[PATCH 4/8] move nagios client to roles
Michael Scherer
misc at zarb.org
Mon Aug 19 19:35:20 UTC 2013
---
files/nagios/client/check_cron.cfg | 1 -
files/nagios/client/check_disk.cfg | 2 -
files/nagios/client/check_lock.cfg | 1 -
files/nagios/client/check_mirrorlist_cache.cfg | 1 -
files/nagios/client/check_postfix_queue.cfg | 1 -
files/nagios/client/check_raid.cfg | 1 -
files/nagios/client/check_swap.cfg | 1 -
files/nagios/client/nrpe.cfg | 223 ---------------------
files/nagios/client/scripts/check_lock | 17 --
files/nagios/client/scripts/check_postfix_queue | 49 -----
files/nagios/client/scripts/check_raid.py | 45 -----
handlers/restart_services.yml | 3 -
playbooks/groups/backup-server.yml | 2 +-
playbooks/groups/badges-backend.yml | 2 +-
playbooks/groups/badges-web.yml | 2 +-
playbooks/groups/beaker.yml | 2 +-
playbooks/groups/gallery.yml | 2 +-
playbooks/groups/kernel-qa.yml | 2 +-
playbooks/groups/keyserver.yml | 2 +-
playbooks/groups/koji-hub.yml | 2 +-
playbooks/groups/mailman.yml | 2 +-
playbooks/groups/mirrorlist.yml | 2 +-
playbooks/groups/postgresl-server.yml | 2 +-
playbooks/groups/releng.yml | 4 +-
playbooks/groups/taskbot.yml | 2 +-
playbooks/groups/virthost.yml | 2 +-
roles/nagios_client/files/check_cron.cfg | 1 +
roles/nagios_client/files/check_disk.cfg | 2 +
roles/nagios_client/files/check_lock.cfg | 1 +
.../nagios_client/files/check_mirrorlist_cache.cfg | 1 +
roles/nagios_client/files/check_postfix_queue.cfg | 1 +
roles/nagios_client/files/check_raid.cfg | 1 +
roles/nagios_client/files/check_swap.cfg | 1 +
roles/nagios_client/files/nrpe.cfg | 223 +++++++++++++++++++++
roles/nagios_client/files/scripts/check_lock | 17 ++
.../files/scripts/check_postfix_queue | 49 +++++
roles/nagios_client/files/scripts/check_raid.py | 45 +++++
roles/nagios_client/handlers/main.yml | 3 +
roles/nagios_client/tasks/main.yml | 63 ++++++
tasks/nagios_client.yml | 63 ------
40 files changed, 424 insertions(+), 422 deletions(-)
delete mode 100644 files/nagios/client/check_cron.cfg
delete mode 100644 files/nagios/client/check_disk.cfg
delete mode 100644 files/nagios/client/check_lock.cfg
delete mode 100644 files/nagios/client/check_mirrorlist_cache.cfg
delete mode 100644 files/nagios/client/check_postfix_queue.cfg
delete mode 100644 files/nagios/client/check_raid.cfg
delete mode 100644 files/nagios/client/check_swap.cfg
delete mode 100644 files/nagios/client/nrpe.cfg
delete mode 100755 files/nagios/client/scripts/check_lock
delete mode 100755 files/nagios/client/scripts/check_postfix_queue
delete mode 100755 files/nagios/client/scripts/check_raid.py
create mode 100644 roles/nagios_client/files/check_cron.cfg
create mode 100644 roles/nagios_client/files/check_disk.cfg
create mode 100644 roles/nagios_client/files/check_lock.cfg
create mode 100644 roles/nagios_client/files/check_mirrorlist_cache.cfg
create mode 100644 roles/nagios_client/files/check_postfix_queue.cfg
create mode 100644 roles/nagios_client/files/check_raid.cfg
create mode 100644 roles/nagios_client/files/check_swap.cfg
create mode 100644 roles/nagios_client/files/nrpe.cfg
create mode 100755 roles/nagios_client/files/scripts/check_lock
create mode 100755 roles/nagios_client/files/scripts/check_postfix_queue
create mode 100755 roles/nagios_client/files/scripts/check_raid.py
create mode 100644 roles/nagios_client/handlers/main.yml
create mode 100644 roles/nagios_client/tasks/main.yml
delete mode 100644 tasks/nagios_client.yml
diff --git a/files/nagios/client/check_cron.cfg b/files/nagios/client/check_cron.cfg
deleted file mode 100644
index e01f407..0000000
--- a/files/nagios/client/check_cron.cfg
+++ /dev/null
@@ -1 +0,0 @@
-command[check_cron]=/usr/lib64/nagios/plugins/check_procs -c 1:10 -C 'crond' -u root
diff --git a/files/nagios/client/check_disk.cfg b/files/nagios/client/check_disk.cfg
deleted file mode 100644
index d5d3290..0000000
--- a/files/nagios/client/check_disk.cfg
+++ /dev/null
@@ -1,2 +0,0 @@
-command[check_disk_/]=/usr/lib64/nagios/plugins/check_disk -w 15% -c 10% -p /
-command[check_disk_/boot]=/usr/lib64/nagios/plugins/check_disk -w 15% -c 10% -p /boot
diff --git a/files/nagios/client/check_lock.cfg b/files/nagios/client/check_lock.cfg
deleted file mode 100644
index 9525f9f..0000000
--- a/files/nagios/client/check_lock.cfg
+++ /dev/null
@@ -1 +0,0 @@
-command[check_lock]=/usr/lib64/nagios/plugins/check_lock
diff --git a/files/nagios/client/check_mirrorlist_cache.cfg b/files/nagios/client/check_mirrorlist_cache.cfg
deleted file mode 100644
index bd4b171..0000000
--- a/files/nagios/client/check_mirrorlist_cache.cfg
+++ /dev/null
@@ -1 +0,0 @@
-command[check_mirrorlist_cache]=/usr/lib64/nagios/plugins/check_file_age -w 14400 -c 129600 -f /var/lib/mirrormanager/mirrorlist_cache.pkl
diff --git a/files/nagios/client/check_postfix_queue.cfg b/files/nagios/client/check_postfix_queue.cfg
deleted file mode 100644
index 5574698..0000000
--- a/files/nagios/client/check_postfix_queue.cfg
+++ /dev/null
@@ -1 +0,0 @@
-command[check_postfix_queue]=/usr/lib64/nagios/plugins/check_postfix_queue -w 2 -c 5
diff --git a/files/nagios/client/check_raid.cfg b/files/nagios/client/check_raid.cfg
deleted file mode 100644
index 5c15d45..0000000
--- a/files/nagios/client/check_raid.cfg
+++ /dev/null
@@ -1 +0,0 @@
-command[check_raid]=/usr/lib64/nagios/plugins/check_raid.py
diff --git a/files/nagios/client/check_swap.cfg b/files/nagios/client/check_swap.cfg
deleted file mode 100644
index bc4f19d..0000000
--- a/files/nagios/client/check_swap.cfg
+++ /dev/null
@@ -1 +0,0 @@
-command[check_swap]=/usr/lib64/nagios/plugins/check_swap -w 15% -c 10%
diff --git a/files/nagios/client/nrpe.cfg b/files/nagios/client/nrpe.cfg
deleted file mode 100644
index 6933f78..0000000
--- a/files/nagios/client/nrpe.cfg
+++ /dev/null
@@ -1,223 +0,0 @@
-#############################################################################
-# Sample NRPE Config File
-# Written by: Ethan Galstad (nagios at nagios.org)
-#
-# Last Modified: 11-23-2007
-#
-# NOTES:
-# This is a sample configuration file for the NRPE daemon. It needs to be
-# located on the remote host that is running the NRPE daemon, not the host
-# from which the check_nrpe client is being executed.
