aboutsummaryrefslogtreecommitdiff
path: root/modules/private
diff options
context:
space:
mode:
authorIsmaël Bouya <ismael.bouya@normalesup.org>2019-12-02 01:33:08 +0100
committerIsmaël Bouya <ismael.bouya@normalesup.org>2019-12-02 01:33:08 +0100
commiteb071dd42518cb40d629e5bde29c6aed72e4d4df (patch)
treef9a109801d540ef8fc4c1b0656436f560ad1f6b7 /modules/private
parent9f2025235d888eb4a7822024a5fad2e288388814 (diff)
downloadNix-eb071dd42518cb40d629e5bde29c6aed72e4d4df.tar.gz
Nix-eb071dd42518cb40d629e5bde29c6aed72e4d4df.tar.zst
Nix-eb071dd42518cb40d629e5bde29c6aed72e4d4df.zip
Use nix expressions to build monitoring list
Diffstat (limited to 'modules/private')
-rw-r--r--modules/private/monitoring/conf/contacts.cfg41
-rw-r--r--modules/private/monitoring/conf/hosts.cfg32
-rw-r--r--modules/private/monitoring/conf/local_services.cfg68
-rw-r--r--modules/private/monitoring/conf/notify.cfg8
-rw-r--r--modules/private/monitoring/conf/objects.cfg84
-rw-r--r--modules/private/monitoring/conf/services.cfg27
-rw-r--r--modules/private/monitoring/conf/specific_backup-2.cfg36
-rw-r--r--modules/private/monitoring/conf/specific_eldiron.cfg29
-rw-r--r--modules/private/monitoring/conf/timeperiods.cfg15
-rw-r--r--modules/private/monitoring/default.nix56
-rw-r--r--modules/private/monitoring/objects_backup-2.nix30
-rw-r--r--modules/private/monitoring/objects_common.nix179
-rw-r--r--modules/private/monitoring/objects_eldiron.nix15
-rw-r--r--modules/private/monitoring/to_objects.nix67
14 files changed, 311 insertions, 376 deletions
diff --git a/modules/private/monitoring/conf/contacts.cfg b/modules/private/monitoring/conf/contacts.cfg
deleted file mode 100644
index b6ea84d..0000000
--- a/modules/private/monitoring/conf/contacts.cfg
+++ /dev/null
@@ -1,41 +0,0 @@
1# vim: filetype=nagios
2
3# CONTACT GROUPS
4define contactgroup {
5 contactgroup_name admins
6 alias Naemon Administrators
7# members immae
8}
9
10# No contact, we go through master
11# define contact {
12# contact_name immae
13# alias Immae
14# use generic-contact
15# email xxxxxxxxxxxxxxxx
16# }
17#
18# define contact {
19# name generic-contact
20# host_notification_commands notify-host-by-email
21# host_notification_options d,u,r,f,s
22# host_notification_period 24x7
23# register 0
24# service_notification_commands notify-service-by-email
25# service_notification_options w,u,c,r,f,s
26# service_notification_period 24x7
27# }
28#
29# define command {
30# command_name notify-host-by-email
31# command_line SERVICENOTIFICATIONID="$SERVICENOTIFICATIONID$" HOSTSTATE="$HOSTSTATE$" HOSTOUTPUT="$HOSTOUTPUT$" $USER2$/notify_by_email host "$NOTIFICATIONTYPE$" "$HOSTALIAS$" "$LONGDATETIME$" "$CONTACTEMAIL$" $OVE
32# #$OVE is to force naemon to run via shell instead of execve which fails here
33# }
34#
35# # 'notify-service-by-email' command definition
36# define command {
37# command_name notify-service-by-email
38# command_line SERVICENOTIFICATIONID="$SERVICENOTIFICATIONID$" SERVICEDESC="$SERVICEDESC$" SERVICESTATE="$SERVICESTATE$" SERVICEOUTPUT="$SERVICEOUTPUT$" $USER2$/notify_by_email service "$NOTIFICATIONTYPE$" "$HOSTALIAS$" "$LONGDATETIME$" "$CONTACTEMAIL$" $OVE
39# # command_line sudo /usr/bin/strace -o /tmp/foo -vf -s 256 -u naemon $USER2$/notify_by_email
40# #$OVE is to force naemon to run via shell instead of execve which fails here
41# }
diff --git a/modules/private/monitoring/conf/hosts.cfg b/modules/private/monitoring/conf/hosts.cfg
deleted file mode 100644
index d903b0a..0000000
--- a/modules/private/monitoring/conf/hosts.cfg
+++ /dev/null
@@ -1,32 +0,0 @@
1# vim: filetype=nagios
2
3define host {
4 name generic-host
5 event_handler_enabled 1
6 flap_detection_enabled 1
7 notification_period 24x7
8 notifications_enabled 1
9 process_perf_data 1
10 register 0
11 retain_nonstatus_information 1
12 retain_status_information 1
13}
14
15define host {
16 name linux-server
17 use generic-host
18 check_command check-host-alive
19 check_interval 5
20 check_period 24x7
21 contact_groups admins
22 max_check_attempts 10
23 notification_interval 120
24 notification_options d,u,r,f
25 register 0
26 retry_interval 1
27}
28
29define command {
30 command_name check-host-alive
31 command_line $USER1$/check_ping -H $HOSTADDRESS$ -w 3000.0,80% -c 5000.0,100% -p 5
32}
diff --git a/modules/private/monitoring/conf/local_services.cfg b/modules/private/monitoring/conf/local_services.cfg
deleted file mode 100644
index 56bc8f6..0000000
--- a/modules/private/monitoring/conf/local_services.cfg
+++ /dev/null
@@ -1,68 +0,0 @@
1# vim: filetype=nagios
2
3# System usage
4define service {
5 service_description Size on root partition
6 use local-service
7 check_command check_local_disk!20%!10%!/
8}
9define command {
10 command_line $USER1$/check_disk -w $ARG1$ -c $ARG2$ -p $ARG3$
11 command_name check_local_disk
12}
13
14define service {
15 service_description Total number of process
16 use local-service
17 check_command check_local_procs!250!400!RSZDT
18}
19define command {
20 command_line $USER1$/check_procs -w $ARG1$ -c $ARG2$ -s $ARG3$
21 command_name check_local_procs
22}
23
24define service {
25 service_description Average load
26 use local-service
27 check_command check_local_load!8.0,8.0,8.0!10.0,10.0,10.0
28}
29define command {
30 command_line $USER1$/check_load -w $ARG1$ -c $ARG2$
31 command_name check_local_load
32}
33
34define service {
35 service_description Swap usage
36 use local-service
37 check_command check_local_swap!20!10
38}
39define command {
40 command_line $USER1$/check_swap -n ok -w $ARG1$ -c $ARG2$
41 command_name check_local_swap
42}
43
44define service {
45 service_description Memory usage
46 use local-service
47 check_command check_memory!80!90
48}
49define command {
50 command_line $USER2$/check_mem.sh -w $ARG1$ -c $ARG2$
51 command_name check_memory
52}
53
54define command {
55 command_line $USER2$/check_command -c "$ARG1$" -s 0 -o "$ARG2$" $ARG3$
56 command_name check_command_output
57}
58
59# Network dependent local services
60define service {
61 service_description NTP is activated and working
62 use local-service
63 check_command check_ntp
64}
65define command {
66 command_line $USER1$/check_ntp_time -t 30 -q -H 0.arch.pool.ntp.org
67 command_name check_ntp
68}
diff --git a/modules/private/monitoring/conf/notify.cfg b/modules/private/monitoring/conf/notify.cfg
deleted file mode 100644
index 63b380d..0000000
--- a/modules/private/monitoring/conf/notify.cfg
+++ /dev/null
@@ -1,8 +0,0 @@
1# vim: filetype=nagios
2
3define command {
4 command_line /etc/naemon/send_nrdp.sh -H "$HOSTADDRESS$" -s "$SERVICEDESC$" -S "$SERVICESTATEID$" -o "$SERVICEOUTPUT$"
5 command_name notify-master
6}
7
8
diff --git a/modules/private/monitoring/conf/objects.cfg b/modules/private/monitoring/conf/objects.cfg
deleted file mode 100644
index 653477f..0000000
--- a/modules/private/monitoring/conf/objects.cfg
+++ /dev/null
@@ -1,84 +0,0 @@
