God of Gods

god-of-gods.god

#
#
#   God of Gods - A god config file
#   Rick Branson <rick@diodeware.com>
#
#   Runs a god instance for every user on the system, provided
#   they have a .godrc file in their home diretory, which is just
#   a regular old god config file. 
#
#
require "etc"

GODRC_FILE = ".godrc"

Etc.passwd do |u|
  next if u.uid == 0 or u.gid == 0
  
  File.exist?(u.dir) && File.directory?(u.dir) && Dir.chdir(u.dir) do
    user_file = File.expand_path(GODRC_FILE)
    
    if File.exist?(user_file)
      God.watch do |w|
        w.dir       = "#{u.dir}"
        w.name      = "#{u.name}-master"
        w.group     = 'user-gods'
        w.interval  = 30.seconds
        w.start     = "/usr/bin/env god -c #{user_file} -D -b"
        w.uid       = u.name 
        
        # determine the state on startup
        w.transition(:init, { true => :up, false => :start }) do |on|
          on.condition(:process_running) do |c|
            c.running = true
          end
        end

        # determine when process has finished starting
        w.transition([:start, :restart], :up) do |on|
          on.condition(:process_running) do |c|
            c.running = true
          end

          # failsafe
          on.condition(:tries) do |c|
            c.times = 5
            c.transition = :start
          end
        end

        # start if process is not running
        w.transition(:up, :start) do |on|
          on.condition(:process_exits)
        end

        # restart if memory or cpu is too high
        w.transition(:up, :restart) do |on|
          on.condition(:memory_usage) do |c|
            c.interval = 20
            c.above = 50.megabytes
            c.times = [3, 5]
          end

          on.condition(:cpu_usage) do |c|
            c.interval = 10
            c.above = 10.percent
            c.times = [3, 5]
          end
        end

        # lifecycle
        w.lifecycle do |on|
          on.condition(:flapping) do |c|
            c.to_state = [:start, :restart]
            c.times = 5
            c.within = 5.minute
            c.transition = :unmonitored
            c.retry_in = 10.minutes
            c.retry_times = 5
            c.retry_within = 2.hours
          end
        end
      end
    end
  end
end