-#############################################################################
-
-
-# LOG FACILITY
-# The syslog facility that should be used for logging purposes.
-
-log_facility=daemon
-
-
-
-# PID FILE
-# The name of the file in which the NRPE daemon should write it's process ID
-# number. The file is only written if the NRPE daemon is started by the root
-# user and is running in standalone mode.
-
-pid_file=/var/run/nrpe/nrpe.pid
-
-
-
-# PORT NUMBER
-# Port number we should wait for connections on.
-# NOTE: This must be a non-priviledged port (i.e. > 1024).
-# NOTE: This option is ignored if NRPE is running under either inetd or xinetd
-
-server_port=5666
-
-
-
-# SERVER ADDRESS
-# Address that nrpe should bind to in case there are more than one interface
-# and you do not want nrpe to bind on all interfaces.
-# NOTE: This option is ignored if NRPE is running under either inetd or xinetd
-
-#server_address=127.0.0.1
-
-
-
-# NRPE USER
-# This determines the effective user that the NRPE daemon should run as.
-# You can either supply a username or a UID.
-#
-# NOTE: This option is ignored if NRPE is running under either inetd or xinetd
-
-nrpe_user=nrpe
-
-
-
-# NRPE GROUP
-# This determines the effective group that the NRPE daemon should run as.
-# You can either supply a group name or a GID.
-#
-# NOTE: This option is ignored if NRPE is running under either inetd or xinetd
-
-nrpe_group=nrpe
-
-
-
-# ALLOWED HOST ADDRESSES
-# This is an optional comma-delimited list of IP address or hostnames
-# that are allowed to talk to the NRPE daemon. Network addresses with a bit mask
-# (i.e. 192.168.1.0/24) are also supported. Hostname wildcards are not currently
-# supported.
-#
-# Note: The daemon only does rudimentary checking of the client's IP
-# address. I would highly recommend adding entries in your /etc/hosts.allow
-# file to allow only the specified host to connect to the port
-# you are running this daemon on.
-#
-# NOTE: This option is ignored if NRPE is running under either inetd or xinetd
-
-
-allowed_hosts=10.5.126.41,192.168.1.10,192.168.1.20,209.132.181.35
-
-
-
-# COMMAND ARGUMENT PROCESSING
-# This option determines whether or not the NRPE daemon will allow clients
-# to specify arguments to commands that are executed. This option only works
-# if the daemon was configured with the --enable-command-args configure script
-# option.
-#
-# *** ENABLING THIS OPTION IS A SECURITY RISK! ***
-# Read the SECURITY file for information on some of the security implications
-# of enabling this variable.
-#
-# Values: 0=do not allow arguments, 1=allow command arguments
-
-dont_blame_nrpe=0
-
-
-
-# COMMAND PREFIX
-# This option allows you to prefix all commands with a user-defined string.
-# A space is automatically added between the specified prefix string and the
-# command line from the command definition.
-#
-# *** THIS EXAMPLE MAY POSE A POTENTIAL SECURITY RISK, SO USE WITH CAUTION! ***
-# Usage scenario:
-# Execute restricted commmands using sudo. For this to work, you need to add
-# the nagios user to your /etc/sudoers. An example entry for alllowing
-# execution of the plugins from might be:
-#
-# nagios ALL=(ALL) NOPASSWD: /usr/lib/nagios/plugins/
-#
-# This lets the nagios user run all commands in that directory (and only them)
-# without asking for a password. If you do this, make sure you don't give
-# random users write access to that directory or its contents!
-
-# command_prefix=/usr/bin/sudo
-
-
-
-# DEBUGGING OPTION
-# This option determines whether or not debugging messages are logged to the
-# syslog facility.
-# Values: 0=debugging off, 1=debugging on
-
-debug=0
-
-
-
-# COMMAND TIMEOUT
-# This specifies the maximum number of seconds that the NRPE daemon will
-# allow plugins to finish executing before killing them off.
-
-command_timeout=60
-
-
-
-# CONNECTION TIMEOUT
-# This specifies the maximum number of seconds that the NRPE daemon will
-# wait for a connection to be established before exiting. This is sometimes
-# seen where a network problem stops the SSL being established even though
-# all network sessions are connected. This causes the nrpe daemons to
-# accumulate, eating system resources. Do not set this too low.
-
-connection_timeout=300
-
-
-
-# WEEK RANDOM SEED OPTION
-# This directive allows you to use SSL even if your system does not have
-# a /dev/random or /dev/urandom (on purpose or because the necessary patches
-# were not applied). The random number generator will be seeded from a file
-# which is either a file pointed to by the environment valiable $RANDFILE
-# or $HOME/.rnd. If neither exists, the pseudo random number generator will
-# be initialized and a warning will be issued.
-# Values: 0=only seed from /dev/[u]random, 1=also seed from weak randomness
-
-#allow_weak_random_seed=1
-
-
-
-# INCLUDE CONFIG FILE
-# This directive allows you to include definitions from an external config file.
-
-#include=<somefile.cfg>
-
-
-
-# INCLUDE CONFIG DIRECTORY
-# This directive allows you to include definitions from config files (with a
-# .cfg extension) in one or more directories (with recursion).
-
-include_dir=/etc/nrpe.d/
-
-
-
-# COMMAND DEFINITIONS
-# Command definitions that this daemon will run. Definitions
-# are in the following format:
-#
-# command[<command_name>]=<command_line>
-#
-# When the daemon receives a request to return the results of <command_name>
-# it will execute the command specified by the <command_line> argument.
-#
-# Unlike Nagios, the command line cannot contain macros - it must be
-# typed exactly as it should be executed.
-#
-# Note: Any plugins that are used in the command lines must reside
-# on the machine that this daemon is running on! The examples below
-# assume that you have plugins installed in a /usr/local/nagios/libexec
-# directory. Also note that you will have to modify the definitions below
-# to match the argument format the plugins expect. Remember, these are
-# examples only!
-
-
-# The following examples use hardcoded command arguments...
-
-command[check_users]=/usr/lib64/nagios/plugins/check_users -w 5 -c 10
-command[check_load]=/usr/lib64/nagios/plugins/check_load -w 15,10,5 -c 30,25,20
-command[check_hda1]=/usr/lib64/nagios/plugins/check_disk -w 20% -c 10% -p /dev/hda1
-command[check_zombie_procs]=/usr/lib64/nagios/plugins/check_procs -w 5 -c 10 -s Z
-command[check_total_procs]=/usr/lib64/nagios/plugins/check_procs -w {{ nrpe_procs_warn }} -c {{ nrpe_procs_crit }}
-
-
-# The following examples allow user-supplied arguments and can
-# only be used if the NRPE daemon was compiled with support for
-# command arguments *AND* the dont_blame_nrpe directive in this
-# config file is set to '1'. This poses a potential security risk, so
-# make sure you read the SECURITY file before doing this.
-
-#command[check_users]=/usr/lib64/nagios/plugins/check_users -w $ARG1$ -c $ARG2$
-#command[check_load]=/usr/lib64/nagios/plugins/check_load -w $ARG1$ -c $ARG2$
-#command[check_disk]=/usr/lib64/nagios/plugins/check_disk -w $ARG1$ -c $ARG2$ -p $ARG3$
-#command[check_procs]=/usr/lib64/nagios/plugins/check_procs -w $ARG1$ -c $ARG2$ -s $ARG3$
-
-
-# NEVER ADD ANYTHING HERE - ANY ENTRIES TO NRPE SHOULD BE in .cfg files in /etc/nrpe.d/
-
-# NEVER NEVER NEVER
-#
diff --git a/files/nagios/client/scripts/check_lock b/files/nagios/client/scripts/check_lock
deleted file mode 100755
index 1a58e95..0000000
--- a/files/nagios/client/scripts/check_lock
+++ /dev/null
@@ -1,17 +0,0 @@
-#!/usr/bin/python
-
-import fcntl
-import sys
-
-try:
- f = open('/mnt/koji/.nagios_test', 'r')
- f.close()
- f = open('/mnt/koji/.nagios_test', 'w')
-except IOError:
- print "Could not create file"
- sys.exit(2)
-
-fcntl.flock(f, fcntl.LOCK_EX)
-f.close()
-print "File Locked Successfully"
-sys.exit(0)
diff --git a/files/nagios/client/scripts/check_postfix_queue b/files/nagios/client/scripts/check_postfix_queue
deleted file mode 100755
index 44ab444..0000000
--- a/files/nagios/client/scripts/check_postfix_queue
+++ /dev/null
@@ -1,49 +0,0 @@
-#!/bin/bash
-#
-# 19-07-2010
-# Author: Cherwin Nooitmeer <cherwin at gmail.com>
-#
-
-# exit codes
-e_ok=0
-e_warning=1
-e_critical=2
-e_unknown=3
-
-# regular expression that matches queue IDs (e.g. D71EF7AC80F8)
-queue_id='^[A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9]'
-
-usage="Invalid command line usage"
-
-if [ -z $1 ]; then
- echo $usage
- exit $e_unknown
-fi
-
-while getopts ":w:c:" options
-do
- case $options in
- w ) warning=$OPTARG ;;
- c ) critical=$OPTARG ;;
- * ) echo $usage
- exit $e_unknown ;;
- esac
-done
-
-# determine queue size
-qsize=$(mailq | egrep -c $queue_id)
-if [ -z $qsize ]
-then
- exit $e_unknown
-fi
-
-if [ $qsize -ge $critical ]; then
- retval=$e_critical
-elif [ $qsize -ge $warning ]; then
- retval=$e_warning
-elif [ $qsize -lt $warning ]; then
- retval=$e_ok
-fi
-
-echo "$qsize mail(s) in queue | mail_queue=$qsize"
-exit $retval
diff --git a/files/nagios/client/scripts/check_raid.py b/files/nagios/client/scripts/check_raid.py
deleted file mode 100755
index 48cddd9..0000000
--- a/files/nagios/client/scripts/check_raid.py
+++ /dev/null
@@ -1,45 +0,0 @@
-#!/usr/bin/env python
-#
-# very simple python script to parse out /proc/mdstat
-# and give results for nagios to monitor
-#
-
-import sys
-import string
-
-devices = []
-
-try:
- mdstat = string.split(open('/proc/mdstat').read(), '\n')
-except IOError:
- # seems we have no software raid on this machines
- sys.exit(0)
-
-error = ""
-i = 0
-for line in mdstat:
- if line[0:2] == 'md':
- device = string.split(line)[0]
- devices.append(device)
- status = string.split(mdstat[i+1])[3]
- if string.count(status, "_"):
- # see if we can figure out what's going on
- err = string.split(mdstat[i+2])
- msg = "device=%s status=%s" % (device, status)
- if len(err) > 0:
- msg = msg + " rebuild=%s" % err[0]
-
- if not error:
- error = msg
- else:
- error = error + ", " + msg
- i = i + 1
-
-if not error:
- print "DEVICES %s OK" % " ".join(devices)
- sys.exit(0)
-
-else:
- print error
- sys.exit(2)
-
diff --git a/handlers/restart_services.yml b/handlers/restart_services.yml
index 32c11e3..8b90f0f 100644
--- a/handlers/restart_services.yml
+++ b/handlers/restart_services.yml
@@ -56,9 +56,6 @@
- name: restart nfslock
action: service name=nfslock state=restarted
-- name: restart nrpe
- action: service name=nrpe state=restarted
-
- name: restart ntpd
action: service name=ntpd state=restarted
diff --git a/playbooks/groups/backup-server.yml b/playbooks/groups/backup-server.yml
index 0820d9f..2b30af4 100644
--- a/playbooks/groups/backup-server.yml
+++ b/playbooks/groups/backup-server.yml
@@ -16,6 +16,7 @@
roles:
- rkhunter
- denyhosts
+ - nagios_client
tasks:
- include: $tasks/hosts.yml
@@ -25,7 +26,6 @@
- include: $tasks/2fa_client.yml
- include: $tasks/motd.yml
- include: $tasks/sudo.yml
- - include: $tasks/nagios_client.yml
- include: $tasks/mysql_server.yml
- include: $tasks/bacula_server.yml
- include: $tasks/rdiff_backup_server.yml
diff --git a/playbooks/groups/badges-backend.yml b/playbooks/groups/badges-backend.yml
index 9d599c1..59b145e 100644
--- a/playbooks/groups/badges-backend.yml
+++ b/playbooks/groups/badges-backend.yml
@@ -32,6 +32,7 @@
roles:
- rkhunter
- denyhosts
+ - nagios_client
tasks:
- include: $tasks/hosts.yml
@@ -41,7 +42,6 @@
- include: $tasks/2fa_client.yml
- include: $tasks/motd.yml
- include: $tasks/sudo.yml
- - include: $tasks/nagios_client.yml
- include: $tasks/openvpn_client.yml
only_if: "'$env' != 'staging'"
- include: $tasks/fedmsg_base.yml
diff --git a/playbooks/groups/badges-web.yml b/playbooks/groups/badges-web.yml
index 4fddc4e..6c33548 100644
--- a/playbooks/groups/badges-web.yml
+++ b/playbooks/groups/badges-web.yml
@@ -35,6 +35,7 @@
roles:
- rkhunter
- denyhosts
+ - nagios_client
tasks:
- include: $tasks/hosts.yml
@@ -44,7 +45,6 @@
- include: $tasks/2fa_client.yml
- include: $tasks/motd.yml
- include: $tasks/sudo.yml
- - include: $tasks/nagios_client.yml
- include: $tasks/openvpn_client.yml
only_if: "'$env' != 'staging'"
- include: $tasks/fedmsg_base.yml
diff --git a/playbooks/groups/beaker.yml b/playbooks/groups/beaker.yml
index 43606c1..5ec502e 100644
--- a/playbooks/groups/beaker.yml
+++ b/playbooks/groups/beaker.yml
@@ -31,6 +31,7 @@
roles:
- rkhunter
- denyhosts
+ - nagios_client
tasks:
# this is how you include other task lists
@@ -42,7 +43,6 @@
- include: $tasks/collectd/client.yml
- include: $tasks/motd.yml
- include: $tasks/sudo.yml
- - include: $tasks/nagios_client.yml
handlers:
- include: $handlers/restart_services.yml
diff --git a/playbooks/groups/gallery.yml b/playbooks/groups/gallery.yml
index 141e613..152455a 100644
--- a/playbooks/groups/gallery.yml
+++ b/playbooks/groups/gallery.yml
@@ -32,6 +32,7 @@
roles:
- rkhunter
- denyhosts
+ - nagios_client
tasks:
- include: $tasks/hosts.yml
@@ -41,7 +42,6 @@
- include: $tasks/2fa_client.yml
- include: $tasks/motd.yml
- include: $tasks/sudo.yml
- - include: $tasks/nagios_client.yml
- include: $tasks/fedmsg_base.yml
- include: $tasks/apache.yml
diff --git a/playbooks/groups/kernel-qa.yml b/playbooks/groups/kernel-qa.yml
index a99e3b5..b78c67e 100644
--- a/playbooks/groups/kernel-qa.yml
+++ b/playbooks/groups/kernel-qa.yml
@@ -15,6 +15,7 @@
roles:
- rkhunter
- denyhosts
+ - nagios_client
tasks:
# this is how you include other task lists
@@ -25,7 +26,6 @@
- include: $tasks/2fa_client.yml
- include: $tasks/motd.yml
- include: $tasks/sudo.yml
- - include: $tasks/nagios_client.yml
handlers:
diff --git a/playbooks/groups/keyserver.yml b/playbooks/groups/keyserver.yml
index 9fc5066..367a189 100644
--- a/playbooks/groups/keyserver.yml
+++ b/playbooks/groups/keyserver.yml
@@ -32,6 +32,7 @@
roles:
- rkhunter
- denyhosts
+ - nagios_client
tasks:
- include: $tasks/hosts.yml
@@ -41,7 +42,6 @@
- include: $tasks/2fa_client.yml
- include: $tasks/motd.yml
- include: $tasks/sudo.yml
- - include: $tasks/nagios_client.yml
- include: $tasks/fedmsg_base.yml
- include: $tasks/apache.yml
- include: $tasks/keyserver.yml
diff --git a/playbooks/groups/koji-hub.yml b/playbooks/groups/koji-hub.yml
index 2ede558..fd077ce 100644
--- a/playbooks/groups/koji-hub.yml
+++ b/playbooks/groups/koji-hub.yml
@@ -33,6 +33,7 @@
roles:
- rkhunter
- denyhosts
+ - nagios_client
tasks:
- include: $tasks/hosts.yml
@@ -42,7 +43,6 @@
- include: $tasks/2fa_client.yml
- include: $tasks/motd.yml
- include: $tasks/sudo.yml
- - include: $tasks/nagios_client.yml
- include: $tasks/collectd/client.yml
- include: $tasks/koji/koji_hub.yml
diff --git a/playbooks/groups/mailman.yml b/playbooks/groups/mailman.yml
index c90f1c5..345aa37 100644
--- a/playbooks/groups/mailman.yml
+++ b/playbooks/groups/mailman.yml
@@ -31,6 +31,7 @@
roles:
- rkhunter
- denyhosts
+ - nagios_client
tasks:
# this is how you include other task lists
@@ -42,7 +43,6 @@
- include: $tasks/collectd/client.yml
- include: $tasks/motd.yml
- include: $tasks/sudo.yml
- - include: $tasks/nagios_client.yml
handlers:
- include: $handlers/restart_services.yml
diff --git a/playbooks/groups/mirrorlist.yml b/playbooks/groups/mirrorlist.yml
index e28e034..8d5b2f8 100644
--- a/playbooks/groups/mirrorlist.yml
+++ b/playbooks/groups/mirrorlist.yml
@@ -41,6 +41,7 @@
roles:
- rkhunter
- denyhosts
+ - nagios_client
tasks:
# this is how you include other task lists
@@ -53,7 +54,6 @@
- include: $tasks/openvpn_client.yml
- include: $tasks/motd.yml
- include: $tasks/sudo.yml
- - include: $tasks/nagios_client.yml
- include: $tasks/apache.yml
- include: $tasks/mod_wsgi.yml
- include: $tasks/geoip.yml
diff --git a/playbooks/groups/postgresl-server.yml b/playbooks/groups/postgresl-server.yml
index 92fdbde..8e8822b 100644
--- a/playbooks/groups/postgresl-server.yml
+++ b/playbooks/groups/postgresl-server.yml
@@ -33,6 +33,7 @@
roles:
- rkhunter
- denyhosts
+ - nagios_client
tasks:
- include: $tasks/hosts.yml
@@ -42,7 +43,6 @@
- include: $tasks/2fa_client.yml
- include: $tasks/motd.yml
- include: $tasks/sudo.yml
- - include: $tasks/nagios_client.yml
- include: $tasks/collectd/client.yml
- include: $tasks/postgresql_server.yml
diff --git a/playbooks/groups/releng.yml b/playbooks/groups/releng.yml
index 649cfbb..f642840 100644
--- a/playbooks/groups/releng.yml
+++ b/playbooks/groups/releng.yml
@@ -31,10 +31,12 @@
- ${private}/vars.yml
- ${vars}/${ansible_distribution}.yml
+ roles:
+ - nagios_client
+
tasks:
- include: $tasks/koji/releng_config.yml
- include: $tasks/motd.yml
- - include: $tasks/nagios_client.yml
handlers:
- include: $handlers/restart_services.yml
diff --git a/playbooks/groups/taskbot.yml b/playbooks/groups/taskbot.yml
index 3d57356..7641266 100644
--- a/playbooks/groups/taskbot.yml
+++ b/playbooks/groups/taskbot.yml
@@ -31,6 +31,7 @@
roles:
- rkhunter
- denyhosts
+ - nagios_client
tasks:
# this is how you include other task lists
@@ -42,7 +43,6 @@
- include: $tasks/collectd/client.yml
- include: $tasks/motd.yml
- include: $tasks/sudo.yml
- - include: $tasks/nagios_client.yml
handlers:
- include: $handlers/restart_services.yml
diff --git a/playbooks/groups/virthost.yml b/playbooks/groups/virthost.yml
index 24761a4..763002b 100644
--- a/playbooks/groups/virthost.yml
+++ b/playbooks/groups/virthost.yml
@@ -15,6 +15,7 @@
roles:
- rkhunter
- denyhosts
+ - nagios_client
tasks:
- include: $tasks/hosts.yml
@@ -24,7 +25,6 @@
- include: $tasks/2fa_client.yml
- include: $tasks/motd.yml
- include: $tasks/sudo.yml
- - include: $tasks/nagios_client.yml
- include: $tasks/collectd/client.yml
- include: $tasks/virthost.yml
diff --git a/roles/nagios_client/files/check_cron.cfg b/roles/nagios_client/files/check_cron.cfg
new file mode 100644
index 0000000..e01f407
--- /dev/null
+++ b/roles/nagios_client/files/check_cron.cfg
@@ -0,0 +1 @@
+command[check_cron]=/usr/lib64/nagios/plugins/check_procs -c 1:10 -C 'crond' -u root
diff --git a/roles/nagios_client/files/check_disk.cfg b/roles/nagios_client/files/check_disk.cfg
new file mode 100644
index 0000000..d5d3290
--- /dev/null
+++ b/roles/nagios_client/files/check_disk.cfg
@@ -0,0 +1,2 @@
+command[check_disk_/]=/usr/lib64/nagios/plugins/check_disk -w 15% -c 10% -p /
+command[check_disk_/boot]=/usr/lib64/nagios/plugins/check_disk -w 15% -c 10% -p /boot
diff --git a/roles/nagios_client/files/check_lock.cfg b/roles/nagios_client/files/check_lock.cfg
new file mode 100644
index 0000000..9525f9f
--- /dev/null
+++ b/roles/nagios_client/files/check_lock.cfg
@@ -0,0 +1 @@
+command[check_lock]=/usr/lib64/nagios/plugins/check_lock
diff --git a/roles/nagios_client/files/check_mirrorlist_cache.cfg b/roles/nagios_client/files/check_mirrorlist_cache.cfg
new file mode 100644
index 0000000..bd4b171
--- /dev/null
+++ b/roles/nagios_client/files/check_mirrorlist_cache.cfg
@@ -0,0 +1 @@
+command[check_mirrorlist_cache]=/usr/lib64/nagios/plugins/check_file_age -w 14400 -c 129600 -f /var/lib/mirrormanager/mirrorlist_cache.pkl
diff --git a/roles/nagios_client/files/check_postfix_queue.cfg b/roles/nagios_client/files/check_postfix_queue.cfg
new file mode 100644
index 0000000..5574698
--- /dev/null
+++ b/roles/nagios_client/files/check_postfix_queue.cfg
@@ -0,0 +1 @@
+command[check_postfix_queue]=/usr/lib64/nagios/plugins/check_postfix_queue -w 2 -c 5
diff --git a/roles/nagios_client/files/check_raid.cfg b/roles/nagios_client/files/check_raid.cfg
new file mode 100644
index 0000000..5c15d45
--- /dev/null
+++ b/roles/nagios_client/files/check_raid.cfg
@@ -0,0 +1 @@
+command[check_raid]=/usr/lib64/nagios/plugins/check_raid.py
diff --git a/roles/nagios_client/files/check_swap.cfg b/roles/nagios_client/files/check_swap.cfg
new file mode 100644
index 0000000..bc4f19d
--- /dev/null
+++ b/roles/nagios_client/files/check_swap.cfg
@@ -0,0 +1 @@
+command[check_swap]=/usr/lib64/nagios/plugins/check_swap -w 15% -c 10%
diff --git a/roles/nagios_client/files/nrpe.cfg b/roles/nagios_client/files/nrpe.cfg
new file mode 100644
index 0000000..6933f78
--- /dev/null
+++ b/roles/nagios_client/files/nrpe.cfg
@@ -0,0 +1,223 @@
+#############################################################################
+# Sample NRPE Config File
+# Written by: Ethan Galstad (nagios at nagios.org)
+#
+# Last Modified: 11-23-2007
+#
+# NOTES:
+# This is a sample configuration file for the NRPE daemon. It needs to be
+# located on the remote host that is running the NRPE daemon, not the host
+# from which the check_nrpe client is being executed.
+#############################################################################
+
+
+# LOG FACILITY
+# The syslog facility that should be used for logging purposes.
+
+log_facility=daemon
+
+
+
+# PID FILE
+# The name of the file in which the NRPE daemon should write it's process ID
+# number. The file is only written if the NRPE daemon is started by the root
+# user and is running in standalone mode.
+
+pid_file=/var/run/nrpe/nrpe.pid
+
+
+
+# PORT NUMBER
+# Port number we should wait for connections on.
+# NOTE: This must be a non-priviledged port (i.e. > 1024).
+# NOTE: This option is ignored if NRPE is running under either inetd or xinetd
+
+server_port=5666
+
+
+
+# SERVER ADDRESS
+# Address that nrpe should bind to in case there are more than one interface
+# and you do not want nrpe to bind on all interfaces.
+# NOTE: This option is ignored if NRPE is running under either inetd or xinetd
+
+#server_address=127.0.0.1
+
+
+
+# NRPE USER
+# This determines the effective user that the NRPE daemon should run as.
+# You can either supply a username or a UID.
+#
+# NOTE: This option is ignored if NRPE is running under either inetd or xinetd
+
+nrpe_user=nrpe
+
+
+
+# NRPE GROUP
+# This determines the effective group that the NRPE daemon should run as.
+# You can either supply a group name or a GID.
+#
+# NOTE: This option is ignored if NRPE is running under either inetd or xinetd
+
+nrpe_group=nrpe
+
+
+
+# ALLOWED HOST ADDRESSES
+# This is an optional comma-delimited list of IP address or hostnames
+# that are allowed to talk to the NRPE daemon. Network addresses with a bit mask
+# (i.e. 192.168.1.0/24) are also supported. Hostname wildcards are not currently
+# supported.
+#
+# Note: The daemon only does rudimentary checking of the client's IP
+# address. I would highly recommend adding entries in your /etc/hosts.allow
+# file to allow only the specified host to connect to the port
+# you are running this daemon on.
+#
+# NOTE: This option is ignored if NRPE is running under either inetd or xinetd
+
+
+allowed_hosts=10.5.126.41,192.168.1.10,192.168.1.20,209.132.181.35
+
+
+
+# COMMAND ARGUMENT PROCESSING
+# This option determines whether or not the NRPE daemon will allow clients
+# to specify arguments to commands that are executed. This option only works
+# if the daemon was configured with the --enable-command-args configure script
+# option.
+#
+# *** ENABLING THIS OPTION IS A SECURITY RISK! ***
+# Read the SECURITY file for information on some of the security implications
+# of enabling this variable.
+#
+# Values: 0=do not allow arguments, 1=allow command arguments
+
+dont_blame_nrpe=0
+
+
+
+# COMMAND PREFIX
+# This option allows you to prefix all commands with a user-defined string.
+# A space is automatically added between the specified prefix string and the
+# command line from the command definition.
+#
+# *** THIS EXAMPLE MAY POSE A POTENTIAL SECURITY RISK, SO USE WITH CAUTION! ***
+# Usage scenario:
+# Execute restricted commmands using sudo. For this to work, you need to add
+# the nagios user to your /etc/sudoers. An example entry for alllowing
+# execution of the plugins from might be:
+#
+# nagios ALL=(ALL) NOPASSWD: /usr/lib/nagios/plugins/
+#
+# This lets the nagios user run all commands in that directory (and only them)
+# without asking for a password. If you do this, make sure you don't give
+# random users write access to that directory or its contents!
+
+# command_prefix=/usr/bin/sudo
+
+
+
+# DEBUGGING OPTION
+# This option determines whether or not debugging messages are logged to the
+# syslog facility.
+# Values: 0=debugging off, 1=debugging on
+
+debug=0
+
+
+
+# COMMAND TIMEOUT
+# This specifies the maximum number of seconds that the NRPE daemon will
+# allow plugins to finish executing before killing them off.
