crp-wrkload-determination - Details for Query 79

Submitted Time: 2026/09/05 18:20:31
Duration: 0.9 s
Succeeded Jobs: 106 107

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 (2)\n \nduration: 20 ms"; tooltip="WholeStageCodegen (2)"; 2 [id="node2" labelType="html" label="HashAggregate time in aggregation build: 20 ms number of output rows: 1" tooltip="HashAggregate(keys=[], functions=[count(1)])"]; } 3 [id="node3" labelType="html" label="Exchange shuffle records written: 200 remote merged reqs duration: 0 ms remote merged blocks fetched: 0 records read: 200 local bytes read: 14.1 KiB merged fetch fallback count: 0 local blocks read: 200 remote merged chunks fetched: 0 remote blocks read: 0 data size total (min, med, max (stageId: taskId)) 3.1 KiB (16.0 B, 16.0 B, 16.0 B (stage 228.0: task 23083)) local merged bytes read: 0.0 B local merged chunks fetched: 0 shuffle write time total (min, med, max (stageId: taskId)) 29 ms (0 ms, 0 ms, 0 ms (stage 228.0: task 23126)) 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: 1 remote reqs duration: 0 ms remote bytes read to disk: 0.0 B shuffle bytes written total (min, med, max (stageId: taskId)) 14.1 KiB (72.0 B, 72.0 B, 72.0 B (stage 228.0: task 23083))" tooltip="Exchange SinglePartition, ENSURE_REQUIREMENTS, [plan_id=5275]"]; subgraph cluster4 { isCluster="true"; id="cluster4"; label="WholeStageCodegen (1)\n \nduration: total (min, med, max (stageId: taskId))\n3 ms (0 ms, 0 ms, 1 ms (stage 228.0: task 23083))"; tooltip="WholeStageCodegen (1)"; 5 [id="node5" labelType="html" label="HashAggregate time in aggregation build total (min, med, max (stageId: taskId)) 0 ms (0 ms, 0 ms, 0 ms (stage 228.0: task 23083)) number of output rows: 200" tooltip="HashAggregate(keys=[], functions=[partial_count(1)])"]; } 6 [id="node6" labelType="html" label="InMemoryTableScan number of output rows: 0" tooltip="InMemoryTableScan"]; 7 [id="node7" labelType="html" label=" AdaptiveSparkPlan " tooltip="AdaptiveSparkPlan isFinalPlan=true"]; subgraph cluster8 { isCluster="true"; id="cluster8"; label="WholeStageCodegen (2)\n \nduration: 0 ms"; tooltip="WholeStageCodegen (2)"; 9 [id="node9" 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#3954, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).length()) AS length#3955L, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).isDir()) AS isDir#3956, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).modificationTime()) AS modificationTime#3957L]"]; } 10 [id="node10" labelType="html" label=" MapGroups " tooltip="MapGroups org.apache.spark.sql.internal.UDFAdaptors$$$Lambda/0x000000080209d5c0@754784c3, invoke(value#3948.toString()), newInstance(class org.apache.spark.sql.delta.SerializableFileStatus), [value#3948], [path#3938, length#3939L, isDir#3940, modificationTime#3941L], obj#3953: org.apache.spark.sql.delta.SerializableFileStatus"]; subgraph cluster11 { isCluster="true"; id="cluster11"; label="WholeStageCodegen (1)\n \nduration: 0 ms"; tooltip="WholeStageCodegen (1)"; 12 [id="node12" labelType="html" label="Sort sort time: 0 ms peak memory: 0.0 B spill size: 0.0 B" tooltip="Sort [value#3948 ASC NULLS FIRST], false, 0"]; } 13 [id="node13" labelType="html" label="Exchange shuffle records written: 0 remote merged reqs duration: 0 ms remote merged blocks fetched: 0 records read: 0 local bytes read: 0.0 B merged fetch fallback count: 0 local blocks read: 0 remote merged chunks fetched: 0 remote blocks read: 0 data size: 0.0 B local merged bytes read: 0.0 B local merged chunks fetched: 0 shuffle write time: 0 ms remote merged bytes read: 0.0 B local merged blocks fetched: 0 corrupt merged block chunks: 0 fetch wait time: 0 ms remote bytes read: 0.0 B number of partitions: 0 remote reqs duration: 0 ms remote bytes read to disk: 0.0 B shuffle bytes written: 0.0 B" tooltip="Exchange hashpartitioning(value#3948, 200), ENSURE_REQUIREMENTS, [plan_id=5143]"]; 14 [id="node14" labelType="html" label=" AppendColumnsWithObject " tooltip="AppendColumnsWithObject org.apache.spark.sql.delta.commands.VacuumCommand$$$Lambda/0x000000080209c000@3c79482b, [static_invoke(UTF8String.fromString(invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).path()))) AS path#3938, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).length()) AS length#3939L, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).isDir()) AS isDir#3940, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).modificationTime()) AS modificationTime#3941L], [static_invoke(UTF8String.fromString(input[0, java.lang.String, true])) AS value#3948]"]; 15 [id="node15" labelType="html" label=" MapElements " tooltip="MapElements org.apache.spark.sql.delta.commands.VacuumCommand$$$Lambda/0x0000000802093950@5e5aa004, obj#3937: org.apache.spark.sql.delta.SerializableFileStatus"]; 16 [id="node16" labelType="html" label="Scan number of output rows: 0" tooltip="Scan[obj#3922]"]; 2->0; 3->2; 5->3; 6->5; 7->6; 9->7; 10->9; 12->10; 13->12; 14->13; 15->14; 16->15; }

