Backup health check

backup_health.py

#!/usr/bin/env python
import os
import sys
import datetime

#rsync config path
rsync_secrets = "/etc/rsyncd.lg-secrets"
backup_root = "/backup"

# Exit statuses recognized by Nagios
UNKNOWN = -1
OK = 0
WARNING = 1
CRITICAL = 2

#CUTOFFHOURS To create warning and critical error
CUTOFFHOUR_WARN = 48
CUTOFFHOUR_CRIT = 72
message = ""
CRIT_SERVERS = []
WARN_SERVERS = []
seconds_per_hour = 3600.0
nagios_templates = {'OK':'%s', 'WARNING':'%s', 'CRITICAL':'%s'}
nagios_exit_codes = {'OK':0,'WARNING':1,'CRITICAL':2,'UNKNOWN':3}


def nagios_print_and_exit(state, message):
    print "%s: %s" % (state, message)
    sys.exit(nagios_exit_codes[state])

SERVERS = [line.strip().split(':')[0] for line in open(rsync_secrets) if line]

def main():
	for server in SERVERS:
		# Determine the age of the path in hours.
		path = os.path.join(backup_root, server)
		if os.path.exists(path):
			path_stat = max(os.stat(root).st_mtime for root,_,_ in os.walk(path))
			path_ctime = datetime.datetime.fromtimestamp(path_stat)
			path_age = ((datetime.datetime.now() - path_ctime).total_seconds()) / seconds_per_hour
			#print path, path_age

			if path_age > CUTOFFHOUR_CRIT:
			    CRIT_SERVERS.append(server)
			elif path_age > CUTOFFHOUR_WARN:
			    WARN_SERVERS.append(server)
			else:
			    current_state = 'OK'


	if CRIT_SERVERS:
	    message = "BACKUP CRIT:" + ','.join(CRIT_SERVERS)
	    current_state = 'CRITICAL'
	    if WARN_SERVERS:
	    	message += " Additional Warning:" + ','.join(WARN_SERVERS)
	elif WARN_SERVERS:
	    message = "BACKUP WARN:" + ','.join(WARN_SERVERS)
	    current_state = 'WARNING'
	else:
	    current_state = 'OK'
	    message = "BACKUP Health is OK"

	nagios_print_and_exit(current_state, nagios_templates[current_state]  % message)

if __name__ == '__main__':
	main()