From 121f9338cefbb1c800fabfea5152899a58176b00 Mon Sep 17 00:00:00 2001
From: Kousuke Saruta <sarutak@oss.nttdata.com>
Date: Tue, 30 Jul 2019 12:45:32 -0700
Subject: [PATCH] [SPARK-28525][DEPLOY] Allow Launcher to be applied Java
 options

Launcher is implemented as a Java application and sometimes I'd like to apply Java options.
One situation I have met is the time I try to attach debugger to Launcher.

Launcher is launched from bin/spark-class but there is no room to apply Java options.

```
build_command() {
  "$RUNNER" -Xmx128m -cp "$LAUNCH_CLASSPATH" org.apache.spark.launcher.Main "$"
  printf "%d\0" $?
}
```

Considering that it's not so many times to apply Java options to Launcher,  one compromise would just modify spark-class by user like as follows.

```
build_command() {
  "$RUNNER" -Xmx128m $SPARK_LAUNCHER_OPTS -cp "$LAUNCH_CLASSPATH" org.apache.spark.launcher.Main "$"
  printf "%d\0" $?
}
```

But it doesn't work when any text related to Java options is output to standard output because whole output is used as command-string for spark-shell and spark-submit in current implementation.

One example is jdwp. When apply agentlib option to use jdwp for debug, we will get output like as follows.

```
Listening for transport dt_socket at address: 9876
```

The output shown above is not a command-string so spark-submit and spark-shell will fail.
To enable Java options for Launcher, we need treat command-string and others.

I changed launcher/Main.java and bin/spark-class to print separator-character and treat it.

## How was this patch tested?

Tested manually using Spark Shell with / without LAUNCHER_JAVA_OPTIONS like as follows.

```
SPARK_LAUNCHER_OPTS="-agentlib:jdwp=transport=dt_socket,suspend=y,address=localhost:9876,server=y" bin/spark-shell
```

Closes #25265 from sarutak/add-spark-launcher-opts.

Authored-by: Kousuke Saruta <sarutak@oss.nttdata.com>
Signed-off-by: Marcelo Vanzin <vanzin@cloudera.com>
---
 bin/spark-class                                | 18 +++++++++++++++---
 conf/spark-env.sh.template                     |  3 +++
 .../java/org/apache/spark/launcher/Main.java   |  3 +++
 3 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/bin/spark-class b/bin/spark-class
index 65d3b96129..c1461a7712 100755
--- a/bin/spark-class
+++ b/bin/spark-class
@@ -68,15 +68,27 @@ fi
 # The exit code of the launcher is appended to the output, so the parent shell removes it from the
 # command array and checks the value to see if the launcher succeeded.
 build_command() {
-  "$RUNNER" -Xmx128m -cp "$LAUNCH_CLASSPATH" org.apache.spark.launcher.Main "$@"
+  "$RUNNER" -Xmx128m $SPARK_LAUNCHER_OPTS -cp "$LAUNCH_CLASSPATH" org.apache.spark.launcher.Main "$@"
   printf "%d\0" $?
 }
 
 # Turn off posix mode since it does not allow process substitution
 set +o posix
 CMD=()
-while IFS= read -d '' -r ARG; do
-  CMD+=("$ARG")
+DELIM=$'\n'
+CMD_START_FLAG="false"
+while IFS= read -d "$DELIM" -r ARG; do
+  if [ "$CMD_START_FLAG" == "true" ]; then
+    CMD+=("$ARG")
+  else
+    if [ "$ARG" == $'\0' ]; then
+      # After NULL character is consumed, change the delimiter and consume command string.
+      DELIM=''
+      CMD_START_FLAG="true"
+    elif [ "$ARG" != "" ]; then
+      echo "$ARG"
+    fi
+  fi
 done < <(build_command "$@")
 
 COUNT=${#CMD[@]}
diff --git a/conf/spark-env.sh.template b/conf/spark-env.sh.template
index bc92c78f0f..df39ad8b0d 100755
--- a/conf/spark-env.sh.template
+++ b/conf/spark-env.sh.template
@@ -56,6 +56,9 @@
 # - SPARK_DAEMON_CLASSPATH, to set the classpath for all daemons
 # - SPARK_PUBLIC_DNS, to set the public dns name of the master or workers
 
+# Options for launcher
+# - SPARK_LAUNCHER_OPTS, to set config properties and Java options for the launcher (e.g. "-Dx=y")
+
 # Generic options for the daemons used in the standalone deploy mode
 # - SPARK_CONF_DIR      Alternate conf dir. (Default: ${SPARK_HOME}/conf)
 # - SPARK_LOG_DIR       Where log files are stored.  (Default: ${SPARK_HOME}/logs)
diff --git a/launcher/src/main/java/org/apache/spark/launcher/Main.java b/launcher/src/main/java/org/apache/spark/launcher/Main.java
index d967aa39a4..e1054c7060 100644
--- a/launcher/src/main/java/org/apache/spark/launcher/Main.java
+++ b/launcher/src/main/java/org/apache/spark/launcher/Main.java
@@ -90,6 +90,9 @@ class Main {
     if (isWindows()) {
       System.out.println(prepareWindowsCommand(cmd, env));
     } else {
+      // A sequence of NULL character and newline separates command-strings and others.
+      System.out.println('\0');
+
       // In bash, use NULL as the arg separator since it cannot be used in an argument.
       List<String> bashCmd = prepareBashCommand(cmd, env);
       for (String c : bashCmd) {