Details

== Physical Plan ==
AdaptiveSparkPlan (25)
+- == Final Plan ==
   ResultQueryStage (21), Statistics(sizeInBytes=8.0 EiB)
   +- * HashAggregate (20)
      +- ShuffleQueryStage (19), Statistics(sizeInBytes=3.1 KiB, rowCount=200)
         +- Exchange (18)
            +- * HashAggregate (17)
               +- TableCacheQueryStage (16), Statistics(sizeInBytes=0.0 B, rowCount=0)
                  +- InMemoryTableScan (1)
                        +- InMemoryRelation (2)
                              +- AdaptiveSparkPlan (15)
                              +- == Final Plan ==
                                 ResultQueryStage (11)
                                 +- * SerializeFromObject (10)
                                    +- MapGroups (9)
                                       +- * Sort (8)
                                          +- ShuffleQueryStage (7), Statistics(sizeInBytes=0.0 B, rowCount=0)
                                             +- Exchange (6)
                                                +- AppendColumnsWithObject (5)
                                                   +- MapElements (4)
                                                      +- Scan (3)
                              +- == Initial Plan ==
                                 SerializeFromObject (14)
                                 +- MapGroups (13)
                                    +- Sort (12)
                                       +- Exchange (6)
                                          +- AppendColumnsWithObject (5)
                                             +- MapElements (4)
                                                +- Scan (3)
+- == Initial Plan ==
   HashAggregate (24)
   +- Exchange (23)
      +- HashAggregate (22)
         +- InMemoryTableScan (1)
               +- InMemoryRelation (2)
                     +- AdaptiveSparkPlan (15)
                     +- == Final Plan ==
                        ResultQueryStage (11)
                        +- * SerializeFromObject (10)
                           +- MapGroups (9)
                              +- * Sort (8)
                                 +- ShuffleQueryStage (7), Statistics(sizeInBytes=0.0 B, rowCount=0)
                                    +- Exchange (6)
                                       +- AppendColumnsWithObject (5)
                                          +- MapElements (4)
                                             +- Scan (3)
                     +- == Initial Plan ==
                        SerializeFromObject (14)
                        +- MapGroups (13)
                           +- Sort (12)
                              +- Exchange (6)
                                 +- AppendColumnsWithObject (5)
                                    +- MapElements (4)
                                       +- Scan (3)


(1) InMemoryTableScan
Output: []

(2) InMemoryRelation
Arguments: [path#3954, length#3955L, isDir#3956, modificationTime#3957L], StorageLevel(disk, memory, deserialized, 1 replicas)

(3) Scan
Output [1]: [obj#3922]
Arguments: obj#3922: org.apache.spark.sql.delta.SerializableFileStatus, MapPartitionsRDD[462] at $anonfun$recordDeltaOperationInternal$1 at DatabricksLogging.scala:128

(4) MapElements
Input [1]: [obj#3922]
Arguments: org.apache.spark.sql.delta.commands.VacuumCommand$$$Lambda/0x0000000802093950@5e5aa004, obj#3937: org.apache.spark.sql.delta.SerializableFileStatus

(5) AppendColumnsWithObject
Input [1]: [obj#3937]
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#3938, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).length()) AS length#3939L, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).isDir()) AS isDir#3940, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).modificationTime()) AS modificationTime#3941L], [static_invoke(UTF8String.fromString(input[0, java.lang.String, true])) AS value#3948]

