--- Prometheus::Alert::Rule[check_mariadb_read_only_backup1-codfw_c754855176474e5a67d2bb5c504a51c1].orig
+++ Prometheus::Alert::Rule[check_mariadb_read_only_backup1-codfw_c754855176474e5a67d2bb5c504a51c1]
- for => 3m
- group => nrpechecks
- summary => NRPE CHECK: MariaDB read only backup1-codfw #page
- instance => ops
- runbook => https://wikitech.wikimedia.org/wiki/MariaDB/troubleshooting#Master_comes_back_in_read_only
- team => observability
- description => NRPE CHECK: MariaDB read only backup1-codfw
- def_label_whitelst => ['team', 'severity']
- site => codfw
- alert_name => nrpe_MariaDB_read_only_backup1_codfw
- expr => (nagios_nrpe_check_result{alert_rule_hash="c754855176474e5a67d2bb5c504a51c1",check_name="check_mariadb_read_only_backup1-codfw", status="CRITICAL", severity="page"} > 0) * on (instance) group_left (team) role_owner
- logs => https://logstash.wikimedia.org/app/dashboards#/view/2d343ac0-6df8-11f0-8e08-7fab0da52b33?_g=(filters:!((query:(match_phrase:(event.module:check_mariadb_read_only_backup1-codfw))),(query:(match_phrase:(host.name:{{$labels.instance|stripPort}})))))
- dashboard => TODO
- ensure => absent
- severity => info
Systemd::Timer[nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw]
- Parameters differences:
--- Systemd::Timer[nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw].orig
+++ Systemd::Timer[nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw]
+ accuracy => 15sec
+ splay => 60
+ unit_name => nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.service
+ timer_intervals => [{'start': 'OnUnitInactiveSec', 'interval': '1min'}, {'interval': '1s', 'start': 'OnActiveSec'}]
+ fixed_random_delay => True
+ ensure => absent
- Systemd::Service[pt-heartbeat-wikimedia]
- Parameters differences:
--- Systemd::Service[pt-heartbeat-wikimedia].orig
+++ Systemd::Service[pt-heartbeat-wikimedia]
@@
- service_params => {'ensure': True}
+ service_params => {'ensure': False}
- File[/lib/systemd/system/nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.timer]
- Parameters differences:
--- File[/lib/systemd/system/nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.timer].orig
+++ File[/lib/systemd/system/nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.timer]
+ notify => Exec[systemd daemon-reload for nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.timer (nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.timer)]
+ group => root
+ mode => 0444
+ ensure => absent
+ owner => root
- Content differences:
--- /lib/systemd/system/nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.timer.orig
+++ /lib/systemd/system/nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.timer
@@ -0,0 +1,14 @@
+[Unit]
+Description=Periodic execution of nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.service
+
+[Timer]
+Unit=nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.service
+# Accuracy sets the maximum time interval around the execution time we want to allow
+AccuracySec=15sec
+OnUnitInactiveSec=1min
+OnActiveSec=1s
+RandomizedDelaySec=60
+FixedRandomDelay=true
+
+[Install]
+WantedBy=multi-user.target
- Exec[systemd daemon-reload for nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.timer (nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.timer)]
- Parameters differences:
--- Exec[systemd daemon-reload for nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.timer (nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.timer)].orig
+++ Exec[systemd daemon-reload for nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.timer (nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.timer)]
+ refreshonly => True
+ command => /bin/systemctl daemon-reload
- Systemd::Service[nrpe2nodexp-mariadb_replica_io_state_backup1-codfw]
- Parameters differences:
--- Systemd::Service[nrpe2nodexp-mariadb_replica_io_state_backup1-codfw].orig
+++ Systemd::Service[nrpe2nodexp-mariadb_replica_io_state_backup1-codfw]
+ unit_type => timer
+ monitoring_enabled => False
+ monitoring_critical => False
