A python script that restarts other node on ovh when fencing occurs Original post http://forum.proxmox.com/threads/11066-Proxmox-HA-Cluster-at-OVH-Fencing?p=75152

ovh_fence.py

# assemled by Dennis Busch, secofor GmbH,
# Germany
# This work is licensed under a
# Creative Commons Attribution-ShareAlike 3.0 Unported License.

# Manual call parametres example
#
# login=ab12345-ovh
# passwd=MYSECRET
# email=admin@myadmin
# ipaddr=ns12345
# action=off

# # where ipaddr is your server's OVH name

import sys, re, pexpect
sys.path.append("/usr/share/fence")
from fencing import *

import sys
from suds.client import Client
from suds.xsd.doctor import ImportDoctor, Import
import time
from datetime import datetime

OVH_RESCUE_PRO_NETBOOT_ID='28'
OVH_HARD_DISK_NETBOOT_ID='1'
STATUS_HARD_DISK_SLEEP=240 # Wait 4 minutes to SO to boot
STATUS_RESCUE_PRO_SLEEP=150 # Wait 2 minutes 30 seconds to Rescue-Pro to run
OVH_FENCE_DEBUG=False # True or False for debug

def netboot_reboot(nodeovh,login,passwd,email,mode):
    imp = Import('http://schemas.xmlsoap.org/soap/encoding/')
    url='https://www.ovh.com/soapi/soapi-re-1.59.wsdl'
    imp.filter.add('http://soapi.ovh.com/manager')
    d = ImportDoctor(imp)
    soap = Client(url, doctor=d)
    session = soap.service.login(login, passwd, 'es', 0)
 
    #dedicatedNetbootModifyById changes the mode of the next reboot
    result = soap.service.dedicatedNetbootModifyById(session, nodeovh, mode, '', email)
 
    #dedicatedHardRebootDo initiates a hard reboot on the given node
    soap.service.dedicatedHardRebootDo(session, nodeovh, 'Fencing initiated by cluster', '', 'es')
 
    soap.service.logout(session)

def reboot_status(nodeovh,login,passwd):
    imp = Import('http://schemas.xmlsoap.org/soap/encoding/')
    url='https://www.ovh.com/soapi/soapi-re-1.59.wsdl'
    imp.filter.add('http://soapi.ovh.com/manager')
    d = ImportDoctor(imp)
    soap = Client(url, doctor=d)
    session = soap.service.login(login, passwd, 'es', 0)
 
    result = soap.service.dedicatedHardRebootStatus(session, nodeovh)
    tmpstart = datetime.strptime(result.start,'%Y-%m-%d %H:%M:%S')
    tmpend = datetime.strptime(result.end,'%Y-%m-%d %H:%M:%S')
    result.start = tmpstart
    result.end = tmpend

    soap.service.logout(session)
    return result

#print stderr to file
save_stderr = sys.stderr
errlog = open("/var/log/fence_ovh_error.log","a")
sys.stderr = errlog

global all_opt

device_opt = [  "email", "ipaddr", "action" , "login" , "passwd" , "nodename" ]

ovh_fence_opt = {
        "email" : {
                "getopt" : "Z:",
                "longopt" : "email",
                "help" : "-Z, --email=<email>          email for reboot message: admin@domain.com",
                "required" : "1",
                "shortdesc" : "Reboot email",
                "default" : "",
                "order" : 1 },
}

all_opt.update(ovh_fence_opt)
all_opt["ipaddr"]["shortdesc"] = "OVH node name"

atexit.register(atexit_handler)
options=check_input(device_opt,process_input(device_opt))
# Not sure if I need this old notation
## Support for -n [switch]:[plug] notation that was used before
if ((options.has_key("-n")) and (-1 != options["-n"].find(":"))):
    (switch, plug) = options["-n"].split(":", 1)
    if ((switch.isdigit()) and (plug.isdigit())):
        options["-s"] = switch
        options["-n"] = plug

if (not (options.has_key("-s"))):
    options["-s"]="1"

docs = { }
docs["shortdesc"] = "Fence agent for OVH"
docs["longdesc"] = "fence_ovh is an Power Fencing agent \
which can be used within OVH datecentre. \
Poweroff is simulated with a reboot into rescue-pro \
mode. \
 /usr/local/etc/ovhsecret example: \
 \
 [OVH] \
 Login = ab12345-ovh \
 Passwd = MYSECRET \
"
docs["vendorurl"] = "http://www.ovh.net"
show_docs(options, docs)


#I use a own logfile for debugging purpose
if OVH_FENCE_DEBUG:
    logfile=open("/var/log/fence_ovh.log", "a");
    logfile.write(time.strftime("\n%d.%m.%Y %H:%M:%S \n"))
    logfile.write("Parameter:\t")
    for val in sys.argv:
    logfile.write(val + " ")
    logfile.write("\n")

print options

action=options['--action']
email=options['--email']
login=options['--username']
passwd=options['--password']
nodeovh=options['--ip']
if nodeovh[-8:] != '.ovh.net':
    nodeovh += '.ovh.net'
    
# Save datetime just before changing netboot
before_netboot_reboot = datetime.now()

if action == 'off':
    netboot_reboot(nodeovh,login,passwd,email,OVH_RESCUE_PRO_NETBOOT_ID) #Reboot in Rescue-pro
elif action == 'on':
    netboot_reboot(nodeovh,login,passwd,email,OVH_HARD_DISK_NETBOOT_ID) #Reboot from HD
elif action == 'reboot':
    netboot_reboot(nodeovh,login,passwd,email,OVH_HARD_DISK_NETBOOT_ID) #Reboot from HD
else:
    if OVH_FENCE_DEBUG:
    logfile.write("nothing to do\n")
    logfile.close()
    errlog.close()
    sys.exit()

if action == 'off':
    time.sleep(STATUS_RESCUE_PRO_SLEEP) #Reboot in vKVM
elif action == 'on':
    time.sleep(STATUS_HARD_DISK_SLEEP) #Reboot from HD
elif action == 'reboot':
    time.sleep(STATUS_HARD_DISK_SLEEP) #Reboot from HD
else:
    if OVH_FENCE_DEBUG:
    logfile.write("No sense! Check script please!\n")
    logfile.close()
    errlog.close()
    
    sys.exit()

after_netboot_reboot = datetime.now()

# Verification of success

reboot_start_end=reboot_status(nodeovh,login,passwd)
if OVH_FENCE_DEBUG:
    logfile.write("reboot_start_end.start: " +reboot_start_end.start.strftime('%Y-%m-%d %H:%M:%S')+"\n")
    logfile.write("before_netboot_reboot: " +before_netboot_reboot.strftime('%Y-%m-%d %H:%M:%S')+"\n")
    logfile.write("reboot_start_end.end: " +reboot_start_end.end.strftime('%Y-%m-%d %H:%M:%S')+"\n")
    logfile.write("after_netboot_reboot: " +after_netboot_reboot.strftime('%Y-%m-%d %H:%M:%S')+"\n")

if ((reboot_start_end.start > before_netboot_reboot) and (reboot_start_end.end < after_netboot_reboot)):
    if OVH_FENCE_DEBUG:
    logfile.write("Netboot reboot went OK.\n")
else:
    if OVH_FENCE_DEBUG:
    logfile.write("ERROR: Netboot reboot wasn't OK.\n")
    logfile.close()
    errlog.close()
    sys.exit(1)


if OVH_FENCE_DEBUG:
    logfile.close()
errlog.close()