ODIn/spark-instrumented-optimizer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

[SPARK-17960][PYSPARK][UPGRADE TO PY4J 0.10.4]

Browse source 
## What changes were proposed in this pull request?

1) Upgrade the Py4J version on the Java side
2) Update the py4j src zip file we bundle with Spark

## How was this patch tested?

Existing doctests & unit tests pass

Author: Jagadeesan <as2@us.ibm.com>

Closes #15514 from jagadeesanas2/SPARK-17960.
This commit is contained in:
Jagadeesan 2016-10-21 09:48:24 +01:00 committed by Sean Owen
parent 57e97fcbd6
commit 595893d33a
No known key found for this signature in database
GPG key ID: BEB3956D6717BDDC
16 changed files with 14 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
LICENSE
View file

@ -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:0.10.3 - http://py4j.sourceforge.net/)
(The New BSD License) Py4J (net.sf.py4j:py4j:0.10.4 - 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)

2
bin/pyspark
View file

@ -57,7 +57,7 @@ export PYSPARK_PYTHON
# Add the PySpark classes to the Python path:
export PYTHONPATH="${SPARK_HOME}/python/:$PYTHONPATH"
export PYTHONPATH="${SPARK_HOME}/python/lib/py4j-0.10.3-src.zip:$PYTHONPATH"
export PYTHONPATH="${SPARK_HOME}/python/lib/py4j-0.10.4-src.zip:$PYTHONPATH"
# Load the PySpark shell.py script when ./pyspark is used interactively:
export OLD_PYTHONSTARTUP="$PYTHONSTARTUP"

2
bin/pyspark2.cmd
View file

@ -30,7 +30,7 @@ if "x%PYSPARK_DRIVER_PYTHON%"=="x" (
)
set PYTHONPATH=%SPARK_HOME%\python;%PYTHONPATH%
set PYTHONPATH=%SPARK_HOME%\python\lib\py4j-0.10.3-src.zip;%PYTHONPATH%
set PYTHONPATH=%SPARK_HOME%\python\lib\py4j-0.10.4-src.zip;%PYTHONPATH%
set OLD_PYTHONSTARTUP=%PYTHONSTARTUP%
set PYTHONSTARTUP=%SPARK_HOME%\python\pyspark\shell.py

2
core/pom.xml
View file

@ -331,7 +331,7 @@
<dependency>
<groupId>net.sf.py4j</groupId>
<artifactId>py4j</artifactId>
<version>0.10.3</version>
<version>0.10.4</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>

2
core/src/main/scala/org/apache/spark/api/python/PythonUtils.scala
View file

@ -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-0.10.3-src.zip").mkString(File.separator)
pythonPath += Seq(sparkHome, "python", "lib", "py4j-0.10.4-src.zip").mkString(File.separator)
}
pythonPath ++= SparkContext.jarOfObject(this)
pythonPath.mkString(File.pathSeparator)

2
dev/deps/spark-deps-hadoop-2.2
View file

@ -140,7 +140,7 @@ 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-0.10.3.jar
py4j-0.10.4.jar
pyrolite-4.13.jar
scala-compiler-2.11.8.jar
scala-library-2.11.8.jar

2
dev/deps/spark-deps-hadoop-2.3
View file

@ -147,7 +147,7 @@ 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-0.10.3.jar
py4j-0.10.4.jar
pyrolite-4.13.jar
scala-compiler-2.11.8.jar
scala-library-2.11.8.jar

2
dev/deps/spark-deps-hadoop-2.4
View file

@ -147,7 +147,7 @@ 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-0.10.3.jar
py4j-0.10.4.jar
pyrolite-4.13.jar
scala-compiler-2.11.8.jar
scala-library-2.11.8.jar

2
dev/deps/spark-deps-hadoop-2.6
View file

@ -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-0.10.3.jar
py4j-0.10.4.jar
pyrolite-4.13.jar
scala-compiler-2.11.8.jar
scala-library-2.11.8.jar

2
dev/deps/spark-deps-hadoop-2.7
View file

@ -156,7 +156,7 @@ 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-0.10.3.jar
py4j-0.10.4.jar
pyrolite-4.13.jar
scala-compiler-2.11.8.jar
scala-library-2.11.8.jar

2
python/docs/Makefile
View file

@ -7,7 +7,7 @@ SPHINXBUILD ?= sphinx-build
PAPER ?=
BUILDDIR ?= _build
export PYTHONPATH=$(realpath ..):$(realpath ../lib/py4j-0.10.3-src.zip)
export PYTHONPATH=$(realpath ..):$(realpath ../lib/py4j-0.10.4-src.zip)
# User-friendly check for sphinx-build
ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1)

BIN
python/lib/py4j-0.10.3-src.zip
View file

Binary file not shown.

BIN
python/lib/py4j-0.10.4-src.zip Normal file
View file

Binary file not shown.

2
sbin/spark-config.sh
View file

@ -28,6 +28,6 @@ export SPARK_CONF_DIR="${SPARK_CONF_DIR:-"${SPARK_HOME}/conf"}"
# Add the PySpark classes to the PYTHONPATH:
if [ -z "${PYSPARK_PYTHONPATH_SET}" ]; then
export PYTHONPATH="${SPARK_HOME}/python:${PYTHONPATH}"
export PYTHONPATH="${SPARK_HOME}/python/lib/py4j-0.10.3-src.zip:${PYTHONPATH}"
export PYTHONPATH="${SPARK_HOME}/python/lib/py4j-0.10.4-src.zip:${PYTHONPATH}"
export PYSPARK_PYTHONPATH_SET=1
fi

2
yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala
View file

@ -1179,7 +1179,7 @@ private[spark] class Client(
val pyArchivesFile = new File(pyLibPath, "pyspark.zip")
require(pyArchivesFile.exists(),
s"$pyArchivesFile not found; cannot run pyspark application in YARN mode.")
val py4jFile = new File(pyLibPath, "py4j-0.10.3-src.zip")
val py4jFile = new File(pyLibPath, "py4j-0.10.4-src.zip")
require(py4jFile.exists(),
s"$py4jFile not found; cannot run pyspark application in YARN mode.")
Seq(pyArchivesFile.getAbsolutePath(), py4jFile.getAbsolutePath())

2
yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala
View file

@ -242,7 +242,7 @@ class YarnClusterSuite extends BaseYarnClusterSuite {
// needed locations.
val sparkHome = sys.props("spark.test.home")
val pythonPath = Seq(
s"$sparkHome/python/lib/py4j-0.10.3-src.zip",
s"$sparkHome/python/lib/py4j-0.10.4-src.zip",
s"$sparkHome/python")
val extraEnvVars = Map(
"PYSPARK_ARCHIVES_PATH" -> pythonPath.map("local:" + _).mkString(File.pathSeparator),