prometheus_snmp: WIP: lldp

group_vars/prom/prometheus/node.yml

@@ -16,7 +16,7 @@ prometheus__rules_node:
     labels:
       severity: warning
     annotations:
-      FreeMemory: !unsafe "{{ $value | humanizePercentage }} %"
+      FreeMemory: !unsafe "{{ $value | humanizePercentage }}"
   - alert: HostSwapIsFillingUp
     expr:
       (
@@ -29,7 +29,7 @@ prometheus__rules_node:
     labels:
       severity: critical
     annotations:
-      UsedSwap: !unsafe "{{ $value | humanizePercentage }} %"
+      UsedSwap: !unsafe "{{ $value | humanizePercentage }}"
   - alert: HostPhysicalComponentTooHot
     expr:
       node_hwmon_temp_celsius > 79
@@ -103,7 +103,7 @@ prometheus__rules_node:
       severity: critical
     annotations:
       Mountpoint: !unsafe "{{ $labels.mountpoint }}"
-      FreeSpace: !unsafe "{{ $value | humanizePercentage }} %"
+      FreeSpace: !unsafe "{{ $value | humanizePercentage }}"
   - alert: HostConntrackLimit
     expr:
       (
@@ -114,7 +114,7 @@ prometheus__rules_node:
     labels:
       severity: warning
     annotations:
-      Filled: !unsafe "{{ $value | humanizePercentage }} %"
+      Filled: !unsafe "{{ $value | humanizePercentage }}"
   - alert: HostClockSkew
     expr:
       (
@@ -149,7 +149,7 @@ prometheus__rules_node:
       severity: warning
     annotations:
       Mountpoint: !unsafe "{{ $labels.mountpoint }}"
-      FreeInodes: !unsafe "{{ $value | humanizePercentage }} %"
+      FreeInodes: !unsafe "{{ $value | humanizePercentage }}"
   - alert: CpuUsage
     expr:
       (
@@ -161,7 +161,7 @@ prometheus__rules_node:
     labels:
       severity: warning
     annotations:
-      Usage: !unsafe "{{ $value | humanizePercentage }} %"
+      Usage: !unsafe "{{ $value | humanizePercentage }}"
   - alert: SystemdServiceFailed
     expr:
       node_systemd_unit_state{state="failed"} == 1
@@ -196,5 +196,5 @@ prometheus__rules_node:
       severity: warning
     annotations:
       Disk: !unsafe "{{ $labels.disk }}"
-      Steal: !unsafe "{{ $value | humanizePercentage }} %"
+      Steal: !unsafe "{{ $value | humanizePercentage }}"
 ...

group_vars/prom/prometheus/switch.yml

@@ -28,7 +28,7 @@ prometheus__rules_switch:
     labels:
       severity: warning
     annotations:
-      ErrorRate: !unsafe "{{ $value | humanizePercentage }} %"
+      ErrorRate: !unsafe "{{ $value | humanizePercentage }}"
       Interface: !unsafe "{{ $labels.ifName }}
         {{ if $labels.ifAlias }}- {{ $labels.ifAlias }}{{ end }}"
   - alert: SwitchOutErrors
@@ -41,7 +41,7 @@ prometheus__rules_switch:
     labels:
       severity: warning
     annotations:
-      ErrorRate: !unsafe "{{ $value | humanizePercentage }} %"
+      ErrorRate: !unsafe "{{ $value | humanizePercentage }}"
       Interface: !unsafe "{{ $labels.ifName }}
         {{ if $labels.ifAlias }}- {{ $labels.ifAlias }}{{ end }}"
   - alert: SwitchInLinkUsage
@@ -52,7 +52,7 @@ prometheus__rules_switch:
     labels:
       severity: warning
     annotations:
-      Usage: !unsafe "{{ $value | humanizePercentage }} %"
+      Usage: !unsafe "{{ $value | humanizePercentage }}"
       Interface: !unsafe "{{ $labels.ifName }}
         {{ if $labels.ifAlias }}- {{ $labels.ifAlias }}{{ end }}"
   - alert: SwitchInLinkUsage
@@ -63,7 +63,7 @@ prometheus__rules_switch:
     labels:
       severity: critical
     annotations:
-      Usage: !unsafe "{{ $value | humanizePercentage }} %"
+      Usage: !unsafe "{{ $value | humanizePercentage }}"
       Interface: !unsafe "{{ $labels.ifName }}
         {{ if $labels.ifAlias }}- {{ $labels.ifAlias }}{{ end }}"
   - alert: SwitchOutLinkUsage
@@ -74,7 +74,7 @@ prometheus__rules_switch:
     labels:
       severity: warning
     annotations:
-      Usage: !unsafe "{{ $value | humanizePercentage }} %"
+      Usage: !unsafe "{{ $value | humanizePercentage }}"
       Interface: !unsafe "{{ $labels.ifName }}
         {{ if $labels.ifAlias }}- {{ $labels.ifAlias }}{{ end }}"
   - alert: SwitchOutLinkUsage
@@ -85,7 +85,7 @@ prometheus__rules_switch:
     labels:
       severity: warning
     annotations:
-      Usage: !unsafe "{{ $value | humanizePercentage }} %"
+      Usage: !unsafe "{{ $value | humanizePercentage }}"
       Interface: !unsafe "{{ $labels.ifName }}
         {{ if $labels.ifAlias }}- {{ $labels.ifAlias }}{{ end }}"
 ...

group_vars/prom/prometheus_snmp/quanta.yml

@@ -2,6 +2,8 @@
 prometheus_snmp__modules_quanta:
   auth:
     community: "{{ vault_snmp_quanta_community }}"
+  timeout: 60s
+  retries: 3
   walk:
     - interfaces
     - ifXTable
@@ -27,6 +29,8 @@ prometheus_snmp__modules_quanta:
     - dot3CollTable
     - lldpLocChassisId
     - lldpRemTable
+    - lldpLocPortTable
+    - dot1dBasePort
   lookups:
     - source_indexes:
         - ifIndex
@@ -59,6 +63,14 @@ prometheus_snmp__modules_quanta:
     - source_indexes:
         - dot3StatsIndex
       lookup: ifName
+    - source_indexes:
+        - lldpRemTimeMark
+        - lldpRemLocalPortNum
+        - lldpRemIndex
+      lookup: lldpRemChassisId
+    #- source_indexes:
+    #    - lldpLocPortNum
+    #  lookup: lldpLocPortIdSubtype
   overrides:
     ifIndex:
       ignore: true
@@ -106,4 +118,8 @@ prometheus_snmp__modules_quanta:
       ignore: true
     dot3StatsDuplexStatus:
       type: EnumAsStateSet
+    lldpLocPortIdSubtype:
+      type: EnumAsInfo
+    lldpRemPortIdSubtype:
+      type: EnumAsInfo
 ...