Add task completion callback to avoid leak in limit after sort

Author: JoshRosen

core/src/main/java/org/apache/spark/util/collection/unsafe/sort/UnsafeExternalSorter.java

@@ -20,6 +20,9 @@
 import java.io.IOException;
 import java.util.LinkedList;
 
+import scala.runtime.AbstractFunction0;
+import scala.runtime.BoxedUnit;
+
 import com.google.common.annotations.VisibleForTesting;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
@@ -90,6 +93,17 @@ public UnsafeExternalSorter(
     this.fileBufferSizeBytes = (int) conf.getSizeAsKb("spark.shuffle.file.buffer", "32k") * 1024;
     this.pageSizeBytes = conf.getSizeAsBytes("spark.buffer.pageSize", "64m");
     initializeForWriting();
+
+    // Register a cleanup task with TaskContext to ensure that memory is guaranteed to be freed at
+    // the end of the task. This is necessary to avoid memory leaks in when the downstream operator
+    // does not fully consume the sorter's output (e.g. sort followed by limit).
+    taskContext.addOnCompleteCallback(new AbstractFunction0<BoxedUnit>() {
+      @Override
+      public BoxedUnit apply() {
+        freeMemory();
+        return null;
+      }
+    });
   }
 
   // TODO: metrics tracking + integration with shuffle write metrics

sql/core/src/test/scala/org/apache/spark/sql/execution/UnsafeExternalSortSuite.scala

@@ -36,10 +36,7 @@ class UnsafeExternalSortSuite extends SparkPlanTest with BeforeAndAfterAll {
     TestSQLContext.conf.setConf(SQLConf.CODEGEN_ENABLED, SQLConf.CODEGEN_ENABLED.defaultValue.get)
   }
 
-  ignore("sort followed by limit should not leak memory") {
-    // TODO: this test is going to fail until we implement a proper iterator interface
-    // with a close() method.
-    TestSQLContext.sparkContext.conf.set("spark.unsafe.exceptionOnMemoryLeak", "false")
+  test("sort followed by limit") {
     checkThatPlansAgree(
       (1 to 100).map(v => Tuple1(v)).toDF("a"),
       (child: SparkPlan) => Limit(10, UnsafeExternalSort('a.asc :: Nil, true, child)),
@@ -48,21 +45,6 @@ class UnsafeExternalSortSuite extends SparkPlanTest with BeforeAndAfterAll {
     )
   }
 
-  test("sort followed by limit") {
-    TestSQLContext.sparkContext.conf.set("spark.unsafe.exceptionOnMemoryLeak", "false")
-    try {
-      checkThatPlansAgree(
-        (1 to 100).map(v => Tuple1(v)).toDF("a"),
-        (child: SparkPlan) => Limit(10, UnsafeExternalSort('a.asc :: Nil, true, child)),
-        (child: SparkPlan) => Limit(10, Sort('a.asc :: Nil, global = true, child)),
-        sortAnswers = false
-      )
-    } finally {
-      TestSQLContext.sparkContext.conf.set("spark.unsafe.exceptionOnMemoryLeak", "false")
-
-    }
-  }
-
   test("sorting does not crash for large inputs") {
     val sortOrder = 'a.asc :: Nil
     val stringLength = 1024 * 1024 * 2