1# vim: filetype=nagios
2
3define command {
4 command_line $USER1$/check_ping -H $HOSTADDRESS$ -w 3000.0,80% -c 5000.0,100% -p 5
5 command_name check-host-alive
6}
7
8define command {
9 command_line $USER2$/check_md_raid
10 command_name check_md_raid
11}
12
13define command {
14 command_line $USER2$/check_command -c "$ARG1$" -o "$ARG2$" $ARG3$
15 command_name check_command_output
16}
17
18
19define command {
20 command_line /usr/bin/sudo -u postgres $USER2$/check_postgres_replication "$ARG1$" "$ARG2$" "$ARG3$"
21 command_name check_postgresql_replication
22}
23
24define service {
25 ## --PUPPET_NAME-- (called '_naginator_name' in the manifest) Databases are present in postgresql
26 active_checks_enabled 1
27 check_command check_command_output!psql -c 'select nspname from pg_catalog.pg_namespace'!public!-r postgres
28 check_freshness 0
29 check_interval 5
30 check_period 24x7
31 contact_groups admins
32 event_handler_enabled 1
33 flap_detection_enabled 1
34 host_name caldance-1.v.immae.eu
35 is_volatile 0
36 max_check_attempts 4
37 notification_interval 60
38 notification_options w,u,c,r
39 notification_period 24x7
40 notifications_enabled 0
41 obsess_over_service 1
42 passive_checks_enabled 1
43 process_perf_data 1
44 retain_nonstatus_information 1
45 retain_status_information 1
46 retry_interval 1
47 service_description Databases are present in postgresql
48}
49
50define command {
51 command_line $USER2$/check_last_file_date "$ARG1$" "$ARG2$" "$ARG3$"
52 command_name check_last_file_date
53}
54
55define command {
56 command_line $USER2$/check_date "$ARG1$" "$ARG2$" "$ARG3$"
57 command_name check_date
58}
59
60define service {
61 ## --PUPPET_NAME-- (called '_naginator_name' in the manifest) Postgresql replication for backup-1 is up to date
62 active_checks_enabled 1
63 check_command check_postgresql_replication!backup-1!/run/postgresql!5432
64 check_freshness 0
65 check_interval 5
66 check_period 24x7
67 contact_groups admins
68 event_handler_enabled 1
69 flap_detection_enabled 1
70 host_name caldance-1.v.immae.eu
71 is_volatile 0
72 max_check_attempts 4
73 notification_interval 60
74 notification_options w,u,c,r
75 notification_period 24x7
76 notifications_enabled 0
77 obsess_over_service 1
78 passive_checks_enabled 1
79 process_perf_data 1
80 retain_nonstatus_information 1
81 retain_status_information 1
82 retry_interval 1
83 service_description Postgresql replication for backup-1 is up to date
84}
diff --git a/modules/private/monitoring/conf/services.cfg b/modules/private/monitoring/conf/services.cfg
deleted file mode 100644
index 0740dc7..0000000
--- a/modules/private/monitoring/conf/services.cfg
+++ /dev/null
@@ -1,27 +0,0 @@
1# vim: filetype=nagios
2
3define service {
4 name generic-service
5 active_checks_enabled 1
6 check_freshness 0
7 check_interval 10
8 check_period 24x7
9 contact_groups admins
10 event_handler_enabled 1
11 flap_detection_enabled 1
12 is_volatile 0
13 max_check_attempts 3
14 notification_interval 60
15 notification_options w,u,c,r,f
16 notification_period 24x7
17 # no notification since we send them to master
18 notifications_enabled 0
19 obsess_over_service 1
20 passive_checks_enabled 1
21 process_perf_data 1
22 register 0
23 retain_nonstatus_information 1
24 retain_status_information 1
25 retry_interval 2
26}
27
diff --git a/modules/private/monitoring/conf/specific_backup-2.cfg b/modules/private/monitoring/conf/specific_backup-2.cfg
deleted file mode 100644