+
+command_timeout=60
+
+
+
+# CONNECTION TIMEOUT
+# This specifies the maximum number of seconds that the NRPE daemon will
+# wait for a connection to be established before exiting. This is sometimes
+# seen where a network problem stops the SSL being established even though
+# all network sessions are connected. This causes the nrpe daemons to
+# accumulate, eating system resources. Do not set this too low.
+
+connection_timeout=300
+
+
+
+# WEEK RANDOM SEED OPTION
+# This directive allows you to use SSL even if your system does not have
+# a /dev/random or /dev/urandom (on purpose or because the necessary patches
+# were not applied). The random number generator will be seeded from a file
+# which is either a file pointed to by the environment valiable $RANDFILE
+# or $HOME/.rnd. If neither exists, the pseudo random number generator will
+# be initialized and a warning will be issued.
+# Values: 0=only seed from /dev/[u]random, 1=also seed from weak randomness
+
+#allow_weak_random_seed=1
+
+
+
+# INCLUDE CONFIG FILE
+# This directive allows you to include definitions from an external config file.
+
+#include=<somefile.cfg>
+
+
+
+# INCLUDE CONFIG DIRECTORY
+# This directive allows you to include definitions from config files (with a
+# .cfg extension) in one or more directories (with recursion).
+
+include_dir=/etc/nrpe.d/
+
+
+
+# COMMAND DEFINITIONS
+# Command definitions that this daemon will run. Definitions
+# are in the following format:
+#
+# command[<command_name>]=<command_line>
+#
+# When the daemon receives a request to return the results of <command_name>
+# it will execute the command specified by the <command_line> argument.
+#
+# Unlike Nagios, the command line cannot contain macros - it must be
+# typed exactly as it should be executed.
+#
+# Note: Any plugins that are used in the command lines must reside
+# on the machine that this daemon is running on! The examples below
+# assume that you have plugins installed in a /usr/local/nagios/libexec
+# directory. Also note that you will have to modify the definitions below
+# to match the argument format the plugins expect. Remember, these are
+# examples only!
+
+
+# The following examples use hardcoded command arguments...
+
+command[check_users]=/usr/lib64/nagios/plugins/check_users -w 5 -c 10
+command[check_load]=/usr/lib64/nagios/plugins/check_load -w 15,10,5 -c 30,25,20
+command[check_hda1]=/usr/lib64/nagios/plugins/check_disk -w 20% -c 10% -p /dev/hda1
+command[check_zombie_procs]=/usr/lib64/nagios/plugins/check_procs -w 5 -c 10 -s Z
+command[check_total_procs]=/usr/lib64/nagios/plugins/check_procs -w {{ nrpe_procs_warn }} -c {{ nrpe_procs_crit }}
+
+
+# The following examples allow user-supplied arguments and can
+# only be used if the NRPE daemon was compiled with support for
+# command arguments *AND* the dont_blame_nrpe directive in this
+# config file is set to '1'. This poses a potential security risk, so
+# make sure you read the SECURITY file before doing this.
+
+#command[check_users]=/usr/lib64/nagios/plugins/check_users -w $ARG1$ -c $ARG2$
+#command[check_load]=/usr/lib64/nagios/plugins/check_load -w $ARG1$ -c $ARG2$
+#command[check_disk]=/usr/lib64/nagios/plugins/check_disk -w $ARG1$ -c $ARG2$ -p $ARG3$
+#command[check_procs]=/usr/lib64/nagios/plugins/check_procs -w $ARG1$ -c $ARG2$ -s $ARG3$
+
+
+# NEVER ADD ANYTHING HERE - ANY ENTRIES TO NRPE SHOULD BE in .cfg files in /etc/nrpe.d/
+
+# NEVER NEVER NEVER
+#
diff --git a/roles/nagios_client/files/scripts/check_lock b/roles/nagios_client/files/scripts/check_lock
new file mode 100755
index 0000000..1a58e95
--- /dev/null
+++ b/roles/nagios_client/files/scripts/check_lock
@@ -0,0 +1,17 @@
+#!/usr/bin/python
+
+import fcntl
+import sys
+
+try:
+ f = open('/mnt/koji/.nagios_test', 'r')
+ f.close()
+ f = open('/mnt/koji/.nagios_test', 'w')
+except IOError:
+ print "Could not create file"
+ sys.exit(2)
+
+fcntl.flock(f, fcntl.LOCK_EX)
+f.close()
+print "File Locked Successfully"
+sys.exit(0)
diff --git a/roles/nagios_client/files/scripts/check_postfix_queue b/roles/nagios_client/files/scripts/check_postfix_queue
new file mode 100755
index 0000000..44ab444
--- /dev/null
+++ b/roles/nagios_client/files/scripts/check_postfix_queue
@@ -0,0 +1,49 @@
+#!/bin/bash
+#
+# 19-07-2010
+# Author: Cherwin Nooitmeer <cherwin at gmail.com>
+#
+
+# exit codes
+e_ok=0
+e_warning=1
+e_critical=2
+e_unknown=3
+
+# regular expression that matches queue IDs (e.g. D71EF7AC80F8)
+queue_id='^[A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9]'
+
+usage="Invalid command line usage"
+
+if [ -z $1 ]; then
+ echo $usage
+ exit $e_unknown
+fi
+
+while getopts ":w:c:" options
+do
+ case $options in
+ w ) warning=$OPTARG ;;
+ c ) critical=$OPTARG ;;
+ * ) echo $usage
+ exit $e_unknown ;;
+ esac
+done
+
+# determine queue size
+qsize=$(mailq | egrep -c $queue_id)
+if [ -z $qsize ]
+then
+ exit $e_unknown
+fi
+
+if [ $qsize -ge $critical ]; then
+ retval=$e_critical
+elif [ $qsize -ge $warning ]; then
+ retval=$e_warning
+elif [ $qsize -lt $warning ]; then
+ retval=$e_ok
+fi
+
+echo "$qsize mail(s) in queue | mail_queue=$qsize"
