Rush has submitted this change and it was merged. (
https://gerrit.wikimedia.org/r/384892 )
Change subject: openstack2: no Icinga paging (SMS) if on labtest
......................................................................
openstack2: no Icinga paging (SMS) if on labtest
Instead of hardcoded "critical => true" for all of the
process checks, make it flexible and a parameter of the class.
Make it true by default.
Then set it to false for "labtest" hosts in Hiera regex.
This should avoid any SMS being sent if things are just on labtest
hosts and not production hosts.
Bug: T178008
Change-Id: I61b50f51d83e517adb711a3d6371b0e910bd9290
---
M hieradata/regex.yaml
M modules/openstack2/manifests/designate/monitor.pp
M modules/openstack2/manifests/nova/conductor/monitor.pp
M modules/openstack2/manifests/nova/network/monitor.pp
4 files changed, 14 insertions(+), 8 deletions(-)
Approvals:
Rush: Looks good to me, approved
jenkins-bot: Verified
diff --git a/hieradata/regex.yaml b/hieradata/regex.yaml
index a2e0319..23ccb75 100644
--- a/hieradata/regex.yaml
+++ b/hieradata/regex.yaml
@@ -125,6 +125,9 @@
cluster: labtest
mariadb::monitor_process::is_critical: false
mariadb::monitor_disk::is_critical: false
+ openstack2::designate::monitor::critical: false
+ openstack2::nova::conductor::monitor::critical: false
+ openstack2::nova::network::monitor::critical: false
swift_be_codfw_dell:
__regex: !ruby/regexp /^ms-be201[3-5]\.codfw\.wmnet$/
diff --git a/modules/openstack2/manifests/designate/monitor.pp
b/modules/openstack2/manifests/designate/monitor.pp
index d37b60b..0188be2 100644
--- a/modules/openstack2/manifests/designate/monitor.pp
+++ b/modules/openstack2/manifests/designate/monitor.pp
@@ -3,6 +3,7 @@
class openstack2::designate::monitor (
$active,
+ $critical = true,
) {
# monitoring::service doesn't take a bool
@@ -13,41 +14,41 @@
$ensure = 'absent'
}
- # Page if designate processes die. We only have one of each of these,
+ # Page if designate processes die and 'critical' is true. We only have
one of each of these,
# and new instance creation will be very broken if services die.
nrpe::monitor_service { 'check_designate_sink_process':
ensure => $ensure,
description => 'designate-sink process',
nrpe_command => "/usr/lib/nagios/plugins/check_procs -c 1:
--ereg-argument-array '^/usr/bin/python /usr/bin/designate-sink'",
- critical => true,
+ critical => $critical,
}
nrpe::monitor_service { 'check_designate_api_process':
ensure => $ensure,
description => 'designate-api process',
nrpe_command => "/usr/lib/nagios/plugins/check_procs -c 1:
--ereg-argument-array '^/usr/bin/python /usr/bin/designate-api'",
- critical => true,
+ critical => $critical,
}
nrpe::monitor_service { 'check_designate_central_process':
ensure => $ensure,
description => 'designate-central process',
nrpe_command => "/usr/lib/nagios/plugins/check_procs -c 1:
--ereg-argument-array '^/usr/bin/python /usr/bin/designate-central'",
- critical => true,
+ critical => $critical,
}
nrpe::monitor_service { 'check_designate_mdns':
ensure => $ensure,
description => 'designate-mdns process',
nrpe_command => "/usr/lib/nagios/plugins/check_procs -c 1:
--ereg-argument-array '^/usr/bin/python /usr/bin/designate-mdns'",
- critical => true,
+ critical => $critical,
}
nrpe::monitor_service { 'check_designate_pool-manager':
ensure => $ensure,
description => 'designate-pool-manager process',
nrpe_command => "/usr/lib/nagios/plugins/check_procs -c 1:
--ereg-argument-array '^/usr/bin/python /usr/bin/designate-pool-manager'",
- critical => true,
+ critical => $critical,
}
monitoring::service { 'designate-api-http':
diff --git a/modules/openstack2/manifests/nova/conductor/monitor.pp
b/modules/openstack2/manifests/nova/conductor/monitor.pp
index e812d7e..e737e06 100644
--- a/modules/openstack2/manifests/nova/conductor/monitor.pp
+++ b/modules/openstack2/manifests/nova/conductor/monitor.pp
@@ -5,6 +5,7 @@
class openstack2::nova::conductor::monitor(
$active,
+ $critical = true,
) {
# monitoring::service doesn't take a bool
@@ -19,6 +20,6 @@
ensure => $ensure,
description => 'nova-conductor process',
nrpe_command => "/usr/lib/nagios/plugins/check_procs -c 1:
--ereg-argument-array '^/usr/bin/python /usr/bin/nova-conductor'",
- critical => true,
+ critical => $critical,
}
}
diff --git a/modules/openstack2/manifests/nova/network/monitor.pp
b/modules/openstack2/manifests/nova/network/monitor.pp
index 56f94c0..0d176c4 100644
--- a/modules/openstack2/manifests/nova/network/monitor.pp
+++ b/modules/openstack2/manifests/nova/network/monitor.pp
@@ -1,5 +1,6 @@
class openstack2::nova::network::monitor(
$active,
+ $critical=true,
) {
# monitoring::service doesn't take a bool
@@ -19,7 +20,7 @@
ensure => $ensure,
description => 'nova-network process',
nrpe_command => "/usr/lib/nagios/plugins/check_procs -c 1:
--ereg-argument-array '^/usr/bin/python /usr/bin/nova-network'",
- critical => true,
+ critical => $critical,
}
nrpe::monitor_service { 'conntrack_table_size':
--
To view, visit https://gerrit.wikimedia.org/r/384892
To unsubscribe, visit https://gerrit.wikimedia.org/r/settings
Gerrit-MessageType: merged
Gerrit-Change-Id: I61b50f51d83e517adb711a3d6371b0e910bd9290
Gerrit-PatchSet: 4
Gerrit-Project: operations/puppet
Gerrit-Branch: production
Gerrit-Owner: Dzahn <[email protected]>
Gerrit-Reviewer: Alexandros Kosiaris <[email protected]>
Gerrit-Reviewer: Andrew Bogott <[email protected]>
Gerrit-Reviewer: Dzahn <[email protected]>
Gerrit-Reviewer: Giuseppe Lavagetto <[email protected]>
Gerrit-Reviewer: Madhuvishy <[email protected]>
Gerrit-Reviewer: Rush <[email protected]>
Gerrit-Reviewer: jenkins-bot <>
_______________________________________________
MediaWiki-commits mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits