Extend weathermap dashboard with BGP/ports tables, per-site throughput, fix node status query
Fix node.statusQuery colliding legends: multi-neighbor devices previously sourced from raw per-neighbor BGP session-state series that collide under one legend, so an arbitrary neighbor won. Replace with a combined device-up * worst-BGP-session query per device, with an explicit fallback so zero-BGP devices (access switches) read as neutral/OK. Add site label via Prometheus relabel (derived from device naming convention) instead of per-query label_replace(). Add site/device template variables, BGP sessions table, ports/interfaces table (Grafana merge transform, not PromQL join), and per-site throughput graphs. Refs #49
This commit is contained in:
@@ -367,6 +367,11 @@ only appears as the sample *value* of
|
||||
`(device, interface, vlan)`. Per-VNI MAC counts require a PromQL join on `vlan`
|
||||
rather than a native `vni` label.
|
||||
|
||||
`site` (`dc`/`campus`/`core`) is also not gnmic-exported. It's added as a
|
||||
Prometheus `metric_relabel_configs` rule deriving it from `device` via the
|
||||
`<area>-<role><n>` naming convention regex (see #49), rather than repeating
|
||||
`label_replace()` in every dashboard query.
|
||||
|
||||
- Config: `configs/prometheus/prometheus.yml`
|
||||
- This is separate from, and does not replace, the existing external Prometheus
|
||||
instance — no cutover yet, both run in parallel pending validation
|
||||
|
||||
@@ -11,6 +11,50 @@
|
||||
"timezone": "browser",
|
||||
"schemaVersion": 39,
|
||||
"version": 0,
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "site",
|
||||
"type": "query",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "cfrlusac89se8a"
|
||||
},
|
||||
"query": {
|
||||
"query": "label_values(interfaces_interface_state_oper_status, site)",
|
||||
"refId": "site"
|
||||
},
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"multi": true,
|
||||
"includeAll": true,
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "device",
|
||||
"type": "query",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "cfrlusac89se8a"
|
||||
},
|
||||
"query": {
|
||||
"query": "label_values(interfaces_interface_state_oper_status{site=~\"$site\"}, device)",
|
||||
"refId": "device"
|
||||
},
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"multi": true,
|
||||
"includeAll": true,
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"panels": [
|
||||
{
|
||||
"id": 1,
|
||||
@@ -29,8 +73,8 @@
|
||||
"targets": [
|
||||
{
|
||||
"refId": "A",
|
||||
"expr": "min by (device) (network_instances_network_instance_protocols_protocol_bgp_neighbors_neighbor_state_session_state{network_instance_name=\"default\", device=~\"campus-spine1|dc-spine1|dc-spine2|campus-spine2|campus-border-leaf1|dc-leaf1|campus-border-leaf2|dc-leaf4|dc-leaf3|dc-leaf5|dc-border-leaf1|dc-leaf6|dc-access1|dc-access2|dc-leaf8|dc-leaf7|dc-access4|dc-access3|dc-border-leaf2|dc-leaf2|campus-leaf1|campus-access1|campus-leaf2|campus-leaf3|campus-access2|campus-leaf4|core1|core2\"})",
|
||||
"legendFormat": "BGP {{device}}",
|
||||
"expr": "min by (device) (interfaces_interface_state_oper_status{device=~\"campus-spine1|dc-spine1|dc-spine2|campus-spine2|campus-border-leaf1|dc-leaf1|campus-border-leaf2|dc-leaf4|dc-leaf3|dc-leaf5|dc-border-leaf1|dc-leaf6|dc-access1|dc-access2|dc-leaf8|dc-leaf7|dc-access4|dc-access3|dc-border-leaf2|dc-leaf2|campus-leaf1|campus-access1|campus-leaf2|campus-leaf3|campus-access2|campus-leaf4|core1|core2\"}) * (min by (device) (network_instances_network_instance_protocols_protocol_bgp_neighbors_neighbor_state_session_state{network_instance_name=\"default\", device=~\"campus-spine1|dc-spine1|dc-spine2|campus-spine2|campus-border-leaf1|dc-leaf1|campus-border-leaf2|dc-leaf4|dc-leaf3|dc-leaf5|dc-border-leaf1|dc-leaf6|dc-access1|dc-access2|dc-leaf8|dc-leaf7|dc-access4|dc-access3|dc-border-leaf2|dc-leaf2|campus-leaf1|campus-access1|campus-leaf2|campus-leaf3|campus-access2|campus-leaf4|core1|core2\"}) or (min by (device) (interfaces_interface_state_oper_status{device=~\"campus-spine1|dc-spine1|dc-spine2|campus-spine2|campus-border-leaf1|dc-leaf1|campus-border-leaf2|dc-leaf4|dc-leaf3|dc-leaf5|dc-border-leaf1|dc-leaf6|dc-access1|dc-access2|dc-leaf8|dc-leaf7|dc-access4|dc-access3|dc-border-leaf2|dc-leaf2|campus-leaf1|campus-access1|campus-leaf2|campus-leaf3|campus-access2|campus-leaf4|core1|core2\"}) * 0 + 1))",
|
||||
"legendFormat": "STATUS {{device}}",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "cfrlusac89se8a"
|
||||
@@ -90,7 +134,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP campus-spine1",
|
||||
"statusQuery": "STATUS campus-spine1",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -146,7 +190,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-spine1",
|
||||
"statusQuery": "STATUS dc-spine1",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -202,7 +246,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-spine2",
|
||||
"statusQuery": "STATUS dc-spine2",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -258,7 +302,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP campus-spine2",
|
||||
"statusQuery": "STATUS campus-spine2",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -314,7 +358,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP campus-border-leaf1",
|
||||
"statusQuery": "STATUS campus-border-leaf1",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -370,7 +414,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-leaf1",
|
||||
"statusQuery": "STATUS dc-leaf1",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -433,7 +477,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP campus-border-leaf2",
|
||||
"statusQuery": "STATUS campus-border-leaf2",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -489,7 +533,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-leaf4",
|
||||
"statusQuery": "STATUS dc-leaf4",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -545,7 +589,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-leaf3",
|
||||
"statusQuery": "STATUS dc-leaf3",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -601,7 +645,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-leaf5",
|
||||
"statusQuery": "STATUS dc-leaf5",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -664,7 +708,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-border-leaf1",
|
||||
"statusQuery": "STATUS dc-border-leaf1",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -720,7 +764,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-leaf6",
|
||||
"statusQuery": "STATUS dc-leaf6",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -783,7 +827,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-access1",
|
||||
"statusQuery": "STATUS dc-access1",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -839,7 +883,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-access2",
|
||||
"statusQuery": "STATUS dc-access2",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -895,7 +939,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-leaf8",
|
||||
"statusQuery": "STATUS dc-leaf8",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -951,7 +995,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-leaf7",
|
||||
"statusQuery": "STATUS dc-leaf7",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -1007,7 +1051,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-access4",
|
||||
"statusQuery": "STATUS dc-access4",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -1063,7 +1107,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-access3",
|
||||
"statusQuery": "STATUS dc-access3",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -1119,7 +1163,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-border-leaf2",
|
||||
"statusQuery": "STATUS dc-border-leaf2",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -1175,7 +1219,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP dc-leaf2",
|
||||
"statusQuery": "STATUS dc-leaf2",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -1238,7 +1282,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP campus-leaf1",
|
||||
"statusQuery": "STATUS campus-leaf1",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -1301,7 +1345,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP campus-access1",
|
||||
"statusQuery": "STATUS campus-access1",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -1357,7 +1401,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP campus-leaf2",
|
||||
"statusQuery": "STATUS campus-leaf2",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -1420,7 +1464,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP campus-leaf3",
