PlusAMP App Middleware - Details for Job 330559

Status: SUCCEEDED
Submitted: 2025/08/01 16:00:17
Duration: 80 ms
Completed Stages: 3

Enable zooming

digraph G { subgraph clusterstage_511661 { label="Stage 511661"; subgraph cluster6269847 { label="Scan csv "; 3605629 [labelType="html" label="FileScanRDD [3605629] $anonfun$withThreadLocalCaptured$1 at FutureTask.java:264"]; 3605630 [labelType="html" label="MapPartitionsRDD [3605630] $anonfun$withThreadLocalCaptured$1 at FutureTask.java:264"]; } subgraph cluster6269844 { label="WholeStageCodegen (1)"; 3605631 [labelType="html" label="MapPartitionsRDD [3605631] $anonfun$withThreadLocalCaptured$1 at FutureTask.java:264"]; } subgraph cluster6269842 { label="InMemoryTableScan"; 3605632 [labelType="html" label="MapPartitionsRDD [3605632] $anonfun$withThreadLocalCaptured$1 at FutureTask.java:264"]; 3605633 [labelType="html" label="*(1) Project [CASE WHEN ((cap#93880496 = NA) OR (cap#93880496 = null)) THEN null ELSE cast(cap#93880496 as int) END AS cap#93880528, CASE WHEN (sort#93880498 = null) THEN null ELSE sort#93880498 END AS sort#93880531, CASE WHEN (description#93880500 = null) THEN null ELSE description#93880500 END AS description#93880533, CASE WHEN ((universe#93880502 = NA) OR (universe#93880502 = null)) THEN null ELSE cast(universe#93880502 as int) END AS universe#93880535]\n+- FileScan csv [cap#93880496,sort#93880498,description#93880500,universe#93880502] 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 [3605633] [Cached] $anonfun$withThreadLocalCaptured$1 at FutureTask.java:264"]; } subgraph cluster6286049 { label="InMemoryTableScan"; 3614955 [labelType="html" label="MapPartitionsRDD [3614955] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3614956 [labelType="html" label="MapPartitionsRDD [3614956] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3614957 [labelType="html" label="MapPartitionsRDD [3614957] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } subgraph cluster6286014 { label="WholeStageCodegen (2)"; 3614958 [labelType="html" label="MapPartitionsRDD [3614958] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } subgraph cluster6286013 { label="Exchange"; 3614977 [labelType="html" label="MapPartitionsRDD [3614977] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } } 3605629->3605630; 3605630->3605631; 3605631->3605632; 3605632->3605633; 3605633->3614955; 3614955->3614956; 3614956->3614957; 3614957->3614958; 3614958->3614977; }

3605633

digraph G { subgraph clusterstage_511662 { label="Stage 511662"; subgraph cluster6286013 { label="Exchange"; 3614979 [labelType="html" label="ShuffledRowRDD [3614979] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } subgraph cluster6286006 { label="WholeStageCodegen (3)"; 3614984 [labelType="html" label="MapPartitionsRDD [3614984] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } subgraph cluster6286005 { label="InMemoryTableScan"; 3614985 [labelType="html" label="MapPartitionsRDD [3614985] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3614986 [labelType="html" label="*(3) Project [cap#94128683, turnover#94125684, (1.0 / cast(turnover#94125684 as double)) AS days_hold#94128738]\n+- *(3) Sort [cap_sort#94128621 ASC NULLS FIRST], true, 0\n +- Exchange rangepartitioning(cap_sort#94128621 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [id=#7515468]\n +- *(2) Project [turnover#94125684, cap_description#94128620 AS cap#94128683, cap_sort#94128621]\n +- *(2) BroadcastHashJoin [knownfloatingpointnormalized(normalizenanandzero(cap#94125439))], [knownfloatingpointnormalized(normalizenanandzero(cast(cap#93880528 as float)))], Inner, BuildLeft, false\n :- BroadcastExchange HashedRelationBroadcastMode(List(knownfloatingpointnormalized(normalizenanandzero(input[0, float, false]))),false), [id=#7515460]\n : +- *(1) Filter isnotnull(cap#94125439)\n : +- *(1) ColumnarToRow\n : +- InMemoryTableScan [cap#94125439, turnover#94125684], [isnotnull(cap#94125439)]\n : +- InMemoryRelation [cap#94125439, retIC#941... [3614986] [Cached] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3614987 [labelType="html" label="MapPartitionsRDD [3614987] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3614988 [labelType="html" label="MapPartitionsRDD [3614988] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3614989 [labelType="html" label="MapPartitionsRDD [3614989] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } subgraph cluster6286004 { label="CollectLimit"; 3614990 [labelType="html" label="MapPartitionsRDD [3614990] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3614991 [labelType="html" label="MapPartitionsRDD [3614991] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } } 3614979->3614984; 3614984->3614985; 3614985->3614986; 3614986->3614987; 3614987->3614988; 3614988->3614989; 3614989->3614990; 3614990->3614991; }

3614977,3614979

3614986

digraph G { subgraph clusterstage_511663 { label="Stage 511663"; subgraph cluster6286004 { label="CollectLimit"; 3614992 [labelType="html" label="ShuffledRowRDD [3614992] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; 3614993 [labelType="html" label="MapPartitionsRDD [3614993] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } subgraph cluster6286093 { label="mapPartitionsInternal"; 3614994 [labelType="html" label="MapPartitionsRDD [3614994] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } subgraph cluster6286094 { label="map"; 3614995 [labelType="html" label="MapPartitionsRDD [3614995] [Unordered] toLocalIterator at SparkDataStreamBuilder.scala:39"]; } } 3614992->3614993; 3614993->3614994; 3614994->3614995; }

3614991,3614992

Completed Stages (3)

Page:

Stage Id ▾	Pool Name	Description	Submitted	Duration	Tasks: Succeeded/Total	Input	Shuffle Read	Shuffle Write
511663	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$WorkQueue.topLevelExec(ForkJoinPool.java:1020) java.base/java.util.concurrent.ForkJoinPool.scan(ForkJoinPool.java:1656) java.base/java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1594) java.base/java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:183)	2025/08/01 16:00:17	18 ms	1/1		154.0 B
511662	default	toLocalIterator at SparkDataStreamBuilder.scala:39 +details RDD: (3) Project [cap#94128683, turnover#94125684, (1.0 / cast(turnover#94125684 as double)) AS days_hold#94128738] +- (3) Sort [cap_sort#94128621 ASC NULLS FIRST], true, 0 +- Exchange rangepartitioning(cap_sort#94128621 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [id=#7515468] +- (2) Project [turnover#94125684, cap_description#94128620 AS cap#94128683, cap_sort#94128621] +- (2) BroadcastHashJoin [knownfloatingpointnormalized(normalizenanandzero(cap#94125439))], [knownfloatingpointnormalized(normalizenanandzero(cast(cap#93880528 as float)))], Inner, BuildLeft, false :- BroadcastExchange HashedRelationBroadcastMode(List(knownfloatingpointnormalized(normalizenanandzero(input[0, float, false]))),false), [id=#7515460] : +- (1) Filter isnotnull(cap#94125439) : +- (1) ColumnarToRow : +- InMemoryTableScan [cap#94125439, turnover#94125684], [isnotnull(cap#94125439)] : +- InMemoryRelation [cap#94125439, retIC#941... org.apache.spark.sql.Dataset.toLocalIterator(Dataset.scala:3000) plusamp.middleware.model.core.data.SparkDataStreamBuilder.$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$WorkQueue.topLevelExec(ForkJoinPool.java:1020) java.base/java.util.concurrent.ForkJoinPool.scan(ForkJoinPool.java:1656) java.base/java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1594) java.base/java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:183)	2025/08/01 16:00:17	36 ms	2/2		134.0 B	154.0 B
511661	default	toLocalIterator at SparkDataStreamBuilder.scala:39 +details RDD: *(1) Project [CASE WHEN ((cap#93880496 = NA) OR (cap#93880496 = null)) THEN null ELSE cast(cap#93880496 as int) END AS cap#93880528, CASE WHEN (sort#93880498 = null) THEN null ELSE sort#93880498 END AS sort#93880531, CASE WHEN (description#93880500 = null) THEN null ELSE description#93880500 END AS description#93880533, CASE WHEN ((universe#93880502 = NA) OR (universe#93880502 = null)) THEN null ELSE cast(universe#93880502 as int) END AS universe#93880535] +- FileScan csv [cap#93880496,sort#93880498,description#93880500,universe#93880502] Batched: false, DataFilters: [], Format: CSV, Location: InMemoryFileIndex(1 paths)[file:/srv/plusamp/data/default/ea-market/curate/curate_cap.csv], PartitionFilters: [], PushedFilters: [], ReadSchema: struct<cap:string,sort:string,description:string,universe:string> org.apache.spark.sql.Dataset.toLocalIterator(Dataset.scala:3000) plusamp.middleware.model.core.data.SparkDataStreamBuilder.$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)	2025/08/01 16:00:17	15 ms	1/1	624.0 B		134.0 B

Stage Id ▾

Pool Name

Description

Submitted

Duration

Tasks: Succeeded/Total

Input

Output

Shuffle Read

Shuffle Write

511663

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)

2025/08/01 16:00:17

18 ms

1/1

154.0 B

511662

default

toLocalIterator at SparkDataStreamBuilder.scala:39 +details

RDD: *(3) Project [cap#94128683, turnover#94125684, (1.0 / cast(turnover#94125684 as double)) AS days_hold#94128738] +- *(3) Sort [cap_sort#94128621 ASC NULLS FIRST], true, 0 +- Exchange rangepartitioning(cap_sort#94128621 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [id=#7515468] +- *(2) Project [turnover#94125684, cap_description#94128620 AS cap#94128683, cap_sort#94128621] +- *(2) BroadcastHashJoin [knownfloatingpointnormalized(normalizenanandzero(cap#94125439))], [knownfloatingpointnormalized(normalizenanandzero(cast(cap#93880528 as float)))], Inner, BuildLeft, false :- BroadcastExchange HashedRelationBroadcastMode(List(knownfloatingpointnormalized(normalizenanandzero(input[0, float, false]))),false), [id=#7515460] : +- *(1) Filter isnotnull(cap#94125439) : +- *(1) ColumnarToRow : +- InMemoryTableScan [cap#94125439, turnover#94125684], [isnotnull(cap#94125439)] : +- InMemoryRelation [cap#94125439, retIC#941...

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)

2025/08/01 16:00:17

36 ms

2/2

134.0 B

154.0 B

511661

default

toLocalIterator at SparkDataStreamBuilder.scala:39 +details

RDD: *(1) Project [CASE WHEN ((cap#93880496 = NA) OR (cap#93880496 = null)) THEN null ELSE cast(cap#93880496 as int) END AS cap#93880528, CASE WHEN (sort#93880498 = null) THEN null ELSE sort#93880498 END AS sort#93880531, CASE WHEN (description#93880500 = null) THEN null ELSE description#93880500 END AS description#93880533, CASE WHEN ((universe#93880502 = NA) OR (universe#93880502 = null)) THEN null ELSE cast(universe#93880502 as int) END AS universe#93880535] +- FileScan csv [cap#93880496,sort#93880498,description#93880500,universe#93880502] 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)

2025/08/01 16:00:17

15 ms

1/1

624.0 B

134.0 B

Page: