diff options
author | Sean Owen <sowen@cloudera.com> | 2016-08-24 20:04:09 +0100 |
---|---|---|
committer | Sean Owen <sowen@cloudera.com> | 2016-08-24 20:04:09 +0100 |
commit | 0b3a4be92ca6b38eef32ea5ca240d9f91f68aa65 (patch) | |
tree | fceae4d22e14f83548bd505535cd67e71b030b3d | |
parent | 2fbdb606392631b1dff88ec86f388cc2559c28f5 (diff) | |
download | spark-0b3a4be92ca6b38eef32ea5ca240d9f91f68aa65.tar.gz spark-0b3a4be92ca6b38eef32ea5ca240d9f91f68aa65.tar.bz2 spark-0b3a4be92ca6b38eef32ea5ca240d9f91f68aa65.zip |
[SPARK-16781][PYSPARK] java launched by PySpark as gateway may not be the same java used in the spark environment
## What changes were proposed in this pull request?
Update to py4j 0.10.3 to enable JAVA_HOME support
## How was this patch tested?
Pyspark tests
Author: Sean Owen <sowen@cloudera.com>
Closes #14748 from srowen/SPARK-16781.
-rw-r--r-- | LICENSE | 2 | ||||
-rwxr-xr-x | bin/pyspark | 2 | ||||
-rw-r--r-- | bin/pyspark2.cmd | 2 | ||||
-rw-r--r-- | core/pom.xml | 2 | ||||
-rw-r--r-- | core/src/main/scala/org/apache/spark/api/python/PythonUtils.scala | 2 | ||||
-rw-r--r-- | dev/deps/spark-deps-hadoop-2.2 | 2 | ||||
-rw-r--r-- | dev/deps/spark-deps-hadoop-2.3 | 2 | ||||
-rw-r--r-- | dev/deps/spark-deps-hadoop-2.4 | 2 | ||||
-rw-r--r-- | dev/deps/spark-deps-hadoop-2.6 | 2 | ||||
-rw-r--r-- | dev/deps/spark-deps-hadoop-2.7 | 2 | ||||
-rw-r--r-- | python/docs/Makefile | 2 | ||||
-rw-r--r-- | python/lib/py4j-0.10.1-src.zip | bin | 61356 -> 0 bytes | |||
-rw-r--r-- | python/lib/py4j-0.10.3-src.zip | bin | 0 -> 91275 bytes | |||
-rwxr-xr-x | sbin/spark-config.sh | 2 | ||||
-rw-r--r-- | yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala | 6 | ||||
-rw-r--r-- | yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala | 2 |
16 files changed, 16 insertions, 16 deletions
@@ -263,7 +263,7 @@ The text of each license is also included at licenses/LICENSE-[project].txt. (New BSD license) Protocol Buffer Java API (org.spark-project.protobuf:protobuf-java:2.4.1-shaded - http://code.google.com/p/protobuf) (The BSD License) Fortran to Java ARPACK (net.sourceforge.f2j:arpack_combined_all:0.1 - http://f2j.sourceforge.net) (The BSD License) xmlenc Library (xmlenc:xmlenc:0.52 - http://xmlenc.sourceforge.net) - (The New BSD License) Py4J (net.sf.py4j:py4j:0.10.1 - http://py4j.sourceforge.net/) + (The New BSD License) Py4J (net.sf.py4j:py4j:0.10.3 - http://py4j.sourceforge.net/) (Two-clause BSD-style license) JUnit-Interface (com.novocode:junit-interface:0.10 - http://github.com/szeiger/junit-interface/) (BSD licence) sbt and sbt-launch-lib.bash (BSD 3 Clause) d3.min.js (https://github.com/mbostock/d3/blob/master/LICENSE) diff --git a/bin/pyspark b/bin/pyspark index a0d7e22e8a..7590309b44 100755 --- a/bin/pyspark +++ b/bin/pyspark @@ -57,7 +57,7 @@ export PYSPARK_PYTHON # Add the PySpark classes to the Python path: export PYTHONPATH="${SPARK_HOME}/python/:$PYTHONPATH" -export PYTHONPATH="${SPARK_HOME}/python/lib/py4j-0.10.1-src.zip:$PYTHONPATH" +export PYTHONPATH="${SPARK_HOME}/python/lib/py4j-0.10.3-src.zip:$PYTHONPATH" # Load the PySpark shell.py script when ./pyspark is used interactively: export OLD_PYTHONSTARTUP="$PYTHONSTARTUP" diff --git a/bin/pyspark2.cmd b/bin/pyspark2.cmd index 3e2ff100fb..1217a4f2f9 100644 --- a/bin/pyspark2.cmd +++ b/bin/pyspark2.cmd @@ -30,7 +30,7 @@ if "x%PYSPARK_DRIVER_PYTHON%"=="x" ( ) set PYTHONPATH=%SPARK_HOME%\python;%PYTHONPATH% -set PYTHONPATH=%SPARK_HOME%\python\lib\py4j-0.10.1-src.zip;%PYTHONPATH% +set PYTHONPATH=%SPARK_HOME%\python\lib\py4j-0.10.3-src.zip;%PYTHONPATH% set OLD_PYTHONSTARTUP=%PYTHONSTARTUP% set PYTHONSTARTUP=%SPARK_HOME%\python\pyspark\shell.py diff --git a/core/pom.xml b/core/pom.xml index 04b94a258c..ab6c3ce805 100644 --- a/core/pom.xml +++ b/core/pom.xml @@ -326,7 +326,7 @@ <dependency> <groupId>net.sf.py4j</groupId> <artifactId>py4j</artifactId> - <version>0.10.1</version> + <version>0.10.3</version> </dependency> <dependency> <groupId>org.apache.spark</groupId> diff --git a/core/src/main/scala/org/apache/spark/api/python/PythonUtils.scala b/core/src/main/scala/org/apache/spark/api/python/PythonUtils.scala index 64cf498171..701097ace8 100644 --- a/core/src/main/scala/org/apache/spark/api/python/PythonUtils.scala +++ b/core/src/main/scala/org/apache/spark/api/python/PythonUtils.scala @@ -32,7 +32,7 @@ private[spark] object PythonUtils { val pythonPath = new ArrayBuffer[String] for (sparkHome <- sys.env.get("SPARK_HOME")) { pythonPath += Seq(sparkHome, "python", "lib", "pyspark.zip").mkString(File.separator) - pythonPath += Seq(sparkHome, "python", "lib", "py4j-0.10.1-src.zip").mkString(File.separator) + pythonPath += Seq(sparkHome, "python", "lib", "py4j-0.10.3-src.zip").mkString(File.separator) } pythonPath ++= SparkContext.jarOfObject(this) pythonPath.mkString(File.pathSeparator) diff --git a/dev/deps/spark-deps-hadoop-2.2 b/dev/deps/spark-deps-hadoop-2.2 index e2433bd718..326271a7e2 100644 --- a/dev/deps/spark-deps-hadoop-2.2 +++ b/dev/deps/spark-deps-hadoop-2.2 @@ -139,7 +139,7 @@ parquet-jackson-1.8.1.jar pmml-model-1.2.15.jar pmml-schema-1.2.15.jar protobuf-java-2.5.0.jar -py4j-0.10.1.jar +py4j-0.10.3.jar pyrolite-4.9.jar scala-compiler-2.11.8.jar scala-library-2.11.8.jar diff --git a/dev/deps/spark-deps-hadoop-2.3 b/dev/deps/spark-deps-hadoop-2.3 index 51eaec5e6a..1ff6ecb734 100644 --- a/dev/deps/spark-deps-hadoop-2.3 +++ b/dev/deps/spark-deps-hadoop-2.3 @@ -146,7 +146,7 @@ parquet-jackson-1.8.1.jar pmml-model-1.2.15.jar pmml-schema-1.2.15.jar protobuf-java-2.5.0.jar -py4j-0.10.1.jar +py4j-0.10.3.jar pyrolite-4.9.jar scala-compiler-2.11.8.jar scala-library-2.11.8.jar diff --git a/dev/deps/spark-deps-hadoop-2.4 b/dev/deps/spark-deps-hadoop-2.4 index 43c85fabfd..68333849cf 100644 --- a/dev/deps/spark-deps-hadoop-2.4 +++ b/dev/deps/spark-deps-hadoop-2.4 @@ -146,7 +146,7 @@ parquet-jackson-1.8.1.jar pmml-model-1.2.15.jar pmml-schema-1.2.15.jar protobuf-java-2.5.0.jar -py4j-0.10.1.jar +py4j-0.10.3.jar pyrolite-4.9.jar scala-compiler-2.11.8.jar scala-library-2.11.8.jar diff --git a/dev/deps/spark-deps-hadoop-2.6 b/dev/deps/spark-deps-hadoop-2.6 index 93f68f3f9e..787d06c351 100644 --- a/dev/deps/spark-deps-hadoop-2.6 +++ b/dev/deps/spark-deps-hadoop-2.6 @@ -154,7 +154,7 @@ parquet-jackson-1.8.1.jar pmml-model-1.2.15.jar pmml-schema-1.2.15.jar protobuf-java-2.5.0.jar -py4j-0.10.1.jar +py4j-0.10.3.jar pyrolite-4.9.jar scala-compiler-2.11.8.jar scala-library-2.11.8.jar diff --git a/dev/deps/spark-deps-hadoop-2.7 b/dev/deps/spark-deps-hadoop-2.7 index 9740fc8d59..386495bf1b 100644 --- a/dev/deps/spark-deps-hadoop-2.7 +++ b/dev/deps/spark-deps-hadoop-2.7 @@ -155,7 +155,7 @@ parquet-jackson-1.8.1.jar pmml-model-1.2.15.jar pmml-schema-1.2.15.jar protobuf-java-2.5.0.jar -py4j-0.10.1.jar +py4j-0.10.3.jar pyrolite-4.9.jar scala-compiler-2.11.8.jar scala-library-2.11.8.jar diff --git a/python/docs/Makefile b/python/docs/Makefile index 12e397e450..de86e97d86 100644 --- a/python/docs/Makefile +++ b/python/docs/Makefile @@ -7,7 +7,7 @@ SPHINXBUILD ?= sphinx-build PAPER ?= BUILDDIR ?= _build -export PYTHONPATH=$(realpath ..):$(realpath ../lib/py4j-0.10.1-src.zip) +export PYTHONPATH=$(realpath ..):$(realpath ../lib/py4j-0.10.3-src.zip) # User-friendly check for sphinx-build ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1) diff --git a/python/lib/py4j-0.10.1-src.zip b/python/lib/py4j-0.10.1-src.zip Binary files differdeleted file mode 100644 index a54bcae03a..0000000000 --- a/python/lib/py4j-0.10.1-src.zip +++ /dev/null diff --git a/python/lib/py4j-0.10.3-src.zip b/python/lib/py4j-0.10.3-src.zip Binary files differnew file mode 100644 index 0000000000..bc54f33af1 --- /dev/null +++ b/python/lib/py4j-0.10.3-src.zip diff --git a/sbin/spark-config.sh b/sbin/spark-config.sh index 5f7bf41caf..a7a44cdde6 100755 --- a/sbin/spark-config.sh +++ b/sbin/spark-config.sh @@ -27,4 +27,4 @@ fi export SPARK_CONF_DIR="${SPARK_CONF_DIR:-"${SPARK_HOME}/conf"}" # Add the PySpark classes to the PYTHONPATH: export PYTHONPATH="${SPARK_HOME}/python:${PYTHONPATH}" -export PYTHONPATH="${SPARK_HOME}/python/lib/py4j-0.10.1-src.zip:${PYTHONPATH}" +export PYTHONPATH="${SPARK_HOME}/python/lib/py4j-0.10.3-src.zip:${PYTHONPATH}" diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala index 93684005f1..7fbbe91de9 100644 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala +++ b/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala @@ -1172,10 +1172,10 @@ private[spark] class Client( val pyLibPath = Seq(sys.env("SPARK_HOME"), "python", "lib").mkString(File.separator) val pyArchivesFile = new File(pyLibPath, "pyspark.zip") require(pyArchivesFile.exists(), - "pyspark.zip not found; cannot run pyspark application in YARN mode.") - val py4jFile = new File(pyLibPath, "py4j-0.10.1-src.zip") + s"$pyArchivesFile not found; cannot run pyspark application in YARN mode.") + val py4jFile = new File(pyLibPath, "py4j-0.10.3-src.zip") require(py4jFile.exists(), - "py4j-0.10.1-src.zip not found; cannot run pyspark application in YARN mode.") + s"$py4jFile not found; cannot run pyspark application in YARN mode.") Seq(pyArchivesFile.getAbsolutePath(), py4jFile.getAbsolutePath()) } } diff --git a/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala b/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala index fb7926f6a1..d245acf49a 100644 --- a/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala +++ b/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala @@ -242,7 +242,7 @@ class YarnClusterSuite extends BaseYarnClusterSuite { // needed locations. val sparkHome = sys.props("spark.test.home") val pythonPath = Seq( - s"$sparkHome/python/lib/py4j-0.10.1-src.zip", + s"$sparkHome/python/lib/py4j-0.10.3-src.zip", s"$sparkHome/python") val extraEnvVars = Map( "PYSPARK_ARCHIVES_PATH" -> pythonPath.map("local:" + _).mkString(File.pathSeparator), |