Skip to content

Commit

Permalink
set progress bars for curl and wget when not run on jenkins, no progr…
Browse files Browse the repository at this point in the history
…ess bar when run on jenkins, moved sbt script to build/sbt, wrote stub and warning under sbt/sbt which calls build/sbt, modified build/sbt to use the correct directory, fixed bug in build/sbt-launch-lib.bash to correctly pull the sbt version
  • Loading branch information
Brennon York committed Dec 23, 2014
1 parent be11317 commit b8437ba
Show file tree
Hide file tree
Showing 6 changed files with 134 additions and 118 deletions.
2 changes: 1 addition & 1 deletion .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
*.pyc
.idea/
.idea_modules/
sbt/*.jar
build/*.jar
.settings
.cache
cache
Expand Down
6 changes: 6 additions & 0 deletions build/mvn
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,9 @@ install_app() {
if [ -n "$AMPLAB_JENKINS" ]; then
curl_opts="-s"
wget_opts="--quiet"
else
curl_opts="--progress-bar"
wget_opts="--progress=bar:force"
fi

if [ -z "$3" -o ! -f "$binary" ]; then
Expand Down Expand Up @@ -120,5 +123,8 @@ if [ -n "${ZINC_INSTALL_FLAG}" -o -z "`${ZINC_BIN} -status`" ]; then
-scala-library "${SCALA_LIBRARY}" &>/dev/null
fi

# Set any `mvn` options if not already present
export MAVEN_OPTS=${MAVEN_OPTS:-"-Xmx2g -XX:MaxPermSize=512M -XX:ReservedCodeCacheSize=512m"}

# Last, call the `mvn` command as usual
${MVN_BIN} "$@"
111 changes: 111 additions & 0 deletions build/sbt
Original file line number Diff line number Diff line change
@@ -0,0 +1,111 @@
#!/usr/bin/env bash

# When creating new tests for Spark SQL Hive, the HADOOP_CLASSPATH must contain the hive jars so
# that we can run Hive to generate the golden answer. This is not required for normal development
# or testing.
for i in "$HIVE_HOME"/lib/*
do HADOOP_CLASSPATH="$HADOOP_CLASSPATH:$i"
done
export HADOOP_CLASSPATH

realpath () {
(
TARGET_FILE="$1"

cd "$(dirname "$TARGET_FILE")"
TARGET_FILE="$(basename "$TARGET_FILE")"

COUNT=0
while [ -L "$TARGET_FILE" -a $COUNT -lt 100 ]
do
TARGET_FILE="$(readlink "$TARGET_FILE")"
cd $(dirname "$TARGET_FILE")
TARGET_FILE="$(basename $TARGET_FILE)"
COUNT=$(($COUNT + 1))
done

echo "$(pwd -P)/"$TARGET_FILE""
)
}

. "$(dirname "$(realpath "$0")")"/sbt-launch-lib.bash


declare -r noshare_opts="-Dsbt.global.base=project/.sbtboot -Dsbt.boot.directory=project/.boot -Dsbt.ivy.home=project/.ivy"
declare -r sbt_opts_file=".sbtopts"
declare -r etc_sbt_opts_file="/etc/sbt/sbtopts"

usage() {
cat <<EOM
Usage: $script_name [options]
-h | -help print this message
-v | -verbose this runner is chattier
-d | -debug set sbt log level to debug
-no-colors disable ANSI color codes
-sbt-create start sbt even if current directory contains no sbt project
-sbt-dir <path> path to global settings/plugins directory (default: ~/.sbt)
-sbt-boot <path> path to shared boot directory (default: ~/.sbt/boot in 0.11 series)
-ivy <path> path to local Ivy repository (default: ~/.ivy2)
-mem <integer> set memory options (default: $sbt_mem, which is $(get_mem_opts $sbt_mem))
-no-share use all local caches; no sharing
-no-global uses global caches, but does not use global ~/.sbt directory.
-jvm-debug <port> Turn on JVM debugging, open at the given port.
-batch Disable interactive mode
# sbt version (default: from project/build.properties if present, else latest release)
-sbt-version <version> use the specified version of sbt
-sbt-jar <path> use the specified jar as the sbt launcher
-sbt-rc use an RC version of sbt
-sbt-snapshot use a snapshot version of sbt
# java version (default: java from PATH, currently $(java -version 2>&1 | grep version))
-java-home <path> alternate JAVA_HOME
# jvm options and output control
JAVA_OPTS environment variable, if unset uses "$java_opts"
SBT_OPTS environment variable, if unset uses "$default_sbt_opts"
.sbtopts if this file exists in the current directory, it is
prepended to the runner args
/etc/sbt/sbtopts if this file exists, it is prepended to the runner args
-Dkey=val pass -Dkey=val directly to the java runtime
-J-X pass option -X directly to the java runtime
(-J is stripped)
-S-X add -X to sbt's scalacOptions (-S is stripped)
-PmavenProfiles Enable a maven profile for the build.
In the case of duplicated or conflicting options, the order above
shows precedence: JAVA_OPTS lowest, command line options highest.
EOM
}

process_my_args () {
while [[ $# -gt 0 ]]; do
case "$1" in
-no-colors) addJava "-Dsbt.log.noformat=true" && shift ;;
-no-share) addJava "$noshare_opts" && shift ;;
-no-global) addJava "-Dsbt.global.base=$(pwd)/project/.sbtboot" && shift ;;
-sbt-boot) require_arg path "$1" "$2" && addJava "-Dsbt.boot.directory=$2" && shift 2 ;;
-sbt-dir) require_arg path "$1" "$2" && addJava "-Dsbt.global.base=$2" && shift 2 ;;
-debug-inc) addJava "-Dxsbt.inc.debug=true" && shift ;;
-batch) exec </dev/null && shift ;;

-sbt-create) sbt_create=true && shift ;;

*) addResidual "$1" && shift ;;
esac
done

# Now, ensure sbt version is used.
[[ "${sbt_version}XXX" != "XXX" ]] && addJava "-Dsbt.version=$sbt_version"
}

loadConfigFile() {
cat "$1" | sed '/^\#/d'
}

# if sbtopts files exist, prepend their contents to $@ so it can be processed by this runner
[[ -f "$etc_sbt_opts_file" ]] && set -- $(loadConfigFile "$etc_sbt_opts_file") "$@"
[[ -f "$sbt_opts_file" ]] && set -- $(loadConfigFile "$sbt_opts_file") "$@"

run "$@"
6 changes: 3 additions & 3 deletions sbt/sbt-launch-lib.bash → build/sbt-launch-lib.bash
Original file line number Diff line number Diff line change
Expand Up @@ -37,10 +37,10 @@ dlog () {
}

acquire_sbt_jar () {
SBT_VERSION=`awk -F "=" '/sbt\\.version/ {print $2}' ./project/build.properties`
SBT_VERSION=`awk -F "=" '/sbt\.version/ {print $2}' ./project/build.properties`
URL1=http://typesafe.artifactoryonline.com/typesafe/ivy-releases/org.scala-sbt/sbt-launch/${SBT_VERSION}/sbt-launch.jar
URL2=http://repo.typesafe.com/typesafe/ivy-releases/org.scala-sbt/sbt-launch/${SBT_VERSION}/sbt-launch.jar
JAR=sbt/sbt-launch-${SBT_VERSION}.jar
JAR=build/sbt-launch-${SBT_VERSION}.jar

sbt_jar=$JAR

Expand Down Expand Up @@ -150,7 +150,7 @@ process_args () {
-java-home) require_arg path "$1" "$2" && java_cmd="$2/bin/java" && export JAVA_HOME=$2 && shift 2 ;;

-D*) addJava "$1" && shift ;;
-J*) addJava "${1:2}" && shift ;;
-J*) addJava "${1:2}" && shift ;;
-P*) enableProfile "$1" && shift ;;
*) addResidual "$1" && shift ;;
esac
Expand Down
13 changes: 7 additions & 6 deletions docs/building-spark.md
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ redirect_from: "building-with-maven.html"

Building Spark using Maven requires Maven 3.0.4 or newer and Java 6+.

# Building with `build/mvn`

# Setting up Maven's Memory Usage

Expand Down Expand Up @@ -105,7 +106,7 @@ mvn -Pyarn-alpha -Phadoop-2.3 -Dhadoop.version=2.3.0 -Dyarn.version=0.23.7 -Dski
# Building With Hive and JDBC Support
To enable Hive integration for Spark SQL along with its JDBC server and CLI,
add the `-Phive` and `Phive-thriftserver` profiles to your existing build options.
By default Spark will build with Hive 0.13.1 bindings. You can also build for
By default Spark will build with Hive 0.13.1 bindings. You can also build for
Hive 0.12.0 using the `-Phive-0.12.0` profile.
{% highlight bash %}
# Apache Hadoop 2.4.X with Hive 13 support
Expand All @@ -127,7 +128,7 @@ supported in Scala 2.11 builds.

# Spark Tests in Maven

Tests are run by default via the [ScalaTest Maven plugin](http://www.scalatest.org/user_guide/using_the_scalatest_maven_plugin).
Tests are run by default via the [ScalaTest Maven plugin](http://www.scalatest.org/user_guide/using_the_scalatest_maven_plugin).

Some of the tests require Spark to be packaged first, so always run `mvn package` with `-DskipTests` the first time. The following is an example of a correct (build, test) sequence:

Expand Down Expand Up @@ -164,9 +165,9 @@ The debian package can then be found under assembly/target. We added the short c
Running only Java 8 tests and nothing else.

mvn install -DskipTests -Pjava8-tests
Java 8 tests are run when `-Pjava8-tests` profile is enabled, they will run in spite of `-DskipTests`.
For these tests to run your system must have a JDK 8 installation.

Java 8 tests are run when `-Pjava8-tests` profile is enabled, they will run in spite of `-DskipTests`.
For these tests to run your system must have a JDK 8 installation.
If you have JDK 8 installed but it is not the system default, you can set JAVA_HOME to point to JDK 8 before running the tests.

# Building for PySpark on YARN
Expand All @@ -178,7 +179,7 @@ then ship it over to the cluster. We are investigating the exact cause for this.

# Packaging without Hadoop Dependencies for YARN

The assembly jar produced by `mvn package` will, by default, include all of Spark's dependencies, including Hadoop and some of its ecosystem projects. On YARN deployments, this causes multiple versions of these to appear on executor classpaths: the version packaged in the Spark assembly and the version on each node, included with yarn.application.classpath. The `hadoop-provided` profile builds the assembly without including Hadoop-ecosystem projects, like ZooKeeper and Hadoop itself.
The assembly jar produced by `mvn package` will, by default, include all of Spark's dependencies, including Hadoop and some of its ecosystem projects. On YARN deployments, this causes multiple versions of these to appear on executor classpaths: the version packaged in the Spark assembly and the version on each node, included with yarn.application.classpath. The `hadoop-provided` profile builds the assembly without including Hadoop-ecosystem projects, like ZooKeeper and Hadoop itself.

# Building with SBT

Expand Down
114 changes: 6 additions & 108 deletions sbt/sbt
Original file line number Diff line number Diff line change
@@ -1,111 +1,9 @@
#!/usr/bin/env bash
#!/bin/bash

# When creating new tests for Spark SQL Hive, the HADOOP_CLASSPATH must contain the hive jars so
# that we can run Hive to generate the golden answer. This is not required for normal development
# or testing.
for i in "$HIVE_HOME"/lib/*
do HADOOP_CLASSPATH="$HADOOP_CLASSPATH:$i"
done
export HADOOP_CLASSPATH
# Determine the current working directory
_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"

realpath () {
(
TARGET_FILE="$1"
echo "WARNING: The sbt/sbt script has been deprecated in place of build/sbt." >&2
echo " Please change all references to point to the new location." >&2

cd "$(dirname "$TARGET_FILE")"
TARGET_FILE="$(basename "$TARGET_FILE")"

COUNT=0
while [ -L "$TARGET_FILE" -a $COUNT -lt 100 ]
do
TARGET_FILE="$(readlink "$TARGET_FILE")"
cd $(dirname "$TARGET_FILE")
TARGET_FILE="$(basename $TARGET_FILE)"
COUNT=$(($COUNT + 1))
done

echo "$(pwd -P)/"$TARGET_FILE""
)
}

. "$(dirname "$(realpath "$0")")"/sbt-launch-lib.bash


declare -r noshare_opts="-Dsbt.global.base=project/.sbtboot -Dsbt.boot.directory=project/.boot -Dsbt.ivy.home=project/.ivy"
declare -r sbt_opts_file=".sbtopts"
declare -r etc_sbt_opts_file="/etc/sbt/sbtopts"

usage() {
cat <<EOM
Usage: $script_name [options]
-h | -help print this message
-v | -verbose this runner is chattier
-d | -debug set sbt log level to debug
-no-colors disable ANSI color codes
-sbt-create start sbt even if current directory contains no sbt project
-sbt-dir <path> path to global settings/plugins directory (default: ~/.sbt)
-sbt-boot <path> path to shared boot directory (default: ~/.sbt/boot in 0.11 series)
-ivy <path> path to local Ivy repository (default: ~/.ivy2)
-mem <integer> set memory options (default: $sbt_mem, which is $(get_mem_opts $sbt_mem))
-no-share use all local caches; no sharing
-no-global uses global caches, but does not use global ~/.sbt directory.
-jvm-debug <port> Turn on JVM debugging, open at the given port.
-batch Disable interactive mode
# sbt version (default: from project/build.properties if present, else latest release)
-sbt-version <version> use the specified version of sbt
-sbt-jar <path> use the specified jar as the sbt launcher
-sbt-rc use an RC version of sbt
-sbt-snapshot use a snapshot version of sbt
# java version (default: java from PATH, currently $(java -version 2>&1 | grep version))
-java-home <path> alternate JAVA_HOME
# jvm options and output control
JAVA_OPTS environment variable, if unset uses "$java_opts"
SBT_OPTS environment variable, if unset uses "$default_sbt_opts"
.sbtopts if this file exists in the current directory, it is
prepended to the runner args
/etc/sbt/sbtopts if this file exists, it is prepended to the runner args
-Dkey=val pass -Dkey=val directly to the java runtime
-J-X pass option -X directly to the java runtime
(-J is stripped)
-S-X add -X to sbt's scalacOptions (-S is stripped)
-PmavenProfiles Enable a maven profile for the build.
In the case of duplicated or conflicting options, the order above
shows precedence: JAVA_OPTS lowest, command line options highest.
EOM
}

process_my_args () {
while [[ $# -gt 0 ]]; do
case "$1" in
-no-colors) addJava "-Dsbt.log.noformat=true" && shift ;;
-no-share) addJava "$noshare_opts" && shift ;;
-no-global) addJava "-Dsbt.global.base=$(pwd)/project/.sbtboot" && shift ;;
-sbt-boot) require_arg path "$1" "$2" && addJava "-Dsbt.boot.directory=$2" && shift 2 ;;
-sbt-dir) require_arg path "$1" "$2" && addJava "-Dsbt.global.base=$2" && shift 2 ;;
-debug-inc) addJava "-Dxsbt.inc.debug=true" && shift ;;
-batch) exec </dev/null && shift ;;

-sbt-create) sbt_create=true && shift ;;

*) addResidual "$1" && shift ;;
esac
done

# Now, ensure sbt version is used.
[[ "${sbt_version}XXX" != "XXX" ]] && addJava "-Dsbt.version=$sbt_version"
}

loadConfigFile() {
cat "$1" | sed '/^\#/d'
}

# if sbtopts files exist, prepend their contents to $@ so it can be processed by this runner
[[ -f "$etc_sbt_opts_file" ]] && set -- $(loadConfigFile "$etc_sbt_opts_file") "$@"
[[ -f "$sbt_opts_file" ]] && set -- $(loadConfigFile "$sbt_opts_file") "$@"

run "$@"
${_DIR}/../build/sbt $@

0 comments on commit b8437ba

Please sign in to comment.