From e7f4d2534bb3361ec4b7af0d42bc798a7a425226 Mon Sep 17 00:00:00 2001
From: Tathagata Das <tathagata.das1565@gmail.com>
Date: Tue, 25 Nov 2014 23:15:58 -0800
Subject: [PATCH] [SPARK-4612] Reduce task latency and increase scheduling
throughput by making configuration initialization lazy
https://github.com/apache/spark/blob/master/core/src/main/scala/org/apache/spark/executor/Executor.scala#L337 creates a configuration object for every task that is launched, even if there is no new dependent file/JAR to update. This is a heavy-weight creation that should be avoided if there is no new file/JAR to update. This PR makes that creation lazy. Quick local test in spark-perf scheduling throughput tests gives the following numbers in a local standalone scheduler mode.
1 job with 10000 tasks: before 7.8395 seconds, after 2.6415 seconds = 3x increase in task scheduling throughput
pwendell JoshRosen
Author: Tathagata Das <tathagata.das1565@gmail.com>
Closes #3463 from tdas/lazy-config and squashes the following commits:
c791c1e [Tathagata Das] Reduce task latency by making configuration initialization lazy
---
core/src/main/scala/org/apache/spark/executor/Executor.scala | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/core/src/main/scala/org/apache/spark/executor/Executor.scala b/core/src/main/scala/org/apache/spark/executor/Executor.scala
index 5fa584591d..835157fc52 100644
--- a/core/src/main/scala/org/apache/spark/executor/Executor.scala
+++ b/core/src/main/scala/org/apache/spark/executor/Executor.scala
@@ -334,7 +334,7 @@ private[spark] class Executor(
* SparkContext. Also adds any new JARs we fetched to the class loader.
*/
private def updateDependencies(newFiles: HashMap[String, Long], newJars: HashMap[String, Long]) {
- val hadoopConf = SparkHadoopUtil.get.newConfiguration(conf)
+ lazy val hadoopConf = SparkHadoopUtil.get.newConfiguration(conf)
synchronized {
// Fetch missing dependencies
for ((name, timestamp) <- newFiles if currentFiles.getOrElse(name, -1L) < timestamp) {
--
GitLab