[SPARK-18016][SQL][FOLLOW-UP] Code Generation: Constant Pool Limit - reduce entries for mutable state

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala

@@ -178,7 +178,7 @@ class CodegenContext {
 
     /**
      * Returns the reference of next available slot in current compacted array. The size of each
-     * compacted array is controlled by the config `CodeGenerator.MUTABLESTATEARRAY_SIZE_LIMIT`.
+     * compacted array is controlled by the constant `CodeGenerator.MUTABLESTATEARRAY_SIZE_LIMIT`.
      * Once reaching the threshold, new compacted array is created.
      */
     def getNextSlot(): String = {
@@ -299,7 +299,7 @@ class CodegenContext {
   def initMutableStates(): String = {
     // It's possible that we add same mutable state twice, e.g. the `mergeExpressions` in
     // `TypedAggregateExpression`, we should call `distinct` here to remove the duplicated ones.
-    val initCodes = mutableStateInitCode.distinct
+    val initCodes = mutableStateInitCode.distinct.map(_ + "\n")
 
     // The generated initialization code may exceed 64kb function size limit in JVM if there are too
     // many mutable states, so split it into multiple functions.

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala

@@ -118,9 +118,8 @@ case class Like(left: Expression, right: Expression) extends StringRegexExpressi
       if (rVal != null) {
         val regexStr =
           StringEscapeUtils.escapeJava(escape(rVal.asInstanceOf[UTF8String].toString()))
-        // inline mutable state since not many Like operations in a task
         val pattern = ctx.addMutableState(patternClass, "patternLike",
-          v => s"""$v = ${patternClass}.compile("$regexStr");""", forceInline = true)
+          v => s"""$v = $patternClass.compile("$regexStr");""")
 
         // We don't use nullSafeCodeGen here because we don't want to re-evaluate right again.
         val eval = left.genCode(ctx)
@@ -143,9 +142,9 @@ case class Like(left: Expression, right: Expression) extends StringRegexExpressi
       val rightStr = ctx.freshName("rightStr")
       nullSafeCodeGen(ctx, ev, (eval1, eval2) => {
         s"""
-          String $rightStr = ${eval2}.toString();
-          ${patternClass} $pattern = ${patternClass}.compile($escapeFunc($rightStr));
-          ${ev.value} = $pattern.matcher(${eval1}.toString()).matches();
+          String $rightStr = $eval2.toString();
+          $patternClass $pattern = $patternClass.compile($escapeFunc($rightStr));
+          ${ev.value} = $pattern.matcher($eval1.toString()).matches();
         """
       })
     }
@@ -194,9 +193,8 @@ case class RLike(left: Expression, right: Expression) extends StringRegexExpress
       if (rVal != null) {
         val regexStr =
           StringEscapeUtils.escapeJava(rVal.asInstanceOf[UTF8String].toString())
-        // inline mutable state since not many RLike operations in a task
         val pattern = ctx.addMutableState(patternClass, "patternRLike",
-          v => s"""$v = ${patternClass}.compile("$regexStr");""", forceInline = true)
+          v => s"""$v = $patternClass.compile("$regexStr");""")
 
         // We don't use nullSafeCodeGen here because we don't want to re-evaluate right again.
         val eval = left.genCode(ctx)
@@ -219,9 +217,9 @@ case class RLike(left: Expression, right: Expression) extends StringRegexExpress
       val pattern = ctx.freshName("pattern")
       nullSafeCodeGen(ctx, ev, (eval1, eval2) => {
         s"""
-          String $rightStr = ${eval2}.toString();
-          ${patternClass} $pattern = ${patternClass}.compile($rightStr);
-          ${ev.value} = $pattern.matcher(${eval1}.toString()).find(0);
+          String $rightStr = $eval2.toString();
+          $patternClass $pattern = $patternClass.compile($rightStr);
+          ${ev.value} = $pattern.matcher($eval1.toString()).find(0);
         """
       })
     }
@@ -338,25 +336,25 @@ case class RegExpReplace(subject: Expression, regexp: Expression, rep: Expressio
 
     nullSafeCodeGen(ctx, ev, (subject, regexp, rep) => {
     s"""
-      if (!$regexp.equals(${termLastRegex})) {
+      if (!$regexp.equals($termLastRegex)) {
         // regex value changed
-        ${termLastRegex} = $regexp.clone();
-        ${termPattern} = ${classNamePattern}.compile(${termLastRegex}.toString());
+        $termLastRegex = $regexp.clone();
+        $termPattern = $classNamePattern.compile($termLastRegex.toString());
       }
-      if (!$rep.equals(${termLastReplacementInUTF8})) {
+      if (!$rep.equals($termLastReplacementInUTF8)) {
         // replacement string changed
-        ${termLastReplacementInUTF8} = $rep.clone();
-        ${termLastReplacement} = ${termLastReplacementInUTF8}.toString();
+        $termLastReplacementInUTF8 = $rep.clone();
+        $termLastReplacement = $termLastReplacementInUTF8.toString();
       }
-      $classNameStringBuffer ${termResult} = new $classNameStringBuffer();
-      java.util.regex.Matcher ${matcher} = ${termPattern}.matcher($subject.toString());
+      $classNameStringBuffer $termResult = new $classNameStringBuffer();
+      java.util.regex.Matcher $matcher = $termPattern.matcher($subject.toString());
 
