From bef14d091897d599f161f06bf4956799ce9c0767 Mon Sep 17 00:00:00 2001
From: Suresh Srinivas <suresh@apache.org>
Date: Tue, 3 May 2011 21:19:25 +0000
Subject: [PATCH] HADOOP-7179. Federation: Improve HDFS startup scripts.
 Contributed by Erik Steffl and Tanping Wang.

git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/trunk@1099262 13f79535-47bb-0310-9956-ffa450edef68
---
 CHANGES.txt          |  3 +++
 bin/hadoop-config.sh | 29 +++++++++++++++++++++++++----
 bin/slaves.sh        | 21 +++++++++------------
 3 files changed, 37 insertions(+), 16 deletions(-)

diff --git a/CHANGES.txt b/CHANGES.txt
index bd4289158a..727ee6e7bc 100644
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@ -102,6 +102,9 @@ Trunk (unreleased changes)
     HADOOP-7235. Refactor the tail command to conform to new FsCommand class.
     (Daryn Sharp via szetszwo)
 
+    HADOOP-7179. Federation: Improve HDFS startup scripts. (Erik Steffl
+    and Tanping Wang via suresh)
+
   OPTIMIZATIONS
 
   BUG FIXES
diff --git a/bin/hadoop-config.sh b/bin/hadoop-config.sh
index dfc9215d59..5b83487290 100644
--- a/bin/hadoop-config.sh
+++ b/bin/hadoop-config.sh
@@ -47,19 +47,40 @@ fi
 # Allow alternate conf dir location.
 export HADOOP_CONF_DIR="${HADOOP_CONF_DIR:-$HADOOP_HOME/conf}"
 
-#check to see it is specified whether to use the slaves or the
-# masters file
+# User can specify hostnames or a file where the hostnames are (not both)
+if [[ ( "$HADOOP_SLAVES" != '' ) && ( "$HADOOP_SLAVE_NAMES" != '' ) ]] ; then
+  echo \
+    "Error: Please specify one variable HADOOP_SLAVES or " \
+    "HADOOP_SLAVE_NAME and not both."
+  exit 1
+fi
+
+# Process command line options that specify hosts or file with host
+# list
 if [ $# -gt 1 ]
 then
     if [ "--hosts" = "$1" ]
     then
         shift
-        slavesfile=$1
+        export HADOOP_SLAVES="${HADOOP_CONF_DIR}/$$1"
+        shift
+    elif [ "--hostnames" = "$1" ]
+    then
+        shift
+        export HADOOP_SLAVE_NAMES=$1
         shift
-        export HADOOP_SLAVES="${HADOOP_CONF_DIR}/$slavesfile"
     fi
 fi
 
+# User can specify hostnames or a file where the hostnames are (not both)
+# (same check as above but now we know it's command line options that cause
+# the problem)
+if [[ ( "$HADOOP_SLAVES" != '' ) && ( "$HADOOP_SLAVE_NAMES" != '' ) ]] ; then
+  echo \
+    "Error: Please specify one of --hosts or --hostnames options and not both."
+  exit 1
+fi
+
 cygwin=false
 case "`uname`" in
 CYGWIN*) cygwin=true;;
diff --git a/bin/slaves.sh b/bin/slaves.sh
index bc6078a8cb..b4bafe1097 100755
--- a/bin/slaves.sh
+++ b/bin/slaves.sh
@@ -40,24 +40,21 @@ bin=`cd "$bin"; pwd`
 
 . "$bin"/hadoop-config.sh
 
-# If the slaves file is specified in the command line,
-# then it takes precedence over the definition in 
-# hadoop-env.sh. Save it here.
-HOSTLIST=$HADOOP_SLAVES
-
 if [ -f "${HADOOP_CONF_DIR}/hadoop-env.sh" ]; then
   . "${HADOOP_CONF_DIR}/hadoop-env.sh"
 fi
 
-if [ "$HOSTLIST" = "" ]; then
-  if [ "$HADOOP_SLAVES" = "" ]; then
-    export HOSTLIST="${HADOOP_CONF_DIR}/slaves"
-  else
-    export HOSTLIST="${HADOOP_SLAVES}"
-  fi
+# Where to start the script, see hadoop-config.sh
+# (it set up the variables based on command line options)
+if [ "$HADOOP_SLAVE_NAMES" != '' ] ; then
+  SLAVE_NAMES=$HADOOP_SLAVE_NAMES
+else
+  SLAVE_FILE=${HADOOP_SLAVES:-${HADOOP_CONF_DIR}/slaves}
+  SLAVE_NAMES=$(cat "$SLAVE_FILE" | sed  's/#.*$//;/^$/d')
 fi
 
-for slave in `cat "$HOSTLIST"|sed  "s/#.*$//;/^$/d"`; do
+# start the daemons
+for slave in $SLAVE_NAMES ; do
  ssh $HADOOP_SSH_OPTS $slave $"${@// /\\ }" \
    2>&1 | sed "s/^/$slave: /" &
  if [ "$HADOOP_SLAVE_SLEEP" != "" ]; then