.apache.spark.sql.delta.commands.VacuumCommand$FileNameAndSize

(24) SerializeFromObject
Input [1]: [obj#1957]
Arguments: [static_invoke(UTF8String.fromString(invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.commands.VacuumCommand$FileNameAndSize, true])).path()))) AS path#1960]

(25) HashAggregate
Input [1]: [path#1960]
Keys [1]: [path#1960]
Functions [1]: [partial_count(1)]
Aggregate Attributes [1]: [count#2035L]
Results [2]: [path#1960, count#2037L]

(26) Exchange
Input [2]: [path#1960, count#2037L]
Arguments: hashpartitioning(path#1960, 200), ENSURE_REQUIREMENTS, [plan_id=2960]

(27) HashAggregate
Input [2]: [path#1960, count#2037L]
Keys [1]: [path#1960]
Functions [1]: [count(1)]
Aggregate Attributes [1]: [count(1)#1966L]
Results [2]: [path#1960, count(1)#1966L AS count#1962L]

(28) Filter
Input [2]: [path#1960, count#1962L]
Condition : (count#1962L = 1)

(29) Project
Output [1]: [path#1960]
Input [2]: [path#1960, count#1962L]

(30) Sort
Input [1]: [path#1960]
Arguments: [path#1960 ASC NULLS FIRST], false, 0

(31) Scan ExistingRDD Delta Table State #0 - hdlfs://065c2b6f-41bb-4a20-b7a2-eb965f9cb071.files.hdl.prod-eu20.hanacloud.ondemand.com:443/crp-workload-determination-service/in/workload-dupl-lock-v3/_delta_log [codegen id : 1]
Output [10]: [txn#113, add#114, remove#115, metaData#116, protocol#117, cdc#118, checkpointMetadata#119, sidecar#120, domainMetadata#121, commitInfo#122]
Arguments: [txn#113, add#114, remove#115, metaData#116, protocol#117, cdc#118, checkpointMetadata#119, sidecar#120, domainMetadata#121, commitInfo#122], Delta Table State #0 - hdlfs://065c2b6f-41bb-4a20-b7a2-eb965f9cb071.files.hdl.prod-eu20.hanacloud.ondemand.com:443/crp-workload-determination-service/in/workload-dupl-lock-v3/_delta_log MapPartitionsRDD[10] at $anonfun$recordDeltaOperationInternal$1 at DatabricksLogging.scala:128, ExistingRDD, UnknownPartitioning(0)

(32) DeserializeToObject
Input [10]: [txn#113, add#114, remove#115, metaData#116, protocol#117, cdc#118, checkpointMetadata#119, sidecar#120, domainMetadata#121, commitInfo#122]
Arguments: newInstance(class org.apache.spark.sql.delta.actions.SingleAction), obj#1655: org.apache.spark.sql.delta.actions.SingleAction

(33) MapPartitions
Input [1]: [obj#1655]
Arguments: org.apache.spark.sql.delta.commands.VacuumCommand$$$Lambda/0x000000080208f3e8@6d88f017, obj#1656: java.lang.String

(34) SerializeFromObject
Input [1]: [obj#1656]
Arguments: [static_invoke(UTF8String.fromString(input[0, java.lang.String, true])) AS value#1657]

(35) Filter
Input [1]: [value#1657]
Condition : isnotnull(value#1657)

(36) Project
Output [1]: [value#1657 AS path#1658]
Input [1]: [value#1657]

(37) Exchange
Input [1]: [path#1658]
Arguments: hashpartitioning(path#1658, 200), ENSURE_REQUIREMENTS, [plan_id=2966]

(38) Sort
Input [1]: [path#1658]
Arguments: [path#1658 ASC NULLS FIRST], false, 0

(39) SortMergeJoin
Left keys [1]: [path#1960]
Right keys [1]: [path#1658]
Join type: LeftAnti
Join condition: None

(40) DeserializeToObject
Input [1]: [path#1960]
Arguments: invoke(path#1960.toString()), obj#2095: java.lang.String

(41) MapElements
Input [1]: [obj#2095]
Arguments: org.apache.spark.sql.delta.commands.VacuumCommand$$$Lambda/0x0000000802109d40@5c492475, obj#2096: java.lang.String

(42) SerializeFromObject
Input [1]: [obj#2096]
Arguments: [static_invoke(UTF8String.fromString(input[0, java.lang.String, true])) AS value#2097]

(43) AdaptiveSparkPlan
Output [1]: [value#2097]
Arguments: isFinalPlan=true

SQL / DataFrame Properties

Name	Value
spark.sql.parquet.fieldId.read.enabled	true
spark.sql.parquet.fieldId.write.enabled	true