]> birchwood-abbey.net Git - Network.git/commitdiff
Add Munin and NAGIOS monitoring for Ord Mantell.
authorMatt Birkholz <matt@birchwood-abbey.net>
Sun, 18 Jan 2026 23:29:40 +0000 (16:29 -0700)
committerMatt Birkholz <matt@birchwood-abbey.net>
Sun, 18 Jan 2026 23:29:40 +0000 (16:29 -0700)
README.org
private_ex/vars-abbey.yml
roles_t/abbey-core/tasks/main.yml
roles_t/abbey-core/templates/nagios-ord-mantell.cfg [new file with mode: 0644]

index 7dfdfc44787ac4d8fb4e9389042a5ba01d26707a..cb49a9bcb61315930fa7e0ebfc472531c1518a2f 100644 (file)
@@ -1417,10 +1417,11 @@ fi
 
 *** Configure NAGIOS Monitoring of The Cloister
 
-The abbey adds monitoring for more servers: Dantooine and Kessel.
-They are ~abbey-cloister~ servers, so they are configured as small
-institute ~campus~ servers, like Gate, with an NRPE (a NAGIOS Remote
-Plugin Executor) server and an ~inst_sensors~ command.
+The abbey adds monitoring for more servers: Dantooine, Kessel and Ord
+Mantell.  They are ~abbey-cloister~ servers, so they are configured as
+small institute ~campus~ servers, like Gate, with an NRPE (a NAGIOS
+Remote Plugin Executor) server and an ~inst_sensors~ or
+~abbey_pisensors~ command.
 
 The configurations for these servers are very similar to Gate's, but
 are idiosyncratically in flux.
@@ -1436,6 +1437,7 @@ included in =private/vars-abbey.yml=.
 ---
 dantooine_addr:             10.84.138.8
 kessel_addr:                10.84.138.10
+ord_mantell_addr:           10.84.138.12
 #+END_SRC
 
 **** Install NAGIOS Configurations
@@ -1450,7 +1452,7 @@ The following task installs each host's NAGIOS configuration.
   template:
     src: nagios-{{ item }}.cfg
     dest: /etc/nagios4/conf.d/{{ item }}.cfg
-  loop: [ dantooine, kessel ]
+  loop: [ dantooine, kessel, ord-mantell ]
   notify: Reload NAGIOS4.
 #+END_SRC
 
@@ -1567,6 +1569,59 @@ define service {
 }
 #+END_SRC
 
+**** NAGIOS Monitoring of Ord-Mantell
+
+#+CAPTION: [[file:roles_t/abbey-core/templates/nagios-ord-mantell.cfg][=roles_t/abbey-core/templates/nagios-ord-mantell.cfg=]]
+#+BEGIN_SRC conf :tangle roles_t/abbey-core/templates/nagios-ord-mantell.cfg
+define host {
+    use                     linux-server
+    host_name               ord-mantell
+    address                 {{ ord_mantell_addr }}
+}
+
+define service {
+    use                     generic-service
+    host_name               ord-mantell
+    service_description     Root Partition
+    check_command           check_nrpe!inst_root
+}
+
+# define service {
+#     use                     generic-service
+#     host_name               ord-mantell
+#     service_description     Current Load
+#     check_command           check_nrpe!check_load
+# }
+
+define service {
+    use                     generic-service
+    host_name               ord-mantell
+    service_description     Zombie Processes
+    check_command           check_nrpe!check_zombie_procs
+}
+
+# define service {
+#     use                     generic-service
+#     host_name               ord-mantell
+#     service_description     Total Processes
+#     check_command           check_nrpe!check_total_procs
+# }
+
+define service {
+    use                     generic-service
+    host_name               ord-mantell
+    service_description     Swap Usage
+    check_command           check_nrpe!inst_swap
+}
+
+define service {
+    use                     generic-service
+    host_name               ord-mantell
+    service_description     Temperature Sensors
+    check_command           check_nrpe!abbey_pisensors
+}
+#+END_SRC
+
 ** Install Munin
 
 The abbey is experimenting with Munin.  NAGIOS is all about notifying
@@ -1620,6 +1675,9 @@ trends in resource usage.
 
       [kessel.birchwood.private]
           address {{ kessel_addr }}
+
+      [ord-mantell.birchwood.private]
+          address {{ ord_mantell_addr }}
     dest: /etc/munin/munin-conf.d/zzz-site.cfg
   notify: Restart Munin.
 
index 036e5c5a7873a21adeff88dcffcbea198034b212..9ddfe89823c14b8d95fc83936bb8ce2dd8e01e43 100644 (file)
@@ -1,3 +1,4 @@
 ---
 dantooine_addr:             10.84.138.8
 kessel_addr:                10.84.138.10
+ord_mantell_addr:           10.84.138.12
index 316f850ff96b149fb2b3d44b21e0a631b4491495..5d4f04f70c197f2848884906750e3338e028c7ce 100644 (file)
   template:
     src: nagios-{{ item }}.cfg
     dest: /etc/nagios4/conf.d/{{ item }}.cfg
-  loop: [ dantooine, kessel ]
+  loop: [ dantooine, kessel, ord-mantell ]
   notify: Reload NAGIOS4.
 
 - name: Install Munin.
 
       [kessel.birchwood.private]
           address {{ kessel_addr }}
+
+      [ord-mantell.birchwood.private]
+          address {{ ord_mantell_addr }}
     dest: /etc/munin/munin-conf.d/zzz-site.cfg
   notify: Restart Munin.
 
diff --git a/roles_t/abbey-core/templates/nagios-ord-mantell.cfg b/roles_t/abbey-core/templates/nagios-ord-mantell.cfg
new file mode 100644 (file)
index 0000000..bf3e7d8
--- /dev/null
@@ -0,0 +1,47 @@
+define host {
+    use                     linux-server
+    host_name               ord-mantell
+    address                 {{ ord_mantell_addr }}
+}
+
+define service {
+    use                     generic-service
+    host_name               ord-mantell
+    service_description     Root Partition
+    check_command           check_nrpe!inst_root
+}
+
+# define service {
+#     use                     generic-service
+#     host_name               ord-mantell
+#     service_description     Current Load
+#     check_command           check_nrpe!check_load
+# }
+
+define service {
+    use                     generic-service
+    host_name               ord-mantell
+    service_description     Zombie Processes
+    check_command           check_nrpe!check_zombie_procs
+}
+
+# define service {
+#     use                     generic-service
+#     host_name               ord-mantell
+#     service_description     Total Processes
+#     check_command           check_nrpe!check_total_procs
+# }
+
+define service {
+    use                     generic-service
+    host_name               ord-mantell
+    service_description     Swap Usage
+    check_command           check_nrpe!inst_swap
+}
+
+define service {
+    use                     generic-service
+    host_name               ord-mantell
+    service_description     Temperature Sensors
+    check_command           check_nrpe!abbey_pisensors
+}