[SPARK-2960][DEPLOY] Support executing Spark from symlinks (reopen)

This PR is based on the work of roji to support running Spark scripts from symlinks. Thanks for the great work roji . Would you mind taking a look at this PR, thanks a lot.

For releases like HDP and others, normally it will expose the Spark executables as symlinks and put in `PATH`, but current Spark's scripts do not support finding real path from symlink recursively, this will make spark fail to execute from symlink. This PR try to solve this issue by finding the absolute path from symlink.

Instead of using `readlink -f` like what this PR (apache/spark#2386) implemented is that `-f` is not support for Mac, so here manually seeking the path through loop.

I've tested with Mac and Linux (Cent OS), looks fine.

This PR did not fix the scripts under `sbin` folder, not sure if it needs to be fixed also?

Please help to review, any comment is greatly appreciated.

Author: jerryshao <[email protected]>
Author: Shay Rojansky <[email protected]>

Closes #8669 from jerryshao/SPARK-2960.

Author: jerryshao

bin/beeline

@@ -23,8 +23,10 @@
 # Enter posix mode for bash
 set -o posix
 
-# Figure out where Spark is installed
-FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
+# Figure out if SPARK_HOME is set
+if [ -z "${SPARK_HOME}" ]; then
+  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+fi
 
 CLASS="org.apache.hive.beeline.BeeLine"
-exec "$FWDIR/bin/spark-class" $CLASS "$@"
+exec "${SPARK_HOME}/bin/spark-class" $CLASS "$@"

bin/load-spark-env.sh

@@ -20,13 +20,17 @@
 # This script loads spark-env.sh if it exists, and ensures it is only loaded once.
 # spark-env.sh is loaded from SPARK_CONF_DIR if set, or within the current directory's
 # conf/ subdirectory.
-FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
+
+# Figure out where Spark is installed
+if [ -z "${SPARK_HOME}" ]; then
+  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+fi
 
 if [ -z "$SPARK_ENV_LOADED" ]; then
   export SPARK_ENV_LOADED=1
 
   # Returns the parent of the directory this script lives in.
-  parent_dir="$(cd "`dirname "$0"`"/..; pwd)"
+  parent_dir="${SPARK_HOME}"
 
   user_conf_dir="${SPARK_CONF_DIR:-"$parent_dir"/conf}"
 
@@ -42,18 +46,18 @@ fi
 
 if [ -z "$SPARK_SCALA_VERSION" ]; then
 
-    ASSEMBLY_DIR2="$FWDIR/assembly/target/scala-2.11"
-    ASSEMBLY_DIR1="$FWDIR/assembly/target/scala-2.10"
+  ASSEMBLY_DIR2="${SPARK_HOME}/assembly/target/scala-2.11"
+  ASSEMBLY_DIR1="${SPARK_HOME}/assembly/target/scala-2.10"
 
-    if [[ -d "$ASSEMBLY_DIR2" && -d "$ASSEMBLY_DIR1" ]]; then
-        echo -e "Presence of build for both scala versions(SCALA 2.10 and SCALA 2.11) detected." 1>&2
-        echo -e 'Either clean one of them or, export SPARK_SCALA_VERSION=2.11 in spark-env.sh.' 1>&2
-        exit 1
-    fi
+  if [[ -d "$ASSEMBLY_DIR2" && -d "$ASSEMBLY_DIR1" ]]; then
+    echo -e "Presence of build for both scala versions(SCALA 2.10 and SCALA 2.11) detected." 1>&2
+    echo -e 'Either clean one of them or, export SPARK_SCALA_VERSION=2.11 in spark-env.sh.' 1>&2
+    exit 1
+  fi
 
-    if [ -d "$ASSEMBLY_DIR2" ]; then
-        export SPARK_SCALA_VERSION="2.11"
-    else
-        export SPARK_SCALA_VERSION="2.10"
-    fi
+  if [ -d "$ASSEMBLY_DIR2" ]; then
+    export SPARK_SCALA_VERSION="2.11"
+  else
+    export SPARK_SCALA_VERSION="2.10"
+  fi
 fi

bin/pyspark

@@ -17,9 +17,11 @@
 # limitations under the License.
 #
 
-export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+if [ -z "${SPARK_HOME}" ]; then
+  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+fi
 
-source "$SPARK_HOME"/bin/load-spark-env.sh
+source "${SPARK_HOME}"/bin/load-spark-env.sh
 export _SPARK_CMD_USAGE="Usage: ./bin/pyspark [options]"
 
 # In Spark <= 1.1, setting IPYTHON=1 would cause the driver to be launched using the `ipython`
@@ -64,12 +66,12 @@ fi
 export PYSPARK_PYTHON
 
 # Add the PySpark classes to the Python path:
-export PYTHONPATH="$SPARK_HOME/python/:$PYTHONPATH"
-export PYTHONPATH="$SPARK_HOME/python/lib/py4j-0.9-src.zip:$PYTHONPATH"
+export PYTHONPATH="${SPARK_HOME}/python/:$PYTHONPATH"
+export PYTHONPATH="${SPARK_HOME}/python/lib/py4j-0.9-src.zip:$PYTHONPATH"
 
 # Load the PySpark shell.py script when ./pyspark is used interactively:
 export OLD_PYTHONSTARTUP="$PYTHONSTARTUP"
-export PYTHONSTARTUP="$SPARK_HOME/python/pyspark/shell.py"
+export PYTHONSTARTUP="${SPARK_HOME}/python/pyspark/shell.py"
 
 # For pyspark tests
 if [[ -n "$SPARK_TESTING" ]]; then
@@ -82,4 +84,4 @@ fi
 
 export PYSPARK_DRIVER_PYTHON
 export PYSPARK_DRIVER_PYTHON_OPTS
-exec "$SPARK_HOME"/bin/spark-submit pyspark-shell-main --name "PySparkShell" "$@"
+exec "${SPARK_HOME}"/bin/spark-submit pyspark-shell-main --name "PySparkShell" "$@"

bin/run-example

@@ -17,11 +17,13 @@
 # limitations under the License.
 #
 
-FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
-export SPARK_HOME="$FWDIR"
-EXAMPLES_DIR="$FWDIR"/examples
+if [ -z "${SPARK_HOME}" ]; then
+  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+fi
+
+EXAMPLES_DIR="${SPARK_HOME}"/examples
 
-. "$FWDIR"/bin/load-spark-env.sh
+. "${SPARK_HOME}"/bin/load-spark-env.sh
 
 if [ -n "$1" ]; then
   EXAMPLE_CLASS="$1"
@@ -34,8 +36,8 @@ else
   exit 1
 fi
 
-if [ -f "$FWDIR/RELEASE" ]; then
-  JAR_PATH="${FWDIR}/lib"
+if [ -f "${SPARK_HOME}/RELEASE" ]; then
+  JAR_PATH="${SPARK_HOME}/lib"
 else
   JAR_PATH="${EXAMPLES_DIR}/target/scala-${SPARK_SCALA_VERSION}"
 fi
@@ -44,7 +46,7 @@ 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 $FWDIR/lib or $FWDIR/examples/target" 1>&2
+    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
@@ -67,7 +69,7 @@ if [[ ! $EXAMPLE_CLASS == org.apache.spark.examples* ]]; then
   EXAMPLE_CLASS="org.apache.spark.examples.$EXAMPLE_CLASS"
 fi
 
-exec "$FWDIR"/bin/spark-submit \
+exec "${SPARK_HOME}"/bin/spark-submit \
   --master $EXAMPLE_MASTER \
   --class $EXAMPLE_CLASS \
   "$SPARK_EXAMPLES_JAR" \

bin/spark-class

@@ -17,10 +17,11 @@
 # limitations under the License.
 #
 
-# Figure out where Spark is installed
-export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+if [ -z "${SPARK_HOME}" ]; then
+  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+fi
 
-. "$SPARK_HOME"/bin/load-spark-env.sh
+. "${SPARK_HOME}"/bin/load-spark-env.sh
 
 # Find the java binary
 if [ -n "${JAVA_HOME}" ]; then
@@ -36,10 +37,10 @@ fi
 
 # Find assembly jar
 SPARK_ASSEMBLY_JAR=
-if [ -f "$SPARK_HOME/RELEASE" ]; then
-  ASSEMBLY_DIR="$SPARK_HOME/lib"
+if [ -f "${SPARK_HOME}/RELEASE" ]; then
+  ASSEMBLY_DIR="${SPARK_HOME}/lib"
 else
-  ASSEMBLY_DIR="$SPARK_HOME/assembly/target/scala-$SPARK_SCALA_VERSION"
+  ASSEMBLY_DIR="${SPARK_HOME}/assembly/target/scala-$SPARK_SCALA_VERSION"
 fi
 
 GREP_OPTIONS=
@@ -65,7 +66,7 @@ LAUNCH_CLASSPATH="$SPARK_ASSEMBLY_JAR"
 
 # Add the launcher build dir to the classpath if requested.
 if [ -n "$SPARK_PREPEND_CLASSES" ]; then
-  LAUNCH_CLASSPATH="$SPARK_HOME/launcher/target/scala-$SPARK_SCALA_VERSION/classes:$LAUNCH_CLASSPATH"
+  LAUNCH_CLASSPATH="${SPARK_HOME}/launcher/target/scala-$SPARK_SCALA_VERSION/classes:$LAUNCH_CLASSPATH"
 fi
 
 export _SPARK_ASSEMBLY="$SPARK_ASSEMBLY_JAR"

bin/spark-shell

@@ -28,7 +28,10 @@ esac
 # Enter posix mode for bash
 set -o posix
 
-export FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
+if [ -z "${SPARK_HOME}" ]; then
+  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+fi
+
 export _SPARK_CMD_USAGE="Usage: ./bin/spark-shell [options]"
 
 # SPARK-4161: scala does not assume use of the java classpath,
@@ -47,11 +50,11 @@ function main() {
     # (see https://github.com/sbt/sbt/issues/562).
     stty -icanon min 1 -echo > /dev/null 2>&1
     export SPARK_SUBMIT_OPTS="$SPARK_SUBMIT_OPTS -Djline.terminal=unix"
-    "$FWDIR"/bin/spark-submit --class org.apache.spark.repl.Main --name "Spark shell" "$@"
+    "${SPARK_HOME}"/bin/spark-submit --class org.apache.spark.repl.Main --name "Spark shell" "$@"
     stty icanon echo > /dev/null 2>&1
   else
     export SPARK_SUBMIT_OPTS
-    "$FWDIR"/bin/spark-submit --class org.apache.spark.repl.Main --name "Spark shell" "$@"
+    "${SPARK_HOME}"/bin/spark-submit --class org.apache.spark.repl.Main --name "Spark shell" "$@"
   fi
 }
 

bin/spark-sql

@@ -17,6 +17,9 @@
 # limitations under the License.
 #
 
-export FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
+if [ -z "${SPARK_HOME}" ]; then
+  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+fi
+
 export _SPARK_CMD_USAGE="Usage: ./bin/spark-sql [options] [cli option]"
-exec "$FWDIR"/bin/spark-submit --class org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver "$@"
+exec "${SPARK_HOME}"/bin/spark-submit --class org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver "$@"

bin/spark-submit

@@ -17,9 +17,11 @@
 # limitations under the License.
 #
 
-SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+if [ -z "${SPARK_HOME}" ]; then
+  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+fi
 
 # disable randomized hash for string in Python 3.3+
 export PYTHONHASHSEED=0
 
-exec "$SPARK_HOME"/bin/spark-class org.apache.spark.deploy.SparkSubmit "$@"
+exec "${SPARK_HOME}"/bin/spark-class org.apache.spark.deploy.SparkSubmit "$@"

bin/sparkR

@@ -17,7 +17,10 @@
 # limitations under the License.
 #
 
-export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
-source "$SPARK_HOME"/bin/load-spark-env.sh
+if [ -z "${SPARK_HOME}" ]; then
+  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+fi
+
+source "${SPARK_HOME}"/bin/load-spark-env.sh
 export _SPARK_CMD_USAGE="Usage: ./bin/sparkR [options]"
-exec "$SPARK_HOME"/bin/spark-submit sparkr-shell-main "$@"
+exec "${SPARK_HOME}"/bin/spark-submit sparkr-shell-main "$@"

sbin/slaves.sh

@@ -36,10 +36,11 @@ if [ $# -le 0 ]; then
   exit 1
 fi
 
-sbin="`dirname "$0"`"
-sbin="`cd "$sbin"; pwd`"
+if [ -z "${SPARK_HOME}" ]; then
+  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+fi
 
-. "$sbin/spark-config.sh"
+. "${SPARK_HOME}/sbin/spark-config.sh"
 
 # If the slaves file is specified in the command line,
 # then it takes precedence over the definition in
@@ -65,7 +66,7 @@ then
   shift
 fi
 
-. "$SPARK_PREFIX/bin/load-spark-env.sh"
+. "${SPARK_HOME}/bin/load-spark-env.sh"
 
 if [ "$HOSTLIST" = "" ]; then
   if [ "$SPARK_SLAVES" = "" ]; then