+ migration_task => T407130
+ monitoring_contact_group => admins
+ restart => False
+ service_params => {}
+ require => Systemd::Unit[nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.service]
+ ensure => absent
+ override => False
- Class[Profile::Mariadb::Mysql_role]
- Parameters differences:
--- Class[Profile::Mariadb::Mysql_role].orig
+++ Class[Profile::Mariadb::Mysql_role]
@@
- role => master
+ role => slave
- File[/etc/rsyslog.d/25-nrpe2nodexp-mariadb-replica-io-state-backup1-codfw.conf]
- Parameters differences:
--- File[/etc/rsyslog.d/25-nrpe2nodexp-mariadb-replica-io-state-backup1-codfw.conf].orig
+++ File[/etc/rsyslog.d/25-nrpe2nodexp-mariadb-replica-io-state-backup1-codfw.conf]
+ notify => Service[rsyslog]
+ group => root
+ mode => 0444
+ ensure => absent
+ owner => root
- Content differences:
--- /etc/rsyslog.d/25-nrpe2nodexp-mariadb-replica-io-state-backup1-codfw.conf.orig
+++ /etc/rsyslog.d/25-nrpe2nodexp-mariadb-replica-io-state-backup1-codfw.conf
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: Apache-2.0
+if $programname contains "nrpe2nodexp-mariadb_replica_io_state_backup1-codfw" then {
+ if ($msg contains "\"ecs.version\": \"1.7.0\"") then {
+ # Send logs to kafka
+ set $.log_outputs = "kafka ecs_170 local";
+ } else {
+ # Filter out non-relevant nrpe2nodexp messages
+ stop
+ }
+}
- Rsyslog::Conf[nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw]
- Parameters differences:
--- Rsyslog::Conf[nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw].orig
+++ Rsyslog::Conf[nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw]
+ priority => 25
+ mode => 0444
+ ensure => absent
- Class[Mariadb::Config]
- Parameters differences:
--- Class[Mariadb::Config].orig
+++ Class[Mariadb::Config]
@@
- read_only => 0
+ read_only => 1
- Exec[systemd daemon-reload for nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer (nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer)]
- Parameters differences:
--- Exec[systemd daemon-reload for nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer (nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer)].orig
+++ Exec[systemd daemon-reload for nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer (nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer)]
+ refreshonly => True
+ command => /bin/systemctl daemon-reload
- Rsyslog::Conf[nrpe2nodexp-mariadb_replica_io_state_backup1-codfw]
- Parameters differences:
--- Rsyslog::Conf[nrpe2nodexp-mariadb_replica_io_state_backup1-codfw].orig
+++ Rsyslog::Conf[nrpe2nodexp-mariadb_replica_io_state_backup1-codfw]
+ priority => 25
+ mode => 0444
+ ensure => absent
- Monitoring::Exported_nagios_service[db2183 mariadb_disk_space]
- Parameters differences:
--- Monitoring::Exported_nagios_service[db2183 mariadb_disk_space].orig
+++ Monitoring::Exported_nagios_service[db2183 mariadb_disk_space]
@@
- contact_groups => admins,sms,admins
+ contact_groups => admins
@@
- notification_interval => 240
+ notification_interval => 0
@@
- service_description => MariaDB disk space #page
+ service_description => MariaDB disk space
- Rsyslog::Conf[nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw]
- Parameters differences:
--- Rsyslog::Conf[nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw].orig
+++ Rsyslog::Conf[nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw]
+ priority => 25
+ mode => 0444
+ ensure => absent
- Systemd::Unit[nrpe2nodexp-mariadb_read_only_backup1-codfw.service]
- Nrpe::Monitor_service[mariadb_disk_space]
- Parameters differences:
--- Nrpe::Monitor_service[mariadb_disk_space].orig
+++ Nrpe::Monitor_service[mariadb_disk_space]
@@
- critical => True
+ critical => False
- Prometheus::Alert::Rule[check_mariadb_read_only_backup1-codfw_8aa8e94c48d271ddfcbf96b11f04e0e8]
- Parameters differences:
--- Prometheus::Alert::Rule[check_mariadb_read_only_backup1-codfw_8aa8e94c48d271ddfcbf96b11f04e0e8].orig
+++ Prometheus::Alert::Rule[check_mariadb_read_only_backup1-codfw_8aa8e94c48d271ddfcbf96b11f04e0e8]
+ for => 3m
