From a8dce9912f8dacaffba91155b8673e6c700e6c17 Mon Sep 17 00:00:00 2001 From: Reynold Xin Date: Mon, 3 Oct 2016 12:08:10 -0700 Subject: Add Spark 2.0.1 release. --- site/releases/spark-release-0-8-0.html | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'site/releases/spark-release-0-8-0.html') diff --git a/site/releases/spark-release-0-8-0.html b/site/releases/spark-release-0-8-0.html index 61d7c573e..2f56fecde 100644 --- a/site/releases/spark-release-0-8-0.html +++ b/site/releases/spark-release-0-8-0.html @@ -150,6 +150,9 @@
Latest News

Archive

@@ -210,13 +210,13 @@

Spark’s internal job scheduler has been refactored and extended to include more sophisticated scheduling policies. In particular, a fair scheduler implementation now allows multiple users to share an instance of Spark, which helps users running shorter jobs to achieve good performance, even when longer-running jobs are running in parallel. Support for topology-aware scheduling has been extended, including the ability to take into account rack locality and support for multiple executors on a single machine.

Easier Deployment and Linking

-

User programs can now link to Spark no matter which Hadoop version they need, without having to publish a version of spark-core specifically for that Hadoop version. An explanation of how to link against different Hadoop versions is provided here.

+

User programs can now link to Spark no matter which Hadoop version they need, without having to publish a version of spark-core specifically for that Hadoop version. An explanation of how to link against different Hadoop versions is provided here.

Expanded EC2 Capabilities

Spark’s EC2 scripts now support launching in any availability zone. Support has also been added for EC2 instance types which use the newer “HVM” architecture. This includes the cluster compute (cc1/cc2) family of instance types. We’ve also added support for running newer versions of HDFS alongside Spark. Finally, we’ve added the ability to launch clusters with maintenance releases of Spark in addition to launching the newest release.

Improved Documentation

-

This release adds documentation about cluster hardware provisioning and inter-operation with common Hadoop distributions. Docs are also included to cover the MLlib machine learning functions and new cluster monitoring features. Existing documentation has been updated to reflect changes in building and deploying Spark.

+

This release adds documentation about cluster hardware provisioning and inter-operation with common Hadoop distributions. Docs are also included to cover the MLlib machine learning functions and new cluster monitoring features. Existing documentation has been updated to reflect changes in building and deploying Spark.

Other Improvements