# Health alerts for Cisco Nexus SNMP monitoring.
# These alerts fire on metrics from the cisco-nexus SNMP profile.
# Chart contexts use the pattern: snmp.device_prof_<metric_name>

# --- vPC (Virtual Port Channel) alerts ---

 template: snmp_cisco_nexus_vpc_peer_keepalive
       on: snmp.device_prof_cVpcPeerKeepAliveStatus
    class: Errors
     type: Switch
component: VPC
   lookup: average -1m unaligned percentage of alive
    units: %
    every: 10s
     warn: $this < 100
    delay: down 1m multiplier 1.5 max 5m
  summary: vPC peer-keepalive not alive (domain ${label:vpc_domain_id})
     info: vPC peer-keepalive link is not in 'alive' state on domain ${label:vpc_domain_id}
       to: sysadmin

 template: snmp_cisco_nexus_vpc_dual_active
       on: snmp.device_prof_cVpcDualActiveDetectionStatus
    class: Errors
     type: Switch
component: VPC
   lookup: average -1m unaligned percentage of detected
    units: %
    every: 10s
     crit: $this > 0
    delay: down 15s multiplier 1.5 max 5m
  summary: vPC dual-active (split-brain) detected (domain ${label:vpc_domain_id})
     info: vPC dual-active condition detected on domain ${label:vpc_domain_id} — both switches may be forwarding independently, risking loops
       to: sysadmin

 template: snmp_cisco_nexus_vpc_member_consistency
       on: snmp.device_prof_cVpcStatusHostLinkConsistencyStatus
    class: Errors
     type: Switch
component: VPC
   lookup: average -1m unaligned percentage of failed
    units: %
    every: 10s
     warn: $this > 0
    delay: down 1m multiplier 1.5 max 5m
  summary: vPC member consistency check failed (domain ${label:vpc_domain_id} vPC ${label:vpc_id})
     info: vPC member ${label:vpc_id} on domain ${label:vpc_domain_id} has a configuration consistency check failure
       to: sysadmin

# --- HSRP (Hot Standby Router Protocol) alerts ---

 template: snmp_cisco_nexus_hsrp_not_active_standby
       on: snmp.device_prof_cHsrpGrpStandbyState
    class: Errors
     type: Switch
component: HSRP
   lookup: average -1m unaligned percentage of active,standby
    units: %
    every: 10s
     warn: $this < 100
    delay: down 1m multiplier 1.5 max 5m
  summary: HSRP group not active/standby (${label:interface} group ${label:hsrp_group})
     info: HSRP group ${label:hsrp_group} on ${label:interface} is not in active or standby state
       to: sysadmin

# --- BFD (Bidirectional Forwarding Detection) alerts ---

 template: snmp_cisco_nexus_bfd_session_down
       on: snmp.device_prof_ciscoBfdSessState
    class: Errors
     type: Switch
component: BFD
   lookup: average -1m unaligned percentage of down
    units: %
    every: 10s
     warn: $this > 0
    delay: down 30s multiplier 1.5 max 5m
  summary: BFD session down (session ${label:bfd_session_index})
     info: BFD session ${label:bfd_session_index} is in 'down' state — sub-second failure detection triggered
       to: sysadmin

# --- NTP alerts ---

 template: snmp_cisco_nexus_ntp_not_synchronized
       on: snmp.device_prof_cntpSysSrvStatus
    class: Errors
     type: Switch
component: NTP
   lookup: average -5m unaligned percentage of sync_to_refclock,sync_to_remote_server,sync_to_local
    units: %
    every: 10s
     warn: $this < 100
    delay: down 5m multiplier 1.5 max 15m
  summary: NTP service not synchronized
     info: Cisco NTP service is not synchronized to any reference clock or remote server
       to: sysadmin

# --- NX-OS Feature Control alerts ---

 template: snmp_cisco_nexus_feature_enabled_not_running
       on: snmp.device_prof_cfcFeatureCtrlOpStatus2
    class: Errors
     type: Switch
component: NX-OS
   lookup: average -1m unaligned percentage of enabled_not_running
    units: %
    every: 10s
     warn: $this > 0
    delay: down 2m multiplier 1.5 max 10m
  summary: NX-OS feature enabled but not running (${label:feature_name})
     info: NX-OS feature '${label:feature_name}' is enabled but not running — the feature process may have crashed
       to: sysadmin