From b9451acdf4c73ab4b0b9d9827ab1ccedbcfb144f Mon Sep 17 00:00:00 2001 From: Patrick Wendell Date: Fri, 6 Dec 2013 19:25:28 -0800 Subject: Adding disclaimer for shuffle file consolidation --- docs/configuration.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'docs/configuration.md') diff --git a/docs/configuration.md b/docs/configuration.md index 22abe1c5a9..65b41b45cb 100644 --- a/docs/configuration.md +++ b/docs/configuration.md @@ -331,7 +331,7 @@ Apart from these, the following properties are also available, and may be useful spark.shuffle.consolidateFiles false - If set to "true", consolidates intermediate files created during a shuffle. Creating fewer files can improve filesystem performance if you run shuffles with large numbers of reduce tasks. + 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 reccomended 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. -- cgit v1.2.3