Skip to content
Snippets Groups Projects
Commit 0a6954cd authored by Lars Beckers's avatar Lars Beckers
Browse files

add baremetal apcupsd and bond tasks

parent 94dfa3de
No related branches found
No related tags found
No related merge requests found
#!/bin/sh
#
# This shell script if placed in /etc/apcupsd
# will be called by /etc/apcupsd/apccontrol before
# apcupsd kills the power in the UPS. You probably
# need to edit this to mount read-only /usr and /var,
# otherwise apcupsd will not run.
wall "portal shutdown imminent. processes using ENCRYPTED will be killed in 10 seconds."
service subsonic stop &
service samba stop &
kill -TERM `lsof -R -t /ENCRYPTED` || true
sleep 10
pkill -9 java
kill -9 `lsof -R -t /ENCRYPTED` || true
zpool export ENCRYPTED
exit 0
#!/bin/sh
#
# This shell script if placed in /etc/apcupsd
# will be called by /etc/apcupsd/apccontrol before
# apcupsd kills the power in the UPS. You probably
# need to edit this to mount read-only /usr and /var,
# otherwise apcupsd will not run.
wall "rumo shutdown imminent. storage services will be terminated within 20 seconds."
service nfs-kernel-server stop
service nfs-common stop
sleep 10
kill -TERM `lsof -R -t /DATA` || true
kill -TERM `lsof -R -t /DATA/eschrank` || true
kill -TERM `lsof -R -t /DATA/home` || true
kill -TERM `lsof -R -t /DATA/isos` || true
kill -TERM `lsof -R -t /DATA/pub` || true
kill -TERM `lsof -R -t /DATA/www` || true
sleep 10
kill -9 `lsof -R -t /DATA` || true
kill -9 `lsof -R -t /DATA/eschrank` || true
kill -9 `lsof -R -t /DATA/home` || true
kill -9 `lsof -R -t /DATA/isos` || true
kill -9 `lsof -R -t /DATA/pub` || true
kill -9 `lsof -R -t /DATA/www` || true
zpool export DATA
exit 0
#!/bin/sh
#
# This shell script if placed in /etc/apcupsd
# will be called by /etc/apcupsd/apccontrol before
# apcupsd kills the power in the UPS. You probably
# need to edit this to mount read-only /usr and /var,
# otherwise apcupsd will not run.
service apache stop
zpool export VIDEOAG
exit 0
#!/bin/sh
#
# This shell script if placed in /etc/apcupsd
# will be called by /etc/apcupsd/apccontrol when the UPS
# goes on batteries.
# We send an email message to root to notify him.
#
SYSADMIN=root
APCUPSD_MAIL="mail"
HOSTNAME=`hostname`
MSG="$HOSTNAME Power Failure !!!"
#
(
echo "Subject: $MSG"
echo " "
echo "$MSG"
echo " "
/sbin/apcaccess status
) | $APCUPSD_MAIL -s "$MSG" $SYSADMIN
/usr/bin/python2.7 /etc/apcupsd/onbattery.py
exit 0
#!/bin/sh
#
# This shell script if placed in /etc/apcupsd
# will be called by /etc/apcupsd/apccontrol when the UPS
# goes on batteries.
# We send an email message to root to notify him.
#
SYSADMIN=root
APCUPSD_MAIL="mail"
HOSTNAME=`hostname`
MSG="$HOSTNAME Power Failure !!!"
#
(
echo "Subject: $MSG"
echo " "
echo "$MSG"
echo " "
/sbin/apcaccess status
) | $APCUPSD_MAIL -s "$MSG" $SYSADMIN
/usr/bin/python2.7 /etc/apcupsd/onbattery.py
exit 0
#!/usr/bin/python
import logging, time, sys, socket, os
import subprocess
sys.path.append("/root/pyproxmox/src/")
from pyproxmox import *
logging.basicConfig(format='%(levelname)s:%(message)s', level=logging.DEBUG)
critical_infra = set([104, 105, 106, 108, 112]) # mail, admin, fsmuw, lists, vpn
hostname = socket.gethostname()
proxmox_auth = prox_auth(hostname+'.fsmpi.rwth-aachen.de', 'apc@pve', '')
pr = pyproxmox(proxmox_auth)
def shutdown( host, vmid ):
pr.shutdownVirtualMachine(host, vmid)
return
def migrate( host, vmid, target ):
pr.migrateVirtualMachine(host, vmid, target, True)
return
def stop( host, vmid ):
pr.stopVirtualMachine(host, vmid)
return
def start( vmid ):
pr.startVirtualMachine(host, vmid)
return
def getVMs( host ):
virt_index_list = pr.getNodeVirtualIndex(host)["data"]
return virt_index_list
def getHostStatus( host ):
cluster = pr.getClusterStatus()
for i in cluster:
for j in cluster[i]:
if j["type"] == "node":
if j["name"] == host:
return bool(j["state"])
else:
return False
return False
def migrateCriticalVMs(dest_host, force=False):
vms = getVMs(hostname)
call_again = False
for vm in vms:
if vm['status'] == 'running':
if vm['vmid'] in critical_infra:
if hostname == dest_host:
logging.info("let vm {0} ({1}) run on {2}".format(vm['vmid'], vm['name'], hostname))
else:
call_again = True
logging.info("migrate vm {0} ({1}) from {2} to {3}".format(vm['vmid'], vm['name'], hostname, dest_host))
migrate(hostname, vm['vmid'], dest_host)
else:
call_again = True
if force:
logging.info("stop vm {0} ({1}) running on {2}".format(vm['vmid'], vm['name'], hostname))
stop(hostname, vm['vmid'])
else:
logging.info("shutdown vm {0} ({1}) running on {2}".format(vm['vmid'], vm['name'], hostname))
shutdown(hostname, vm['vmid'])
return call_again
# issue vm migration and shutdown
other_hostname = "vm01" if hostname == "vm02" else "vm01"
#if getHostStatus(other_hostname):
for i in range(0, 3):
time.sleep(120*i)
force = True if i > 1 else False
logging.info("migrating critical vms from {0} to {1} (force: {2}).".format(hostname, "vm02", str(force)))
call_again = migrateCriticalVMs("vm02", force)
if not call_again:
break
#else:
# logging.warn("{0} is offline. vm migration is impossible".format(other_hostname))
vmsonhost = getVMs(hostname)
setvms = set()
for i in vmsonhost:
setvms.add(i['vmid'])
# issue shutdown
if not len(setvms & critical_infra):
logging.info("no critical infra left. {0} may shutdown now.".format(hostname))
subprocess.call(["shutdown", "-h", "now"])
else:
logging.info("this host serves critical infra. {0} shall not halt.".format(hostname))
---
# file: roles/baremetal/handlers/main.yml
- name: restart lldpd
service: name=lldpd state=restarted
- name: restart apcupsd
service: name=apcupsd state=restarted
---
# file: roles/baremetal/tasks/apcupsd.yml
- name: ensure apcupsd is installed
apt: state=latest name=apcupsd
notify:
- restart apcupsd
tags:
- usv
- packages
- name: ensure apcupsd is configured
template: src=apcupsd.conf.j2 dest=/etc/apcupsd/apcupsd.conf owner=root group=root mode=0644
notify:
- restart apcupsd
tags:
- usv
- config
- name: gather apcupsd killpower files
local_action: stat path=apcupsd/killpower/{{ ansible_hostname }}
register: killpower
- name: ensure apcupsd killpower is configured
copy: src=apcupsd/killpower/{{ ansible_hostname }} dest=/etc/apcupsd/killpower owner=root group=root mode=0755
when: killpower.stat.exists
tags:
- usv
- config
- name: gather apcupsd onbattery files
local_action: stat path=apcupsd/onbattery/{{ ansible_hostname }}
register: onbattery
- name: ensure apcupsd onbattery is configured
copy: src=apcupsd/onbattery/{{ ansible_hostname }} dest=/etc/apcupsd/onbattery owner=root group=root mode=0755
when: onbattery.stat.exists
tags:
- usv
- config
- name: ensure on vm hosts there is our fancy onbattery script
copy: src=apcupsd/vm-onbattery.py dest=/etc/apcupsd/onbattery.py owner=root group=root mode=0755
when: "'vm' in ansible_hostname"
tags:
- usv
- config
- name: ensure apcupsd is enabled and running
service: name=apcupsd state=running enabled=yes
tags:
- usv
- service
---
# file: roles/baremetal/tasks/bond.yml
- name: ensure ifenslave is installed
apt: state=latest name=ifenslave
tags:
- bond
- packages
- name: ensure bonding is configured
template: src=interfaces.j2 dest=/etc/network/interfaces owner=root group=root mode=0644
when: "not 'vm' in ansible_hostname"
tags:
- bond
- config
--- ---
# file: roles/baremetal/tasks/software.yml # file: roles/baremetal/tasks/lldpd.yml
- name: ensure lldpd is installed - name: ensure lldpd is installed
apt: state=latest name=lldpd apt: state=latest name=lldpd
notify:
- restart lldpd
tags: tags:
- lldpd - lldpd
- packages - packages
......
---
# file: roles/baremetal/tasks/main.yml
- include: apcupsd.yml
- meta: flush_handlers
- include: bond.yml
- meta: flush_handlers
- include: lldpd.yml
- meta: flush_handlers
## apcupsd.conf v1.1 ##
#
# for apcupsd release 3.14.10 (13 September 2011) - debian
#
# "apcupsd" POSIX config file
#
# ========= General configuration parameters ============
#
# UPSNAME xxx
# Use this to give your UPS a name in log files and such. This
# is particulary useful if you have multiple UPSes. This does not
# set the EEPROM. It should be 8 characters or less.
UPSNAME {{ ups_name }}
# UPSCABLE <cable>
# Defines the type of cable connecting the UPS to your computer.
#
# Possible generic choices for <cable> are:
# simple, smart, ether, usb
#
# Or a specific cable model number may be used:
# 940-0119A, 940-0127A, 940-0128A, 940-0020B,
# 940-0020C, 940-0023A, 940-0024B, 940-0024C,
# 940-1524C, 940-0024G, 940-0095A, 940-0095B,
# 940-0095C, M-04-02-2000
#
UPSCABLE {{ ups_cable }}
# To get apcupsd to work, in addition to defining the cable
# above, you must also define a UPSTYPE, which corresponds to
# the type of UPS you have (see the Description for more details).
# You must also specify a DEVICE, sometimes referred to as a port.
# For USB UPSes, please leave the DEVICE directive blank. For
# other UPS types, you must specify an appropriate port or address.
#
# UPSTYPE DEVICE Description
# apcsmart /dev/tty** Newer serial character device, appropriate for
# SmartUPS models using a serial cable (not USB).
#
# usb <BLANK> Most new UPSes are USB. A blank DEVICE
# setting enables autodetection, which is
# the best choice for most installations.
#
# net hostname:port Network link to a master apcupsd through apcupsd's
# Network Information Server. This is used if the
# UPS powering your computer is connected to a
# different computer for monitoring.
#
# snmp hostname:port:vendor:community
# SNMP network link to an SNMP-enabled UPS device.
# Hostname is the ip address or hostname of the UPS
# on the network. Vendor can be can be "APC" or
# "APC_NOTRAP". "APC_NOTRAP" will disable SNMP trap
# catching; you usually want "APC". Port is usually
# 161. Community is usually "private".
#
# netsnmp hostname:port:vendor:community
# OBSOLETE
# Same as SNMP above but requires use of the
# net-snmp library. Unless you have a specific need
# for this old driver, you should use 'snmp' instead.
#
# dumb /dev/tty** Old serial character device for use with
# simple-signaling UPSes.
#
# pcnet ipaddr:username:passphrase:port
# PowerChute Network Shutdown protocol which can be
# used as an alternative to SNMP with the AP9617
# family of smart slot cards. ipaddr is the IP
# address of the UPS management card. username and
# passphrase are the credentials for which the card
# has been configured. port is the port number on
# which to listen for messages from the UPS, normally
# 3052. If this parameter is empty or missing, the
# default of 3052 will be used.
#
UPSTYPE {{ ups_type }}
DEVICE {{ ups_device }}
# POLLTIME <int>
# Interval (in seconds) at which apcupsd polls the UPS for status. This
# setting applies both to directly-attached UPSes (UPSTYPE apcsmart, usb,
# dumb) and networked UPSes (UPSTYPE net, snmp). Lowering this setting
# will improve apcupsd's responsiveness to certain events at the cost of
# higher CPU utilization. The default of 60 is appropriate for most
# situations.
#POLLTIME 60
# LOCKFILE <path to lockfile>
# Path for device lock file. Not used on Win32.
LOCKFILE /var/lock
# SCRIPTDIR <path to script directory>
# Directory in which apccontrol and event scripts are located.
SCRIPTDIR /etc/apcupsd
# PWRFAILDIR <path to powerfail directory>
# Directory in which to write the powerfail flag file. This file
# is created when apcupsd initiates a system shutdown and is
# checked in the OS halt scripts to determine if a killpower
# (turning off UPS output power) is required.
PWRFAILDIR /etc/apcupsd
# NOLOGINDIR <path to nologin directory>
# Directory in which to write the nologin file. The existence
# of this flag file tells the OS to disallow new logins.
NOLOGINDIR /etc
#
# ======== Configuration parameters used during power failures ==========
#
# The ONBATTERYDELAY is the time in seconds from when a power failure
# is detected until we react to it with an onbattery event.
#
# This means that, apccontrol will be called with the powerout argument
# immediately when a power failure is detected. However, the
# onbattery argument is passed to apccontrol only after the
# ONBATTERYDELAY time. If you don't want to be annoyed by short
# powerfailures, make sure that apccontrol powerout does nothing
# i.e. comment out the wall.
ONBATTERYDELAY {{ ups_onbatdelay }}
#
# Note: BATTERYLEVEL, MINUTES, and TIMEOUT work in conjunction, so
# the first that occurs will cause the initation of a shutdown.
#
# If during a power failure, the remaining battery percentage
# (as reported by the UPS) is below or equal to BATTERYLEVEL,
# apcupsd will initiate a system shutdown.
BATTERYLEVEL {{ ups_batlevel }}
# If during a power failure, the remaining runtime in minutes
# (as calculated internally by the UPS) is below or equal to MINUTES,
# apcupsd, will initiate a system shutdown.
MINUTES {{ ups_minutes }}
# If during a power failure, the UPS has run on batteries for TIMEOUT
# many seconds or longer, apcupsd will initiate a system shutdown.
# A value of 0 disables this timer.
#
# Note, if you have a Smart UPS, you will most likely want to disable
# this timer by setting it to zero. That way, you UPS will continue
# on batteries until either the % charge remaing drops to or below BATTERYLEVEL,
# or the remaining battery runtime drops to or below MINUTES. Of course,
# if you are testing, setting this to 60 causes a quick system shutdown
# if you pull the power plug.
# If you have an older dumb UPS, you will want to set this to less than
# the time you know you can run on batteries.
TIMEOUT {{ ups_timeout }}
# Time in seconds between annoying users to signoff prior to
# system shutdown. 0 disables.
ANNOY {{ ups_annoy }}
# Initial delay after power failure before warning users to get
# off the system.
ANNOYDELAY {{ ups_annoydelay }}
# The condition which determines when users are prevented from
# logging in during a power failure.
# NOLOGON <string> [ disable | timeout | percent | minutes | always ]
NOLOGON {{ ups_nologon }}
# If KILLDELAY is non-zero, apcupsd will continue running after a
# shutdown has been requested, and after the specified time in
# seconds attempt to kill the power. This is for use on systems
# where apcupsd cannot regain control after a shutdown.
# KILLDELAY <seconds> 0 disables
KILLDELAY {{ ups_killdelay }}
#
# ==== Configuration statements for Network Information Server ====
#
# NETSERVER [ on | off ] on enables, off disables the network
# information server. If netstatus is on, a network information
# server process will be started for serving the STATUS and
# EVENT data over the network (used by CGI programs).
NETSERVER on
# NISIP <dotted notation ip address>
# IP address on which NIS server will listen for incoming connections.
# This is useful if your server is multi-homed (has more than one
# network interface and IP address). Default value is 0.0.0.0 which
# means any incoming request will be serviced. Alternatively, you can
# configure this setting to any specific IP address of your server and
# NIS will listen for connections only on that interface. Use the
# loopback address (127.0.0.1) to accept connections only from the
# local machine.
NISIP 127.0.0.1
# NISPORT <port> default is 3551 as registered with the IANA
# port to use for sending STATUS and EVENTS data over the network.
# It is not used unless NETSERVER is on. If you change this port,
# you will need to change the corresponding value in the cgi directory
# and rebuild the cgi programs.
NISPORT 3551
# If you want the last few EVENTS to be available over the network
# by the network information server, you must define an EVENTSFILE.
EVENTSFILE /var/log/apcupsd.events
# EVENTSFILEMAX <kilobytes>
# By default, the size of the EVENTSFILE will be not be allowed to exceed
# 10 kilobytes. When the file grows beyond this limit, older EVENTS will
# be removed from the beginning of the file (first in first out). The
# parameter EVENTSFILEMAX can be set to a different kilobyte value, or set
# to zero to allow the EVENTSFILE to grow without limit.
EVENTSFILEMAX 10
#
# ========== Configuration statements used if sharing =============
# a UPS with more than one machine
#
# Remaining items are for ShareUPS (APC expansion card) ONLY
#
# UPSCLASS [ standalone | shareslave | sharemaster ]
# Normally standalone unless you share an UPS using an APC ShareUPS
# card.
UPSCLASS standalone
# UPSMODE [ disable | share ]
# Normally disable unless you share an UPS using an APC ShareUPS card.
UPSMODE disable
#
# ===== Configuration statements to control apcupsd system logging ========
#
# Time interval in seconds between writing the STATUS file; 0 disables
STATTIME 0
# Location of STATUS file (written to only if STATTIME is non-zero)
STATFILE /var/log/apcupsd.status
# LOGSTATS [ on | off ] on enables, off disables
# Note! This generates a lot of output, so if
# you turn this on, be sure that the
# file defined in syslog.conf for LOG_NOTICE is a named pipe.
# You probably do not want this on.
LOGSTATS off
# Time interval in seconds between writing the DATA records to
# the log file. 0 disables.
DATATIME 0
# FACILITY defines the logging facility (class) for logging to syslog.
# If not specified, it defaults to "daemon". This is useful
# if you want to separate the data logged by apcupsd from other
# programs.
#FACILITY DAEMON
#
# ========== Configuration statements used in updating the UPS EPROM =========
#
#
# These statements are used only by apctest when choosing "Set EEPROM with conf
# file values" from the EEPROM menu. THESE STATEMENTS HAVE NO EFFECT ON APCUPSD.
#
# UPS name, max 8 characters
#UPSNAME UPS_IDEN
# Battery date - 8 characters
#BATTDATE mm/dd/yy
# Sensitivity to line voltage quality (H cause faster transfer to batteries)
# SENSITIVITY H M L (default = H)
#SENSITIVITY H
# UPS delay after power return (seconds)
# WAKEUP 000 060 180 300 (default = 0)
#WAKEUP 60
# UPS Grace period after request to power off (seconds)
# SLEEP 020 180 300 600 (default = 20)
#SLEEP 180
# Low line voltage causing transfer to batteries
# The permitted values depend on your model as defined by last letter
# of FIRMWARE or APCMODEL. Some representative values are:
# D 106 103 100 097
# M 177 172 168 182
# A 092 090 088 086
# I 208 204 200 196 (default = 0 => not valid)
#LOTRANSFER 208
# High line voltage causing transfer to batteries
# The permitted values depend on your model as defined by last letter
# of FIRMWARE or APCMODEL. Some representative values are:
# D 127 130 133 136
# M 229 234 239 224
# A 108 110 112 114
# I 253 257 261 265 (default = 0 => not valid)
#HITRANSFER 253
# Battery charge needed to restore power
# RETURNCHARGE 00 15 50 90 (default = 15)
#RETURNCHARGE 15
# Alarm delay
# 0 = zero delay after pwr fail, T = power fail + 30 sec, L = low battery, N = never
# BEEPSTATE 0 T L N (default = 0)
#BEEPSTATE T
# Low battery warning delay in minutes
# LOWBATT 02 05 07 10 (default = 02)
#LOWBATT 2
# UPS Output voltage when running on batteries
# The permitted values depend on your model as defined by last letter
# of FIRMWARE or APCMODEL. Some representative values are:
# D 115
# M 208
# A 100
# I 230 240 220 225 (default = 0 => not valid)
#OUTPUTVOLTS 230
# Self test interval in hours 336=2 weeks, 168=1 week, ON=at power on
# SELFTEST 336 168 ON OFF (default = 336)
#SELFTEST 336
# This file describes the network interfaces available on your system
# and how to activate them. For more information, see interfaces(5).
source /etc/network/interfaces.d/*
# The loopback network interface
auto lo
iface lo inet loopback
# The bond0
auto lo bond0
iface bond0 inet static
address {{ ipaddr }}
netmask {{ netmask }}
gateway {{ gateway }}
slaves eth0 eth1
bond_mode 802.3ad
bond_xmit_hash_policy layer2+3
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment