GanetiMaster

#!/bin/sh
#
#   Resource Agent for managing Ganeti master role.
#
#   License:       GNU General Public License (GPL)
#
#   (c) 2010-2013  Giuseppe Paterno' <gpaterno@gpaterno.com>
#                  Guido Trotter <ultrotter@google.com>
#
#
# This resource agent will ensure that ganeti-masterd and
# ganeti-rapi are running in the master node.
#
# Copy this on:
# /usr/lib/ocf/resource.d/ganeti
#
#

# Agent version
VERSION="0.3"

: ${OCF_ROOT=/usr/lib/ocf}
# Load standard OCF functions
: ${OCF_FUNCTIONS_DIR=${OCF_ROOT}/resource.d/heartbeat}
. ${OCF_FUNCTIONS_DIR}/.ocf-shellfuncs

#/usr/lib/ganeti/daemon-util check-config

## Adding in path Ganeti
PATH=$PATH:/usr/lib/ganeti

## Binaries
DAEMON_UTIL="daemon-util"
MASTERD="ganeti-masterd"
CLUSTER_CLI="gnt-cluster"
RAPI="ganeti-rapi"

## Not using Ganeti's voting system
## as pacemaker will take care of voting and quorum
MASTERD_OPTIONS="--no-voting --yes-do-it"

## Who am I
HOSTNAME=$(hostname -f)

## List of master candidates
MASTER_CND_FILE="/var/lib/ganeti/ssconf_master_candidates"

## RAPI endpoint
RAPI_URL="https://localhost:5080/2/info"

# Pre-flight checks
ganeti_master_validate_all() {

   # Check binaries
   check_binary $DAEMON_UTIL
   check_binary $MASTERD
   check_binary $RAPI
   check_binary $CLUSTER_CLI

   # Check if I'm master/master-candidate
   grep -Fx $HOSTNAME $MASTER_CND_FILE >/dev/null

   if [ $? -ne 0 ] ; then
       ocf_log err "$HOSTNAME is not Ganeti master neither master candidate"
       return $OCF_ERR_INSTALLED
   fi

   return $OCF_SUCCESS

}

# Script usage :)
ganeti_master_usage() {

     cat << END
usage: $0 action

action:
        start       : start Ganeti master role
        stop        : stop Ganeti mater role
        status      : return the status of Ganeti master daemon
        monitor     : return if Ganeti Master daemon is working
        meta-data   : show meta data message
        validate-all: validate the instance parameters

END

     return $OCF_ERR_ARGS
}

# Return meta-data information
ganeti_master_meta_data() {
    cat <<END
<?xml version="1.0"?>
<!DOCTYPE resource-agent SYSTEM "ra-api-1.dtd">
<resource-agent name="GanetiMaster">
<version>$VERSION</version>

<longdesc lang="en">
OCF script to manage the ganeti master role in a cluster.
Can be used to failover the ganeti master between master candidate nodes.
</longdesc>

<shortdesc lang="en">Manages the ganeti master role</shortdesc>

<parameters>
</parameters>

<actions>
<action name="start" timeout="60s" />
<action name="stop" timeout="60s" />
<action name="monitor" depth="0" timeout="20s" interval="30s" />
<action name="meta-data" timeout="5s" />
<action name="recover" timeout="20s" />
<action name="reload" timeout="30s" />
</actions>
</resource-agent>
END

   return $OCF_SUCCESS
}

# Start Master
ganeti_master_start() {
   # exit immediately if configuration is not valid
   ganeti_master_validate_all || exit $?

   # Check if masterd is running and start if not
   is_masterd_running

   if [ $? -ne 0 ]
   then

      # Check who's the previous master
      CUR_MASTER=$($CLUSTER_CLI getmaster)
      ocf_log debug "Current master is $CUR_MASTER"

      # Executing failover if we are not the master
      if [ "x$CUR_MASTER" != "x$HOSTNAME" ] ; then
          ocf_log info "$CUR_MASTER is no longer the master, taking over ..."
          $CLUSTER_CLI master-failover $MASTERD_OPTIONS
      else
          # Start masterd
          ocf_log info "Starting $MASTERD"
          ocf_run $DAEMON_UTIL start $MASTERD $MASTERD_OPTIONS
      fi

      # Distribute configuration if I wasn't
      # the previous master. I cannot guarantee
      # the conf of a dead node
      ocf_log info "Redistributing config in the Ganeti cluster ..."
      $CLUSTER_CLI redist-conf

      ## I should check the exit code
      ## but masterd might fail activating IP  

   fi

   # Check if RAPI endpoint is running and start if not
   is_rapi_running

   if [ $? -ne 0 ] 
   then

       # Start RAPI
       ocf_log info "Starting $RAPI"
       ocf_run $DAEMON_UTIL start $RAPI || exit $OCF_ERR_GENERIC

   fi

   return $OCF_SUCCESS

}

# Stop Master
ganeti_master_stop() {

   # Stopping masterd
   ocf_log info "Sopping $MASTERD"
   ocf_run $DAEMON_UTIL stop $MASTERD

   # Stopping RAPI
   ocf_log info "Stopping $RAPI"
   ocf_run $DAEMON_UTIL stop $RAPI

   return $OCF_SUCCESS

}

## Check if RAPI is running
is_rapi_running() {

   curl -k $RAPI_URL >/dev/null 2>/dev/null
    
   if [ $? -ne 0 ] 
   then
      ocf_log info "RAPI endpoint not running." 
      return $OCF_NOT_RUNNING
   else
      ocf_log info "RAPI endpoint running."
      return $OCF_SUCCESS
   fi

}

## Check if masterd is running
is_masterd_running() {

   $CLUSTER_CLI master-ping

   if [ $? -ne 0 ] 
   then
      ocf_log info "Master daemon not running." 
      return $OCF_NOT_RUNNING
   else
      ocf_log info "Master daemon running."
      return $OCF_SUCCESS
   fi

}

# Monitor masterd status
ganeti_master_monitor() {

   is_masterd_running
   master_status=$?

   is_rapi_running
   rapi_status=$?

   if [ $master_status -eq 0 -a $rapi_status -eq 0 ] 
   then
      ocf_log info "Ganeti master service is running"
      return $OCF_SUCCESS
   else
      ocf_log info "Ganeti master service is not running"
      return $OCF_NOT_RUNNING
   fi

}


# Make sure meta-data and usage always succeed
case $__OCF_ACTION in

   meta-data)      ganeti_master_meta_data
                   exit $OCF_SUCCESS
                   ;;
   usage|help)     ganeti_master_usage
                   exit $OCF_SUCCESS
                   ;;

esac

# Anything other than meta-data and usage must pass validation
ganeti_master_validate_all || exit $?

# Translate each action into the appropriate function call
case $__OCF_ACTION in

   start)          ganeti_master_start 
                   ;;
   stop)           ganeti_master_stop 
                   ;;
   status|monitor) ganeti_master_monitor 
                   ;;
   promote)        exit $OCF_SUCCESS 
                   ;;
   demote)         exit $OCF_SUCCESS 
                   ;;
   reload)         ocf_log info "Reloading Ganeti Master..."
                   ganeti_master_start
                   ;;
   validate-all)   ;;
   *)              ganeti_master_usage
                   exit $OCF_ERR_UNIMPLEMENTED
                   ;;

esac
rc=$?

# Final debug
ocf_log debug "${OCF_RESOURCE_INSTANCE} $__OCF_ACTION returned $rc"
exit $rc