aboutsummaryrefslogtreecommitdiff
path: root/bin
diff options
context:
space:
mode:
authorMarcelo Vanzin <vanzin@cloudera.com>2016-03-15 09:44:48 -0700
committerMarcelo Vanzin <vanzin@cloudera.com>2016-03-15 09:44:51 -0700
commit48978abfa4d8f2cf79a4b053cc8bc7254cc2d61b (patch)
tree009d0b0870a8eb6a185cf192acb172d2d91b540c /bin
parentbd5365bbe9ff6518cde9402ee8843ec1002fff5b (diff)
downloadspark-48978abfa4d8f2cf79a4b053cc8bc7254cc2d61b.tar.gz
spark-48978abfa4d8f2cf79a4b053cc8bc7254cc2d61b.tar.bz2
spark-48978abfa4d8f2cf79a4b053cc8bc7254cc2d61b.zip
[SPARK-13576][BUILD] Don't create assembly for examples.
As part of the goal to stop creating assemblies in Spark, this change modifies the mvn and sbt builds to not create an assembly for examples. Instead, dependencies are copied to the build directory (under target/scala-xx/jars), and in the final archive, into the "examples/jars" directory. To avoid having to deal too much with Windows batch files, I made examples run through the launcher library; the spark-submit launcher now has a special mode to run examples, which adds all the necessary jars to the spark-submit command line, and replaces the bash and batch scripts that were used to run examples. The scripts are now just a thin wrapper around spark-submit; another advantage is that now all spark-submit options are supported. There are a few glitches; in the mvn build, a lot of duplicated dependencies get copied, because they are promoted to "compile" scope due to extra dependencies in the examples module (such as HBase). In the sbt build, all dependencies are copied, because there doesn't seem to be an easy way to filter things. I plan to clean some of this up when the rest of the tasks are finished. When the main assembly is replaced with jars, we can remove duplicate jars from the examples directory during packaging. Tested by running SparkPi in: maven build, sbt build, dist created by make-distribution.sh. Finally: note that running the "assembly" target in sbt doesn't build the examples anymore. You need to run "package" for that. Author: Marcelo Vanzin <vanzin@cloudera.com> Closes #11452 from vanzin/SPARK-13576.
Diffstat (limited to 'bin')
-rwxr-xr-xbin/run-example55
-rw-r--r--bin/run-example.cmd7
-rw-r--r--bin/run-example2.cmd85
3 files changed, 5 insertions, 142 deletions
diff --git a/bin/run-example b/bin/run-example
index e1b0d5789b..dd0e3c4120 100755
--- a/bin/run-example
+++ b/bin/run-example
@@ -21,56 +21,5 @@ if [ -z "${SPARK_HOME}" ]; then
export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
fi
-EXAMPLES_DIR="${SPARK_HOME}"/examples
-
-. "${SPARK_HOME}"/bin/load-spark-env.sh
-
-if [ -n "$1" ]; then
- EXAMPLE_CLASS="$1"
- shift
-else
- echo "Usage: ./bin/run-example <example-class> [example-args]" 1>&2
- echo " - set MASTER=XX to use a specific master" 1>&2
- echo " - can use abbreviated example class name relative to com.apache.spark.examples" 1>&2
- echo " (e.g. SparkPi, mllib.LinearRegression, streaming.KinesisWordCountASL)" 1>&2
- exit 1
-fi
-
-if [ -f "${SPARK_HOME}/RELEASE" ]; then
- JAR_PATH="${SPARK_HOME}/lib"
-else
- JAR_PATH="${EXAMPLES_DIR}/target/scala-${SPARK_SCALA_VERSION}"
-fi
-
-JAR_COUNT=0
-
-for f in "${JAR_PATH}"/spark-examples-*hadoop*.jar; do
- if [[ ! -e "$f" ]]; then
- echo "Failed to find Spark examples assembly in ${SPARK_HOME}/lib or ${SPARK_HOME}/examples/target" 1>&2
- echo "You need to build Spark before running this program" 1>&2
- exit 1
- fi
- SPARK_EXAMPLES_JAR="$f"
- JAR_COUNT=$((JAR_COUNT+1))
-done
-
-if [ "$JAR_COUNT" -gt "1" ]; then
- echo "Found multiple Spark examples assembly jars in ${JAR_PATH}" 1>&2
- ls "${JAR_PATH}"/spark-examples-*hadoop*.jar 1>&2
- echo "Please remove all but one jar." 1>&2
- exit 1
-fi
-
-export SPARK_EXAMPLES_JAR
-
-EXAMPLE_MASTER=${MASTER:-"local[*]"}
-
-if [[ ! $EXAMPLE_CLASS == org.apache.spark.examples* ]]; then
- EXAMPLE_CLASS="org.apache.spark.examples.$EXAMPLE_CLASS"
-fi
-
-exec "${SPARK_HOME}"/bin/spark-submit \
- --master $EXAMPLE_MASTER \
- --class $EXAMPLE_CLASS \
- "$SPARK_EXAMPLES_JAR" \
- "$@"
+export _SPARK_CMD_USAGE="Usage: ./bin/run-example [options] example-class [example args]"
+exec "${SPARK_HOME}"/bin/spark-submit run-example "$@"
diff --git a/bin/run-example.cmd b/bin/run-example.cmd
index 64f6bc3728..f9b786e92b 100644
--- a/bin/run-example.cmd
+++ b/bin/run-example.cmd
@@ -17,7 +17,6 @@ rem See the License for the specific language governing permissions and
rem limitations under the License.
rem
-rem This is the entry point for running a Spark example. To avoid polluting
-rem the environment, it just launches a new cmd to do the real work.
-
-cmd /V /E /C "%~dp0run-example2.cmd" %*
+set SPARK_HOME=%~dp0..
+set _SPARK_CMD_USAGE=Usage: ./bin/run-example [options] example-class [example args]
+cmd /V /E /C "%~dp0spark-submit.cmd" run-example %*
diff --git a/bin/run-example2.cmd b/bin/run-example2.cmd
deleted file mode 100644
index fada43581d..0000000000
--- a/bin/run-example2.cmd
+++ /dev/null
@@ -1,85 +0,0 @@
-@echo off
-
-rem
-rem Licensed to the Apache Software Foundation (ASF) under one or more
-rem contributor license agreements. See the NOTICE file distributed with
-rem this work for additional information regarding copyright ownership.
-rem The ASF licenses this file to You under the Apache License, Version 2.0
-rem (the "License"); you may not use this file except in compliance with
-rem the License. You may obtain a copy of the License at
-rem
-rem http://www.apache.org/licenses/LICENSE-2.0
-rem
-rem Unless required by applicable law or agreed to in writing, software
-rem distributed under the License is distributed on an "AS IS" BASIS,
-rem WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-rem See the License for the specific language governing permissions and
-rem limitations under the License.
-rem
-
-set SCALA_VERSION=2.10
-
-rem Figure out where the Spark framework is installed
-set SPARK_HOME=%~dp0..
-
-call "%SPARK_HOME%\bin\load-spark-env.cmd"
-
-rem Test that an argument was given
-if not "x%1"=="x" goto arg_given
- echo Usage: run-example ^<example-class^> [example-args]
- echo - set MASTER=XX to use a specific master
- echo - can use abbreviated example class name relative to com.apache.spark.examples
- echo (e.g. SparkPi, mllib.LinearRegression, streaming.KinesisWordCountASL)
- goto exit
-:arg_given
-
-set EXAMPLES_DIR=%SPARK_HOME%\examples
-
-rem Figure out the JAR file that our examples were packaged into.
-set SPARK_EXAMPLES_JAR=
-if exist "%SPARK_HOME%\RELEASE" (
- for %%d in ("%SPARK_HOME%\lib\spark-examples*.jar") do (
- set SPARK_EXAMPLES_JAR=%%d
- )
-) else (
- for %%d in ("%EXAMPLES_DIR%\target\scala-%SCALA_VERSION%\spark-examples*.jar") do (
- set SPARK_EXAMPLES_JAR=%%d
- )
-)
-if "x%SPARK_EXAMPLES_JAR%"=="x" (
- echo Failed to find Spark examples assembly JAR.
- echo You need to build Spark before running this program.
- goto exit
-)
-
-rem Set master from MASTER environment variable if given
-if "x%MASTER%"=="x" (
- set EXAMPLE_MASTER=local[*]
-) else (
- set EXAMPLE_MASTER=%MASTER%
-)
-
-rem If the EXAMPLE_CLASS does not start with org.apache.spark.examples, add that
-set EXAMPLE_CLASS=%1
-set PREFIX=%EXAMPLE_CLASS:~0,25%
-if not %PREFIX%==org.apache.spark.examples (
- set EXAMPLE_CLASS=org.apache.spark.examples.%EXAMPLE_CLASS%
-)
-
-rem Get the tail of the argument list, to skip the first one. This is surprisingly
-rem complicated on Windows.
-set "ARGS="
-:top
-shift
-if "%~1" neq "" (
- set ARGS=%ARGS% "%~1"
- goto :top
-)
-if defined ARGS set ARGS=%ARGS:~1%
-
-call "%SPARK_HOME%\bin\spark-submit.cmd" ^
- --master %EXAMPLE_MASTER% ^
- --class %EXAMPLE_CLASS% ^
- "%SPARK_EXAMPLES_JAR%" %ARGS%
-
-:exit