From 1a7fc74ccf1b98d929aa4b2ab45c24d4c3d42c1a Mon Sep 17 00:00:00 2001
From: Sun Rui <rui.sun@intel.com>
Date: Fri, 22 Apr 2016 11:19:52 -0700
Subject: [PATCH] [SPARK-13178] RRDD faces with concurrency issue in case of
rdd.zip(rdd).count().
## What changes were proposed in this pull request?
The concurrency issue reported in SPARK-13178 was fixed by the PR https://github.com/apache/spark/pull/10947 for SPARK-12792.
This PR just removes a workaround not needed anymore.
## How was this patch tested?
SparkR unit tests.
Author: Sun Rui <rui.sun@intel.com>
Closes #12606 from sun-rui/SPARK-13178.
---
R/pkg/inst/tests/testthat/test_mllib.R | 2 --
1 file changed, 2 deletions(-)
diff --git a/R/pkg/inst/tests/testthat/test_mllib.R b/R/pkg/inst/tests/testthat/test_mllib.R
index 47bbf7e5bd..1597306bb6 100644
--- a/R/pkg/inst/tests/testthat/test_mllib.R
+++ b/R/pkg/inst/tests/testthat/test_mllib.R
@@ -131,8 +131,6 @@ test_that("kmeans", {
newIris$Species <- NULL
training <- suppressWarnings(createDataFrame(sqlContext, newIris))
- # Cache the DataFrame here to work around the bug SPARK-13178.
- cache(training)
take(training, 1)
model <- kmeans(x = training, centers = 2)
--
GitLab