It 4953

Puppetfile

@@ -40,19 +40,19 @@ mod 'saz/sudo', '6.0.0'
 mod 'puppetlabs-puppet_agent', '4.9.0'
 mod 'saz/resolv_conf', '4.1.0'
 mod 'puppet-cron', '3.0.0'
-mod 'puppet/r10k', '8.0.0'
+mod 'puppet/r10k', '10.3.0'
 # mod 'camptocamp-systemd', '3.0.0'
 mod 'puppet-systemd', '3.2.0'
 mod 'bodgit/scl', '1.0.1'
 mod 'theforeman/dhcp', '6.1.0'
 mod 'theforeman/dns', '8.0.0'
 mod 'puppet-archive', '6.0.2'
 mod 'puppetlabs/concat', '6.0.0'
-mod 'puppetlabs-inifile', '5.0.1'
+mod 'puppetlabs-inifile', '5.2.0'
 mod 'puppetlabs-java', '7.3.0'
 mod 'puppetlabs-java_ks', '4.2.0'
 mod 'puppetlabs-stdlib', '8.4.0'
-mod 'puppetlabs/vcsrepo', '3.0.0'
+mod 'puppetlabs-vcsrepo', '5.0.0'
 mod 'puppet/ssh_keygen', '4.0.0'
 mod 'puppetlabs-hocon', '1.1.0'  # dependency
 mod 'example42-network', '3.6.0'

data/node/puppetm-tuc-2.lsst.org.yaml

@@ -0,0 +1,17 @@
+---
+classes:
+  - profile::base_linux
+  - profile::puppet_master
+profile::base_linux::graylog: true
+profile::base_linux::postfix: true
+network::interfaces_hash:
+  eth0:
+    type: Ethernet
+    ipaddress: 140.252.32.101
+    netmask: 255.255.254.0
+    gateway: 140.252.32.1
+    dns1: 140.252.32.125
+    dns2: 140.252.32.126
+    peerdns: yes
+    bootproto: none
+    onboot: yes

data/site/po/role/foreman.yaml

@@ -0,0 +1,13 @@
+---
+r10k::version: '3.15.4'
+r10k::mcollective: false
+r10k::cachedir: "/var/cache/r10k"
+r10k::sources:
+  private:
+    remote: "[email protected]:/lsst-it/pmo-puppet-private.git"
+    basedir: "/etc/puppetlabs/code/data/private"
+    invalid_branches: "correct"
+  control:
+    remote: "https://github.com/lsst-it/pmo-puppet"
+    basedir: "/etc/puppetlabs/code/environments"
+    invalid_branches: "correct"

data/site/po/role/prometheus.yaml

@@ -59,6 +59,24 @@ prometheus::alerts:
             summary: Windows Server disk Space Usage (instance {{ $labels.instance }})
             identifier: '{{ $labels.instance }}'
             description: "Disk usage is more than 85%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+# Windows memory usage
+        - alert: WindowsHighMemoryUsage
+          expr: ((windows_cs_physical_memory_bytes - windows_os_physical_memory_free_bytes) / (windows_cs_physical_memory_bytes)) * 100 > 80
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "High memory usage on Windows server"
+            description: "Memory usage is above 80% on Windows server {{ $labels.instance }}"
+# windows high CPU usage
+        - alert: windowsHostHighCpuLoad
+          expr: 100 - (avg by(instance) (rate(windows_cpu_time_total{mode="idle"}[2m])) * 100) > 80
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: Host high CPU load (instance {{ $labels.instance }})
+            description: "CPU load is > 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"# Windows Defender Firewall service
 # Windows Defender Firewall service
         - alert: WindowsFirewallServiceStatus
           expr: windows_service_state{name="mpssvc", state="running"} == 0
@@ -569,3 +587,21 @@ prometheus::alerts:
           annotations:
             summary: pingfederate.service down (instance {{ $labels.instance }})
             description: "pingfederate.service service is down on {{ $labels.instance }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+# Linux memory usage
+        - alert: HighMemoryUsage
+          expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 20
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "High memory usage on Windows server"
+            description: "Memory usage is above 80% on Linux server {{ $labels.instance }}"
+# Linux high cpu usage
+        - alert: HostHighCpuLoad
+          expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 90
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: Host high CPU load (instance {{ $labels.instance }})
+            description: "CPU load is > 90%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

site/profile/manifests/puppet_master.pp

@@ -1,8 +1,13 @@
 # puppet master config
 class profile::puppet_master {
+  include r10k
   # The toml gem is required for grafana ldap.
   package { 'toml':
     ensure   => present,
     provider => 'puppetserver_gem',
   }
+  package { 'hiera-eyaml':
+    ensure   => '3.4.0',
+    provider => 'puppetserver_gem',
+  }
 }