A node.js process supervisor and a sample use with health checks - see http://blog.argteam.com/coding/hardening-nodejs-production-process-supervisor/

child_monitor.coffee

{_} = require 'underscore'
child_process = require 'child_process'
async = require 'async'

healthCheckInterval = 60 * 1000
bounceInterval = 60 * 1000
bounceWait = bounceInterval + 30 * 1000

delayTimeout = (ms, func) -> setTimeout func, ms
class MonitoredChild
  constructor: (@script, @port, @healthCheck, @environmentVariables) ->
    @currentChild = null
    @healthCheckTimeout = null
    @bounceTimeout = null
    @expectedExit = false

  bounce: ->
    return @respawn() unless @currentChild?
    console.log "Requested bounce of #{@currentChild.pid}, port #{@port}"
    clearTimeout @healthCheckTimeout
    @expectedExit = true
    @currentChild.kill()
    @bounceTimeout = delayTimeout bounceInterval, =>
      console.error "Child did not exit in time, forcefully killing it"
      @currentChild.kill "SIGKILL"

  delayedHealthCheck: ->
    @healthCheckTimeout = delayTimeout config.healthCheckInterval, =>
      start = new Date()
      @healthCheck @port, (healthy) =>
        if healthy
          console.log "#{@port} is healthy - ping time #{new Date() - start}ms"
          @delayedHealthCheck()
        else
          console.error "#{@port} did not respond in time, killing it harshly"
          @currentChild.kill "SIGKILL"

  respawn: ->
    @currentChild = child_process.spawn process.execPath, [@script],
      env: _.extend(@environmentVariables, process.env)

    console.log "Started child", {port: @port, pid: @currentChild.pid}

    @currentChild.stdout.pipe process.stdout
    @currentChild.stderr.pipe process.stderr

    @currentChild.on 'exit', (code, signal) =>
      clearTimeout @healthCheckTimeout if @healthCheckTimeout?
      clearTimeout @bounceTimeout if @bounceTimeout?
      if @expectedExit
        @expectedExit = false
        console.info "Expected exit from child #{@currentChild.pid}, port #{@port} - respawning"
      else
        console.error "Child #{@currentChild.pid}, port #{@port} exited with code #{code}, signal #{signal}, respawning"
      @respawn()

    @delayedHealthCheck()


exports.bounceChildren = (monitoredChildren, callback) ->
  async.forEachSeries monitoredChildren,
    (monitoredChild, seriesCallback) ->
      monitoredChild.bounce()
      delayTimeout bounceWait, seriesCallback
    callback

exports.spawnMonitoredChild = (script, port, healthCheck, environmentVariables) ->
  ret = new MonitoredChild(script, port, healthCheck, environmentVariables)
  ret.respawn()
  ret

sfs_sockets.coffee

healthCheck = (port, cb) ->
  c = net.connect port, 'localhost'
  c.setEncoding "utf8"

  gotAuth = false
  c.on 'data', (data) ->
    d = null
    try
      d = JSON.parse(data)
    catch error
      c.end()
      console.error "Health check failed: bad initial response, #{data}"
      return cb(false)

    if !gotAuth
      if d.cmd == "PLSAUTH"
        gotAuth = true
        c.write JSON.stringify({cmd:"RING"}) + "\r\n"
      else
        c.end()
        console.error "Health check failed: bad initial response, #{data}"
        return cb(false)
    else
      c.end()
      console.info "Health check response", {res: d}
      return cb(true)

  c.on 'error', (e) ->
    console.error "Health check failed: error connecting #{e}"
    cb(false)

  c.setTimeout config.healthCheckTimeout, -> c.destroy()

numWorkers = 2
startPort = 31337
children = []
for i in [0..numWorkers-1]
  port = startPort + i
  children.push(child_monitor.spawnMonitoredChild './lib/sfs_socket', "sfs_socket_#{port}", healthCheck, {SFS_SOCKET_PORT: port, SFS_SOCKET_HOST: socketHost})

process.on "SIGHUP", ->
  console.log "Received SIGHUP, respawning children"
  child_monitor.bounceChildren(children)