From 80f8e07e75431f360ffbd0f3daee305cd87363c6 Mon Sep 17 00:00:00 2001 From: thierry Date: Sun, 18 Feb 2007 15:31:25 +0000 Subject: [PATCH] creation : creates nagios config from a set of sites --- nagios/configurator/NagiosConfig.py | 450 +++++++++++++ nagios/configurator/cgi.cfg | 275 ++++++++ nagios/configurator/comon_query.py | 188 ++++++ nagios/configurator/configurator.py | 111 ++++ nagios/configurator/generic.cfg | 212 ++++++ nagios/configurator/makeHTML.py | 590 +++++++++++++++++ nagios/configurator/misccommands.cfg | 104 +++ nagios/configurator/nagios.cfg | 939 +++++++++++++++++++++++++++ nagios/configurator/nagios.py | 6 + nagios/configurator/onelab.txt | 1 + 10 files changed, 2876 insertions(+) create mode 100644 nagios/configurator/NagiosConfig.py create mode 100644 nagios/configurator/cgi.cfg create mode 100755 nagios/configurator/comon_query.py create mode 100755 nagios/configurator/configurator.py create mode 100644 nagios/configurator/generic.cfg create mode 100644 nagios/configurator/makeHTML.py create mode 100644 nagios/configurator/misccommands.cfg create mode 100644 nagios/configurator/nagios.cfg create mode 100644 nagios/configurator/nagios.py create mode 100644 nagios/configurator/onelab.txt diff --git a/nagios/configurator/NagiosConfig.py b/nagios/configurator/NagiosConfig.py new file mode 100644 index 0000000..d159279 --- /dev/null +++ b/nagios/configurator/NagiosConfig.py @@ -0,0 +1,450 @@ +import os +import sys +import xmlrpclib + +### downloaded makeHTML from: +### article +### http://www.hoboes.com/Mimsy/?ART=128 +### download \ +### http://www.hoboes.com/Mimsy/library/downloads/makeHTML.py.gz +import makeHTML + +# utilities for building comon queries +import comon_query + + +class NagiosConfig: + + # static + _admin_role=10 + _pi_role=20 + # person emails to exclude + _exclude_admins={'maint@localhost.localdomain':True} + + # set of services to check on each node + # these refer to generic services you must have in generic.cfg + _full_node_services = ['ssh', + 'ssh-root', + 'ssh-pl_conf', + ] + _restricted_node_services = ['ssh', + 'planetlab', + ] + + _verbose = False +# WARNING : some site names come with wierd unicode chars +# in this case verbose mode might fail +# _verbose = True + + plchost=None + xmlrpcserver = None + auth=None + + dest_email = None + + # a tree of sites, for access to nodes and contacts + siteTree = None + # list of admin people + allAdmins = {} + + ### record arguments + def __init__ (self, plchost, plcid, plcpasswd, plcrole): + self.plchost = plchost + + self.auth={} + self.auth['Username'] = plcid + self.auth['AuthMethod'] = "password" + self.auth['AuthString'] = plcpasswd + self.auth['Role']=plcrole + + def Auth (self): + return self.auth + + ### connect to xml rpc server + def Connect (self): + + try: + self.xmlrpcserver = xmlrpclib.Server("https://%s/PLCAPI/" + % (self.plchost)) + except: + self.xmlrpcserver = None + + return self.xmlrpcserver + + def set_verbose (self): + self._verbose = True + + def verbose (self,arg): + if (self._verbose): + print str(arg) + + def GatherData (self, email, sitefile): + + # if email is None, we NEED to have admin role + # otherwise let's dont wait 10 minutes before we fail + AdminRoleRequired = "admin role required, or provide -o/-O" + if not email: + if self.auth['Role'] != 'admin': + raise AdminRoleRequired + + self.dest_email = email + + self.verbose ("Gathering") + server = self.Connect() + auth = self.Auth () + + if sitefile: + # open and parse the file, let's gather site_ids in the process + self.verbose("Opening site file %s"%sitefile) + siteF=open(sitefile,'r') + selected_ids=[] + while 1: + siteline=siteF.readline() + if not siteline: + break + selected_ids += [int(siteline.split(' ')[0])] + siteF.close() + sitesList = server.GetSites(auth,selected_ids) + else: + # get list of all sites + sitesList = server.GetSites(auth) + self.verbose("Working on a total of %d sites"%len(sitesList)) + + selectedNodeIds = []; + for site in sitesList: + selectedNodeIds += site['node_ids'] + + # get all nodenetworks + allNodeNetworks = server.GetNodeNetworks (auth) + allNodeNetworksIndex = dict ( [ ( nn['nodenetwork_id'],nn) for nn in allNodeNetworks ] ) + + # get list of nodes + # might wish to restrict the returned attributes + selectedNodes = server.GetNodes(auth,selectedNodeIds,['node_id','hostname','nodenetwork_ids']) + self.verbose("Got a total of %d nodes"%len(selectedNodes)) + + for node in selectedNodes: + if not node['nodenetwork_ids']: + print 'WARNING : Node %s has no nodenetwork thus no IP'%node['hostname'] + nn = allNodeNetworksIndex[node['nodenetwork_ids'][0]] + node['ip'] = nn['ip'] + + + # index it by node_id + selectedNodesIndex = dict( [ (node['node_id'],node) for node in selectedNodes ] ) + + self.siteTree = {} + for site in sitesList : + self.verbose( "SITE = %s" % site['name']) + site_id=site['site_id'] + siteHash = {} + self.siteTree[site_id] = siteHash + node_ids = site['node_ids'] + self.verbose( "NODES IDS = " + str(node_ids)) + siteNodes=[ selectedNodesIndex[node_id] for node_id in node_ids ] + nodesHash = dict ( [ (node['node_id'],node) for node in siteNodes ] ) + personsHash = {} + siteHash['site'] = site + siteHash['nodes'] = nodesHash + siteHash['persons'] = personsHash + + # We are provided a hard-wired e-mail : + # dont scan all people (maybe we cannot) + if not email: + + # get list of people + allPersons = server.GetPersons (auth, [],['person_id','email', + 'first_name','last_name']) + for person in allPersons: + person_id = person['person_id'] + # keep only PIs + roles = server.AdmGetPersonRoles (auth,person_id) + is_admin = roles.has_key(str(self._admin_role)) + is_pi = roles.has_key(str(self._pi_role)) + if is_admin: + ### handle exclude list + if not self._exclude_admins.has_key(person['email']): + self.allAdmins[person_id]=person + elif is_pi: + person_sites=server.AdmGetPersonSites(auth,person_id) + for site_id in person_sites: + personsHash = self.siteTree[site_id]['persons'] + personsHash[person_id]=person + person['full_name']=person['first_name']+person['last_name'] + self.verbose("Added PI %s" % person['full_name']) + + _define_host="""define host{ + use generic-host + host_name %s + alias %s + address %s + contact_groups %s_pis + }\n""" + _define_hostgroup="""define hostgroup{ + hostgroup_name %s + alias %s + members %s + }\n""" + # as of nagios-2.5-2.fc4 - apparently cannot use genericity in contacts + _define_contact="""define contact{ + contact_name %s + alias %s %s + email %s + service_notification_period 24x7 + host_notification_period 24x7 + service_notification_options w,u,c,r + host_notification_options d,r + service_notification_commands notify-by-email + host_notification_commands host-notify-by-email + }\n""" + _define_contactgroup="""define contactgroup{ + contactgroup_name %s_pis + alias %s + members %s + }\n""" + _define_service="""define service{ + use generic-%s + host_name %s + contact_groups %s_pis + servicegroups %s + }\n""" + _define_servicegroup="""define servicegroup{ + servicegroup_name %s + alias all %s + }\n""" + + def WriteNagiosConfig (self, dirname): + + site_ids=self.siteTree.keys() + site_ids.sort() + + + # by default use all avail services + node_services = self._full_node_services + # but in restricted mode some wont work out + if self.dest_email: + node_services = self._restricted_node_services + + # generate contact file + # with people with admin roles, and also + # centraladmin if email was provided + # located in main dir so we can have control on load order + filename = "%s/%s.cfg"%(dirname,"planetlab") + print ( "Opening %s for writing" % filename) + file = open (filename,'w') + for admin_id in self.allAdmins.keys(): + admin=self.allAdmins[admin_id] + file.write(self._define_contact% + ('rootadmin','root','admin',admin['email'])) + if self.dest_email: + file.write(self._define_contact% + (self.dest_email,'central','admin',self.dest_email)) + + for service in node_services: + file.write(self._define_servicegroup + %(service,service)) + + file.close() + + ### manage planetlab subdir + planetlabdir="%s/planetlab/"%dirname + import os.path + if not os.path.isdir (planetlabdir): + try: + print "Trying to create subdir %s"%planetlabdir + os.mkdir (planetlabdir) + except Exception,e: + print "Failed -- exiting" + sys.exit(1) + + import dircache + ls = dircache.listdir(planetlabdir) + import re + m=re.compile('^.*\.cfg$') + cfgs=filter(lambda x: m.match(x),ls) + if len(cfgs) != 0: + print "Warning : you have %d nagios configs left in %s"%( + len(cfgs),planetlabdir) + print "It's OK to keep them, if that's what you're trying to do" + + ### scan over sites + for site_id in site_ids: + + siteHash=self.siteTree[site_id] + site = siteHash['site'] + sitename = site['name'] + sitebase = site['login_base'] + + nodes = siteHash['nodes'] + node_ids = nodes.keys() + node_ids.sort() + if len(node_ids) != 0: + + filename = "%s/%s.cfg"%(planetlabdir,sitebase) + print ( "Opening %s for writing" % filename) + file = open (filename,'w') + + ### without email / use real people + if not self.dest_email: + persons = siteHash ['persons'] + + self.verbose("retrieved PIs = %s"%str(persons)) + + if len(persons) != 0: + personnames='' + for person_id in persons.keys(): + person=persons[person_id] + personname=person['full_name'] + if len(personnames) == 0: + personnames = personname + else: + personnames = "%s,%s"%(personnames,personname) + file.write(self._define_contact + %(personname, + person['first_name'], + person['last_name'], + person['email'])) + + file.write(self._define_contactgroup + %(sitebase,sitename,personnames)) + else: + file.write(self._define_contactgroup + %(sitebase,sitename,self.dest_email)) + + + nodenames="" + for node_id in node_ids: + node = nodes[node_id] + if len(nodenames) == 0: + nodenames = node['hostname'] + else: + nodenames = "%s,%s"%(nodenames,node['hostname']) + file.write(self._define_host + %(node['hostname'],node['hostname'], + node['ip'],sitebase)) + + for service in node_services: + file.write(self._define_service + %(service,node['hostname'],sitebase,service)) + + + file.write(self._define_hostgroup + %(sitebase,sitename,nodenames)) + + file.close() + +#################### static html file with bookmarks to comon site-centric queries +# a first draft tried to create a column for easying the bookmarking process +# I did not completely succeed, because +# the javascript interface for firefox seems to only allow +# the creation of bookmarks in the sidebar +# in fact you can bookmark the link, but when you use that bookmark +# the target url is opened in the sidebar +# you can easily fix this by editing the bookmark and uncheck +# a dialob box, but that's not what we want +# it's much easier to directly use the 'Bookmark this link' +# from the firefox menu +# so let's forget about this altogether + +# ### bookmarks +# def ManualBookmark (self, url, text, bookmark_name): +# bookmark_link=""" +# %s""" +# # the single quotes in the URL need to be html-encoded +# cleanurl = url.replace ("'","%27") +# return bookmark_link%(makeHTML.encode(cleanurl),bookmark_name,text) +# +# bookmark_code="""""" ### ' for fooling emacs + + def ComonNodesSelect (self,nodes): + names = map(lambda node: node['hostname'],nodes) + filters = map (comon_query.filter_node,names) + server = comon_query.SERVER + return comon_query.full_url(server,'||'.join(filters)) + + ### could not find the makeHTML tool for that + def ManualAnchor (self,name,value): + return '%s' % (name,value) + + def SiteRow (self,site_id): + ### returns a (makeHTML) row for the given site + + siteHash = self.siteTree[site_id] + site = siteHash['site'] + sitename = site['name'] + sitebase = site['login_base'] + + nodes = siteHash['nodes'].values() + if len(nodes) == 0 : + return None + else: + row = makeHTML.tableRow() + query=self.ComonNodesSelect(nodes) + row.addCells([makeHTML.link(content=sitename, url=query), + self.ManualAnchor(sitebase,sitebase), +# self.ManualBookmark(query, +# "Bookmark it", +# "Comon on %s"%sitename), + ]) + return row + + def MakeSiteTable (self, sites): + ### create table / sitename + table = makeHTML.table () + ### first row + head_row = makeHTML.tableRow() + head_row.addCells ( ['Site name', + 'Site login', +# 'Comon query', + ]) + table.addRow(rowList=[head_row]) + + for site in sites: + table.addRow ( rowList=[self.SiteRow(site['site_id'])]) + return table + + ### Write a single index page that contains one bookmark per site + def WriteComonLinks (self, indexname): + + pageHead = makeHTML.part('head') + pageHead.addPart('title',content='Comon links for all sites') +# pageHead.addPiece(bookmark_code) + + pageBody = makeHTML.part('body') + pageBody.addPart('h1',content='Comon links, per site') + + sites = map(lambda s: s['site'],self.siteTree.values()) + + pageBody.addPart('h2',content='By site name') + + sites.sort (lambda s1,s2: cmp(s1['name'],s2['name'])) + pageBody.addPart('p',self.MakeSiteTable(sites)) + + pageBody.addPart('h2',content='By site login') + + sites.sort (lambda s1,s2: cmp(s1['login_base'],s2['login_base'])) + pageBody.addPart('p',self.MakeSiteTable(sites)) + + fullPage = makeHTML.part('html') + fullPage.addPiece(pageHead) + fullPage.addPiece(pageBody) + + text=fullPage.make() + + print ( "Opening %s for writing" % indexname) + index=open (indexname,"w") + index.write(text+"\n") + index.close() diff --git a/nagios/configurator/cgi.cfg b/nagios/configurator/cgi.cfg new file mode 100644 index 0000000..b5f1752 --- /dev/null +++ b/nagios/configurator/cgi.cfg @@ -0,0 +1,275 @@ +################################################################# +# +# CGI.CFG - Sample CGI Configuration File for Nagios +# +# Last Modified: 05-05-2005 +# +################################################################# + + +# MAIN CONFIGURATION FILE +# This tells the CGIs where to find your main configuration file. +# The CGIs will read the main and host config files for any other +# data they might need. + +main_config_file=/etc/nagios/nagios.cfg + + + +# PHYSICAL HTML PATH +# This is the path where the HTML files for Nagios reside. This +# value is used to locate the logo images needed by the statusmap +# and statuswrl CGIs. + +physical_html_path=/usr/share/nagios/share + + + +# URL HTML PATH +# This is the path portion of the URL that corresponds to the +# physical location of the Nagios HTML files (as defined above). +# This value is used by the CGIs to locate the online documentation +# and graphics. If you access the Nagios pages with an URL like +# http://www.myhost.com/nagios, this value should be '/nagios' +# (without the quotes). + +url_html_path=/nagios + + + +# CONTEXT-SENSITIVE HELP +# This option determines whether or not a context-sensitive +# help icon will be displayed for most of the CGIs. +# Values: 0 = disables context-sensitive help +# 1 = enables context-sensitive help + +show_context_help=0 + + + +# NAGIOS PROCESS CHECK COMMAND +# This is the full path and filename of the program used to check +# the status of the Nagios process. It is used only by the CGIs +# and is completely optional. However, if you don't use it, you'll +# see warning messages in the CGIs about the Nagios process +# not running and you won't be able to execute any commands from +# the web interface. The program should follow the same rules +# as plugins; the return codes are the same as for the plugins, +# it should have timeout protection, it should output something +# to STDIO, etc. +# +# Note: The command line for the check_nagios plugin below may +# have to be tweaked a bit, as different versions of the plugin +# use different command line arguments/syntaxes. + +nagios_check_command=/usr/lib/nagios/plugins/check_nagios /var/log/nagios/status.dat 5 '/usr/sbin/nagios' + + + +# AUTHENTICATION USAGE +# This option controls whether or not the CGIs will use any +# authentication when displaying host and service information, as +# well as committing commands to Nagios for processing. +# +# Read the HTML documentation to learn how the authorization works! +# +# NOTE: It is a really *bad* idea to disable authorization, unless +# you plan on removing the command CGI (cmd.cgi)! Failure to do +# so will leave you wide open to kiddies messing with Nagios and +# possibly hitting you with a denial of service attack by filling up +# your drive by continuously writing to your command file! +# +# Setting this value to 0 will cause the CGIs to *not* use +# authentication (bad idea), while any other value will make them +# use the authentication functions (the default). + +use_authentication=1 + + + +# DEFAULT USER +# Setting this variable will define a default user name that can +# access pages without authentication. This allows people within a +# secure domain (i.e., behind a firewall) to see the current status +# without authenticating. You may want to use this to avoid basic +# authentication if you are not using a sercure server since basic +# authentication transmits passwords in the clear. +# +# Important: Do not define a default username unless you are +# running a secure web server and are sure that everyone who has +# access to the CGIs has been authenticated in some manner! If you +# define this variable, anyone who has not authenticated to the web +# server will inherit all rights you assign to this user! + +#default_user_name=guest + + + +# SYSTEM/PROCESS INFORMATION ACCESS +# This option is a comma-delimited list of all usernames that +# have access to viewing the Nagios process information as +# provided by the Extended Information CGI (extinfo.cgi). By +# default, *no one* has access to this unless you choose to +# not use authorization. You may use an asterisk (*) to +# authorize any user who has authenticated to the web server. + +#authorized_for_system_information=nagiosadmin,theboss,jdoe + + + +# CONFIGURATION INFORMATION ACCESS +# This option is a comma-delimited list of all usernames that +# can view ALL configuration information (hosts, commands, etc). +# By default, users can only view configuration information +# for the hosts and services they are contacts for. You may use +# an asterisk (*) to authorize any user who has authenticated +# to the web server. + +#authorized_for_configuration_information=nagiosadmin,jdoe + + + +# SYSTEM/PROCESS COMMAND ACCESS +# This option is a comma-delimited list of all usernames that +# can issue shutdown and restart commands to Nagios via the +# command CGI (cmd.cgi). Users in this list can also change +# the program mode to active or standby. By default, *no one* +# has access to this unless you choose to not use authorization. +# You may use an asterisk (*) to authorize any user who has +# authenticated to the web server. + +#authorized_for_system_commands=nagiosadmin + + + +# GLOBAL HOST/SERVICE VIEW ACCESS +# These two options are comma-delimited lists of all usernames that +# can view information for all hosts and services that are being +# monitored. By default, users can only view information +# for hosts or services that they are contacts for (unless you +# you choose to not use authorization). You may use an asterisk (*) +# to authorize any user who has authenticated to the web server. + + +authorized_for_all_services=thierry.parmentelat@sophia.inria.fr +authorized_for_all_hosts=thierry.parmentelat@sophia.inria.fr + + + +# GLOBAL HOST/SERVICE COMMAND ACCESS +# These two options are comma-delimited lists of all usernames that +# can issue host or service related commands via the command +# CGI (cmd.cgi) for all hosts and services that are being monitored. +# By default, users can only issue commands for hosts or services +# that they are contacts for (unless you you choose to not use +# authorization). You may use an asterisk (*) to authorize any +# user who has authenticated to the web server. + +#authorized_for_all_service_commands=nagiosadmin +#authorized_for_all_host_commands=nagiosadmin + + + + +# STATUSMAP BACKGROUND IMAGE +# This option allows you to specify an image to be used as a +# background in the statusmap CGI. It is assumed that the image +# resides in the HTML images path (i.e. /usr/local/nagios/share/images). +# This path is automatically determined by appending "/images" +# to the path specified by the 'physical_html_path' directive. +# Note: The image file may be in GIF, PNG, JPEG, or GD2 format. +# However, I recommend that you convert your image to GD2 format +# (uncompressed), as this will cause less CPU load when the CGI +# generates the image. + +#statusmap_background_image=smbackground.gd2 + + + +# DEFAULT STATUSMAP LAYOUT METHOD +# This option allows you to specify the default layout method +# the statusmap CGI should use for drawing hosts. If you do +# not use this option, the default is to use user-defined +# coordinates. Valid options are as follows: +# 0 = User-defined coordinates +# 1 = Depth layers +# 2 = Collapsed tree +# 3 = Balanced tree +# 4 = Circular +# 5 = Circular (Marked Up) + +default_statusmap_layout=5 + + + +# DEFAULT STATUSWRL LAYOUT METHOD +# This option allows you to specify the default layout method +# the statuswrl (VRML) CGI should use for drawing hosts. If you +# do not use this option, the default is to use user-defined +# coordinates. Valid options are as follows: +# 0 = User-defined coordinates +# 2 = Collapsed tree +# 3 = Balanced tree +# 4 = Circular + +default_statuswrl_layout=4 + + + +# STATUSWRL INCLUDE +# This option allows you to include your own objects in the +# generated VRML world. It is assumed that the file +# resides in the HTML path (i.e. /usr/local/nagios/share). + +#statuswrl_include=myworld.wrl + + + +# PING SYNTAX +# This option determines what syntax should be used when +# attempting to ping a host from the WAP interface (using +# the statuswml CGI. You must include the full path to +# the ping binary, along with all required options. The +# $HOSTADDRESS$ macro is substituted with the address of +# the host before the command is executed. +# Please note that the syntax for the ping binary is +# notorious for being different on virtually ever *NIX +# OS and distribution, so you may have to tweak this to +# work on your system. + +ping_syntax=/bin/ping -n -U -c 5 $HOSTADDRESS$ + + + +# REFRESH RATE +# This option allows you to specify the refresh rate in seconds +# of various CGIs (status, statusmap, extinfo, and outages). + +refresh_rate=90 + + + +# SOUND OPTIONS +# These options allow you to specify an optional audio file +# that should be played in your browser window when there are +# problems on the network. The audio files are used only in +# the status CGI. Only the sound for the most critical problem +# will be played. Order of importance (higher to lower) is as +# follows: unreachable hosts, down hosts, critical services, +# warning services, and unknown services. If there are no +# visible problems, the sound file optionally specified by +# 'normal_sound' variable will be played. +# +# +# = +# +# Note: All audio files must be placed in the /media subdirectory +# under the HTML path (i.e. /usr/local/nagios/share/media/). + +#host_unreachable_sound=hostdown.wav +#host_down_sound=hostdown.wav +#service_critical_sound=critical.wav +#service_warning_sound=warning.wav +#service_unknown_sound=warning.wav +#normal_sound=noproblem.wav + diff --git a/nagios/configurator/comon_query.py b/nagios/configurator/comon_query.py new file mode 100755 index 0000000..9aa2685 --- /dev/null +++ b/nagios/configurator/comon_query.py @@ -0,0 +1,188 @@ +#!/usr/bin/env python + +# +# This module checks for a planetlab node by +# (*) connecting to the comon central query interface +# (*) retrieving the latest info for a given node +# + +import sys +import socket +import re +import string +import urllib2 + +import nagios + +# default server +SERVER='summer.cs.princeton.edu' + +NodeUnknownException="NodeUnknownByComon" + +#################### +def check (node,server=None): + + if (server == None): + server = SERVER + + try: + + # compute node IP number + node_address = compute_address (node) +# print 'int address',node_address + # build URL, connect and return attributes dict + node_dict = query_node (server,node_address) + for key in node_dict.keys(): + print key,node_dict[key] + # interpret + return interpret (node_dict) + + except NodeUnknownException: + return nagios.UNKNOWN + except Exception,e: + print "comon_query.check got exception",e + return nagios.UNKNOWN + +########## +re_dec="([0-9]{1,3})" +re_ipsep="\." +re_ip=(re_dec+re_ipsep)*3+re_dec +ma_ip = re.compile (re_ip) + +def compute_address (nodename): + ip=socket.gethostbyname(nodename) + ints=map(int,ma_ip.match(ip).groups()) + res=ints[0] + for i in range(1,4): + res = (res*256)+ints[i] + return res + +########## +URL_FORMAT="http://%s/status/tabulator.cgi" +ARGS_FORMAT="table=table_nodeviewshort&select='%s'" +FILTER_FORMAT="address==%d" +CSV_FORMAT="&format=formatcsv" + +def filter_address (address): + return FILTER_FORMAT%address +def filter_node (nodename): + return filter_address(compute_address(nodename)) + +def full_url (server, filter): + return (URL_FORMAT%server + + '?' + + ARGS_FORMAT%filter) + +def full_url_csv (server,filter): + return full_url(server,filter)+CSV_FORMAT + + +# mention field here means we'll parse it and keep it +# see store_dict below +FIELDS_FOCUS={ + 'resptime': 'float', + 'sshstatus':'int', + 'bootstate':'string', + } + +NOTHING_MATCHED='nothing matched select statement' +########## +def query_node (server,address): + filter=filter_address(address) + full_url=full_url_csv(server,filter) + req = urllib2.urlopen(full_url) + # let's parse this manually + headers=map(string.strip,req.readline().split(',')) + # handle the case where the node is unknown to comon + values=req.readline() + if values.find(NOTHING_MATCHED) != -1: + raise NodeUnknownException + + values=values.split(',') + + print 'h',headers + print 'v', values + + dict={} +# store_dict=lambda key,val: dict[key]=val +# -> SyntaxError: can't assign to lambda + def store_dict (key,val): + if FIELDS_FOCUS.has_key(key): + format = FIELDS_FOCUS[key] + if format == 'float': + dict[key]=float(val) + elif format == 'int': + dict[key]=int(val) + elif format == 'string': + dict[key]=string.strip(val) + map (store_dict, headers, values) + + return dict + +########## +# function for decomposing a number along units +# tuple [n] must be a multiple of tuple[n+1] +# e.g. +# 1223456, (10000, 500, 10) -> (122, 68, 5) +# coz 1223456 = 122*10000 + 68*500 + 5*10 + 6 +def split_number (n,tuple): + result=() + for i in range(0,len(tuple)): + base=tuple[i] + result+=(n/base,) + n=n%base + return result + +### +MINUTE=60 +HOUR=60*MINUTE +DAY=HOUR*24 +WEEK=DAY*7 +MONTH=DAY*30 + +# from a delay in seconds, returns a human-readable string +def seconds_printable (seconds): + month,week,day,hour,minute = split_number(seconds, + (MONTH,WEEK,DAY,HOUR,MINUTE)) + if month != 0: + return "%d month(s), %d weeks, %d day(s)"%(month,week,day) + elif week !=0: + return "%d weeks, %d day(s), %d hour(s)"%(week,day,hour) + elif day != 0: + return "%d day(s), %d hour(s)"%(day,hour) + elif hour != 0: + return "%d hour(s), %d minute(s)"%(hour,minute) + else: + return "%d minute(s)"%(minute) + +########## +def interpret (dict): + # check sshstatus is null + sshstatus=dict['sshstatus'] + if sshstatus != 0: + print 'No response to comon/ssh for %s'%seconds_printable(sshstatus) + if sshstatus >= 10*MINUTE: + return nagios.KO + else: + return nagios.WARNING + else: + # let's focus on resptime + resptime = dict['resptime'] + print "Response time as measured by comon = %.2f s"%resptime + if resptime >= 10.0: + return nagios.KO + elif resptime >= 5.0: + return nagios.WARNING + else: + return nagios.OK + +#################### quick test +def usage(): + print "Usage comon_query.py node" + sys.exit(1) + +if __name__=='__main__': + if len(sys.argv) != 2: + usage() + print 'comon_query.check would return %d'%check(sys.argv[1]) +# print 'get >%s<',seconds_printable(int(sys.argv[1])) diff --git a/nagios/configurator/configurator.py b/nagios/configurator/configurator.py new file mode 100755 index 0000000..e9f8090 --- /dev/null +++ b/nagios/configurator/configurator.py @@ -0,0 +1,111 @@ +#!/usr/bin/env python + +# WARNING - you might need to set your locale before you can run this script +# e.g. +# export LANG=en_US.UTF-8 +# nagios.py ... + +import sys +import getopt + +from NagiosConfig import NagiosConfig + +SERVER="www.planet-lab.org" +DIRNAME="/etc/nagios" + +options='h:o:Os:d:nNv' + +usage_string="""Usage : %s [options] plc-id plc-passwd role +Outputs a nagios config for watching a given set of sites +Also writes a static HTML page for bookmarking site-centric queries to comon +Options: + -h plc-hostname To provide an alternate plc hostname + (defaults to %s) + -o e-mail If you provide an e-mail address, all notifications + will be sent there. Otherwise, you'll need admin role + so that we can determine the respective PI's e-mails + -O same as -e with the plc-id as dest. e-mail + -s site-file You can provide a list of sites in a separate file + expected format is one line per site, site_id first + the default is to list all sites + -d dirname To specify an alternate output dir + (defaults to %s) + -n Does not generate the nagios config + -N Does not generate the HTML page + -v Runs in verbose mode +"""%(sys.argv[0],SERVER,DIRNAME) + +def usage (): + print usage_string + sys.exit(1) + + +def main (): + command = sys.argv[0] + argv = sys.argv[1:] + + try: + opts,args = getopt.getopt(argv, options) + except getopt.GetoptError: + print "Unknown option" + usage() + + plc_server=SERVER + output_mail=None + opt_same_email=False + site_file=None + dirname=DIRNAME + opt_nagios = True + opt_html = True + opt_verbose = False + + for o,a in opts: + if o in ['-h']: + plc_server = a + elif o in ['-o']: + output_mail = a + elif o in ['-O']: + opt_same_email = True + elif o in ['-s']: + site_file = a + elif o in ['-d']: + dirname = a + elif o in ['-n']: + opt_nagios = False + elif o in ['-N']: + opt_html = False + elif o in ['-v']: + opt_verbose = True + else: + print "Unknown option",o + usage() + + if not len(args) == 3: + usage() + + (plc_id,passwd,role) = args + if opt_same_email: + output_mail=plc_id + +# print plc_server,output_mail,dirname,opt_nagios,opt_html +# print plc_id,passwd,role,site_file + + print "Connecting to %s and gathering data"%plc_server + config = NagiosConfig (plc_server,plc_id,passwd,role) + if opt_verbose: + config.set_verbose() + config.GatherData (output_mail,site_file) + + if opt_nagios: + print "Creating nagios config in %s"%dirname + config.WriteNagiosConfig (dirname) + + if opt_html: + html_page = "%s/comon.html"%dirname + config.WriteComonLinks (html_page) + + +#################### +if __name__ == "__main__": + main () + diff --git a/nagios/configurator/generic.cfg b/nagios/configurator/generic.cfg new file mode 100644 index 0000000..3788228 --- /dev/null +++ b/nagios/configurator/generic.cfg @@ -0,0 +1,212 @@ +############################################################################### +# MINIMAL.CFG +# +# MINIMALISTIC OBJECT CONFIG FILE (Template-Based Object File Format) +# +# Last Modified: 05-30-2006 +# +# +# NOTE: This config file is intended to be used to test a Nagios installation +# that has been compiled with support for the template-based object +# configuration files. +# +# This config file is intended to servce as an *extremely* simple +# example of how you can create your object configuration file(s). +# If you're interested in more complex object configuration files for +# Nagios, look in the sample-config/template-object/ subdirectory of +# the distribution. +# +############################################################################### + + + +############################################################################### +############################################################################### +# +# TIME PERIODS +# +############################################################################### +############################################################################### + +# This defines a timeperiod where all times are valid for checks, +# notifications, etc. The classic "24x7" support nightmare. :-) + +define timeperiod{ + timeperiod_name 24x7 + alias 24 Hours A Day, 7 Days A Week + sunday 00:00-24:00 + monday 00:00-24:00 + tuesday 00:00-24:00 + wednesday 00:00-24:00 + thursday 00:00-24:00 + friday 00:00-24:00 + saturday 00:00-24:00 + } + + +################################################################################ +# +# SERVICE CHECK COMMANDS +# +################################################################################ + +# 'check_udp' command definition +define command{ + command_name check_udp + command_line $USER1$/check_udp -H $HOSTADDRESS$ -p $ARG1$ + } + +define command{ + command_name check_ssh + command_line $USER1$/check_ssh $HOSTADDRESS$ + } + +define command{ + command_name check_ssh_root + command_line $USER1$/check_by_ssh -H $HOSTADDRESS$ -l root -i /etc/nagios/root_ssh_key.rsa -C date + } + +define command{ + command_name check_ssh_pl_conf + command_line $USER1$/check_by_ssh -H $HOSTADDRESS$ -l root -i /etc/nagios/root_ssh_key.rsa -C "server pl_conf status 2>/dev/null" + } + +define command{ + command_name check_planetlab + command_line $USER1$/check_planetlab.py -t 3 $HOSTADDRESS$ + } + +################################################################################ +# +# HOST CHECK COMMAND +# +################################################################################ + +# This command checks to see if a host is "alive" by pinging it +# The check must result in a 100% packet loss or 5 second (5000ms) round trip +# average time to produce a critical error. +# Note: Only one ICMP echo packet is sent (determined by the '-p 1' argument) + +# 'check-host-alive' command definition +define command{ + command_name check-host-alive + command_line $USER1$/check_ping -H $HOSTADDRESS$ -w 3000.0,40% -c 5000.0,80% -p 1 + } + +############################################################################### +############################################################################### +# +# HOSTS +# +############################################################################### +############################################################################### + +# Generic host definition template - This is NOT a real host, just a template! + +define host{ + name generic-host ; The name of this host template + notifications_enabled 1 ; Host notifications are enabled + event_handler_enabled 1 ; Host event handler is enabled + flap_detection_enabled 1 ; Flap detection is enabled + failure_prediction_enabled 1 ; Failure prediction is enabled + process_perf_data 1 ; Process performance data + retain_status_information 1 ; Retain status information across program restarts + retain_nonstatus_information 1 ; Retain non-status information across program restarts + check_command check-host-alive + max_check_attempts 10 + check_period 24x7 + notification_interval 1440 + notification_period 24x7 + notification_options d,r + register 0 ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL HOST, JUST A TEMPLATE! + } + +# actual hosts to be defined by python in planetlab.cfg + +############################################################################### +############################################################################### +# +# SERVICES +# +############################################################################### +############################################################################### + +# Generic service definition template - This is NOT a real service, just a template! + +define service{ + name generic-service ; The 'name' of this service template + active_checks_enabled 1 ; Active service checks are enabled + passive_checks_enabled 1 ; Passive service checks are enabled/accepted + parallelize_check 1 ; Active service checks should be parallelized (disabling this can lead to major performance problems) + obsess_over_service 1 ; We should obsess over this service (if necessary) + check_freshness 0 ; Default is to NOT check service 'freshness' + notifications_enabled 1 ; Service notifications are enabled + event_handler_enabled 1 ; Service event handler is enabled + flap_detection_enabled 1 ; Flap detection is enabled + failure_prediction_enabled 1 ; Failure prediction is enabled + process_perf_data 1 ; Process performance data + retain_status_information 1 ; Retain status information across program restarts + retain_nonstatus_information 1 ; Retain non-status information across program restarts + register 0 ; DONT REGISTER THIS DEFINITION - ITS NOT A REAL SERVICE, JUST A TEMPLATE! + is_volatile 0 + check_period 24x7 + max_check_attempts 2 + normal_check_interval 240 ; every 2 hours is OK + retry_check_interval 5 +### + notification_options c,r + notification_interval 1440 + notification_period 24x7 + } + + +### ping tunings +# warning is set to 2 seconds, 40% packet loss +# critical is set to 5 seconds, 80% packet loss +### We DONT register this service because it's basically what nagios reverts to +# if the others services turn out to be not responding +define service{ + use generic-service + name generic-ping + service_description ping +# check_command check_ping!100.0,20%!500.0,60% + check_command check_ping!2000.0,40%!5000.0,80% + register 0 + } + + +define service{ + use generic-service + name generic-ssh + service_description ssh server + check_command check_ssh + register 0 + } + +define service{ + use generic-service + name generic-ssh-root + service_description ssh root + check_command check_ssh_root + register 0 + } + +define service{ + use generic-service + name generic-ssh-pl_conf + service_description pl_conf vserver + check_command check_ssh_pl_conf + register 0 + } + +define service{ + use generic-service + name generic-planetlab + service_description comon + check_command check_planetlab + register 0 + } + +# actual services to be defined by python in planetlab.cfg + +# EOF diff --git a/nagios/configurator/makeHTML.py b/nagios/configurator/makeHTML.py new file mode 100644 index 0000000..54e0623 --- /dev/null +++ b/nagios/configurator/makeHTML.py @@ -0,0 +1,590 @@ +#makeHTML.py version 0.8 May 1, 2005 Jerry Stratton +# +#part(code="tag" (defaults to paragraph), content="text" style="css style name", id="css id", attributes={named array of attributes for tag} +# addAttribute(attributename="name for tag attribute", attributevalue="value for tag attribute") +# addPart(code, content, style, id, attributes): adds at end +# addPiece(thePart=another part object or "content text") +# addPieces(pices=a list of part objects or content texts) +# insertPart(code, content, style, id, attributes): inserts at start +# insertPiece(thePart) +# make(tab="initial tabs") +# makePart(code, content, style, id, attributes): returns a part object +# __len__: parts support the len() function; return number of pieces directly contained +#snippet(code (defaults to "em"), content, posttext="text that comes directly after tag", pretext="text that comes directly before tag", style, id, attributes) +# +#head(title="text for title of page") +#body(title="text for main headline", style, id, attributes) +#page(pieces, style, id, attributes) +#styleSheet(sheet="url of stylesheet", media="relevance of style sheet") +# +#headline(content="text content" (required), level="numerical level", style, id, attributes) +# +#table(rows=list of data for rows, style, thStyle="css style for table headers", tdStyle="css style for table cells", +# trStyle="css style for table rows", tdBlankStyle="css style for blank cells", firstRowHeader=1--if first row is a header row, +# firstColumnHeader=1--if first column is a header column, id, attributes) +# addRow(rowList=[list of cells or data], celltype="th or td", cellclass="css style of cells", attributes, style) +# addRows(rows=[list of list of cells or data], celltype, cellclass, attributes) +# columnCount() +#tableByColumn(columns=[list of columns], style, thStyle, tdStyle, trStyle, tdBlankStyle, firstRowHeader, firstColumnHeader, id, attributes) +# addColumn(columnList=[list of column data or cells], celltype, cellclass, attributes) +# addColumns(columns=[list of list of columns or column data], celltype, cellclass, attributes) +#tableColumn(column=[list of data or cells for column], celltype, cellclass, firstRowHeader, thStyle, tdBlankStyle, attributes) +# addCell(cell="cell or cell content", celltype, cellclass, id, attributes) +# addCells(column="list of cells or cell contents", celltype, cellclass, attributes) +#tableRow(celltype, row=[list of cells or cell data], style, cellclass, firstColumnHeader, thStyle, id, attributes) +# addCell(cell="cell or cell content", celltype, cellclass, colspan="numerical span of cell vertically", rowspan="numerical span of cell horizontally") +# addCells(cells=[list of cells or cell content]) +# columnCount() +# +#linkedList(links=[list of items of the form [url, name]], outer="outer html tag", inner="inner html tag", style="outer css style", +# iclass="inner css style", id, attributes) +# addLink(link=[url, name]) +# addLinks(links) +#simpleList(items=[list of text items], outer, inner, defaultname="text for marking default entry", default="text of default entry", +# style, iclass, id, attributes) +# addItem(item="text of item") +# addItems(items) +# +#image(src="url of image", alt="alternate text for image", align="alignment", style, id, attributes) +#link(content, url, posttext, pretext, style, id, attributes) +# +#form(submitText="text of submit button", pieces, method="submit method", action="form action", submitName="name for submit button", submitAction="javascript for submission" +# headline="headline text", headlineLevel (defaults to 2), style, attributes, id) +#input(type="type of form input", name="name for input", value="default value for input", size="size for input", maxlength="maximum characters accepted", +# style, id, attributes) +#select(name, items, default, style, iclass, id, attributes +#textinput(name, text, value, size, maxlength, style, id, attributes, type, tableRow=true if this should be a tr row, otherwise it is a paragraph) + +#basic parts +class part: + def __init__(self, code="p", content=None, style=None, id=None, attributes=None): + self.style = style + self.id=id + self.pieces = [] + self.code = code + if attributes == None: + self.attributes = {} + else: + self.attributes = attributes + if isinstance(content, list): + self.addPieces(content) + elif content != None: + self.addPiece(content) + + def __len__(self): + return len(self.pieces) + + def addAttribute(self, attributename, attributevalue): + self.attributes[attributename] = attributevalue + + def addPart(self, code='p', content=None, style=None, id=None, attributes=None): + newPart = self.makePart(code, content, style, id, attributes) + self.addPiece(newPart) + + def addPiece(self, thePart): + self.pieces.append(thePart) + + def addPieces(self, theParts): + if theParts != None: + if isinstance(theParts, list): + for part in theParts: + self.addPiece(part) + else: + self.addPiece(theParts) + + def insertPart(self, code='p', content=None, style=None, id=None, attributes=None): + newPart = self.makePart(code, content, style, id, attributes) + self.insertPiece(newPart) + + def insertPiece(self, thePart): + self.pieces.insert(0, thePart) + + def make(self, tab="\t"): + startHTML = '<' + self.code + + if (self.attributes): + for attribute in self.attributes: + content = self.attributes[attribute] + if content == None: + startHTML += ' ' + attribute + else: + startHTML += ' ' + attribute + '="' + str(content) + '"' + + if (self.style): + startHTML += ' class="' + self.style + '"' + + if (self.id): + startHTML += ' id="' + self.id + '"' + + if self.pieces: + startHTML += '>' + + partItems = [startHTML] + + if len(self.pieces) > 1: + sep = "\n" + tab + finalSep = sep[:-1] + newtab = tab + "\t" + else: + newtab = tab + sep = "" + finalSep = "" + + for piece in self.pieces: + if isinstance(piece, str): + partItems.append(piece) + elif isinstance(piece, int) or isinstance(piece, float): + partItems.append(str(piece)) + elif piece == None: + partItems.append("") + else: + partItems.append(piece.make(newtab)) + + code = sep.join(partItems) + code += finalSep + '' + return code + + else: + startHTML += ' />' + return startHTML + + def makePart(self, code='p', content=None, style=None, id=None, attributes=None): + if content == None: + newPart = part(code) + else: + newPart = part(code, content, style, id, attributes) + + return newPart + +class snippet(part): + def __init__(self, code="em", content=None, posttext=None, pretext=None, style=None, id=None, attributes=None): + part.__init__(self, code, content, style, id, attributes) + self.posttext = posttext + self.pretext = pretext + + def make(self, tab=''): + snippets = [] + + if self.pretext: + snippets.append(self.pretext) + + snippets.append(part.make(self, tab)) + + if self.posttext: + snippets.append(self.posttext) + + return "".join(snippets) + +#common body parts + +class head(part): + def __init__(self, title=None): + part.__init__(self, code="head") + if title: + self.addPiece(part("title", title)) + +class body(part): + def __init__(self, title=None, style=None, id=None, attributes=None): + part.__init__(self, code="body", style=style, id=id, attributes=attributes) + if title: + self.addPiece(headline(title, 1)) + +class page(part): + def __init__(self, pieces=None, style=None, id=None, attributes=None): + part.__init__(self, code="html", style=style, id=id, attributes=attributes) + if isinstance(pieces, list): + self.addPieces(pieces) + elif isinstance(pieces, part): + self.addPiece(pieces) + + def make(self, tab=''): + pageContent = part.make(self) + + print 'Content-type: text/html' + print '' + + print pageContent + +class styleSheet(part): + def __init__(self, sheet, media='all'): + attributes = {} + attributes['rel'] = "StyleSheet" + attributes['href'] = sheet + '.css' + attributes['type'] = "text/css" + attributes['media'] = media + part.__init__(self, code="link", attributes=attributes) + + +#paragraph level parts +class headline(part): + def __init__(self, content, level=2, style=None, id=None, attributes=None): + code = "h"+str(level) + part.__init__(self, content=content, style=style, code=code, id=id, attributes=attributes) + + + +#tables +class table(part): + def __init__(self, rows=None, style=None, thStyle=None, tdStyle=None, trStyle=None, tdBlankStyle=None, firstRowHeader=None, firstColumnHeader=None, id=None, attributes=None): + part.__init__(self, code="table", style=style, id=id, attributes=attributes) + self.rowclass=trStyle + self.cellclass=tdStyle + self.cellheaderclass=thStyle + self.cellblankclass=tdBlankStyle + self.firstRowHeader=firstRowHeader + self.firstColumnHeader=firstColumnHeader + if rows: + self.addRows(rows) + + def addRow(self, rowList, celltype=None, cellclass=None, attributes=None, style=None): + if cellclass==None: + if self.firstRowHeader and len(self.pieces) == 0: + celltype="th" + cellclass=self.cellheaderclass + else: + cellclass=self.cellclass + + if style==None: + style = self.rowclass + + newRow = tableRow(celltype, rowList, style, cellclass, self.firstColumnHeader, self.cellheaderclass, attributes) + self.addPiece(newRow) + + def addRows(self, rows, cellclass=None, celltype=None, attributes=None): + for row in rows: + self.addRow(row) + + def columnCount(self): + maxCount = 0 + for row in self.pieces: + if isinstance(row, tableRow): + colCount = row.columnCount() + maxCount = max(maxCount, colCount) + + return maxCount + +class tableByColumn(table): + def __init__(self, columns=None, style=None, thStyle=None, tdStyle=None, trStyle=None, tdBlankStyle=None, firstRowHeader=None, firstColumnHeader=None, id=None, attributes=None): + table.__init__(self, [], style, thStyle, tdStyle, trStyle, tdBlankStyle, firstRowHeader, firstColumnHeader, id, attributes) + self.columns = [] + if columns: + self.addColumns(columns) + + def addColumn(self, columnList, celltype=None, cellclass=None, attributes=None): + if cellclass==None: + if celltype == "th" or (self.firstColumnHeader and len(self.columns) == 0): + celltype="th" + cellclass=self.cellheaderclass + else: + cellclass=self.cellclass + + newColumn = tableColumn(columnList, celltype, cellclass, self.firstRowHeader, self.cellheaderclass, self.cellblankclass, attributes) + self.columns.append(newColumn) + + def addColumns(self, columns, celltype=None, cellclass=None, attributes=None): + for column in columns: + self.addColumn(column) + + def addPiece(self, thePart): + if isinstance(thePart, tableColumn): + self.columns.append(thePart) + else: + part.addPiece(self, thePart) + + def make(self, tabs): + rowCount = 0 + for column in self.columns: + rowCount = max(rowCount, len(column.pieces)) + + if rowCount: + for cRow in range(rowCount): + row = tableRow() + for column in self.columns: + if cRow < len(column.pieces): + cell = column.pieces[cRow] + else: + cell = part("td") + row.addPiece(cell) + + self.addPiece(row) + + myPart = part.make(self, tabs) + return myPart + + +class tableColumn(part): + def __init__(self, column=None, celltype="td", cellclass=None, firstRowHeader=None, thStyle=None, tdBlankStyle=None, attributes=None): + part.__init__(self, "column", style=cellclass, attributes=attributes) + if celltype==None: + self.celltype = "td" + else: + self.celltype=celltype + + self.firstRowHeader=firstRowHeader + self.cellheaderclass=thStyle + self.cellblankclass=tdBlankStyle + + if column: + self.addCells(column) + + def addCell(self, cell=None, celltype=None, cellclass=None, id=None, attributes=None): + if self.cellblankclass and (cell==None or cell==""): + celltype="td" + cellclass = self.cellblankclass + elif self.firstRowHeader and len(self.pieces) == 0: + celltype = "th" + cellclass = self.cellheaderclass + else: + if celltype == None: + celltype = self.celltype + if cellclass == None: + cellclass = self.style + if cell == None: + cell = "" + + tableCell = part(code=celltype, style=cellclass, content=cell, id=id, attributes=attributes) + self.addPiece(tableCell) + + def addCells(self, column, celltype=None, cellclass=None, attributes=None): + for cell in column: + self.addCell(cell, celltype, cellclass, attributes=attributes) + + def make(self): + print "Problem: columns should never be requested to make themselves." + print "Columns are not true html structures, and should only be added to tableByColumn parts." + + +class tableRow(part): + def __init__(self, celltype="td", row=None, style=None, cellclass=None, firstColumnHeader=None, thStyle=None, id=None, attributes=None): + part.__init__(self, "tr", style=style, id=id, attributes=attributes) + self.celltype=celltype + self.cellclass=cellclass + self.firstColumnHeader=firstColumnHeader + self.cellheaderclass=thStyle + if row: + self.addCells(row) + + def addCell(self, cell, celltype=None, cellclass=None, colspan=None, rowspan=None): + if self.firstColumnHeader and len(self.pieces) == 0: + celltype="th" + cellclass=self.cellheaderclass + elif celltype == None: + celltype = self.celltype + + if celltype == None: + celltype = "td" + + if cellclass==None: + cellclass=self.cellclass + + attributes = {} + if colspan: + attributes['colspan'] = colspan + if rowspan: + attributes['rowspan'] = rowspan + + if cell == None: + cell = "" + + self.addPiece(part(code=celltype, style=cellclass, content=cell, attributes=attributes)) + + def addCells(self, cells): + for cell in cells: + self.addCell(cell) + + def columnCount(self): + return len(self.pieces) + + +#lists + +class linkedList(part): + def __init__(self, links=None, outer = "ul", inner="li", style=None, iclass=None, id=None, attributes=None): + part.__init__(self, code=outer, style=style, id=id, attributes=attributes) + self.innercode = inner + self.innerstyle = iclass + if isinstance(links, list): + self.addLinks(links) + + def addLink(self, link): + [url, name] = link + link = part("a", attributes={"href": url}, content=name) + listitem = part(self.innercode, content=link, style=self.innerstyle) + self.pieces.append(listitem) + + def addLinks(self, links): + theLinks = [] + for link in links: + self.addLink(link) + +class simpleList(part): + def __init__(self, items=None, outer = "ul", inner="li", defaultname=None, default=None, style=None, iclass=None, id=None, attributes=None): + part.__init__(self, code=outer, style=style, id=id, attributes=attributes) + self.innercode = inner + self.innerstyle = iclass + self.defaultname = defaultname + self.default=default + if isinstance(items, list): + self.addItems(items) + + def addItem(self, item): + attributes = {} + if self.defaultname: + if item == self.default: + attributes[self.defaultname] = None + + theItem = part(self.innercode, content=item, style=self.innerstyle, attributes=attributes) + self.pieces.append(theItem) + + def addItems(self, items): + theList = [] + for item in items: + self.addItem(item) + +#individual pieces + +class image(part): + def __init__(self, src, alt=None, align=None, style=None, id=None, attributes=None): + if attributes == None: + attributes = {} + attributes['src'] = src + if alt: + attributes['alt'] = alt + if align: + attributes['align'] = align + + part.__init__(self, 'img', style=style, id=id, attributes=attributes) + +class link(snippet): + def __init__(self, content=None, url=None, posttext=None, pretext=None, style=None, id=None, attributes=None): + if url != None: + if attributes == None: + attributes = {} + attributes['href'] = url + + snippet.__init__(self, "a", content, posttext, pretext, style, id, attributes) + + +#forms + +class form(part): + def __init__(self, submitText="Submit", pieces=None, method="get", action='./', submitName = None, submitAction=None, headline=None, headlineLevel = 2, style=None, attributes=None): + self.submitText = submitText + self.submitName = submitName + self.making = None + if attributes == None: + attributes = {} + if action != None: + attributes['action'] = action + if method != None: + attributes['method'] = method + if submitAction != None: + attributes['onSubmit'] = '"' + submitaction + '"' + + part.__init__(self, 'form', style=style, attributes=attributes) + + if headline != None: + headcode = "h" + headlineLevel + self.addPart(headcode, content=headline) + + self.addPieces(pieces) + + + def make(self, tab=''): + if self.making: + return part.make(self, tab) + else: + if self.submitName: + submitButton = input("submit", value=self.submitText, name=self.submitName) + else: + submitButton = input("submit", value=self.submitText) + trueForm = self + trueForm.making = 1 + trueForm.addPiece(submitButton) + pageContent = trueForm.make(tab) + return pageContent + +class input(part): + def __init__(self, type, name=None, value=None, size=None, maxlength=None, style=None, id=None, attributes=None): + if attributes == None: + attributes = {} + + attributes['type'] = type + if name: + attributes['name'] = name + if value!=None: + attributes['value'] = value + if size: + attributes['size'] = size + if maxlength: + attributes['maxlength'] = maxlength + + part.__init__(self, 'input', style=style, id=id, attributes=attributes) + +class select(simpleList): + def __init__(self, name, items=None, default=None, style=None, iclass=None, id=None, attributes=None): + if attributes==None: + attributes={} + attributes['name'] = name + + simpleList.__init__(self, items, outer='select', inner='option', defaultname='selected', default=default, style=style, iclass=iclass, id=id, attributes=attributes) + +class textinput(part): + def __init__(self, name=None, text=None, value=None, size=None, maxlength=None, style=None, id=None, attributes=None, type="text", tableRow=None): + if (text == None): + text = name + self.field = input(type=type, name=name, value=value, size=size, maxlength=maxlength, style=style, id=id, attributes=attributes) + self.text = text + + if tableRow == None: + part.__init__(self, 'p', style=style, attributes=attributes) + self.addPiece(self.text) + self.addPiece(self.field) + else: + part.__init__(self, 'tr', style=style, attributes=attributes) + self.addPart('th', content=self.text) + self.addPart('td', content=self.field) + + + +#need some functions for HTML +#ought to be somewhere else in Python? +#cgi.escape only seems to do <, >, and & +from htmlentitydefs import entitydefs +import re + +entitydefs_inverted = {} +for k,v in entitydefs.items(): + entitydefs_inverted[v] = k + +needencoding = re.compile('|'.join(entitydefs.values())) +alreadyencoded = re.compile('&\w+;|&#[0-9]+;') + +#encodes any special characters to their HTML equivalents +def encode(text, skip=None, once_only=1): + # if extra_careful, check to see if this text has already been converted + if not (once_only and alreadyencoded.findall(text)): + if not isinstance(skip, list): + skip = [skip] + + #do ampersands on their own or we might end up converting our conversions + if '&' not in skip: + text = text.replace('&','&') + skip.append('&') + + needlist= [] + #grab the characters in the text that need encoding + for x in needencoding.findall(text): + #and make sure we aren't skipping them + if x not in skip: + needlist.append(x) + + for uncoded in needlist: + encoded = entitydefs_inverted[uncoded] + #if it is not a numerical encoding, we need to do the & and ; ourselves + if not encoded.startswith('&#'): + encoded = '&%s;'%entitydefs_inverted[uncoded] + + text = text.replace(uncoded, encoded) + + return text diff --git a/nagios/configurator/misccommands.cfg b/nagios/configurator/misccommands.cfg new file mode 100644 index 0000000..715e515 --- /dev/null +++ b/nagios/configurator/misccommands.cfg @@ -0,0 +1,104 @@ +################################################################################ +# Sample object config file for Nagios +# +# Read the documentation for more information on this configuration file. I've +# provided some comments here, but things may not be so clear without further +# explanation, so make sure to read the HTML documentation! +# +# Last Modified: 12-17-2005 +# +################################################################################ + + +################################################################################ +# COMMAND DEFINITIONS +# +# SYNTAX: +# +# define command{ +# template +# name +# command_name +# command_line +# } +# +# WHERE: +# +# = object name of another command definition that should be +# used as a template for this definition (optional) +# = object name of command definition, referenced by other +# command definitions that use it as a template (optional) +# = name of the command, as recognized/used by Nagios +# = command line +# +################################################################################ + + + + +################################################################################ +# +# SAMPLE NOTIFICATION COMMANDS +# +# These are some example notification commands. They may or may not work on +# your system without modification. +# +################################################################################ + + +# 'host-notify-by-email' command definition +define command{ + command_name host-notify-by-email + command_line /usr/bin/printf "%b" "***** Nagios *****\n\nNotification Type: $NOTIFICATIONTYPE$\nHost: $HOSTNAME$\nState: $HOSTSTATE$\nAddress: $HOSTADDRESS$\nInfo: $HOSTOUTPUT$\n\nDate/Time: $LONGDATETIME$\n" | /bin/mail -s "Host $HOSTSTATE$ alert for $HOSTNAME$!" $CONTACTEMAIL$ + } + + +# 'host-notify-by-epager' command definition +define command{ + command_name host-notify-by-epager + command_line /usr/bin/printf "%b" "Host '$HOSTALIAS$' is $HOSTSTATE$\nInfo: $HOSTOUTPUT$\nTime: $LONGDATETIME$" | /bin/mail -s "$NOTIFICATIONTYPE$ alert - Host $HOSTNAME$ is $HOSTSTATE$" $CONTACTPAGER$ + } + +# 'notify-by-email' command definition +define command{ + command_name notify-by-email + command_line /usr/bin/printf "%b" "***** Nagios *****\n\nNotification Type: $NOTIFICATIONTYPE$\n\nService: $SERVICEDESC$\nHost: $HOSTALIAS$\nAddress: $HOSTADDRESS$\nState: $SERVICESTATE$\n\nDate/Time: $LONGDATETIME$\n\nAdditional Info:\n\n$SERVICEOUTPUT$" | /bin/mail -s "** $NOTIFICATIONTYPE$ alert - $HOSTALIAS$/$SERVICEDESC$ is $SERVICESTATE$ **" $CONTACTEMAIL$ + } + + +# 'notify-by-epager' command definition +define command{ + command_name notify-by-epager + command_line /usr/bin/printf "%b" "Service: $SERVICEDESC$\nHost: $HOSTNAME$\nAddress: $HOSTADDRESS$\nState: $SERVICESTATE$\nInfo: $SERVICEOUTPUT$\nDate: $LONGDATETIME$" | /bin/mail -s "$NOTIFICATIONTYPE$: $HOSTALIAS$/$SERVICEDESC$ is $SERVICESTATE$" $CONTACTPAGER$ + } + + + + + +################################################################################ +# +# SAMPLE PERFORMANCE DATA COMMANDS +# +# These are sample performance data commands that can be used to send performance +# data output to two text files (one for hosts, another for services). If you +# plan on simply writing performance data out to a file, consider using the +# host_perfdata_file and service_perfdata_file options in the main config file. +# +################################################################################ + + +# 'process-host-perfdata' command definition +define command{ + command_name process-host-perfdata + command_line /usr/bin/printf "%b" "$LASTHOSTCHECK$\t$HOSTNAME$\t$HOSTSTATE$\t$HOSTATTEMPT$\t$HOSTSTATETYPE$\t$HOSTEXECUTIONTIME$\t$HOSTOUTPUT$\t$HOSTPERFDATA$\n" >> /var/log/nagios/host-perfdata.out + } + + +# 'process-service-perfdata' command definition +define command{ + command_name process-service-perfdata + command_line /usr/bin/printf "%b" "$LASTSERVICECHECK$\t$HOSTNAME$\t$SERVICEDESC$\t$SERVICESTATE$\t$SERVICEATTEMPT$\t$SERVICESTATETYPE$\t$SERVICEEXECUTIONTIME$\t$SERVICELATENCY$\t$SERVICEOUTPUT$\t$SERVICEPERFDATA$\n" >> /var/log/nagios/service-perfdata.out + } + + diff --git a/nagios/configurator/nagios.cfg b/nagios/configurator/nagios.cfg new file mode 100644 index 0000000..f79e782 --- /dev/null +++ b/nagios/configurator/nagios.cfg @@ -0,0 +1,939 @@ +############################################################################## +# +# NAGIOS.CFG - Sample Main Config File for Nagios +# +# Read the documentation for more information on this configuration +# file. I've provided some comments here, but things may not be so +# clear without further explanation. +# +# Last Modified: 11-23-2005 +# +############################################################################## + + +# LOG FILE +# This is the main log file where service and host events are logged +# for historical purposes. This should be the first option specified +# in the config file!!! + +log_file=/var/log/nagios/nagios.log + + + +# OBJECT CONFIGURATION FILE(S) +# This is the configuration file in which you define hosts, host +# groups, contacts, contact groups, services, etc. I guess it would +# be better called an object definition file, but for historical +# reasons it isn't. You can split object definitions into several +# different config files by using multiple cfg_file statements here. +# Nagios will read and process all the config files you define. +# This can be very useful if you want to keep command definitions +# separate from host and contact definitions... + +# Plugin commands (service and host check commands) +# Arguments are likely to change between different releases of the +# plugins, so you should use the same config file provided with the +# plugin release rather than the one provided with Nagios. +# merged into generic.cfg +#cfg_file=/etc/nagios/checkcommands.cfg + +# Misc commands (notification and event handler commands, etc) +cfg_file=/etc/nagios/misccommands.cfg + +# You can split other types of object definitions across several +# config files if you wish (as done here), or keep them all in a +# single config file. + +# we define here the generic stuff that planetlab.cfg relies upon +cfg_file=/etc/nagios/generic.cfg + +# python-generated common definitions - need to be loaded first +cfg_file=/etc/nagios/planetlab.cfg + +# python-generated details +cfg_dir=/etc/nagios/planetlab/ + + + +# OBJECT CACHE FILE +# This option determines where object definitions are cached when +# Nagios starts/restarts. The CGIs read object definitions from +# this cache file (rather than looking at the object config files +# directly) in order to prevent inconsistencies that can occur +# when the config files are modified after Nagios starts. + +object_cache_file=/var/log/nagios/objects.cache + + +# RESOURCE FILE +# This is an optional resource file that contains $USERx$ macro +# definitions. Multiple resource files can be specified by using +# multiple resource_file definitions. The CGIs will not attempt to +# read the contents of resource files, so information that is +# considered to be sensitive (usernames, passwords, etc) can be +# defined as macros in this file and restrictive permissions (600) +# can be placed on this file. + +resource_file=/etc/nagios/private/resource.cfg + + + +# STATUS FILE +# This is where the current status of all monitored services and +# hosts is stored. Its contents are read and processed by the CGIs. +# The contents of the status file are deleted every time Nagios +# restarts. + +status_file=/var/log/nagios/status.dat + + + +# NAGIOS USER +# This determines the effective user that Nagios should run as. +# You can either supply a username or a UID. + +nagios_user=nagios + + + +# NAGIOS GROUP +# This determines the effective group that Nagios should run as. +# You can either supply a group name or a GID. + +nagios_group=nagios + + + +# EXTERNAL COMMAND OPTION +# This option allows you to specify whether or not Nagios should check +# for external commands (in the command file defined below). By default +# Nagios will *not* check for external commands, just to be on the +# cautious side. If you want to be able to use the CGI command interface +# you will have to enable this. Setting this value to 0 disables command +# checking (the default), other values enable it. + +check_external_commands=1 + + + +# EXTERNAL COMMAND CHECK INTERVAL +# This is the interval at which Nagios should check for external commands. +# This value works of the interval_length you specify later. If you leave +# that at its default value of 60 (seconds), a value of 1 here will cause +# Nagios to check for external commands every minute. If you specify a +# number followed by an "s" (i.e. 15s), this will be interpreted to mean +# actual seconds rather than a multiple of the interval_length variable. +# Note: In addition to reading the external command file at regularly +# scheduled intervals, Nagios will also check for external commands after +# event handlers are executed. +# NOTE: Setting this value to -1 causes Nagios to check the external +# command file as often as possible. + +#command_check_interval=1 +#command_check_interval=15s +command_check_interval=-1 + + + +# EXTERNAL COMMAND FILE +# This is the file that Nagios checks for external command requests. +# It is also where the command CGI will write commands that are submitted +# by users, so it must be writeable by the user that the web server +# is running as (usually 'nobody'). Permissions should be set at the +# directory level instead of on the file, as the file is deleted every +# time its contents are processed. + +command_file=/var/spool/nagios/cmd/nagios.cmd + + + +# COMMENT FILE +# This is the file that Nagios will use for storing host and service +# comments. + +comment_file=/var/log/nagios/comments.dat + + + +# DOWNTIME FILE +# This is the file that Nagios will use for storing host and service +# downtime data. + +downtime_file=/var/log/nagios/downtime.dat + + + +# LOCK FILE +# This is the lockfile that Nagios will use to store its PID number +# in when it is running in daemon mode. + +lock_file=/var/run/nagios.pid + + + +# TEMP FILE +# This is a temporary file that is used as scratch space when Nagios +# updates the status log, cleans the comment file, etc. This file +# is created, used, and deleted throughout the time that Nagios is +# running. + +temp_file=/var/log/nagios/nagios.tmp + + + +# EVENT BROKER OPTIONS +# Controls what (if any) data gets sent to the event broker. +# Values: 0 = Broker nothing +# -1 = Broker everything +# = See documentation + +event_broker_options=-1 + + + +# EVENT BROKER MODULE(S) +# This directive is used to specify an event broker module that should +# by loaded by Nagios at startup. Use multiple directives if you want +# to load more than one module. Arguments that should be passed to +# the module at startup are seperated from the module path by a space. +# +# Example: +# +# broker_module= [moduleargs] + +#broker_module=/somewhere/module1.o +#broker_module=/somewhere/module2.o arg1 arg2=3 debug=0 + + + + +# LOG ROTATION METHOD +# This is the log rotation method that Nagios should use to rotate +# the main log file. Values are as follows.. +# n = None - don't rotate the log +# h = Hourly rotation (top of the hour) +# d = Daily rotation (midnight every day) +# w = Weekly rotation (midnight on Saturday evening) +# m = Monthly rotation (midnight last day of month) + +log_rotation_method=d + + + +# LOG ARCHIVE PATH +# This is the directory where archived (rotated) log files should be +# placed (assuming you've chosen to do log rotation). + +log_archive_path=/var/log/nagios/archives + + + +# LOGGING OPTIONS +# If you want messages logged to the syslog facility, as well as the +# NetAlarm log file set this option to 1. If not, set it to 0. + +use_syslog=1 + + + +# NOTIFICATION LOGGING OPTION +# If you don't want notifications to be logged, set this value to 0. +# If notifications should be logged, set the value to 1. + +log_notifications=1 + + + +# SERVICE RETRY LOGGING OPTION +# If you don't want service check retries to be logged, set this value +# to 0. If retries should be logged, set the value to 1. + +log_service_retries=1 + + + +# HOST RETRY LOGGING OPTION +# If you don't want host check retries to be logged, set this value to +# 0. If retries should be logged, set the value to 1. + +log_host_retries=1 + + + +# EVENT HANDLER LOGGING OPTION +# If you don't want host and service event handlers to be logged, set +# this value to 0. If event handlers should be logged, set the value +# to 1. + +log_event_handlers=1 + + + +# INITIAL STATES LOGGING OPTION +# If you want Nagios to log all initial host and service states to +# the main log file (the first time the service or host is checked) +# you can enable this option by setting this value to 1. If you +# are not using an external application that does long term state +# statistics reporting, you do not need to enable this option. In +# this case, set the value to 0. + +log_initial_states=0 + + + +# EXTERNAL COMMANDS LOGGING OPTION +# If you don't want Nagios to log external commands, set this value +# to 0. If external commands should be logged, set this value to 1. +# Note: This option does not include logging of passive service +# checks - see the option below for controlling whether or not +# passive checks are logged. + +log_external_commands=1 + + + +# PASSIVE CHECKS LOGGING OPTION +# If you don't want Nagios to log passive host and service checks, set +# this value to 0. If passive checks should be logged, set +# this value to 1. + +log_passive_checks=1 + + + +# GLOBAL HOST AND SERVICE EVENT HANDLERS +# These options allow you to specify a host and service event handler +# command that is to be run for every host or service state change. +# The global event handler is executed immediately prior to the event +# handler that you have optionally specified in each host or +# service definition. The command argument is the short name of a +# command definition that you define in your host configuration file. +# Read the HTML docs for more information. + +#global_host_event_handler=somecommand +#global_service_event_handler=somecommand + + + +# SERVICE INTER-CHECK DELAY METHOD +# This is the method that Nagios should use when initially +# "spreading out" service checks when it starts monitoring. The +# default is to use smart delay calculation, which will try to +# space all service checks out evenly to minimize CPU load. +# Using the dumb setting will cause all checks to be scheduled +# at the same time (with no delay between them)! This is not a +# good thing for production, but is useful when testing the +# parallelization functionality. +# n = None - don't use any delay between checks +# d = Use a "dumb" delay of 1 second between checks +# s = Use "smart" inter-check delay calculation +# x.xx = Use an inter-check delay of x.xx seconds + +service_inter_check_delay_method=s + + + +# MAXIMUM SERVICE CHECK SPREAD +# This variable determines the timeframe (in minutes) from the +# program start time that an initial check of all services should +# be completed. Default is 30 minutes. + +max_service_check_spread=30 + + + +# SERVICE CHECK INTERLEAVE FACTOR +# This variable determines how service checks are interleaved. +# Interleaving the service checks allows for a more even +# distribution of service checks and reduced load on remote +# hosts. Setting this value to 1 is equivalent to how versions +# of Nagios previous to 0.0.5 did service checks. Set this +# value to s (smart) for automatic calculation of the interleave +# factor unless you have a specific reason to change it. +# s = Use "smart" interleave factor calculation +# x = Use an interleave factor of x, where x is a +# number greater than or equal to 1. + +service_interleave_factor=s + + + +# HOST INTER-CHECK DELAY METHOD +# This is the method that Nagios should use when initially +# "spreading out" host checks when it starts monitoring. The +# default is to use smart delay calculation, which will try to +# space all host checks out evenly to minimize CPU load. +# Using the dumb setting will cause all checks to be scheduled +# at the same time (with no delay between them)! +# n = None - don't use any delay between checks +# d = Use a "dumb" delay of 1 second between checks +# s = Use "smart" inter-check delay calculation +# x.xx = Use an inter-check delay of x.xx seconds + +host_inter_check_delay_method=s + + + +# MAXIMUM HOST CHECK SPREAD +# This variable determines the timeframe (in minutes) from the +# program start time that an initial check of all hosts should +# be completed. Default is 30 minutes. + +max_host_check_spread=30 + + + +# MAXIMUM CONCURRENT SERVICE CHECKS +# This option allows you to specify the maximum number of +# service checks that can be run in parallel at any given time. +# Specifying a value of 1 for this variable essentially prevents +# any service checks from being parallelized. A value of 0 +# will not restrict the number of concurrent checks that are +# being executed. + +max_concurrent_checks=0 + + + +# SERVICE CHECK REAPER FREQUENCY +# This is the frequency (in seconds!) that Nagios will process +# the results of services that have been checked. + +service_reaper_frequency=10 + + + + +# AUTO-RESCHEDULING OPTION +# This option determines whether or not Nagios will attempt to +# automatically reschedule active host and service checks to +# "smooth" them out over time. This can help balance the load on +# the monitoring server. +# WARNING: THIS IS AN EXPERIMENTAL FEATURE - IT CAN DEGRADE +# PERFORMANCE, RATHER THAN INCREASE IT, IF USED IMPROPERLY + +auto_reschedule_checks=0 + + + +# AUTO-RESCHEDULING INTERVAL +# This option determines how often (in seconds) Nagios will +# attempt to automatically reschedule checks. This option only +# has an effect if the auto_reschedule_checks option is enabled. +# Default is 30 seconds. +# WARNING: THIS IS AN EXPERIMENTAL FEATURE - IT CAN DEGRADE +# PERFORMANCE, RATHER THAN INCREASE IT, IF USED IMPROPERLY + +auto_rescheduling_interval=30 + + + + +# AUTO-RESCHEDULING WINDOW +# This option determines the "window" of time (in seconds) that +# Nagios will look at when automatically rescheduling checks. +# Only host and service checks that occur in the next X seconds +# (determined by this variable) will be rescheduled. This option +# only has an effect if the auto_reschedule_checks option is +# enabled. Default is 180 seconds (3 minutes). +# WARNING: THIS IS AN EXPERIMENTAL FEATURE - IT CAN DEGRADE +# PERFORMANCE, RATHER THAN INCREASE IT, IF USED IMPROPERLY + +auto_rescheduling_window=180 + + + +# SLEEP TIME +# This is the number of seconds to sleep between checking for system +# events and service checks that need to be run. + +sleep_time=0.25 + + + +# TIMEOUT VALUES +# These options control how much time Nagios will allow various +# types of commands to execute before killing them off. Options +# are available for controlling maximum time allotted for +# service checks, host checks, event handlers, notifications, the +# ocsp command, and performance data commands. All values are in +# seconds. + +service_check_timeout=60 +host_check_timeout=30 +event_handler_timeout=30 +notification_timeout=30 +ocsp_timeout=5 +perfdata_timeout=5 + + + +# RETAIN STATE INFORMATION +# This setting determines whether or not Nagios will save state +# information for services and hosts before it shuts down. Upon +# startup Nagios will reload all saved service and host state +# information before starting to monitor. This is useful for +# maintaining long-term data on state statistics, etc, but will +# slow Nagios down a bit when it (re)starts. Since its only +# a one-time penalty, I think its well worth the additional +# startup delay. + +retain_state_information=1 + + + +# STATE RETENTION FILE +# This is the file that Nagios should use to store host and +# service state information before it shuts down. The state +# information in this file is also read immediately prior to +# starting to monitor the network when Nagios is restarted. +# This file is used only if the preserve_state_information +# variable is set to 1. + +state_retention_file=/var/log/nagios/retention.dat + + + +# RETENTION DATA UPDATE INTERVAL +# This setting determines how often (in minutes) that Nagios +# will automatically save retention data during normal operation. +# If you set this value to 0, Nagios will not save retention +# data at regular interval, but it will still save retention +# data before shutting down or restarting. If you have disabled +# state retention, this option has no effect. + +retention_update_interval=60 + + + +# USE RETAINED PROGRAM STATE +# This setting determines whether or not Nagios will set +# program status variables based on the values saved in the +# retention file. If you want to use retained program status +# information, set this value to 1. If not, set this value +# to 0. + +use_retained_program_state=1 + + + +# USE RETAINED SCHEDULING INFO +# This setting determines whether or not Nagios will retain +# the scheduling info (next check time) for hosts and services +# based on the values saved in the retention file. If you +# If you want to use retained scheduling info, set this +# value to 1. If not, set this value to 0. + +use_retained_scheduling_info=0 + + + +# INTERVAL LENGTH +# This is the seconds per unit interval as used in the +# host/contact/service configuration files. Setting this to 60 means +# that each interval is one minute long (60 seconds). Other settings +# have not been tested much, so your mileage is likely to vary... + +interval_length=60 + + + +# AGGRESSIVE HOST CHECKING OPTION +# If you don't want to turn on aggressive host checking features, set +# this value to 0 (the default). Otherwise set this value to 1 to +# enable the aggressive check option. Read the docs for more info +# on what aggressive host check is or check out the source code in +# base/checks.c + +use_aggressive_host_checking=0 + + + +# SERVICE CHECK EXECUTION OPTION +# This determines whether or not Nagios will actively execute +# service checks when it initially starts. If this option is +# disabled, checks are not actively made, but Nagios can still +# receive and process passive check results that come in. Unless +# you're implementing redundant hosts or have a special need for +# disabling the execution of service checks, leave this enabled! +# Values: 1 = enable checks, 0 = disable checks + +execute_service_checks=1 + + + +# PASSIVE SERVICE CHECK ACCEPTANCE OPTION +# This determines whether or not Nagios will accept passive +# service checks results when it initially (re)starts. +# Values: 1 = accept passive checks, 0 = reject passive checks + +accept_passive_service_checks=1 + + + +# HOST CHECK EXECUTION OPTION +# This determines whether or not Nagios will actively execute +# host checks when it initially starts. If this option is +# disabled, checks are not actively made, but Nagios can still +# receive and process passive check results that come in. Unless +# you're implementing redundant hosts or have a special need for +# disabling the execution of host checks, leave this enabled! +# Values: 1 = enable checks, 0 = disable checks + +execute_host_checks=1 + + + +# PASSIVE HOST CHECK ACCEPTANCE OPTION +# This determines whether or not Nagios will accept passive +# host checks results when it initially (re)starts. +# Values: 1 = accept passive checks, 0 = reject passive checks + +accept_passive_host_checks=1 + + + +# NOTIFICATIONS OPTION +# This determines whether or not Nagios will sent out any host or +# service notifications when it is initially (re)started. +# Values: 1 = enable notifications, 0 = disable notifications + +enable_notifications=1 + + + +# EVENT HANDLER USE OPTION +# This determines whether or not Nagios will run any host or +# service event handlers when it is initially (re)started. Unless +# you're implementing redundant hosts, leave this option enabled. +# Values: 1 = enable event handlers, 0 = disable event handlers + +enable_event_handlers=1 + + + +# PROCESS PERFORMANCE DATA OPTION +# This determines whether or not Nagios will process performance +# data returned from service and host checks. If this option is +# enabled, host performance data will be processed using the +# host_perfdata_command (defined below) and service performance +# data will be processed using the service_perfdata_command (also +# defined below). Read the HTML docs for more information on +# performance data. +# Values: 1 = process performance data, 0 = do not process performance data + +process_performance_data=0 + + + +# HOST AND SERVICE PERFORMANCE DATA PROCESSING COMMANDS +# These commands are run after every host and service check is +# performed. These commands are executed only if the +# enable_performance_data option (above) is set to 1. The command +# argument is the short name of a command definition that you +# define in your host configuration file. Read the HTML docs for +# more information on performance data. + +#host_perfdata_command=process-host-perfdata +#service_perfdata_command=process-service-perfdata + + + +# HOST AND SERVICE PERFORMANCE DATA FILES +# These files are used to store host and service performance data. +# Performance data is only written to these files if the +# enable_performance_data option (above) is set to 1. + +#host_perfdata_file=/tmp/host-perfdata +#service_perfdata_file=/tmp/service-perfdata + + + +# HOST AND SERVICE PERFORMANCE DATA FILE TEMPLATES +# These options determine what data is written (and how) to the +# performance data files. The templates may contain macros, special +# characters (\t for tab, \r for carriage return, \n for newline) +# and plain text. A newline is automatically added after each write +# to the performance data file. Some examples of what you can do are +# shown below. + +#host_perfdata_file_template=[HOSTPERFDATA]\t$TIMET$\t$HOSTNAME$\t$HOSTEXECUTIONTIME$\t$HOSTOUTPUT$\t$HOSTPERFDATA$ +#service_perfdata_file_template=[SERVICEPERFDATA]\t$TIMET$\t$HOSTNAME$\t$SERVICEDESC$\t$SERVICEEXECUTIONTIME$\t$SERVICELATENCY$\t$SERVICEOUTPUT$\t$SERVICEPERFDATA$ + + + + +# HOST AND SERVICE PERFORMANCE DATA FILE MODES +# This option determines whether or not the host and service +# performance data files are opened in write ("w") or append ("a") +# mode. Unless you are the files are named pipes, you will probably +# want to use the default mode of append ("a"). + +#host_perfdata_file_mode=a +#service_perfdata_file_mode=a + + + +# HOST AND SERVICE PERFORMANCE DATA FILE PROCESSING INTERVAL +# These options determine how often (in seconds) the host and service +# performance data files are processed using the commands defined +# below. A value of 0 indicates the files should not be periodically +# processed. + +#host_perfdata_file_processing_interval=0 +#service_perfdata_file_processing_interval=0 + + + +# HOST AND SERVICE PERFORMANCE DATA FILE PROCESSING COMMANDS +# These commands are used to periodically process the host and +# service performance data files. The interval at which the +# processing occurs is determined by the options above. + +#host_perfdata_file_processing_command=process-host-perfdata-file +#service_perfdata_file_processing_command=process-service-perfdata-file + + + +# OBSESS OVER SERVICE CHECKS OPTION +# This determines whether or not Nagios will obsess over service +# checks and run the ocsp_command defined below. Unless you're +# planning on implementing distributed monitoring, do not enable +# this option. Read the HTML docs for more information on +# implementing distributed monitoring. +# Values: 1 = obsess over services, 0 = do not obsess (default) + +obsess_over_services=0 + + + +# OBSESSIVE COMPULSIVE SERVICE PROCESSOR COMMAND +# This is the command that is run for every service check that is +# processed by Nagios. This command is executed only if the +# obsess_over_service option (above) is set to 1. The command +# argument is the short name of a command definition that you +# define in your host configuration file. Read the HTML docs for +# more information on implementing distributed monitoring. + +#ocsp_command=somecommand + + + +# ORPHANED SERVICE CHECK OPTION +# This determines whether or not Nagios will periodically +# check for orphaned services. Since service checks are not +# rescheduled until the results of their previous execution +# instance are processed, there exists a possibility that some +# checks may never get rescheduled. This seems to be a rare +# problem and should not happen under normal circumstances. +# If you have problems with service checks never getting +# rescheduled, you might want to try enabling this option. +# Values: 1 = enable checks, 0 = disable checks + +check_for_orphaned_services=0 + + + +# SERVICE FRESHNESS CHECK OPTION +# This option determines whether or not Nagios will periodically +# check the "freshness" of service results. Enabling this option +# is useful for ensuring passive checks are received in a timely +# manner. +# Values: 1 = enabled freshness checking, 0 = disable freshness checking + +check_service_freshness=1 + + + +# SERVICE FRESHNESS CHECK INTERVAL +# This setting determines how often (in seconds) Nagios will +# check the "freshness" of service check results. If you have +# disabled service freshness checking, this option has no effect. + +service_freshness_check_interval=60 + + + +# HOST FRESHNESS CHECK OPTION +# This option determines whether or not Nagios will periodically +# check the "freshness" of host results. Enabling this option +# is useful for ensuring passive checks are received in a timely +# manner. +# Values: 1 = enabled freshness checking, 0 = disable freshness checking + +check_host_freshness=0 + + + +# HOST FRESHNESS CHECK INTERVAL +# This setting determines how often (in seconds) Nagios will +# check the "freshness" of host check results. If you have +# disabled host freshness checking, this option has no effect. + +host_freshness_check_interval=60 + + + +# AGGREGATED STATUS UPDATES +# This option determines whether or not Nagios will +# aggregate updates of host, service, and program status +# data. Normally, status data is updated immediately when +# a change occurs. This can result in high CPU loads if +# you are monitoring a lot of services. If you want Nagios +# to only refresh status data every few seconds, disable +# this option. +# Values: 1 = enable aggregate updates, 0 = disable aggregate updates + +aggregate_status_updates=1 + + + +# AGGREGATED STATUS UPDATE INTERVAL +# Combined with the aggregate_status_updates option, +# this option determines the frequency (in seconds!) that +# Nagios will periodically dump program, host, and +# service status data. If you are not using aggregated +# status data updates, this option has no effect. + +status_update_interval=15 + + + +# FLAP DETECTION OPTION +# This option determines whether or not Nagios will try +# and detect hosts and services that are "flapping". +# Flapping occurs when a host or service changes between +# states too frequently. When Nagios detects that a +# host or service is flapping, it will temporarily suppress +# notifications for that host/service until it stops +# flapping. Flap detection is very experimental, so read +# the HTML documentation before enabling this feature! +# Values: 1 = enable flap detection +# 0 = disable flap detection (default) + +enable_flap_detection=0 + + + +# FLAP DETECTION THRESHOLDS FOR HOSTS AND SERVICES +# Read the HTML documentation on flap detection for +# an explanation of what this option does. This option +# has no effect if flap detection is disabled. + +low_service_flap_threshold=5.0 +high_service_flap_threshold=20.0 +low_host_flap_threshold=5.0 +high_host_flap_threshold=20.0 + + + +# DATE FORMAT OPTION +# This option determines how short dates are displayed. Valid options +# include: +# us (MM-DD-YYYY HH:MM:SS) +# euro (DD-MM-YYYY HH:MM:SS) +# iso8601 (YYYY-MM-DD HH:MM:SS) +# strict-iso8601 (YYYY-MM-DDTHH:MM:SS) +# + +date_format=us + + + +# P1.PL FILE LOCATION +# This value determines where the p1.pl perl script (used by the +# embedded Perl interpreter) is located. If you didn't compile +# Nagios with embedded Perl support, this option has no effect. + +p1_file=/usr/sbin/p1.pl + + + +# ILLEGAL OBJECT NAME CHARACTERS +# This option allows you to specify illegal characters that cannot +# be used in host names, service descriptions, or names of other +# object types. + +illegal_object_name_chars=`~!$%^&*|'"<>?,()= + + + +# ILLEGAL MACRO OUTPUT CHARACTERS +# This option allows you to specify illegal characters that are +# stripped from macros before being used in notifications, event +# handlers, etc. This DOES NOT affect macros used in service or +# host check commands. +# The following macros are stripped of the characters you specify: +# $HOSTOUTPUT$ +# $HOSTPERFDATA$ +# $HOSTACKAUTHOR$ +# $HOSTACKCOMMENT$ +# $SERVICEOUTPUT$ +# $SERVICEPERFDATA$ +# $SERVICEACKAUTHOR$ +# $SERVICEACKCOMMENT$ + +illegal_macro_output_chars=`~$&|'"<> + + + +# REGULAR EXPRESSION MATCHING +# This option controls whether or not regular expression matching +# takes place in the object config files. Regular expression +# matching is used to match host, hostgroup, service, and service +# group names/descriptions in some fields of various object types. +# Values: 1 = enable regexp matching, 0 = disable regexp matching + +use_regexp_matching=0 + + + +# "TRUE" REGULAR EXPRESSION MATCHING +# This option controls whether or not "true" regular expression +# matching takes place in the object config files. This option +# only has an effect if regular expression matching is enabled +# (see above). If this option is DISABLED, regular expression +# matching only occurs if a string contains wildcard characters +# (* and ?). If the option is ENABLED, regexp matching occurs +# all the time (which can be annoying). +# Values: 1 = enable true matching, 0 = disable true matching + +use_true_regexp_matching=0 + + + + +# ADMINISTRATOR EMAIL ADDRESS +# The email address of the administrator of *this* machine (the one +# doing the monitoring). Nagios never uses this value itself, but +# you can access this value by using the $ADMINEMAIL$ macro in your +# notification commands. + +admin_email=nagios + + + +# ADMINISTRATOR PAGER NUMBER/ADDRESS +# The pager number/address for the administrator of *this* machine. +# Nagios never uses this value itself, but you can access this +# value by using the $ADMINPAGER$ macro in your notification +# commands. + +admin_pager=pagenagios + + + +# DAEMON CORE DUMP OPTION +# This option determines whether or not Nagios is allowed to create +# a core dump when it runs as a daemon. Note that it is generally +# considered bad form to allow this, but it may be useful for +# debugging purposes. +# Values: 1 - Allow core dumps +# 0 - Do not allow core dumps (default) + +daemon_dumps_core=0 + + + +# EOF (End of file) + diff --git a/nagios/configurator/nagios.py b/nagios/configurator/nagios.py new file mode 100644 index 0000000..0cccbe1 --- /dev/null +++ b/nagios/configurator/nagios.py @@ -0,0 +1,6 @@ +## as per nagios doc +OK=0 +WARNING=1 +KO=2 +UNKNOWN=3 + diff --git a/nagios/configurator/onelab.txt b/nagios/configurator/onelab.txt new file mode 100644 index 0000000..89d5ec5 --- /dev/null +++ b/nagios/configurator/onelab.txt @@ -0,0 +1 @@ +2 INRIA Sophia OneLab -- 2.47.0