From 1714350bddd78cd1398e1a816f675ab729001081 Mon Sep 17 00:00:00 2001
From: Yin Huai <yhuai@databricks.com>
Date: Wed, 18 Nov 2015 00:42:52 -0800
Subject: [SPARK-11792][SQL] SizeEstimator cannot provide a good size
 estimation of UnsafeHashedRelations

https://issues.apache.org/jira/browse/SPARK-11792

Right now, SizeEstimator will "think" a small UnsafeHashedRelation is several GBs.

Author: Yin Huai <yhuai@databricks.com>

Closes #9788 from yhuai/SPARK-11792.
---
 .../org/apache/spark/memory/TaskMemoryManager.java |  3 +++
 .../org/apache/spark/util/SizeEstimator.scala      | 26 ++++++++++++++++++----
 .../org/apache/spark/util/SizeEstimatorSuite.scala | 22 ++++++++++++++++++
 3 files changed, 47 insertions(+), 4 deletions(-)

(limited to 'core')

diff --git a/core/src/main/java/org/apache/spark/memory/TaskMemoryManager.java b/core/src/main/java/org/apache/spark/memory/TaskMemoryManager.java
index 5f743b2885..d31eb449eb 100644
--- a/core/src/main/java/org/apache/spark/memory/TaskMemoryManager.java
+++ b/core/src/main/java/org/apache/spark/memory/TaskMemoryManager.java
@@ -215,6 +215,9 @@ public class TaskMemoryManager {
       logger.info(
         "{} bytes of memory were used by task {} but are not associated with specific consumers",
         memoryNotAccountedFor, taskAttemptId);
+      logger.info(
+        "{} bytes of memory are used for execution and {} bytes of memory are used for storage",
+        memoryManager.executionMemoryUsed(), memoryManager.storageMemoryUsed());
     }
   }
 
diff --git a/core/src/main/scala/org/apache/spark/util/SizeEstimator.scala b/core/src/main/scala/org/apache/spark/util/SizeEstimator.scala
index 23ee4eff08..c3a2675ee5 100644
--- a/core/src/main/scala/org/apache/spark/util/SizeEstimator.scala
+++ b/core/src/main/scala/org/apache/spark/util/SizeEstimator.scala
@@ -31,6 +31,16 @@ import org.apache.spark.Logging
 import org.apache.spark.annotation.DeveloperApi
 import org.apache.spark.util.collection.OpenHashSet
 
+/**
+ * A trait that allows a class to give [[SizeEstimator]] more accurate size estimation.
+ * When a class extends it, [[SizeEstimator]] will query the `estimatedSize` first.
+ * If `estimatedSize` does not return [[None]], [[SizeEstimator]] will use the returned size
+ * as the size of the object. Otherwise, [[SizeEstimator]] will do the estimation work.
+ */
+private[spark] trait SizeEstimation {
+  def estimatedSize: Option[Long]
+}
+
 /**
  * :: DeveloperApi ::
  * Estimates the sizes of Java objects (number of bytes of memory they occupy), for use in
@@ -199,10 +209,18 @@ object SizeEstimator extends Logging {
       // the size estimator since it references the whole REPL. Do nothing in this case. In
       // general all ClassLoaders and Classes will be shared between objects anyway.
     } else {
-      val classInfo = getClassInfo(cls)
-      state.size += alignSize(classInfo.shellSize)
-      for (field <- classInfo.pointerFields) {
-        state.enqueue(field.get(obj))
+      val estimatedSize = obj match {
+        case s: SizeEstimation => s.estimatedSize
+        case _ => None
+      }
+      if (estimatedSize.isDefined) {
+        state.size += estimatedSize.get
+      } else {
+        val classInfo = getClassInfo(cls)
+        state.size += alignSize(classInfo.shellSize)
+        for (field <- classInfo.pointerFields) {
+          state.enqueue(field.get(obj))
+        }
       }
     }
   }
diff --git a/core/src/test/scala/org/apache/spark/util/SizeEstimatorSuite.scala b/core/src/test/scala/org/apache/spark/util/SizeEstimatorSuite.scala
index 20550178fb..9b6261af12 100644
--- a/core/src/test/scala/org/apache/spark/util/SizeEstimatorSuite.scala
+++ b/core/src/test/scala/org/apache/spark/util/SizeEstimatorSuite.scala
@@ -60,6 +60,18 @@ class DummyString(val arr: Array[Char]) {
   @transient val hash32: Int = 0
 }
 
+class DummyClass8 extends SizeEstimation {
+  val x: Int = 0
+
+  override def estimatedSize: Option[Long] = Some(2015)
+}
+
+class DummyClass9 extends SizeEstimation {
+  val x: Int = 0
+
+  override def estimatedSize: Option[Long] = None
+}
+
 class SizeEstimatorSuite
   extends SparkFunSuite
   with BeforeAndAfterEach
@@ -214,4 +226,14 @@ class SizeEstimatorSuite
     // Class should be 32 bytes on s390x if recognised as 64 bit platform
     assertResult(32)(SizeEstimator.estimate(new DummyClass7))
   }
+
+  test("SizeEstimation can provide the estimated size") {
+    // DummyClass8 provides its size estimation.
+    assertResult(2015)(SizeEstimator.estimate(new DummyClass8))
+    assertResult(20206)(SizeEstimator.estimate(Array.fill(10)(new DummyClass8)))
+
+    // DummyClass9 does not provide its size estimation.
+    assertResult(16)(SizeEstimator.estimate(new DummyClass9))
+    assertResult(216)(SizeEstimator.estimate(Array.fill(10)(new DummyClass9)))
+  }
 }
-- 
cgit v1.2.3