PlusAMP App Middleware - Details for Job 331413

Status: SUCCEEDED
Submitted: 2025/08/02 15:22:32
Duration: 73 ms
Completed Stages: 3

Enable zooming

digraph G { subgraph clusterstage_512981 { label="Stage 512981"; subgraph cluster6288174 { label="Scan csv "; 3616158 [labelType="html" label="FileScanRDD [3616158] $anonfun$withThreadLocalCaptured$1 at FutureTask.java:264"]; 3616159 [labelType="html" label="MapPartitionsRDD [3616159] $anonfun$withThreadLocalCaptured$1 at FutureTask.java:264"]; } subgraph cluster6288170 { label="WholeStageCodegen (1)"; 3616160 [labelType="html" label="MapPartitionsRDD [3616160] $anonfun$withThreadLocalCaptured$1 at FutureTask.java:264"]; } subgraph cluster6288169 { label="InMemoryTableScan"; 3616161 [labelType="html" label="MapPartitionsRDD [3616161] $anonfun$withThreadLocalCaptured$1 at FutureTask.java:264"]; 3616162 [labelType="html" label="*(1) Project [CASE WHEN ((cap#94160377 = NA) OR (cap#94160377 = null)) THEN null ELSE cast(cap#94160377 as int) END AS cap#94160394, CASE WHEN (sort#94160378 = null) THEN null ELSE sort#94160378 END AS sort#94160395, CASE WHEN (description#94160379 = null) THEN null ELSE description#94160379 END AS description#94160396, CASE WHEN ((universe#94160380 = NA) OR (universe#94160380 = null)) THEN null ELSE cast(universe#94160380 as int) END AS universe#94160397]\n+- FileScan csv [cap#94160377,sort#94160378,description#94160379,universe#94160380] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/srv/plusamp/data/default/ea-market/curate/curate_cap.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<cap:string,sort:string,description:string,universe:string>\n [3616162] [Cached] $anonfun$withThreadLocalCaptured$1 at FutureTask.java:264"]; } subgraph cluster6302297 { label="InMemoryTableScan"; 3624263 [labelType="html" label="MapPartitionsRDD [3624263] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3624264 [labelType="html" label="MapPartitionsRDD [3624264] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3624265 [labelType="html" label="MapPartitionsRDD [3624265] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } subgraph cluster6302247 { label="WholeStageCodegen (2)"; 3624266 [labelType="html" label="MapPartitionsRDD [3624266] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } subgraph cluster6302246 { label="Exchange"; 3624283 [labelType="html" label="MapPartitionsRDD [3624283] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } } 3616158->3616159; 3616159->3616160; 3616160->3616161; 3616161->3616162; 3616162->3624263; 3624263->3624264; 3624264->3624265; 3624265->3624266; 3624266->3624283; }

3616162

digraph G { subgraph clusterstage_512982 { label="Stage 512982"; subgraph cluster6302246 { label="Exchange"; 3624284 [labelType="html" label="ShuffledRowRDD [3624284] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } subgraph cluster6302235 { label="WholeStageCodegen (3)"; 3624285 [labelType="html" label="MapPartitionsRDD [3624285] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } subgraph cluster6302234 { label="InMemoryTableScan"; 3624286 [labelType="html" label="MapPartitionsRDD [3624286] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3624287 [labelType="html" label="*(3) Project [cap#94371319, turnover#94368165, (1.0 / cast(turnover#94368165 as double)) AS days_hold#94371349]\n+- *(3) Sort [cap_sort#94371230 ASC NULLS FIRST], true, 0\n +- Exchange rangepartitioning(cap_sort#94371230 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [id=#7534802]\n +- *(2) Project [turnover#94368165, cap_description#94371229 AS cap#94371319, cap_sort#94371230]\n +- *(2) BroadcastHashJoin [knownfloatingpointnormalized(normalizenanandzero(cap#94368001))], [knownfloatingpointnormalized(normalizenanandzero(cast(cap#94160394 as float)))], Inner, BuildLeft, false\n :- BroadcastExchange HashedRelationBroadcastMode(List(knownfloatingpointnormalized(normalizenanandzero(input[0, float, false]))),false), [id=#7534794]\n : +- *(1) Filter isnotnull(cap#94368001)\n : +- *(1) ColumnarToRow\n : +- InMemoryTableScan [cap#94368001, turnover#94368165], [isnotnull(cap#94368001)]\n : +- InMemoryRelation [cap#94368001, retIC#943... [3624287] [Cached] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3624288 [labelType="html" label="MapPartitionsRDD [3624288] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3624289 [labelType="html" label="MapPartitionsRDD [3624289] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3624290 [labelType="html" label="MapPartitionsRDD [3624290] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } subgraph cluster6302232 { label="CollectLimit"; 3624291 [labelType="html" label="MapPartitionsRDD [3624291] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3624292 [labelType="html" label="MapPartitionsRDD [3624292] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } } 3624284->3624285; 3624285->3624286; 3624286->3624287; 3624287->3624288; 3624288->3624289; 3624289->3624290; 3624290->3624291; 3624291->3624292; }

3624283,3624284

3624287

digraph G { subgraph clusterstage_512983 { label="Stage 512983"; subgraph cluster6302232 { label="CollectLimit"; 3624293 [labelType="html" label="ShuffledRowRDD [3624293] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3624294 [labelType="html" label="MapPartitionsRDD [3624294] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } subgraph cluster6302311 { label="mapPartitionsInternal"; 3624295 [labelType="html" label="MapPartitionsRDD [3624295] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } subgraph cluster6302312 { label="map"; 3624296 [labelType="html" label="MapPartitionsRDD [3624296] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } } 3624293->3624294; 3624294->3624295; 3624295->3624296; }

3624292,3624293

Completed Stages (3)

Page:

Stage Id ▾	Pool Name	Description	Submitted	Duration	Tasks: Succeeded/Total	Input	Shuffle Read	Shuffle Write
512983	default	toStream at SparkDataStreamBuilder.scala:39 +details scala.collection.AbstractIterator.toStream(Iterator.scala:1431) plusamp.middleware.model.core.data.SparkDataStreamBuilder.$anonfun$stream$1(SparkDataStreamBuilder.scala:39) plusamp.scala.util.Profile$.time(Profile.scala:22) plusamp.middleware.model.core.data.SparkDataStreamBuilder.<init>(SparkDataStreamBuilder.scala:39) plusamp.middleware.graphql.datafile.SparkAccessor.$anonfun$retrieveData$3(SparkAccessor.scala:77) scala.util.Success.$anonfun$map$1(Try.scala:255) scala.util.Success.map(Try.scala:213) scala.concurrent.Future.$anonfun$map$1(Future.scala:292) scala.concurrent.impl.Promise.liftedTree1$1(Promise.scala:33) scala.concurrent.impl.Promise.$anonfun$transform$1(Promise.scala:33) scala.concurrent.impl.CallbackRunnable.run(Promise.scala:64) java.base/java.util.concurrent.ForkJoinTask$RunnableExecuteAction.exec(ForkJoinTask.java:1426) java.base/java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:290) java.base/java.util.concurrent.ForkJoinPool$WorkQueue.topLevelExec(ForkJoinPool.java:1020) java.base/java.util.concurrent.ForkJoinPool.scan(ForkJoinPool.java:1656) java.base/java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1594) java.base/java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:183)	2025/08/02 15:22:32	13 ms	1/1		155.0 B
512982	default	toLocalIterator at SparkDataStreamBuilder.scala:39 +details RDD: (3) Project [cap#94371319, turnover#94368165, (1.0 / cast(turnover#94368165 as double)) AS days_hold#94371349] +- (3) Sort [cap_sort#94371230 ASC NULLS FIRST], true, 0 +- Exchange rangepartitioning(cap_sort#94371230 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [id=#7534802] +- (2) Project [turnover#94368165, cap_description#94371229 AS cap#94371319, cap_sort#94371230] +- (2) BroadcastHashJoin [knownfloatingpointnormalized(normalizenanandzero(cap#94368001))], [knownfloatingpointnormalized(normalizenanandzero(cast(cap#94160394 as float)))], Inner, BuildLeft, false :- BroadcastExchange HashedRelationBroadcastMode(List(knownfloatingpointnormalized(normalizenanandzero(input[0, float, false]))),false), [id=#7534794] : +- (1) Filter isnotnull(cap#94368001) : +- (1) ColumnarToRow : +- InMemoryTableScan [cap#94368001, turnover#94368165], [isnotnull(cap#94368001)] : +- InMemoryRelation [cap#94368001, retIC#943... org.apache.spark.sql.Dataset.toLocalIterator(Dataset.scala:3000) plusamp.middleware.model.core.data.SparkDataStreamBuilder.$anonfun$stream$1(SparkDataStreamBuilder.scala:39) plusamp.scala.util.Profile$.time(Profile.scala:22) plusamp.middleware.model.core.data.SparkDataStreamBuilder.<init>(SparkDataStreamBuilder.scala:39) plusamp.middleware.graphql.datafile.SparkAccessor.$anonfun$retrieveData$3(SparkAccessor.scala:77) scala.util.Success.$anonfun$map$1(Try.scala:255) scala.util.Success.map(Try.scala:213) scala.concurrent.Future.$anonfun$map$1(Future.scala:292) scala.concurrent.impl.Promise.liftedTree1$1(Promise.scala:33) scala.concurrent.impl.Promise.$anonfun$transform$1(Promise.scala:33) scala.concurrent.impl.CallbackRunnable.run(Promise.scala:64) java.base/java.util.concurrent.ForkJoinTask$RunnableExecuteAction.exec(ForkJoinTask.java:1426) java.base/java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:290) java.base/java.util.concurrent.ForkJoinPool$WorkQueue.topLevelExec(ForkJoinPool.java:1020) java.base/java.util.concurrent.ForkJoinPool.scan(ForkJoinPool.java:1656) java.base/java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1594) java.base/java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:183)	2025/08/02 15:22:32	42 ms	2/2		133.0 B	155.0 B
512981	default	toLocalIterator at SparkDataStreamBuilder.scala:39 +details RDD: *(1) Project [CASE WHEN ((cap#94160377 = NA) OR (cap#94160377 = null)) THEN null ELSE cast(cap#94160377 as int) END AS cap#94160394, CASE WHEN (sort#94160378 = null) THEN null ELSE sort#94160378 END AS sort#94160395, CASE WHEN (description#94160379 = null) THEN null ELSE description#94160379 END AS description#94160396, CASE WHEN ((universe#94160380 = NA) OR (universe#94160380 = null)) THEN null ELSE cast(universe#94160380 as int) END AS universe#94160397] +- FileScan csv [cap#94160377,sort#94160378,description#94160379,universe#94160380] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/srv/plusamp/data/default/ea-market/curate/curate_cap.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<cap:string,sort:string,description:string,universe:string> org.apache.spark.sql.Dataset.toLocalIterator(Dataset.scala:3000) plusamp.middleware.model.core.data.SparkDataStreamBuilder.$anonfun$stream$1(SparkDataStreamBuilder.scala:39) plusamp.scala.util.Profile$.time(Profile.scala:22) plusamp.middleware.model.core.data.SparkDataStreamBuilder.<init>(SparkDataStreamBuilder.scala:39) plusamp.middleware.graphql.datafile.SparkAccessor.$anonfun$retrieveData$3(SparkAccessor.scala:77) scala.util.Success.$anonfun$map$1(Try.scala:255) scala.util.Success.map(Try.scala:213) scala.concurrent.Future.$anonfun$map$1(Future.scala:292) scala.concurrent.impl.Promise.liftedTree1$1(Promise.scala:33) scala.concurrent.impl.Promise.$anonfun$transform$1(Promise.scala:33) scala.concurrent.impl.CallbackRunnable.run(Promise.scala:64) java.base/java.util.concurrent.ForkJoinTask$RunnableExecuteAction.exec(ForkJoinTask.java:1426) java.base/java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:290) java.base/java.util.concurrent.ForkJoinPool$WorkQueue.topLevelExec(ForkJoinPool.java:1020) java.base/java.util.concurrent.ForkJoinPool.scan(ForkJoinPool.java:1656) java.base/java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1594) java.base/java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:183)	2025/08/02 15:22:32	9 ms	1/1	624.0 B		133.0 B

