From a94e898cc6ac3e799cb01bbe47e054526617e62d Mon Sep 17 00:00:00 2001 From: Niranjan Artal Date: Thu, 2 Nov 2023 16:16:49 -0700 Subject: [PATCH] addressed review comments --- .../rapids/tool/qualification/QualificationAppInfo.scala | 8 +++----- .../QualificationExpectations/complex_dec_expectation.csv | 2 +- 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/sql/rapids/tool/qualification/QualificationAppInfo.scala b/core/src/main/scala/org/apache/spark/sql/rapids/tool/qualification/QualificationAppInfo.scala index 560571a26..33cc5c23c 100644 --- a/core/src/main/scala/org/apache/spark/sql/rapids/tool/qualification/QualificationAppInfo.scala +++ b/core/src/main/scala/org/apache/spark/sql/rapids/tool/qualification/QualificationAppInfo.scala @@ -201,12 +201,12 @@ class QualificationAppInfo( private def checkStageIdInExec(prev: Option[ExecInfo], execInfo: ExecInfo, next: Option[ExecInfo]): (Seq[(Int, ExecInfo)], Option[ExecInfo]) = { val associatedStages = { - if (execInfo.stages.size > 1) { + if (execInfo.stages.size >= 1) { execInfo.stages.toSeq - } else if (execInfo.stages.size < 1) { + } else { if (prev.exists(_.stages.size >= 1)) { prev.flatMap(_.stages.headOption).toSeq - } else if (next.exists(_.stages.size >= 1)) { + } else if (next.nonEmpty) { next.flatMap(_.stages.headOption).toSeq } else { // we don't know what stage its in or its duration @@ -214,8 +214,6 @@ class QualificationAppInfo( s"so speedup factor isn't applied anywhere.") Seq.empty } - } else { - Seq(execInfo.stages.head) } } if (associatedStages.nonEmpty) { diff --git a/core/src/test/resources/QualificationExpectations/complex_dec_expectation.csv b/core/src/test/resources/QualificationExpectations/complex_dec_expectation.csv index f2fb0a114..753bdcacf 100644 --- a/core/src/test/resources/QualificationExpectations/complex_dec_expectation.csv +++ b/core/src/test/resources/QualificationExpectations/complex_dec_expectation.csv @@ -1,2 +1,2 @@ App Name,App ID,Recommendation,Estimated GPU Speedup,Estimated GPU Duration,Estimated GPU Time Saved,SQL DF Duration,SQL Dataframe Task Duration,App Duration,GPU Opportunity,Executor CPU Time Percent,SQL Ids with Failures,Unsupported Read File Formats and Types,Unsupported Write Data Format,Complex Types,Nested Complex Types,Potential Problems,Longest SQL Duration,NONSQL Task Duration Plus Overhead,Unsupported Task Duration,Supported SQL DF Task Duration,Task Speedup Factor,App Duration Estimated,Unsupported Execs,Unsupported Expressions,Estimated Job Frequency (monthly) -"Spark shell","local-1626104300434","Not Recommended",1.0,129898.52,1205.47,2429,1469,131104,1923,88.35,"","","","struct,lastname:string>;struct,previous:struct,city:string>>;array>;map;map>;map>;array>;array","struct,lastname:string>;struct,previous:struct,city:string>>;array>;map>;map>;array>","NESTED COMPLEX TYPE",1260,128847,306,1163,2.68,false,"CollectLimit","",30 \ No newline at end of file +"Spark shell","local-1626104300434","Not Recommended",1.0,129898.52,1205.47,2429,1469,131104,1923,88.35,"","","","struct,lastname:string>;struct,previous:struct,city:string>>;array>;map;map>;map>;array>;array","struct,lastname:string>;struct,previous:struct,city:string>>;array>;map>;map>;array>","NESTED COMPLEX TYPE",1260,128847,306,1163,2.68,false,"CollectLimit","",30