+exit $retval
diff --git a/roles/nagios_client/files/scripts/check_raid.py b/roles/nagios_client/files/scripts/check_raid.py
new file mode 100755
index 0000000..48cddd9
--- /dev/null
+++ b/roles/nagios_client/files/scripts/check_raid.py
@@ -0,0 +1,45 @@
+#!/usr/bin/env python
+#
+# very simple python script to parse out /proc/mdstat
+# and give results for nagios to monitor
+#
+
+import sys
+import string
+
+devices = []
+
+try:
+ mdstat = string.split(open('/proc/mdstat').read(), '\n')
+except IOError:
+ # seems we have no software raid on this machines
+ sys.exit(0)
+
+error = ""
+i = 0
+for line in mdstat:
+ if line[0:2] == 'md':
+ device = string.split(line)[0]
+ devices.append(device)
+ status = string.split(mdstat[i+1])[3]
+ if string.count(status, "_"):
+ # see if we can figure out what's going on
+ err = string.split(mdstat[i+2])
+ msg = "device=%s status=%s" % (device, status)
+ if len(err) > 0:
+ msg = msg + " rebuild=%s" % err[0]
+
+ if not error:
+ error = msg
+ else:
+ error = error + ", " + msg
+ i = i + 1
+
+if not error:
+ print "DEVICES %s OK" % " ".join(devices)
+ sys.exit(0)
+
+else:
+ print error
+ sys.exit(2)
+
diff --git a/roles/nagios_client/handlers/main.yml b/roles/nagios_client/handlers/main.yml
new file mode 100644
index 0000000..1086c3d
--- /dev/null
+++ b/roles/nagios_client/handlers/main.yml
@@ -0,0 +1,3 @@
+---
+- name: restart nrpe
+ action: service name=nrpe state=restarted
diff --git a/roles/nagios_client/tasks/main.yml b/roles/nagios_client/tasks/main.yml
new file mode 100644
index 0000000..5888ede
--- /dev/null
+++ b/roles/nagios_client/tasks/main.yml
@@ -0,0 +1,63 @@
+# nagios-client/nrpe
+
+---
+# install pkgs:
+- name: install nagios client pkgs
+ yum: name=$item state=installed
+ with_items:
+ - nrpe
+ - nagios-plugins
+ - nagios-plugins-disk
+ - nagios-plugins-file_age
+ - nagios-plugins-users
+ - nagios-plugins-procs
+ - nagios-plugins-swap
+ - nagios-plugins-load
+ - nagios-plugins-ping
+ tags:
+ - packages
+
+- name: install local nrpe check scripts that are not packaged
+ copy: src=scripts/$item dest=/usr/lib64/nagios/plugins/$item mode=0755 owner=nagios group=nagios
+ with_items:
+ - check_postfix_queue
+ - check_raid.py
+ - check_lock
+
+# create dirs
+# puppet used to make /var/spool/nagios (owned by nagios.nagios) mode 750
+# and /usr/lib/nagios/plugins (owned by root) mode 755 - but we don't know WHY
+# then stuff it with plugins from the plugins dir in the nagios module
+# then we symlinked that to /usr/lib64/nagios/plugins
+# it was a nightmare - don't do that - my ghost will haunt you if you do
+# skvidal 2013-05-21
+
+
+# FIXME? figure out nrpe selinux policy of DOOM is needed
+
+- name: /etc/nagios/nrpe.cfg
+ template: src=nrpe.cfg dest=/etc/nagios/nrpe.cfg
+ notify:
+ - restart nrpe
+ tags:
+ - config
+
+- name: install nrpe client configs
+ template: src=$item dest=/etc/nrpe.d/$item
+ with_items:
+ - check_mirrorlist_cache.cfg
+ - check_raid.cfg
+ - check_cron.cfg
+ - check_disk.cfg
+ - check_swap.cfg
+ - check_postfix_queue.cfg
+ - check_lock.cfg
+ notify:
+ - restart nrpe
+ tags:
+ - config
+
+- name: nrpe service start
+ service: name=nrpe state=running enabled=true
+ tags:
+ - service
diff --git a/tasks/nagios_client.yml b/tasks/nagios_client.yml
deleted file mode 100644
index 56093f0..0000000
--- a/tasks/nagios_client.yml
+++ /dev/null
@@ -1,63 +0,0 @@
-# nagios-client/nrpe
-
----
-# install pkgs:
-- name: install nagios client pkgs
- yum: name=$item state=installed
- with_items:
- - nrpe
- - nagios-plugins
- - nagios-plugins-disk
- - nagios-plugins-file_age
- - nagios-plugins-users
- - nagios-plugins-procs
- - nagios-plugins-swap
- - nagios-plugins-load
- - nagios-plugins-ping
- tags:
- - packages
-
-- name: install local nrpe check scripts that are not packaged
- copy: src=$files/nagios/client/scripts/$item dest=/usr/lib64/nagios/plugins/$item mode=0755 owner=nagios group=nagios
- with_items:
- - check_postfix_queue
- - check_raid.py
- - check_lock
-
-# create dirs
-# puppet used to make /var/spool/nagios (owned by nagios.nagios) mode 750
-# and /usr/lib/nagios/plugins (owned by root) mode 755 - but we don't know WHY
-# then stuff it with plugins from the plugins dir in the nagios module
-# then we symlinked that to /usr/lib64/nagios/plugins
-# it was a nightmare - don't do that - my ghost will haunt you if you do
-# skvidal 2013-05-21
-
-
-# FIXME? figure out nrpe selinux policy of DOOM is needed
-
-- name: /etc/nagios/nrpe.cfg
- template: src=$files/nagios/client/nrpe.cfg dest=/etc/nagios/nrpe.cfg
- notify:
- - restart nrpe
- tags:
- - config
-
-- name: install nrpe client configs
- template: src=$files/nagios/client/$item dest=/etc/nrpe.d/$item
- with_items:
- - check_mirrorlist_cache.cfg
- - check_raid.cfg
- - check_cron.cfg
- - check_disk.cfg
- - check_swap.cfg
- - check_postfix_queue.cfg
- - check_lock.cfg
- notify:
- - restart nrpe
- tags:
- - config
-
-- name: nrpe service start
- service: name=nrpe state=running enabled=true
- tags:
- - service
--
1.8.3.1
More information about the infrastructure
mailing list