-      while (${matcher}.find()) {
-        ${matcher}.appendReplacement(${termResult}, ${termLastReplacement});
+      while ($matcher.find()) {
+        $matcher.appendReplacement($termResult, $termLastReplacement);
       }
-      ${matcher}.appendTail(${termResult});
-      ${ev.value} = UTF8String.fromString(${termResult}.toString());
-      ${termResult} = null;
+      $matcher.appendTail($termResult);
+      ${ev.value} = UTF8String.fromString($termResult.toString());
+      $termResult = null;
       $setEvNotNull
     """
     })
@@ -425,19 +423,19 @@ case class RegExpExtract(subject: Expression, regexp: Expression, idx: Expressio
 
     nullSafeCodeGen(ctx, ev, (subject, regexp, idx) => {
       s"""
-      if (!$regexp.equals(${termLastRegex})) {
+      if (!$regexp.equals($termLastRegex)) {
         // regex value changed
-        ${termLastRegex} = $regexp.clone();
-        ${termPattern} = ${classNamePattern}.compile(${termLastRegex}.toString());
+        $termLastRegex = $regexp.clone();
+        $termPattern = $classNamePattern.compile($termLastRegex.toString());
       }
-      java.util.regex.Matcher ${matcher} =
-        ${termPattern}.matcher($subject.toString());
-      if (${matcher}.find()) {
-        java.util.regex.MatchResult ${matchResult} = ${matcher}.toMatchResult();
-        if (${matchResult}.group($idx) == null) {
+      java.util.regex.Matcher $matcher =
+        $termPattern.matcher($subject.toString());
+      if ($matcher.find()) {
+        java.util.regex.MatchResult $matchResult = $matcher.toMatchResult();
+        if ($matchResult.group($idx) == null) {
           ${ev.value} = UTF8String.EMPTY_UTF8;
         } else {
-          ${ev.value} = UTF8String.fromString(${matchResult}.group($idx));
+          ${ev.value} = UTF8String.fromString($matchResult.group($idx));
         }
         $setEvNotNull
       } else {

sql/core/src/main/scala/org/apache/spark/sql/execution/WholeStageCodegenExec.scala

@@ -283,7 +283,7 @@ case class InputAdapter(child: SparkPlan) extends UnaryExecNode with CodegenSupp
 
   override def doProduce(ctx: CodegenContext): String = {
     // Right now, InputAdapter is only used when there is one input RDD.
-    // inline mutable state since an inputAdaptor in a task
+    // inline mutable state since an InputAdapter is used once in a task for WholeStageCodegen
     val input = ctx.addMutableState("scala.collection.Iterator", "input", v => s"$v = inputs[0];",
       forceInline = true)
     val row = ctx.freshName("row")

sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala

@@ -587,20 +587,24 @@ case class HashAggregateExec(
           fastHashMapClassName, groupingKeySchema, bufferSchema).generate()
         ctx.addInnerClass(generatedMap)
 
+        // inline mutable state since not many aggregation operations in a task
         fastHashMapTerm = ctx.addMutableState(fastHashMapClassName, "vectorizedHastHashMap",
-          v => s"$v = new $fastHashMapClassName();")
-        ctx.addMutableState(s"java.util.Iterator<InternalRow>", "vectorizedFastHashMapIter")
+          v => s"$v = new $fastHashMapClassName();", forceInline = true)
+        ctx.addMutableState(s"java.util.Iterator<InternalRow>", "vectorizedFastHashMapIter",
+          forceInline = true)
       } else {
         val generatedMap = new RowBasedHashMapGenerator(ctx, aggregateExpressions,
           fastHashMapClassName, groupingKeySchema, bufferSchema).generate()
         ctx.addInnerClass(generatedMap)
 
+        // inline mutable state since not many aggregation operations in a task
         fastHashMapTerm = ctx.addMutableState(fastHashMapClassName, "fastHashMap",
           v => s"$v = new $fastHashMapClassName(" +
-            s"$thisPlan.getTaskMemoryManager(), $thisPlan.getEmptyAggregationBuffer());")
+            s"$thisPlan.getTaskMemoryManager(), $thisPlan.getEmptyAggregationBuffer());",
+          forceInline = true)
         ctx.addMutableState(
           "org.apache.spark.unsafe.KVIterator<UnsafeRow, UnsafeRow>",
-          "fastHashMapIter")
+          "fastHashMapIter", forceInline = true)
       }
     }
 
@@ -611,7 +615,7 @@ case class HashAggregateExec(
     // create hashMap
     val hashMapClassName = classOf[UnsafeFixedWidthAggregationMap].getName
     hashMapTerm = ctx.addMutableState(hashMapClassName, "hashMap",
-      v => s"$v = $thisPlan.createHashMap();")
+      v => s"$v = $thisPlan.createHashMap();", forceInline = true)
     sorterTerm = ctx.addMutableState(classOf[UnsafeKVExternalSorter].getName, "sorter",
       forceInline = true)
 

sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala

@@ -440,8 +440,9 @@ case class SortMergeJoinExec(
     val spillThreshold = getSpillThreshold
     val inMemoryThreshold = getInMemoryThreshold
 
+    // inline mutable state since not many join operations in a task
     val matches = ctx.addMutableState(clsName, "matches",
-      v => s"$v = new $clsName($inMemoryThreshold, $spillThreshold);")
+      v => s"$v = new $clsName($inMemoryThreshold, $spillThreshold);", forceInline = true)
     // Copy the left keys as class members so they could be used in next function call.
     val matchedKeyVars = copyKeys(ctx, leftKeyVars)