+ group => nrpechecks
+ summary => NRPE CHECK: MariaDB read only backup1-codfw
+ instance => ops
+ runbook => https://wikitech.wikimedia.org/wiki/MariaDB/troubleshooting#Master_comes_back_in_read_only
+ team => observability
+ description => NRPE CHECK: MariaDB read only backup1-codfw
+ def_label_whitelst => ['team', 'severity']
+ site => codfw
+ alert_name => nrpe_MariaDB_read_only_backup1_codfw
+ expr => (nagios_nrpe_check_result{alert_rule_hash="8aa8e94c48d271ddfcbf96b11f04e0e8",check_name="check_mariadb_read_only_backup1-codfw", status=~"(WARNING|CRITICAL)", severity=~"(warning|critical)"} > 0) * on (instance) group_left (team) role_owner
+ logs => https://logstash.wikimedia.org/app/dashboards#/view/2d343ac0-6df8-11f0-8e08-7fab0da52b33?_g=(filters:!((query:(match_phrase:(event.module:check_mariadb_read_only_backup1-codfw))),(query:(match_phrase:(host.name:{{$labels.instance|stripPort}})))))
+ dashboard => TODO
+ ensure => absent
+ severity => info
- Systemd::Unit[nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.service]
- Parameters differences:
--- Systemd::Unit[nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.service].orig
+++ Systemd::Unit[nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.service]
+ restart => False
+ override => False
+ require => ['Class[Systemd]']
+ override_filename => puppet-override.conf
+ ensure => absent
+ unit => nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.service
- Service[nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer]
- Parameters differences:
--- Service[nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer].orig
+++ Service[nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer]
+ provider => systemd
+ enable => False
+ ensure => stopped
+ before => ['Exec[systemd daemon-reload for nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer (nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer)]']
- Monitoring::Exported_nagios_service[db2183 mariadb_replica_sql_lag_backup1-codfw]
- Parameters differences:
--- Monitoring::Exported_nagios_service[db2183 mariadb_replica_sql_lag_backup1-codfw].orig
+++ Monitoring::Exported_nagios_service[db2183 mariadb_replica_sql_lag_backup1-codfw]
+ servicegroups => mysql_codfw
+ notes_url => https://wikitech.wikimedia.org/wiki/MariaDB/Troubleshooting#Incident_Response
+ host_name => db2183
+ check_command => nrpe_check!check_mariadb_replica_sql_lag_backup1-codfw!10
+ contact_groups => admins
+ check_period => 24x7
+ check_freshness => 0
+ notification_options => c,r,f
+ is_volatile => 0
+ notification_period => 24x7
+ retry_interval => 1
+ passive_checks_enabled => 1
+ active_checks_enabled => 1
+ notification_interval => 0
+ service_description => MariaDB Replica Lag: backup1-codfw
+ check_interval => 1
+ notifications_enabled => 1
+ max_check_attempts => 10
+ ensure => present
- Class[Mariadb::Monitor_process]
- Parameters differences:
--- Class[Mariadb::Monitor_process].orig
+++ Class[Mariadb::Monitor_process]
@@
- is_critical => True
+ is_critical => False
- Nrpe::Monitor_service[mariadb_replica_sql_lag_backup1-codfw]
- Parameters differences:
--- Nrpe::Monitor_service[mariadb_replica_sql_lag_backup1-codfw].orig
+++ Nrpe::Monitor_service[mariadb_replica_sql_lag_backup1-codfw]
+ notes_url => https://wikitech.wikimedia.org/wiki/MariaDB/Troubleshooting#Incident_Response
+ critical => False
+ migration_task => T315866
+ enable_icinga_check => True
+ contact_group => admins
+ nrpe2nodexp_parse_perf_data => False
+ timeout => 10
+ retries => 10
+ description => MariaDB Replica Lag: backup1-codfw
+ nrpe_command => /usr/local/lib/nagios/plugins/check_mariadb --sock=/run/mysqld/mysqld.sock --user=nagios --pass= --warn-stopped --check=slave_sql_lag --shard=backup1-codfw --datacenter=codfw --sql-lag-warn=60 --sql-lag-crit=300
+ retry_interval => 1
+ alertmanager_team => observability
+ check_interval => 1
+ ensure => present
+ enable_nrpe2nodexp => False
- File[/lib/systemd/system/nrpe2nodexp-mariadb_disk_space.service]
- Content differences:
--- /lib/systemd/system/nrpe2nodexp-mariadb_disk_space.service.orig
+++ /lib/systemd/system/nrpe2nodexp-mariadb_disk_space.service
@@ -8,4 +8,4 @@
Group=prometheus-node-exporter
SyslogIdentifier=nrpe2nodexp-mariadb_disk_space
-ExecStart=-/usr/local/bin/nrpe2nodexp --alert-rule-hash "40ee06f86a277811ae30c96774f3ddc0" --timeout 10 --check-command "check_mariadb_disk_space" --page
+ExecStart=-/usr/local/bin/nrpe2nodexp --alert-rule-hash "d2aae7bfec5549be1a8b9413215bd86c" --timeout 10 --check-command "check_mariadb_disk_space"
- Monitoring::Service[mysqld]
- Parameters differences:
--- Monitoring::Service[mysqld].orig
+++ Monitoring::Service[mysqld]
@@
- critical => True
+ critical => False
- File[/lib/systemd/system/nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer]
- Parameters differences:
--- File[/lib/systemd/system/nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer].orig
+++ File[/lib/systemd/system/nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer]
+ notify => Exec[systemd daemon-reload for nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer (nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer)]
+ group => root
+ mode => 0444
+ ensure => absent
+ owner => root
- Content differences:
--- /lib/systemd/system/nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer.orig
+++ /lib/systemd/system/nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.timer
@@ -0,0 +1,14 @@
+[Unit]
+Description=Periodic execution of nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.service
+
+[Timer]
+Unit=nrpe2nodexp-mariadb_replica_io_state_backup1-codfw.service
+# Accuracy sets the maximum time interval around the execution time we want to allow
+AccuracySec=15sec
+OnUnitInactiveSec=1min
+OnActiveSec=1s
+RandomizedDelaySec=60
+FixedRandomDelay=true
+
+[Install]
+WantedBy=multi-user.target
- Prometheus::Alert::Rule[check_mariadb_disk_space_d2aae7bfec5549be1a8b9413215bd86c]
- Parameters differences:
--- Prometheus::Alert::Rule[check_mariadb_disk_space_d2aae7bfec5549be1a8b9413215bd86c].orig
+++ Prometheus::Alert::Rule[check_mariadb_disk_space_d2aae7bfec5549be1a8b9413215bd86c]
+ for => 3m
+ group => nrpechecks
+ summary => NRPE CHECK: MariaDB disk space
+ instance => ops
+ runbook => https://wikitech.wikimedia.org/wiki/MariaDB/troubleshooting
+ team => observability
+ description => NRPE CHECK: MariaDB disk space
+ def_label_whitelst => ['team', 'severity']
+ site => codfw
+ alert_name => nrpe_MariaDB_disk_space
+ expr => (nagios_nrpe_check_result{alert_rule_hash="d2aae7bfec5549be1a8b9413215bd86c",check_name="check_mariadb_disk_space", status=~"(WARNING|CRITICAL)", severity=~"(warning|critical)"} > 0) * on (instance) group_left (team) role_owner
+ logs => https://logstash.wikimedia.org/app/dashboards#/view/2d343ac0-6df8-11f0-8e08-7fab0da52b33?_g=(filters:!((query:(match_phrase:(event.module:check_mariadb_disk_space))),(query:(match_phrase:(host.name:{{$labels.instance|stripPort}})))))
+ dashboard => TODO
+ ensure => absent
+ severity => info
- File[/etc/nagios/nrpe.d/check_mariadb_replica_sql_state_backup1-codfw.cfg]
- Parameters differences:
--- File[/etc/nagios/nrpe.d/check_mariadb_replica_sql_state_backup1-codfw.cfg].orig
+++ File[/etc/nagios/nrpe.d/check_mariadb_replica_sql_state_backup1-codfw.cfg]
+ tag => nrpe::check
+ notify => Service[nagios-nrpe-server]
+ group => root
+ mode => 0444
+ require => Package[nagios-nrpe-server]
+ ensure => present
+ owner => root
- Content differences:
--- /etc/nagios/nrpe.d/check_mariadb_replica_sql_state_backup1-codfw.cfg.orig
+++ /etc/nagios/nrpe.d/check_mariadb_replica_sql_state_backup1-codfw.cfg
@@ -0,0 +1,2 @@
+# File generated by puppet. DO NOT edit by hand
+command[check_mariadb_replica_sql_state_backup1-codfw]=/usr/local/lib/nagios/plugins/check_mariadb --sock=/run/mysqld/mysqld.sock --user=nagios --pass= --warn-stopped --check=slave_sql_state
- Nrpe::Check[check_mariadb_replica_io_state_backup1-codfw]
- Parameters differences:
--- Nrpe::Check[check_mariadb_replica_io_state_backup1-codfw].orig
