fixed a bug in elasticsearch.in.sh (conf dir was pointing to work dir…

…), rakefile is a little cleaner and easier to understand, adding notes for upcoming blog post

Rakefile

@@ -1,13 +1,12 @@
 #!/usr/bin/env ruby
 
 require 'rubygems'
-require 'wukong'
 require 'configliere' ; Configliere.use(:commandline, :env_var, :define)
 
 WORK_DIR=File.expand_path(File.dirname(__FILE__))
 Settings.define :src,         :default => "#{WORK_DIR}/src",                :description => "Java source dir"
 Settings.define :target,      :default => "#{WORK_DIR}/build",              :description => "Build target, this is where compiled classes live"
-Settings.define :main_class,  :default => "ElasticBulkLoader",              :description => "Main java class to run"
+Settings.define :jar_name,    :default => "wonderdog",                      :description => "Name of the target jar"
 Settings.define :hadoop_home, :default => "/usr/lib/hadoop",                :description => "Path to hadoop installation",       :env_var => "HADOOP_HOME"
 Settings.define :es_home,     :default => "/usr/local/share/elasticsearch", :description => "Path to elasticsearch installation",:env_var => "ES_HOME"
 Settings.resolve!
@@ -31,20 +30,20 @@ end
 
 def srcs options
   sources = Dir[
-    "#{options.src}/*.java",
+    "#{options.src}/**/*.java",
   ].inject([]){|sources, src| sources << src; sources}
   sources.join(' ')
 end
 
-#
-# FIXME: Needs to be idempotent ...
-#
-task :compile do
-  puts "Compiling #{options.src} ..."
-  snakeized = options.main_class.underscore
-  mkdir_p File.join(options.target, snakeized)
-  system "javac -cp #{classpath(options)} -d #{options.target}/#{snakeized} #{srcs(options)}"
-  system "jar -cvf  #{options.target}/#{snakeized}.jar -C #{options.target}/#{snakeized} . "
+jar_dir = File.join(options.target, options.jar_name)
+directory jar_dir
+
+task :compile => jar_dir do
+  sh "javac -cp #{classpath(options)} -d #{jar_dir} #{srcs(options)}"
+end
+
+task :jar => :compile do
+  sh "jar -cvf  #{jar_dir}.jar -C #{jar_dir} . "
 end
 
-task :default => [:compile]
+task :default => [:jar]

config/elasticsearch.in.sh

@@ -1,4 +1,4 @@
-export ES_CONF_DIR=${ES_WORK_DIR-/etc/elasticsearch}
+export ES_CONF_DIR=${ES_CONF_DIR-/etc/elasticsearch}
 export ES_WORK_DIR=${ES_WORK_DIR-/mnt/elasticsearch/work}
 export ES_DATA_DIR=${ES_DATA_DIR-/mnt/elasticsearch/data}
 

notes.txt

@@ -1,10 +1,32 @@
-<h2>Install and start ElasticSearch</h2>
+<h2>Getting Started with ElasticSearch</h2>
 
 <pre class="brush: bash">
 $: wget http://github.com/downloads/elasticsearch/elasticsearch/elasticsearch-0.14.2.zip
 $: sudo mv elasticsearch-0.14.2 /usr/local/share/
 $: sudo ln -s /usr/local/share/elasticsearch-0.14.2 /usr/local/share/elasticsearch
-$: /usr/local/share/elasticsearch/bin/elasticsearch
 </pre>
 
-You'll probably want to change the configuration for your particular setup but that should at least get you started.
+Next you'll want to make sure there is an 'elasticsearch' user and that there are suitable data, work, and log directories that 'elasticsearch' owns:
+
+<pre class="brush: bash">
+$: sudo useradd elasticsearch
+$: sudo mkdir -p /var/log/elasticsearch /var/run/elasticsearch/{data,work}
+$: sudo chown -R elasticsearch /var/{log,run}/elasticsearch
+</pre>
+
+Go ahead and copy the example configuration:
+
+<pre class="brush: bash">
+$: sudo mkdir -p /etc/elasticsearch
+$: sudo cp config/elasticsearch-example.yml /etc/elasticsearch/elasticsearch.yml
+$: sudo cp config/logging.yml /etc/elasticsearch/
+$: sudo cp config/elasticsearch.in.sh /etc/elasticsearch/
+</pre>
+
+and make changes to 'elasticsearch.yml' such that it points to the correct data, work, and log directories. Also, you'll want to change the number of 'recovery_after_nodes' and 'expected_nodes' in elasticsearch.yml to however many nodes (machines) you actually expect to have in your cluster. You'll probably also want to do a quick once-over of elasticsearch.in.sh and make sure the jvm settings, etc are sane for your particular setup. Finally, to startup do:
+
+<pre class="brush: bash">
+sudo -u elasticsearch /usr/local/share/elasticsearch/bin/elasticsearch -Des.config=/etc/elasticsearch/elasticsearch.yml
+</pre>
+
+You should now have a happily running (reasonably configured) elasticsearch data node.