Split weathermap generation from dashboard composition
generate_weathermap.py now emits only the weathermap panel (targets + options.weathermap) and merges it into a manually-authored dashboard base (configs/grafana/dashboard-base.json) at a reserved slot panel, keeping the base's gridPos so layout stays manual. The BGP sessions table, ports/interfaces table, throughput graphs, and template variables move out of the script entirely into that base file. Verified zero regression: merged output is identical to the prior generator-only output except for JSON key ordering, and all panel queries re-validated via /api/ds/query. Refs #52
This commit is contained in:
197
configs/grafana/dashboard-base.json
Normal file
197
configs/grafana/dashboard-base.json
Normal file
@@ -0,0 +1,197 @@
|
|||||||
|
{
|
||||||
|
"uid": "evpn-vxlan-fabric-weathermap",
|
||||||
|
"title": "EVPN/VXLAN Fabric Weathermap",
|
||||||
|
"tags": ["evpn", "vxlan", "weathermap", "auto-generated"],
|
||||||
|
"timezone": "browser",
|
||||||
|
"schemaVersion": 39,
|
||||||
|
"version": 0,
|
||||||
|
"templating": {
|
||||||
|
"list": [
|
||||||
|
{
|
||||||
|
"name": "site",
|
||||||
|
"type": "query",
|
||||||
|
"datasource": { "type": "prometheus", "uid": "__DATASOURCE_UID__" },
|
||||||
|
"query": { "query": "label_values(interfaces_interface_state_oper_status, site)", "refId": "site" },
|
||||||
|
"refresh": 2,
|
||||||
|
"sort": 1,
|
||||||
|
"multi": true,
|
||||||
|
"includeAll": true,
|
||||||
|
"current": { "text": "All", "value": "$__all" }
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "device",
|
||||||
|
"type": "query",
|
||||||
|
"datasource": { "type": "prometheus", "uid": "__DATASOURCE_UID__" },
|
||||||
|
"query": {
|
||||||
|
"query": "label_values(interfaces_interface_state_oper_status{site=~\"$site\"}, device)",
|
||||||
|
"refId": "device"
|
||||||
|
},
|
||||||
|
"refresh": 2,
|
||||||
|
"sort": 1,
|
||||||
|
"multi": true,
|
||||||
|
"includeAll": true,
|
||||||
|
"current": { "text": "All", "value": "$__all" }
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"panels": [
|
||||||
|
{
|
||||||
|
"id": 1,
|
||||||
|
"title": "__WEATHERMAP_SLOT__",
|
||||||
|
"gridPos": { "h": 24, "w": 24, "x": 0, "y": 0 }
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": 2,
|
||||||
|
"type": "table",
|
||||||
|
"title": "BGP Sessions",
|
||||||
|
"gridPos": { "h": 10, "w": 12, "x": 0, "y": 24 },
|
||||||
|
"datasource": { "type": "prometheus", "uid": "__DATASOURCE_UID__" },
|
||||||
|
"targets": [
|
||||||
|
{
|
||||||
|
"refId": "A",
|
||||||
|
"datasource": { "type": "prometheus", "uid": "__DATASOURCE_UID__" },
|
||||||
|
"instant": true,
|
||||||
|
"format": "table",
|
||||||
|
"expr": "network_instances_network_instance_protocols_protocol_bgp_neighbors_neighbor_state_session_state{device=~\"$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": "__DATASOURCE_UID__" },
|
||||||
|
"targets": [
|
||||||
|
{
|
||||||
|
"refId": "A",
|
||||||
|
"datasource": { "type": "prometheus", "uid": "__DATASOURCE_UID__" },
|
||||||
|
"instant": true,
|
||||||
|
"format": "table",
|
||||||
|
"expr": "interfaces_interface_state_oper_status{device=~\"$device\"}"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"refId": "B",
|
||||||
|
"datasource": { "type": "prometheus", "uid": "__DATASOURCE_UID__" },
|
||||||
|
"instant": true,
|
||||||
|
"format": "table",
|
||||||
|
"expr": "rate(interfaces_interface_state_counters_in_octets{device=~\"$device\"}[5m]) * 8"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"refId": "C",
|
||||||
|
"datasource": { "type": "prometheus", "uid": "__DATASOURCE_UID__" },
|
||||||
|
"instant": true,
|
||||||
|
"format": "table",
|
||||||
|
"expr": "rate(interfaces_interface_state_counters_out_octets{device=~\"$device\"}[5m]) * 8"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"transformations": [
|
||||||
|
{ "id": "merge", "options": {} },
|
||||||
|
{