+++ Nrpe::Check[check_mariadb_replica_io_state_backup1-codfw]
+ command => /usr/local/lib/nagios/plugins/check_mariadb --sock=/run/mysqld/mysqld.sock --user=nagios --pass= --warn-stopped --check=slave_io_state
+ ensure => present
+ before => Monitoring::Service[mariadb_replica_io_state_backup1-codfw]
- Sudo::User[nrpe-check_mariadb_replica_io_state_backup1-codfw]
- Parameters differences:
--- Sudo::User[nrpe-check_mariadb_replica_io_state_backup1-codfw].orig
+++ Sudo::User[nrpe-check_mariadb_replica_io_state_backup1-codfw]
+ privileges => []
+ user => nagios
+ tag => nrpe::check
+ require => ['Class[Sudo]']
+ ensure => absent
- File[/var/lib/prometheus/node.d/check_mariadb_replica_sql_state_backup1-codfw.prom]
- Parameters differences:
--- File[/var/lib/prometheus/node.d/check_mariadb_replica_sql_state_backup1-codfw.prom].orig
+++ File[/var/lib/prometheus/node.d/check_mariadb_replica_sql_state_backup1-codfw.prom]
+ group => root
+ ensure => absent
+ owner => root
- Systemd::Timer::Job[nrpe2nodexp-mariadb_disk_space]
- Parameters differences:
--- Systemd::Timer::Job[nrpe2nodexp-mariadb_disk_space].orig
+++ Systemd::Timer::Job[nrpe2nodexp-mariadb_disk_space]
@@
- command => /usr/local/bin/nrpe2nodexp --alert-rule-hash "40ee06f86a277811ae30c96774f3ddc0" --timeout 10 --check-command "check_mariadb_disk_space" --page
+ command => /usr/local/bin/nrpe2nodexp --alert-rule-hash "d2aae7bfec5549be1a8b9413215bd86c" --timeout 10 --check-command "check_mariadb_disk_space"
- Service[nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.timer]
- Parameters differences:
--- Service[nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.timer].orig
+++ Service[nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.timer]
+ provider => systemd
+ enable => False
+ ensure => stopped
+ before => ['Exec[systemd daemon-reload for nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.timer (nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.timer)]']
- Prometheus::Alert::Rule[check_mariadb_disk_space_40ee06f86a277811ae30c96774f3ddc0]
- Parameters differences:
--- Prometheus::Alert::Rule[check_mariadb_disk_space_40ee06f86a277811ae30c96774f3ddc0].orig
+++ Prometheus::Alert::Rule[check_mariadb_disk_space_40ee06f86a277811ae30c96774f3ddc0]
- for => 3m
- group => nrpechecks
- summary => NRPE CHECK: MariaDB disk space #page
- instance => ops
- runbook => https://wikitech.wikimedia.org/wiki/MariaDB/troubleshooting
- team => observability
- description => NRPE CHECK: MariaDB disk space
- def_label_whitelst => ['team', 'severity']
- site => codfw
- alert_name => nrpe_MariaDB_disk_space
- expr => (nagios_nrpe_check_result{alert_rule_hash="40ee06f86a277811ae30c96774f3ddc0",check_name="check_mariadb_disk_space", status="CRITICAL", severity="page"} > 0) * on (instance) group_left (team) role_owner
- logs => https://logstash.wikimedia.org/app/dashboards#/view/2d343ac0-6df8-11f0-8e08-7fab0da52b33?_g=(filters:!((query:(match_phrase:(event.module:check_mariadb_disk_space))),(query:(match_phrase:(host.name:{{$labels.instance|stripPort}})))))
- dashboard => TODO
- ensure => absent
- severity => info
- File[/lib/systemd/system/nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.service]
- Parameters differences:
--- File[/lib/systemd/system/nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.service].orig
+++ File[/lib/systemd/system/nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.service]
+ notify => Exec[systemd daemon-reload for nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.service (nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.service)]
+ group => root
+ mode => 0444
+ ensure => absent
+ owner => root
- Content differences:
--- /lib/systemd/system/nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.service.orig
+++ /lib/systemd/system/nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw.service
@@ -0,0 +1,11 @@
+[Unit]
+Description=execution of nrpe2nodexp for the check_mariadb_replica_sql_lag_backup1-codfw command.
