From 460f655cc60b1a1759b6f85ae8860595fc7586b4 Mon Sep 17 00:00:00 2001 From: Patrick Wendell <pwendell@gmail.com> Date: Thu, 9 Jan 2014 22:42:50 -0800 Subject: [PATCH] Enable shuffle consolidation by default. Bump this to being enabled for 0.9.0. --- .../scala/org/apache/spark/storage/ShuffleBlockManager.scala | 2 +- docs/configuration.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/storage/ShuffleBlockManager.scala b/core/src/main/scala/org/apache/spark/storage/ShuffleBlockManager.scala index e2b24298a5..6e0ff143b7 100644 --- a/core/src/main/scala/org/apache/spark/storage/ShuffleBlockManager.scala +++ b/core/src/main/scala/org/apache/spark/storage/ShuffleBlockManager.scala @@ -64,7 +64,7 @@ class ShuffleBlockManager(blockManager: BlockManager) { // Turning off shuffle file consolidation causes all shuffle Blocks to get their own file. // TODO: Remove this once the shuffle file consolidation feature is stable. val consolidateShuffleFiles = - conf.getBoolean("spark.shuffle.consolidateFiles", false) + conf.getBoolean("spark.shuffle.consolidateFiles", true) private val bufferSize = conf.getInt("spark.shuffle.file.buffer.kb", 100) * 1024 diff --git a/docs/configuration.md b/docs/configuration.md index 6717757781..b1a0e19167 100644 --- a/docs/configuration.md +++ b/docs/configuration.md @@ -371,7 +371,7 @@ Apart from these, the following properties are also available, and may be useful <tr> <td>spark.shuffle.consolidateFiles</td> - <td>false</td> + <td>true</td> <td> If set to "true", consolidates intermediate files created during a shuffle. Creating fewer files can improve filesystem performance for shuffles with large numbers of reduce tasks. It is recommended to set this to "true" when using ext4 or xfs filesystems. On ext3, this option might degrade performance on machines with many (>8) cores due to filesystem limitations. </td> -- GitLab