index ff91322..0000000
--- a/modules/private/monitoring/conf/specific_backup-2.cfg
+++ /dev/null
@@ -1,36 +0,0 @@
1# vim: filetype=nagios
2
3define service {
4 service_description Size on /backup2 partition
5 check_command check_local_disk!10%!5%!/backup2
6 use local-service
7}
8
9define command {
10 command_line /run/wrappers/bin/sudo -u "$ARG3$" $USER2$/check_last_file_date "$ARG1$" "$ARG2$"
11 command_name check_last_file_date
12}
13
14define service {
15 service_description Last backup in /backup2/phare is not too old
16 check_command check_last_file_date!/backup2/phare!14!backup
17 use local-service
18}
19
20define service {
21 service_description Last backup in /backup2/immae_eu is not too old
22 check_command check_last_file_date!/backup2/immae_eu!14!backup
23 use local-service
24}
25
26define service {
27 service_description Last backup in /backup2/immae_fr is not too old
28 check_command check_last_file_date!/backup2/immae_fr!14!backup
29 use local-service
30}
31
32define service {
33 service_description Last postgresql dump in /backup2/eldiron/postgresql_backup is not too old
34 check_command check_last_file_date!/backup2/eldiron/postgresql_backup!7!postgres
35 use local-service
36}
diff --git a/modules/private/monitoring/conf/specific_eldiron.cfg b/modules/private/monitoring/conf/specific_eldiron.cfg
deleted file mode 100644
index fd5a43d..0000000
--- a/modules/private/monitoring/conf/specific_eldiron.cfg
+++ /dev/null
@@ -1,29 +0,0 @@
1# vim: filetype=nagios
2#
3define command {
4 command_line /run/wrappers/bin/sudo -u postgres $USER2$/check_postgres_replication "$ARG1$" "$ARG2$" "$ARG3$"
5 command_name check_postgresql_replication
6}
7
8define service {
9 service_description Postgresql replication for backup-1 is up to date
10 check_command check_postgresql_replication!backup-1!/run/postgresql!5432
11 use local-service
12}
13
14define service {
15 service_description Postgresql replication for backup-2 is up to date
16 check_command check_postgresql_replication!backup-2!/run/postgresql!5432
17 use local-service
18}
19
20define service {
21 service_description mailq is empty
22 use local-service
23 check_command check_mailq
24}
25
26define command {
27 command_name check_mailq
28 command_line $USER1$/check_mailq -s -w 1 -c 2
29}
diff --git a/modules/private/monitoring/conf/timeperiods.cfg b/modules/private/monitoring/conf/timeperiods.cfg
deleted file mode 100644
index 5ffe4ca..0000000
--- a/modules/private/monitoring/conf/timeperiods.cfg
+++ /dev/null
@@ -1,15 +0,0 @@
1# vim: filetype=nagios
2
3define timeperiod {
4 alias 24 Hours A Day, 7 Days A Week
5 friday 00:00-24:00
6 monday 00:00-24:00
7 saturday 00:00-24:00
8 sunday 00:00-24:00
9 thursday 00:00-24:00
10 timeperiod_name 24x7
11 tuesday 00:00-24:00
12 wednesday 00:00-24:00
13}
14
15
diff --git a/modules/private/monitoring/default.nix b/modules/private/monitoring/default.nix
index 6062aba..0259cbf 100644
--- a/modules/private/monitoring/default.nix
+++ b/modules/private/monitoring/default.nix
@@ -17,42 +17,26 @@ let
17 pkgs.postgresql 17 pkgs.postgresql
18 ]} 18 ]}
19 ''; 19 '';
20 defaultObjects = 20 toObjects = pkgs.callPackage ./to_objects.nix {};
21 let specific_file = ./conf + "/specific_" + name + ".cfg"; 21 commonConfig = {
22 eldiron = {
23 processWarn = "250"; processAlert = "400";
24 loadWarn = "8.0"; loadAlert = "10.0";
25 };
26 backup-2 = {
27 processWarn = "50"; processAlert = "60";
28 loadWarn = "1.0"; loadAlert = "2.0";
29 };
30 };
31 commonObjects = pkgs.callPackage ./objects_common.nix ({
32 inherit hostFQDN;
33 sudo = "/run/wrappers/bin/sudo";
34 } // builtins.getAttr name commonConfig);
35 hostObjects =
36 let
37 specific_file = ./. + "/objects_" + name + ".nix";
22 in 38 in
23 builtins.readFile ./conf/local_services.cfg 39 lib.attrsets.optionalAttrs (builtins.pathExists specific_file) (pkgs.callPackage specific_file {});
24 + builtins.readFile ./conf/timeperiods.cfg
25 + builtins.readFile ./conf/services.cfg
26 + builtins.readFile ./conf/contacts.cfg
27 + builtins.readFile ./conf/hosts.cfg
28 + ''
29 define command {
30 command_line ${myplugins}/send_nrdp.sh -u "$USER200$" -t "$USER201$" -H "$HOSTADDRESS$" -s "$SERVICEDESC$" -S "$SERVICESTATEID$" -o "$SERVICEOUTPUT$"
31 command_name notify-master
32 }
33 define service {
34 service_description No mdadm array is degraded
35 use local-service
36 check_command check_command_output!${pkgs.mdadm}/bin/mdadm --monitor --scan -1!^$!-s 0 -r root
37 }
38
39 define service {
40 name local-service
41 use generic-service
42 host_name ${hostFQDN}
43 check_interval 5
44 max_check_attempts 4
45 register 0
46 retry_interval 1
47 }
48 define host {
49 host_name ${hostFQDN}
50 alias ${hostFQDN}
51 address ${hostFQDN}
52 use linux-server
53 }
54 ''
55 + lib.strings.optionalString (builtins.pathExists specific_file) (builtins.readFile specific_file);
56in 40in
57{ 41{
58 options = { 42 options = {
@@ -122,7 +106,7 @@ in
122 $USER200$=${myconfig.env.monitoring.status_url} 106 $USER200$=${myconfig.env.monitoring.status_url}
123 $USER201$=${myconfig.env.monitoring.status_token} 107 $USER201$=${myconfig.env.monitoring.status_token}
124 ''; 108 '';
125 objectDefs = defaultObjects; 109 objectDefs = toObjects commonObjects + toObjects hostObjects;
126 }; 110 };
127 }; 111 };
128} 112}
diff --git a/modules/private/monitoring/objects_backup-2.nix b/modules/private/monitoring/objects_backup-2.nix
new file mode 100644
index 0000000..b8ecb81
--- /dev/null
+++ b/modules/private/monitoring/objects_backup-2.nix
@@ -0,0 +1,30 @@
1{ ... }:
2{
3 service = [
4 {
5 service_description = "Size on /backup2 partition";
6 use = "local-service";
7 check_command = ["check_local_disk" "10%" "5%" "/backup2"];
8 }
9 {
10 service_description = "Last backup in /backup2/phare is not too old";
11 use = "local-service";
12 check_command = ["check_last_file_date" "/backup2/phare" "14" "backup"];
13 }
14 {
15 service_description = "Last backup in /backup2/immae_eu is not too old";
16 use = "local-service";
17 check_command = ["check_last_file_date" "/backup2/immae_eu" "14" "backup"];
18 }
19 {
20 service_description = "Last backup in /backup2/immae_fr is not too old";
21 use = "local-service";
22 check_command = ["check_last_file_date" "/backup2/immae_fr" "14" "backup"];
23 }
24 {
25 service_description = "Last postgresql dump in /backup2/eldiron/postgresql_backup is not too old";
26 use = "local-service";
27 check_command = ["check_last_file_date" "/backup2/eldiron/postgresql_backup" "7" "postgres"];
28 }
29 ];
30}
diff --git a/modules/private/monitoring/objects_common.nix b/modules/private/monitoring/objects_common.nix
new file mode 100644
index 0000000..8466fdb
--- /dev/null
+++ b/modules/private/monitoring/objects_common.nix
@@ -0,0 +1,179 @@
1{ hostFQDN
2, processWarn ? "250"
3, processAlert ? "400"
4, loadWarn ? "8.0"
5, loadAlert ? "10.0"
6, mdadm
7, sudo
8, ...
9}:
10{
11 host = {
12 "${hostFQDN}" = {
13 alias = hostFQDN;
14 address = hostFQDN;
15 use = "linux-server";
16 };
17 };
18 service = [
19 {
20 service_description = "Size on root partition";
21 use = "local-service";
22 check_command = ["check_local_disk" "20%" "10%" "/"];
23 }
24 {
25 service_description = "Total number of process";
26 use = "local-service";
27 check_command = [
28 "check_local_procs"
29 processWarn
30 processAlert
31 "RSZDT"
32 ];
33 }
34 {
35 service_description = "Average load";
36 use = "local-service";
37 check_command = [
38 "check_local_load"
39 "${loadWarn},${loadWarn},${loadWarn}"
40 "${loadAlert},${loadAlert},${loadAlert}"
41 ];
42 }
43 {
44 service_description = "Swap usage";
45 use = "local-service";
46 check_command = ["check_local_swap" "20" "10"];
47 }
48 {
49 service_description = "Memory usage";
50 use = "local-service";
51 check_command = ["check_memory" "80" "90"];
52 }
53 {
54 service_description = "NTP is activated and working";
55 use = "local-service";
56 check_command = ["check_ntp"];
57 }
58 {
59 service_description = "No mdadm array is degraded";
60 use = "local-service";
61 check_command = [
62 "check_command_output"
63 "${mdadm}/bin/mdadm --monitor --scan -1"
64 "^$"
65 "-s 0 -r root"
66 ];
67 }
68 ];
69 command = {
70 check_local_disk = "$USER1$/check_disk -w $ARG1$ -c $ARG2$ -p $ARG3$";
71 check_local_procs = "$USER1$/check_procs -w $ARG1$ -c $ARG2$ -s $ARG3$";
72 check_local_load = "$USER1$/check_load -w $ARG1$ -c $ARG2$";
73 check_local_swap = "$USER1$/check_swap -n ok -w $ARG1$ -c $ARG2$";
74 check_memory = "$USER2$/check_mem.sh -w $ARG1$ -c $ARG2$";
75 check_command_output = "$USER2$/check_command -c \"$ARG1$\" -s 0 -o \"$ARG2$\" $ARG3$";
76 check_ntp = "$USER1$/check_ntp_time -t 30 -q -H 0.arch.pool.ntp.org";
77 check_postgresql_replication = "${sudo} -u postgres $USER2$/check_postgres_replication \"$ARG1$\" \"$ARG2$\" \"$ARG3$\"";
78 check_mailq = "$USER1$/check_mailq -s -w 1 -c 2";
79
80 check_host_alive = "$USER1$/check_ping -H $HOSTADDRESS$ -w 3000.0,80% -c 5000.0,100% -p 5";
81 check_last_file_date = "${sudo} -u \"$ARG3$\" $USER2$/check_last_file_date \"$ARG1$\" \"$ARG2$\"";
82
83 # No notify commands, we go through master
84 # notify_host_by_email = "SERVICENOTIFICATIONID=\"$SERVICENOTIFICATIONID$\" HOSTSTATE=\"$HOSTSTATE$\" HOSTOUTPUT=\"$HOSTOUTPUT$\" $USER2$/notify_by_email host \"$NOTIFICATIONTYPE$\" \"$HOSTALIAS$\" \"$LONGDATETIME$\" \"$CONTACTEMAIL$\" $OVE";
85 # #$OVE is to force naemon to run via shell instead of execve which fails here
86 # notify_service_by_email = "SERVICENOTIFICATIONID=\"$SERVICENOTIFICATIONID$\" SERVICEDESC=\"$SERVICEDESC$\" SERVICESTATE=\"$SERVICESTATE$\" SERVICEOUTPUT=\"$SERVICEOUTPUT$\" $USER2$/notify_by_email service \"$NOTIFICATIONTYPE$\" \"$HOSTALIAS$\" \"$LONGDATETIME$\" \"$CONTACTEMAIL$\" $OVE";