+Documentation=https://wikitech.wikimedia.org/wiki/Monitoring/systemd_unit_state
+
+[Service]
+Type=oneshot
+User=nagios
+
+Group=prometheus-node-exporter
+SyslogIdentifier=nrpe2nodexp-mariadb_replica_sql_lag_backup1-codfw
+ExecStart=-/usr/local/bin/nrpe2nodexp --alert-rule-hash "8688c7f4c31f8bd2553cec605fe5ef5e" --timeout 10 --check-command "check_mariadb_replica_sql_lag_backup1-codfw"
- Monitoring::Service[mariadb_disk_space]
- Parameters differences:
--- Monitoring::Service[mariadb_disk_space].orig
+++ Monitoring::Service[mariadb_disk_space]
@@
- critical => True
+ critical => False
- Monitoring::Service[mariadb_read_only_backup1-codfw]
- Parameters differences:
--- Monitoring::Service[mariadb_read_only_backup1-codfw].orig
+++ Monitoring::Service[mariadb_read_only_backup1-codfw]
@@
- critical => True
+ critical => False
- Monitoring::Exported_nagios_service[db2183 mariadb_replica_sql_state_backup1-codfw]
- Parameters differences:
--- Monitoring::Exported_nagios_service[db2183 mariadb_replica_sql_state_backup1-codfw].orig
+++ Monitoring::Exported_nagios_service[db2183 mariadb_replica_sql_state_backup1-codfw]
+ servicegroups => mysql_codfw
+ notes_url => https://wikitech.wikimedia.org/wiki/MariaDB/Troubleshooting#Incident_Response
+ host_name => db2183
+ check_command => nrpe_check!check_mariadb_replica_sql_state_backup1-codfw!10
+ contact_groups => admins
+ check_period => 24x7
+ check_freshness => 0
+ notification_options => c,r,f
+ is_volatile => 0
+ notification_period => 24x7
+ retry_interval => 1
+ passive_checks_enabled => 1
+ active_checks_enabled => 1
+ notification_interval => 0
+ service_description => MariaDB Replica SQL: backup1-codfw
+ check_interval => 1
+ notifications_enabled => 1
+ max_check_attempts => 3
+ ensure => present
- File[/lib/systemd/system/nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.timer]
- Parameters differences:
--- File[/lib/systemd/system/nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.timer].orig
+++ File[/lib/systemd/system/nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.timer]
+ notify => Exec[systemd daemon-reload for nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.timer (nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.timer)]
+ group => root
+ mode => 0444
+ ensure => absent
+ owner => root
- Content differences:
--- /lib/systemd/system/nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.timer.orig
+++ /lib/systemd/system/nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.timer
@@ -0,0 +1,14 @@
+[Unit]
+Description=Periodic execution of nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.service
+
+[Timer]
+Unit=nrpe2nodexp-mariadb_replica_sql_state_backup1-codfw.service
+# Accuracy sets the maximum time interval around the execution time we want to allow
+AccuracySec=15sec
+OnUnitInactiveSec=1min
+OnActiveSec=1s
+RandomizedDelaySec=60
+FixedRandomDelay=true
+
+[Install]
+WantedBy=multi-user.target
- File[/etc/sudoers.d/nrpe-check_mariadb_replica_io_state_backup1-codfw]