|
||||
"statusQuery": "STATUS campus-leaf3",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -1483,7 +1527,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP campus-access2",
|
||||
"statusQuery": "STATUS campus-access2",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -1539,7 +1583,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP campus-leaf4",
|
||||
"statusQuery": "STATUS campus-leaf4",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -1602,7 +1646,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP core1",
|
||||
"statusQuery": "STATUS core1",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -1658,7 +1702,7 @@
|
||||
"statusDown": "#F2495C"
|
||||
},
|
||||
"nodeIcon": null,
|
||||
"statusQuery": "BGP core2",
|
||||
"statusQuery": "STATUS core2",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [
|
||||
{
|
||||
@@ -3910,6 +3954,287 @@
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"type": "table",
|
||||
"title": "BGP Sessions",
|
||||
"gridPos": {
|
||||
"h": 10,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 24
|
||||
},
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "cfrlusac89se8a"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"refId": "A",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "cfrlusac89se8a"
|
||||
},
|
||||
"instant": true,
|
||||
"format": "table",
|
||||
"expr": "network_instances_network_instance_protocols_protocol_bgp_neighbors_neighbor_state_session_state{device=~\"$device\"}"
|
||||
}
|
||||
],
|
||||
"transformations": [
|
||||
{
|
||||
"id": "organize",
|
||||
"options": {
|
||||
"excludeByName": {
|
||||
"Time": true,
|
||||
"__name__": true,
|
||||
"instance": true,
|
||||
"job": true,
|
||||
"protocol_identifier": true,
|
||||
"protocol_name": true,
|
||||
"subscription_name": true
|
||||
},
|
||||
"renameByName": {
|
||||
"device": "Device",
|
||||
"neighbor_address": "Neighbor Address",
|
||||
"network_instance_name": "VRF",
|
||||
"Value": "State"
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"mappings": [
|
||||
{
|
||||
"type": "value",
|
||||
"options": {
|
||||
"0": {
|
||||
"text": "Down",
|
||||
"color": "red"
|
||||
},
|
||||
"1": {
|
||||
"text": "Up",
|
||||
"color": "green"
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"custom": {
|
||||
"cellOptions": {
|
||||
"type": "color-background"
|
||||
}
|
||||
}
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "State"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.cellOptions",
|
||||
"value": {
|
||||
"type": "color-background"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "mappings",
|
||||
"value": [
|
||||
{
|
||||
"type": "value",
|
||||
"options": {
|
||||
"0": {
|
||||
"text": "Down",
|
||||
"color": "red"
|
||||
},
|
||||
"1": {
|
||||
"text": "Up",
|
||||
"color": "green"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"type": "table",
|
||||
"title": "Ports / Interfaces",
|
||||
"gridPos": {
|
||||
"h": 10,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 24
|
||||
},
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "cfrlusac89se8a"
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"refId": "A",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "cfrlusac89se8a"
|
||||
},
|
||||
"instant": true,
|
||||
"format": "table",
|
||||
"expr": "interfaces_interface_state_oper_status{device=~\"$device\"}"
|
||||
},
|
||||
{
|
||||
"refId": "B",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "cfrlusac89se8a"
|
||||
},
|
||||
"instant": true,
|
||||
"format": "table",
|
||||
"expr": "rate(interfaces_interface_state_counters_in_octets{device=~\"$device\"}[5m]) * 8"
|
||||
},
|
||||
{
|
||||
"refId": "C",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "cfrlusac89se8a"
|
||||
},
|
||||
"instant": true,
|
||||
"format": "table",
|
||||
"expr": "rate(interfaces_interface_state_counters_out_octets{device=~\"$device\"}[5m]) * 8"
|
||||
}
|
||||
],
|
||||
"transformations": [
|
||||
{
|
||||
"id": "merge",
|
||||
"options": {}
|
||||
},
|
||||
{
|
||||
"id": "organize",
|
||||
"options": {
|
||||
"excludeByName": {
|
||||
"Time": true,
|
||||
"__name__": true,
|
||||
"instance": true,
|
||||
"job": true,
|
||||
"subscription_name": true
|
||||
},
|
||||
"renameByName": {
|
||||
"device": "Device",
|
||||
"interface": "Interface",
|
||||
"Value #A": "Status",
|
||||
"Value #B": "In (bps)",
|
||||
"Value #C": "Out (bps)"
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Status"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "custom.cellOptions",
|
||||
"value": {
|
||||
"type": "color-background"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "mappings",
|
||||
"value": [
|
||||
{
|
||||
"type": "value",
|
||||
"options": {
|
||||
"0": {
|
||||
"text": "Down",
|
||||
"color": "red"
|
||||
},
|
||||
"1": {
|
||||
"text": "Up",
|
||||
"color": "green"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "In (bps)"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "unit",
|
||||
"value": "bps"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Out (bps)"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "unit",
|
||||
"value": "bps"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"type": "timeseries",
|
||||
"title": "Throughput per Site",
|
||||
"gridPos": {
|
||||
"h": 10,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 34
|
||||
},
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "cfrlusac89se8a"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "bps"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"refId": "A",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "cfrlusac89se8a"
|
||||
},
|
||||
"expr": "sum by (site) (rate(interfaces_interface_state_counters_in_octets{site=~\"$site\"}[5m]) * 8)",
|
||||
"legendFormat": "{{site}} in"
|
||||
},
|
||||
{
|
||||
"refId": "B",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "cfrlusac89se8a"
|
||||
},
|
||||
"expr": "-sum by (site) (rate(interfaces_interface_state_counters_out_octets{site=~\"$site\"}[5m]) * 8)",
|
||||
"legendFormat": "{{site}} out"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -16,6 +16,16 @@ scrape_configs:
|
||||
- action: labeldrop
|
||||
regex: source
|
||||
|
||||
# site: not exported by gnmic -- derived from the hostname naming
|
||||
# convention (see CLAUDE.md: dc-*/campus-*/core* regex used for
|
||||
# IPFabric site separation) here instead of repeating label_replace()
|
||||
# in every dashboard query, see issue #49
|
||||
- source_labels: [device]
|
||||
target_label: site
|
||||
regex: (campus|core|dc)-?.*
|
||||
replacement: $1
|
||||
action: replace
|
||||
|
||||
# interface: raw label is already "interface_name" (OpenConfig key on the
|
||||
# "interface" path element) — normalize to "interface" for consistency
|
||||
- source_labels: [interface_name]
|
||||
|
||||
@@ -265,7 +265,7 @@ def build_weathermap(devices, links, interface_speeds, positions, prometheus_url
|
||||
"padding": {"horizontal": 12, "vertical": 6},
|
||||
"colors": dict(NODE_COLORS),
|
||||
"nodeIcon": None,
|
||||
"statusQuery": f"BGP {host}",
|
||||
"statusQuery": f"STATUS {host}",
|
||||
"nodeStatusColorTarget": "border",
|
||||
"statusValueMappings": [dict(m) for m in STATUS_VALUE_MAPPINGS],
|
||||
"anchors": {a: {"numLinks": anchor_counts[host][a], "numFilledLinks": 0} for a in ANCHOR.values()},
|
||||
@@ -317,11 +317,26 @@ def build_weathermap(devices, links, interface_speeds, positions, prometheus_url
|
||||
interface_regex = "|".join(sorted(interface_regex_parts))
|
||||
|
||||
# -- targets (one query per metric family, per task spec) --
|
||||
#
|
||||
# Node status (refId A): a device is "up" only if at least one interface
|
||||
# is up AND every BGP session is up, if it has any -- see #49. The old
|
||||
# "BGP {{device}}" query sourced raw per-neighbor session-state series,
|
||||
# so a device with multiple neighbors collided on one legend string and
|
||||
# only one arbitrarily won. `min by (device)` picks the *worst* session
|
||||
# (0 beats 1), and devices with zero BGP sessions (access switches) are
|
||||
# not penalized: the `or` fallback substitutes a constant 1 for any
|
||||
# device present in device-up but absent from the BGP series entirely.
|
||||
device_up = f'min by (device) (interfaces_interface_state_oper_status{{device=~"{host_regex}"}})'
|
||||
bgp_worst = (
|
||||
f'min by (device) (network_instances_network_instance_protocols_protocol_bgp_neighbors_neighbor_state_session_state'
|
||||
f'{{network_instance_name="default", device=~"{host_regex}"}})'
|
||||
)
|
||||
bgp_ok_or_not_applicable = f'({bgp_worst} or ({device_up} * 0 + 1))'
|
||||
targets = [
|
||||
{
|
||||
"refId": "A",
|
||||
"expr": f'min by (device) (network_instances_network_instance_protocols_protocol_bgp_neighbors_neighbor_state_session_state{{network_instance_name="default", device=~"{host_regex}"}})',
|
||||
"legendFormat": "BGP {{device}}",
|
||||
"expr": f'{device_up} * {bgp_ok_or_not_applicable}',
|
||||
"legendFormat": "STATUS {{device}}",
|
||||
},
|
||||
{
|
||||
"refId": "B",
|
||||
@@ -378,7 +393,202 @@ def build_weathermap(devices, links, interface_speeds, positions, prometheus_url
|
||||
# Grafana provisioning
|
||||
# --------------------------------------------------------------------------
|
||||
|
||||
def build_templating(datasource_uid):
|
||||
ds = {"type": "prometheus", "uid": datasource_uid}
|
||||
return {
|
||||
"list": [
|
||||
{
|
||||
"name": "site",
|
||||
"type": "query",
|
||||
"datasource": ds,
|
||||
"query": {"query": "label_values(interfaces_interface_state_oper_status, site)", "refId": "site"},
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"multi": True,
|
||||
"includeAll": True,
|
||||
"current": {"text": "All", "value": "$__all"},
|
||||
},
|
||||
{
|
||||
"name": "device",
|
||||
"type": "query",
|
||||
"datasource": ds,
|
||||
# chained: only devices belonging to the selected site(s)
|
||||
"query": {
|
||||
"query": 'label_values(interfaces_interface_state_oper_status{site=~"$site"}, device)',
|
||||
"refId": "device",
|
||||
},
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"multi": True,
|
||||
"includeAll": True,
|
||||
"current": {"text": "All", "value": "$__all"},
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
|
||||
def build_bgp_table_panel(panel_id, datasource_uid, grid_y):
|
||||
ds = {"type": "prometheus", "uid": datasource_uid}
|
||||
return {
|
||||
"id": panel_id,
|
||||
"type": "table",
|
||||
"title": "BGP Sessions",
|
||||
"gridPos": {"h": 10, "w": 12, "x": 0, "y": grid_y},
|
||||
"datasource": ds,
|
||||
"targets": [
|
||||
{
|
||||
"refId": "A",
|
||||
"datasource": ds,
|
||||
"instant": True,
|
||||
"format": "table",
|
||||
"expr": (
|
||||
'network_instances_network_instance_protocols_protocol_bgp_neighbors_neighbor_state_session_state'
|
||||
'{device=~"$device"}'
|
||||
),
|
||||
}
|
||||
],
|
||||
"transformations": [
|
||||
{
|
||||
"id": "organize",
|
||||
"options": {
|
||||
"excludeByName": {
|
||||
"Time": True, "__name__": True, "instance": True, "job": True,
|
||||
"protocol_identifier": True, "protocol_name": True, "subscription_name": True,
|
||||
},
|
||||
"renameByName": {
|
||||
"device": "Device",
|
||||
"neighbor_address": "Neighbor Address",
|
||||
"network_instance_name": "VRF",
|
||||
"Value": "State",
|
||||
},
|
||||
},
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"mappings": [
|
||||
{"type": "value", "options": {"0": {"text": "Down", "color": "red"}, "1": {"text": "Up", "color": "green"}}}
|
||||
],
|
||||
"custom": {"cellOptions": {"type": "color-background"}},
|
||||
},
|
||||
"overrides": [
|
||||
{"matcher": {"id": "byName", "options": "State"}, "properties": [
|
||||
{"id": "custom.cellOptions", "value": {"type": "color-background"}},
|
||||
{"id": "mappings", "value": [
|
||||
{"type": "value", "options": {"0": {"text": "Down", "color": "red"}, "1": {"text": "Up", "color": "green"}}}
|
||||
]},
|
||||
]}
|
||||
],
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
def build_ports_table_panel(panel_id, datasource_uid, grid_y):
|
||||
ds = {"type": "prometheus", "uid": datasource_uid}
|
||||
return {
|
||||
"id": panel_id,
|
||||
"type": "table",
|
||||
"title": "Ports / Interfaces",
|
||||
"gridPos": {"h": 10, "w": 12, "x": 12, "y": grid_y},
|
||||
"datasource": ds,
|
||||
"targets": [
|
||||
{
|
||||
"refId": "A",
|
||||
"datasource": ds,
|
||||
"instant": True,
|
||||
"format": "table",
|
||||
"expr": 'interfaces_interface_state_oper_status{device=~"$device"}',
|
||||
},
|
||||
{
|
||||
"refId": "B",
|
||||
"datasource": ds,
|
||||
"instant": True,
|
||||
"format": "table",
|
||||
"expr": 'rate(interfaces_interface_state_counters_in_octets{device=~"$device"}[5m]) * 8',
|
||||
},
|
||||
{
|
||||
"refId": "C",
|
||||
"datasource": ds,
|
||||
"instant": True,
|
||||
"format": "table",
|
||||
"expr": 'rate(interfaces_interface_state_counters_out_octets{device=~"$device"}[5m]) * 8',
|
||||
},
|
||||
],
|
||||
# Grafana-side merge (not a PromQL join) -- see #44/#48 VXLAN join
|
||||
# failure; joining on (device, interface) in PromQL across these
|
||||
# three metric families is fragile, merging the three table results
|
||||
# in Grafana on shared field values is not.
|
||||
"transformations": [
|
||||
{"id": "merge", "options": {}},
|
||||
{
|
||||
"id": "organize",
|
||||
"options": {
|
||||
"excludeByName": {
|
||||
"Time": True, "__name__": True, "instance": True, "job": True, "subscription_name": True,
|
||||
},
|
||||
"renameByName": {
|
||||
"device": "Device",
|
||||
"interface": "Interface",
|
||||
"Value #A": "Status",
|
||||
"Value #B": "In (bps)",
|
||||
"Value #C": "Out (bps)",
|
||||
},
|
||||
},
|
||||
},
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {},
|
||||
"overrides": [
|
||||
{"matcher": {"id": "byName", "options": "Status"}, "properties": [
|
||||
{"id": "custom.cellOptions", "value": {"type": "color-background"}},
|
||||
{"id": "mappings", "value": [
|
||||
{"type": "value", "options": {"0": {"text": "Down", "color": "red"}, "1": {"text": "Up", "color": "green"}}}
|
||||
]},
|
||||
]},
|
||||
{"matcher": {"id": "byName", "options": "In (bps)"}, "properties": [{"id": "unit", "value": "bps"}]},
|
||||
{"matcher": {"id": "byName", "options": "Out (bps)"}, "properties": [{"id": "unit", "value": "bps"}]},
|
||||
],
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
def build_throughput_panel(panel_id, datasource_uid, grid_y):
|
||||
ds = {"type": "prometheus", "uid": datasource_uid}
|
||||
return {
|
||||
"id": panel_id,
|
||||
"type": "timeseries",
|
||||
"title": "Throughput per Site",
|
||||
"gridPos": {"h": 10, "w": 24, "x": 0, "y": grid_y},
|
||||
"datasource": ds,
|
||||
"fieldConfig": {"defaults": {"unit": "bps"}, "overrides": []},
|
||||
"targets": [
|
||||
{
|
||||
"refId": "A",
|
||||
"datasource": ds,
|
||||
"expr": 'sum by (site) (rate(interfaces_interface_state_counters_in_octets{site=~"$site"}[5m]) * 8)',
|
||||
"legendFormat": "{{site}} in",
|
||||
},
|
||||
{
|
||||
"refId": "B",
|
||||
"datasource": ds,
|
||||
# negated so in/out render as a signed graph (in above zero, out below)
|
||||
"expr": '-sum by (site) (rate(interfaces_interface_state_counters_out_octets{site=~"$site"}[5m]) * 8)',
|
||||
"legendFormat": "{{site}} out",
|
||||
},
|
||||
],
|
||||
}
|
||||
|
||||
|
||||
def build_dashboard(weathermap, targets, dashboard_uid, datasource_uid, plugin_id):
|
||||
weathermap_panel = {
|
||||
"id": 1,
|
||||
"type": plugin_id,
|
||||
"title": "Fabric Weathermap",
|
||||
"gridPos": {"h": 24, "w": 24, "x": 0, "y": 0},
|
||||
"datasource": {"type": "prometheus", "uid": datasource_uid},
|
||||
"targets": [dict(t, datasource={"type": "prometheus", "uid": datasource_uid}) for t in targets],
|
||||
"options": {"weathermap": weathermap},
|
||||
}
|
||||
return {
|
||||
"dashboard": {
|
||||
"uid": dashboard_uid,
|
||||
@@ -387,16 +597,12 @@ def build_dashboard(weathermap, targets, dashboard_uid, datasource_uid, plugin_i
|
||||
"timezone": "browser",
|
||||
"schemaVersion": 39,
|
||||
"version": 0,
|
||||
"templating": build_templating(datasource_uid),
|
||||
"panels": [
|
||||
{
|
||||
"id": 1,
|
||||
"type": plugin_id,
|
||||
"title": "Fabric Weathermap",
|
||||
"gridPos": {"h": 24, "w": 24, "x": 0, "y": 0},
|
||||
"datasource": {"type": "prometheus", "uid": datasource_uid},
|
||||
"targets": [dict(t, datasource={"type": "prometheus", "uid": datasource_uid}) for t in targets],
|
||||
"options": {"weathermap": weathermap},
|
||||
}
|
||||
weathermap_panel,
|
||||
build_bgp_table_panel(2, datasource_uid, 24),
|
||||
build_ports_table_panel(3, datasource_uid, 24),
|
||||
build_throughput_panel(4, datasource_uid, 34),
|
||||
],
|
||||
},
|
||||
"overwrite": True,
|
||||
|
||||
Reference in New Issue
Block a user