Stage Id ▾

Pool Name

Description

Submitted

Duration

Tasks: Succeeded/Total

Input

Output

Shuffle Read

Shuffle Write

512983

default

toStream at SparkDataStreamBuilder.scala:39 +details

scala.collection.AbstractIterator.toStream(Iterator.scala:1431)
plusamp.middleware.model.core.data.SparkDataStreamBuilder.$anonfun$stream$1(SparkDataStreamBuilder.scala:39)
plusamp.scala.util.Profile$.time(Profile.scala:22)
plusamp.middleware.model.core.data.SparkDataStreamBuilder.<init>(SparkDataStreamBuilder.scala:39)
plusamp.middleware.graphql.datafile.SparkAccessor.$anonfun$retrieveData$3(SparkAccessor.scala:77)
scala.util.Success.$anonfun$map$1(Try.scala:255)
scala.util.Success.map(Try.scala:213)
scala.concurrent.Future.$anonfun$map$1(Future.scala:292)
scala.concurrent.impl.Promise.liftedTree1$1(Promise.scala:33)
scala.concurrent.impl.Promise.$anonfun$transform$1(Promise.scala:33)
scala.concurrent.impl.CallbackRunnable.run(Promise.scala:64)
java.base/java.util.concurrent.ForkJoinTask$RunnableExecuteAction.exec(ForkJoinTask.java:1426)
java.base/java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:290)
java.base/java.util.concurrent.ForkJoinPool$WorkQueue.topLevelExec(ForkJoinPool.java:1020)
java.base/java.util.concurrent.ForkJoinPool.scan(ForkJoinPool.java:1656)
java.base/java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1594)
java.base/java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:183)

2025/08/02 15:22:32

13 ms

1/1

155.0 B

512982

default

toLocalIterator at SparkDataStreamBuilder.scala:39 +details

RDD: *(3) Project [cap#94371319, turnover#94368165, (1.0 / cast(turnover#94368165 as double)) AS days_hold#94371349] +- *(3) Sort [cap_sort#94371230 ASC NULLS FIRST], true, 0 +- Exchange rangepartitioning(cap_sort#94371230 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [id=#7534802] +- *(2) Project [turnover#94368165, cap_description#94371229 AS cap#94371319, cap_sort#94371230] +- *(2) BroadcastHashJoin [knownfloatingpointnormalized(normalizenanandzero(cap#94368001))], [knownfloatingpointnormalized(normalizenanandzero(cast(cap#94160394 as float)))], Inner, BuildLeft, false :- BroadcastExchange HashedRelationBroadcastMode(List(knownfloatingpointnormalized(normalizenanandzero(input[0, float, false]))),false), [id=#7534794] : +- *(1) Filter isnotnull(cap#94368001) : +- *(1) ColumnarToRow : +- InMemoryTableScan [cap#94368001, turnover#94368165], [isnotnull(cap#94368001)] : +- InMemoryRelation [cap#94368001, retIC#943...