(6) Exchange
Input [5]: [path#3938, length#3939L, isDir#3940, modificationTime#3941L, value#3948]
Arguments: hashpartitioning(value#3948, 200), ENSURE_REQUIREMENTS, [plan_id=5143]

(7) ShuffleQueryStage
Output [5]: [path#3938, length#3939L, isDir#3940, modificationTime#3941L, value#3948]
Arguments: 0

(8) Sort [codegen id : 1]
Input [5]: [path#3938, length#3939L, isDir#3940, modificationTime#3941L, value#3948]
Arguments: [value#3948 ASC NULLS FIRST], false, 0

(9) MapGroups
Input [5]: [path#3938, length#3939L, isDir#3940, modificationTime#3941L, value#3948]
Arguments: org.apache.spark.sql.internal.UDFAdaptors$$$Lambda/0x000000080209d5c0@754784c3, invoke(value#3948.toString()), newInstance(class org.apache.spark.sql.delta.SerializableFileStatus), [value#3948], [path#3938, length#3939L, isDir#3940, modificationTime#3941L], obj#3953: org.apache.spark.sql.delta.SerializableFileStatus

(10) SerializeFromObject [codegen id : 2]
Input [1]: [obj#3953]
Arguments: [static_invoke(UTF8String.fromString(invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).path()))) AS path#3954, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).length()) AS length#3955L, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).isDir()) AS isDir#3956, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).modificationTime()) AS modificationTime#3957L]

(11) ResultQueryStage
Output [4]: [path#3954, length#3955L, isDir#3956, modificationTime#3957L]
Arguments: 1

(12) Sort
Input [5]: [path#3938, length#3939L, isDir#3940, modificationTime#3941L, value#3948]
Arguments: [value#3948 ASC NULLS FIRST], false, 0

(13) MapGroups
Input [5]: [path#3938, length#3939L, isDir#3940, modificationTime#3941L, value#3948]
Arguments: org.apache.spark.sql.internal.UDFAdaptors$$$Lambda/0x000000080209d5c0@754784c3, invoke(value#3948.toString()), newInstance(class org.apache.spark.sql.delta.SerializableFileStatus), [value#3948], [path#3938, length#3939L, isDir#3940, modificationTime#3941L], obj#3953: org.apache.spark.sql.delta.SerializableFileStatus

(14) SerializeFromObject
Input [1]: [obj#3953]
Arguments: [static_invoke(UTF8String.fromString(invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).path()))) AS path#3954, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).length()) AS length#3955L, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).isDir()) AS isDir#3956, invoke(knownnotnull(assertnotnull(input[0, org.apache.spark.sql.delta.SerializableFileStatus, true])).modificationTime()) AS modificationTime#3957L]

(15) AdaptiveSparkPlan
Output [4]: [path#3954, length#3955L, isDir#3956, modificationTime#3957L]
Arguments: isFinalPlan=true

(16) TableCacheQueryStage
Output: []
Arguments: 0

(17) HashAggregate [codegen id : 1]
Input: []
Keys: []
Functions [1]: [partial_count(1)]
Aggregate Attributes [1]: [count#4162L]
Results [1]: [count#4163L]

(18) Exchange
Input [1]: [count#4163L]
Arguments: SinglePartition, ENSURE_REQUIREMENTS, [plan_id=5275]

(19) ShuffleQueryStage
Output [1]: [count#4163L]
Arguments: 1

(20) HashAggregate [codegen id : 2]
Input [1]: [count#4163L]
Keys: []
Functions [1]: [count(1)]
Aggregate Attributes [1]: [count(1)#4101L]
Results [1]: [count(1)#4101L AS count#4096L]

(21) ResultQueryStage
Output [1]: [count#4096L]
Arguments: 2

(22) HashAggregate
Input: []
Keys: []
Functions [1]: [partial_count(1)]
Aggregate Attributes [1]: [count#4162L]
Results [1]: [count#4163L]

(23) Exchange
Input [1]: [count#4163L]
Arguments: SinglePartition, ENSURE_REQUIREMENTS, [plan_id=5251]

(24) HashAggregate
Input [1]: [count#4163L]
Keys: []
Functions [1]: [count(1)]
Aggregate Attributes [1]: [count(1)#4101L]
Results [1]: [count(1)#4101L AS count#4096L]

(25) AdaptiveSparkPlan
Output [1]: [count#4096L]
Arguments: isFinalPlan=true

SQL / DataFrame Properties

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