87 # #sudo /usr/bin/strace -o /tmp/foo -vf -s 256 -u naemon $USER2$/notify_by_email
88 # #$OVE is to force naemon to run via shell instead of execve which fails here
89
90 notify-master = "$USER2$/send_nrdp.sh -u \"$USER200$\" -t \"$USER201$\" -H \"$HOSTADDRESS$\" -s \"$SERVICEDESC$\" -S \"$SERVICESTATEID$\" -o \"$SERVICEOUTPUT$\"";
91 };
92 timeperiod = {
93 "24x7" = {
94 alias = "24 Hours A Day, 7 Days A Week";
95 monday = "00:00-24:00";
96 tuesday = "00:00-24:00";
97 wednesday = "00:00-24:00";
98 thursday = "00:00-24:00";
99 friday = "00:00-24:00";
100 saturday = "00:00-24:00";
101 sunday = "00:00-24:00";
102 };
103 };
104 contactgroup = {
105 admins = { alias = "Naemon Administrators"; };
106 };
107 # No contact, we go through master
108 # contact = {
109 # immae = {
110 # alias = "Immae";
111 # use = "generic-contact";
112 # email = "xxxxxxxxxxxxxxxx";
113 # };
114 # };
115 templates = {
116 service = {
117 generic-service = {
118 active_checks_enabled = "1";
119 check_freshness = "0";
120 check_interval = "10";
121 check_period = "24x7";
122 contact_groups = "admins";
123 event_handler_enabled = "1";
124 flap_detection_enabled = "1";
125 is_volatile = "0";
126 max_check_attempts = "3";
127 notification_interval = "60";
128 notification_options = "w,u,c,r,f,s";
129 notification_period = "24x7";
130 notifications_enabled = "0"; # no notification since we send them to master
131 obsess_over_service = "1";
132 passive_checks_enabled = "1";
133 process_perf_data = "1";
134 retain_nonstatus_information = "1";
135 retain_status_information = "1";
136 retry_interval = "2";
137 };
138 local-service = {
139 use = "generic-service";
140 host_name = hostFQDN;
141 check_interval = "5";
142 max_check_attempts = "4";
143 retry_interval = "1";
144 };
145 };
146 # No contact, we go through master
147 # contact = {
148 # generic-contact = {
149 # host_notification_commands = "notify_host_by_email";
150 # host_notification_options = "d,u,r,f,s";
151 # host_notification_period = "24x7";
152 # service_notification_commands = "notify_service_by_email";
153 # service_notification_options = "w,u,c,r,f,s";
154 # service_notification_period = "24x7";
155 # };
156 # };
157 host = {
158 generic-host = {
159 event_handler_enabled = "1";
160 flap_detection_enabled = "1";
161 notification_period = "24x7";
162 notifications_enabled = "1";
163 process_perf_data = "1";
164 retain_nonstatus_information = "1";
165 retain_status_information = "1";
166 };
167 linux-server = {
168 check_command = "check_host_alive";
169 check_interval = "5";
170 check_period = "24x7";
171 contact_groups = "admins";
172 max_check_attempts = "10";
173 notification_interval = "120";
174 notification_options = "d,u,r,f";
175 retry_interval = "1";
176 };
177 };
178 };
179}
diff --git a/modules/private/monitoring/objects_eldiron.nix b/modules/private/monitoring/objects_eldiron.nix
new file mode 100644
index 0000000..897fc15
--- /dev/null
+++ b/modules/private/monitoring/objects_eldiron.nix
@@ -0,0 +1,15 @@
1{ ... }:
2{
3 service = [
4 {
5 service_description = "Postgresql replication for backup-2 is up to date";
6 use = "local-service";
7 check_command = ["check_postgresql_replication" "backup-2" "/run/postgresql" "5432"];
8 }
9 {
10 service_description = "mailq is empty";
11 use = "local-service";
12 check_command = ["check_mailq"];
13 }
14 ];
15}
diff --git a/modules/private/monitoring/to_objects.nix b/modules/private/monitoring/to_objects.nix
new file mode 100644
index 0000000..5ad76e0
--- /dev/null
+++ b/modules/private/monitoring/to_objects.nix
@@ -0,0 +1,67 @@
1{ lib }:
2 with lib.attrsets;
3 with lib.strings;
4 with lib.lists;
5 with lib.trivial;
6let
7 pad = width: str: let
8 padWidth = width - stringLength str;
9 padding = concatStrings (genList (const " ") padWidth);
10 in str + optionalString (padWidth > 0) padding;
11 toStr = k: v:
12 if k == "check_command" && builtins.isList v
13 then builtins.concatStringsSep "!" v
14 else v;
15
16 toService = service: ''
17 define service {
18 ${builtins.concatStringsSep "\n" (mapAttrsToList (k: v:
19 " ${pad 30 k} ${toStr k v}"
20 ) service)}
21 }
22 '';
23 toServices = services: builtins.concatStringsSep "\n" (map toService services);
24
25 toCommand = k: v: ''
26 define command {
27 ${pad 30 "command_name"} ${k}
28 ${pad 30 "command_line"} ${v}
29 }
30 '';
31 toCommands = a: builtins.concatStringsSep "\n" (mapAttrsToList toCommand a);
32
33 toOther = keyname: k: v: ''
34 define ${keyname} {
35 ${pad 30 "${keyname}_name"} ${k}
36 ${builtins.concatStringsSep "\n" (mapAttrsToList (kk: vv:
37 " ${pad 30 kk} ${vv}"
38 ) v)}
39 }
40 '';
41 toOthers = keyname: a: builtins.concatStringsSep "\n" (mapAttrsToList (toOther keyname) a);
42
43 toTemplate = keyname: k: v: ''
44 define ${keyname} {
45 ${pad 30 "name"} ${k}
46 ${pad 30 "register"} 0
47 ${builtins.concatStringsSep "\n" (mapAttrsToList (kk: vv:
48 " ${pad 30 kk} ${vv}"
49 ) v)}
50 }
51 '';
52 toTemplates' = keyname: a: builtins.concatStringsSep "\n" (mapAttrsToList (toTemplate keyname) a);
53 toTemplates = v: builtins.concatStringsSep "\n" (mapAttrsToList toTemplates' v);
54
55 toObjects' = keyname: v:
56 if keyname == "service"
57 then toServices v
58 else if keyname == "command"
59 then toCommands v
60 else if keyname == "templates"
61 then toTemplates v
62 else if builtins.elem keyname ["host" "contactgroup" "contact" "timeperiod"]
63 then toOthers keyname v
64 else "";
65 toObjects = v: builtins.concatStringsSep "\n" (mapAttrsToList toObjects' v);
66in
67 toObjects
generated by cgit v1.2.3 (git 2.25.1) at 2025-02-27 23:53:00 +0000