org.apache.spark.sql.Dataset.toLocalIterator(Dataset.scala:3000)
plusamp.middleware.model.core.data.SparkDataStreamBuilder.$anonfun$stream$1(SparkDataStreamBuilder.scala:39)
plusamp.scala.util.Profile$.time(Profile.scala:22)
plusamp.middleware.model.core.data.SparkDataStreamBuilder.<init>(SparkDataStreamBuilder.scala:39)
plusamp.middleware.graphql.datafile.SparkAccessor.$anonfun$retrieveData$3(SparkAccessor.scala:77)
scala.util.Success.$anonfun$map$1(Try.scala:255)
scala.util.Success.map(Try.scala:213)
scala.concurrent.Future.$anonfun$map$1(Future.scala:292)
scala.concurrent.impl.Promise.liftedTree1$1(Promise.scala:33)
scala.concurrent.impl.Promise.$anonfun$transform$1(Promise.scala:33)
scala.concurrent.impl.CallbackRunnable.run(Promise.scala:64)
java.base/java.util.concurrent.ForkJoinTask$RunnableExecuteAction.exec(ForkJoinTask.java:1426)
java.base/java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:290)
java.base/java.util.concurrent.ForkJoinPool$WorkQueue.topLevelExec(ForkJoinPool.java:1020)
java.base/java.util.concurrent.ForkJoinPool.scan(ForkJoinPool.java:1656)
java.base/java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1594)
java.base/java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:183)

2025/08/02 15:22:32

42 ms

2/2

133.0 B

155.0 B

512981

default

toLocalIterator at SparkDataStreamBuilder.scala:39 +details

RDD: *(1) Project [CASE WHEN ((cap#94160377 = NA) OR (cap#94160377 = null)) THEN null ELSE cast(cap#94160377 as int) END AS cap#94160394, CASE WHEN (sort#94160378 = null) THEN null ELSE sort#94160378 END AS sort#94160395, CASE WHEN (description#94160379 = null) THEN null ELSE description#94160379 END AS description#94160396, CASE WHEN ((universe#94160380 = NA) OR (universe#94160380 = null)) THEN null ELSE cast(universe#94160380 as int) END AS universe#94160397] +- FileScan csv [cap#94160377,sort#94160378,description#94160379,universe#94160380] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/srv/plusamp/data/default/ea-market/curate/curate_cap.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<cap:string,sort:string,description:string,universe:string>

org.apache.spark.sql.Dataset.toLocalIterator(Dataset.scala:3000)
plusamp.middleware.model.core.data.SparkDataStreamBuilder.$anonfun$stream$1(SparkDataStreamBuilder.scala:39)
plusamp.scala.util.Profile$.time(Profile.scala:22)
plusamp.middleware.model.core.data.SparkDataStreamBuilder.<init>(SparkDataStreamBuilder.scala:39)
plusamp.middleware.graphql.datafile.SparkAccessor.$anonfun$retrieveData$3(SparkAccessor.scala:77)
scala.util.Success.$anonfun$map$1(Try.scala:255)
scala.util.Success.map(Try.scala:213)
scala.concurrent.Future.$anonfun$map$1(Future.scala:292)
scala.concurrent.impl.Promise.liftedTree1$1(Promise.scala:33)
scala.concurrent.impl.Promise.$anonfun$transform$1(Promise.scala:33)
scala.concurrent.impl.CallbackRunnable.run(Promise.scala:64)
java.base/java.util.concurrent.ForkJoinTask$RunnableExecuteAction.exec(ForkJoinTask.java:1426)
java.base/java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:290)
java.base/java.util.concurrent.ForkJoinPool$WorkQueue.topLevelExec(ForkJoinPool.java:1020)
java.base/java.util.concurrent.ForkJoinPool.scan(ForkJoinPool.java:1656)
java.base/java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1594)
java.base/java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:183)

2025/08/02 15:22:32

9 ms

1/1

624.0 B

133.0 B

Page: