From a2d7e25e7c85ce17c8ceac5e1806afe96d3acc14 Mon Sep 17 00:00:00 2001
From: Adam Roberts <aroberts@uk.ibm.com>
Date: Fri, 4 Nov 2016 12:06:06 -0700
Subject: [PATCH] [SPARK-18197][CORE] Optimise AppendOnlyMap implementation
## What changes were proposed in this pull request?
This improvement works by using the fastest comparison test first and we observed a 1% throughput performance improvement on PageRank (HiBench large profile) with this change.
We used tprof and before the change in AppendOnlyMap.changeValue (where the optimisation occurs) this method was being used for 8053 profiling ticks representing 0.72% of the overall application time.
After this change we observed this method only occurring for 2786 ticks and for 0.25% of the overall time.
## How was this patch tested?
Existing unit tests and for performance we used HiBench large, profiling with tprof and IBM Healthcenter.
Author: Adam Roberts <aroberts@uk.ibm.com>
Closes #15714 from a-roberts/patch-9.
(cherry picked from commit a42d738c5de08bd395a7c220c487146173c6c163)
Signed-off-by: Reynold Xin <rxin@databricks.com>
---
.../apache/spark/util/collection/AppendOnlyMap.scala | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/core/src/main/scala/org/apache/spark/util/collection/AppendOnlyMap.scala b/core/src/main/scala/org/apache/spark/util/collection/AppendOnlyMap.scala
index 6b74a29ace..bcb95b416d 100644
--- a/core/src/main/scala/org/apache/spark/util/collection/AppendOnlyMap.scala
+++ b/core/src/main/scala/org/apache/spark/util/collection/AppendOnlyMap.scala
@@ -140,16 +140,16 @@ class AppendOnlyMap[K, V](initialCapacity: Int = 64)
var i = 1
while (true) {
val curKey = data(2 * pos)
- if (k.eq(curKey) || k.equals(curKey)) {
- val newValue = updateFunc(true, data(2 * pos + 1).asInstanceOf[V])
- data(2 * pos + 1) = newValue.asInstanceOf[AnyRef]
- return newValue
- } else if (curKey.eq(null)) {
+ if (curKey.eq(null)) {
val newValue = updateFunc(false, null.asInstanceOf[V])
data(2 * pos) = k
data(2 * pos + 1) = newValue.asInstanceOf[AnyRef]
incrementSize()
return newValue
+ } else if (k.eq(curKey) || k.equals(curKey)) {
+ val newValue = updateFunc(true, data(2 * pos + 1).asInstanceOf[V])
+ data(2 * pos + 1) = newValue.asInstanceOf[AnyRef]
+ return newValue
} else {
val delta = i
pos = (pos + delta) & mask
--
GitLab