|
||||||
|
"id": "organize",
|
||||||
|
"options": {
|
||||||
|
"excludeByName": {
|
||||||
|
"Time": true,
|
||||||
|
"__name__": true,
|
||||||
|
"instance": true,
|
||||||
|
"job": true,
|
||||||
|
"subscription_name": true
|
||||||
|
},
|
||||||
|
"renameByName": {
|
||||||
|
"device": "Device",
|
||||||
|
"interface": "Interface",
|
||||||
|
"Value #A": "Status",
|
||||||
|
"Value #B": "In (bps)",
|
||||||
|
"Value #C": "Out (bps)"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"fieldConfig": {
|
||||||
|
"defaults": {},
|
||||||
|
"overrides": [
|
||||||
|
{
|
||||||
|
"matcher": { "id": "byName", "options": "Status" },
|
||||||
|
"properties": [
|
||||||
|
{ "id": "custom.cellOptions", "value": { "type": "color-background" } },
|
||||||
|
{
|
||||||
|
"id": "mappings",
|
||||||
|
"value": [
|
||||||
|
{ "type": "value", "options": { "0": { "text": "Down", "color": "red" }, "1": { "text": "Up", "color": "green" } } }
|
||||||
|
]
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{ "matcher": { "id": "byName", "options": "In (bps)" }, "properties": [{ "id": "unit", "value": "bps" }] },
|
||||||
|
{ "matcher": { "id": "byName", "options": "Out (bps)" }, "properties": [{ "id": "unit", "value": "bps" }] }
|
||||||
|
]
|
||||||
|
}
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": 4,
|
||||||
|
"type": "timeseries",
|
||||||
|
"title": "Throughput per Site",
|
||||||
|
"gridPos": { "h": 10, "w": 24, "x": 0, "y": 34 },
|
||||||
|
"datasource": { "type": "prometheus", "uid": "__DATASOURCE_UID__" },
|
||||||
|
"fieldConfig": { "defaults": { "unit": "bps" }, "overrides": [] },
|
||||||
|
"targets": [
|
||||||
|
{
|
||||||
|
"refId": "A",
|
||||||
|
"datasource": { "type": "prometheus", "uid": "__DATASOURCE_UID__" },
|
||||||
|
"expr": "sum by (site) (rate(interfaces_interface_state_counters_in_octets{site=~\"$site\", interface!~\"Management.*\"}[5m]) * 8)",
|
||||||
|
"legendFormat": "{{site}} in"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"refId": "B",
|
||||||
|
"datasource": { "type": "prometheus", "uid": "__DATASOURCE_UID__" },
|
||||||
|
"expr": "-sum by (site) (rate(interfaces_interface_state_counters_out_octets{site=~\"$site\", interface!~\"Management.*\"}[5m]) * 8)",
|
||||||
|
"legendFormat": "{{site}} out"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
@@ -58,7 +58,6 @@
|
|||||||
"panels": [
|
"panels": [
|
||||||
{
|
{
|
||||||
"id": 1,
|
"id": 1,
|
||||||
"type": "tamirsuliman-weathermap-panel",
|
|
||||||
"title": "Fabric Weathermap",
|
"title": "Fabric Weathermap",
|
||||||
"gridPos": {
|
"gridPos": {
|
||||||
"h": 24,
|
"h": 24,
|
||||||
@@ -66,6 +65,7 @@
|
|||||||
"x": 0,
|
"x": 0,
|
||||||
"y": 0
|
"y": 0
|
||||||
},
|
},
|
||||||
|
"type": "tamirsuliman-weathermap-panel",
|
||||||
"datasource": {
|
"datasource": {
|
||||||
"type": "prometheus",
|
"type": "prometheus",
|
||||||
"uid": "cfrlusac89se8a"
|
"uid": "cfrlusac89se8a"
|
||||||
|
|||||||
@@ -1,10 +1,25 @@
|
|||||||
# scripts/generate_weathermap.py
|
# scripts/generate_weathermap.py
|
||||||
|
|
||||||
Generates a [weathermap-ng](https://github.com/allamiro/grafana-network-weathermap-ng)
|
Generates a [weathermap-ng](https://github.com/allamiro/grafana-network-weathermap-ng)
|
||||||
panel from live IPFabric topology + gnmic/Prometheus metrics, and writes a full
|
**panel only** from live IPFabric topology + gnmic/Prometheus metrics, merges
|
||||||
Grafana dashboard-as-code JSON to `configs/grafana/weathermap-dashboard.json`
|
it into a manually-authored dashboard base, and writes the merged result to
|
||||||
(committed to Gitea as the source of truth, same pattern as the retired Flow
|
`configs/grafana/weathermap-dashboard.json` (committed to Gitea as the build
|
||||||
Panel YAML). Optionally provisions it into Grafana via the HTTP API.
|
artifact, same pattern as the retired Flow Panel YAML). Optionally provisions
|
||||||
|
it into Grafana via the HTTP API.
|
||||||
|
|
||||||
|
## File structure (see #52)
|
||||||
|
|
||||||
|
| File | What it is |
|
||||||
|
|---|---|
|
||||||
|
| `configs/grafana/dashboard-base.json` | **Manually authored**, committed source of truth for everything except the weathermap panel: BGP sessions table, ports/interfaces table, throughput-per-site graphs, `site`/`device` template variables, panel layout. Edit this directly for anything in those panels. Contains a reserved slot panel titled `__WEATHERMAP_SLOT__` (id `1`, `gridPos` fixed) that the script splices the generated weathermap panel into. |
|
||||||
|
| `configs/grafana/weathermap-dashboard.json` | **Generated build artifact** — base + freshly-generated weathermap panel, merged. This is what actually gets provisioned to Grafana. Don't hand-edit; re-run the script. |
|
||||||
|
|
||||||
|
The script itself only ever knows about the weathermap panel (`targets` +
|
||||||
|
`options.weathermap`) — it has no knowledge of the other three panels or the
|
||||||
|
template variables. That split is deliberate: topology-driven content
|
||||||
|
(nodes/links, generated from live IPFabric+Prometheus data) is separated from
|
||||||
|
hand-tuned dashboard composition (table layout, transformations, thresholds),
|
||||||
|
which doesn't need to regenerate on every topology change.
|
||||||
|
|
||||||
See issue #48 for the panel schema research this is built against, and its
|
See issue #48 for the panel schema research this is built against, and its
|
||||||
comment thread for the live-validation history (auth quirks, plugin id, a
|
comment thread for the live-validation history (auth quirks, plugin id, a
|
||||||
@@ -16,7 +31,7 @@ anchor/regex-escaping logic).
|
|||||||
```bash
|
```bash
|
||||||
export IPFABRIC_URL=https://<ipfabric-instance>
|
export IPFABRIC_URL=https://<ipfabric-instance>
|
||||||
export IPFABRIC_TOKEN=<token>
|
export IPFABRIC_TOKEN=<token>
|
||||||
python3 scripts/generate_weathermap.py # writes the JSON only
|
python3 scripts/generate_weathermap.py # writes the merged JSON only
|
||||||
|
|
||||||
export GRAFANA_URL=https://<external-grafana-instance>
|
export GRAFANA_URL=https://<external-grafana-instance>
|
||||||
export GRAFANA_TOKEN=<token>
|
export GRAFANA_TOKEN=<token>
|
||||||
@@ -24,13 +39,25 @@ export GRAFANA_DATASOURCE_UID=<prometheus-datasource-uid-in-grafana>
|
|||||||
python3 scripts/generate_weathermap.py --provision # also provisions via the Grafana API
|
python3 scripts/generate_weathermap.py --provision # also provisions via the Grafana API
|
||||||
```
|
```
|
||||||
|
|
||||||
Re-run after any topology change (`evpn-lab.clab.yml`) to regenerate and
|
Re-run after any topology change (`evpn-lab.clab.yml`) to regenerate the
|
||||||
re-provision.
|
weathermap panel and re-merge/re-provision. The script always regenerates the
|
||||||
|
weathermap panel fresh from live IPFabric data (no diffing/incremental
|
||||||
|
state), so a plain re-run already picks up any topology change — there's no
|
||||||
|
separate "detect changes" step. The only manual/operational step is
|
||||||
|
*triggering* that re-run after a change; there's no watcher or CI hook doing
|
||||||
|
it automatically yet.
|
||||||
|
|
||||||
|
If you need to change the BGP/ports/throughput panels, template variables, or
|
||||||
|
layout, edit `configs/grafana/dashboard-base.json` directly and re-run the
|
||||||
|
script (or run it with `--provision` to push the edit live) — no topology
|
||||||
|
data is needed for that path, the weathermap panel just gets regenerated
|
||||||
|
alongside it.
|
||||||
|
|
||||||
## Environment variables
|
## Environment variables
|
||||||
|
|
||||||
| Variable | Required | Default | Notes |
|
| Variable | Required | Default | Notes |
|
||||||
|---|---|---|---|
|
|---|---|---|---|
|
||||||
|
| `--base` (CLI flag, not env) | no | `configs/grafana/dashboard-base.json` | Manual dashboard base to merge the weathermap panel into. |
|
||||||
| `IPFABRIC_URL` | yes | — | e.g. `https://ipfabric.example.com` |
|
| `IPFABRIC_URL` | yes | — | e.g. `https://ipfabric.example.com` |
|
||||||
| `IPFABRIC_TOKEN` | yes | — | Inventory/Snapshots read access. Sent as `X-API-Token`, not `Authorization: Bearer` — IPFabric's REST API does not use bearer auth. |
|
| `IPFABRIC_TOKEN` | yes | — | Inventory/Snapshots read access. Sent as `X-API-Token`, not `Authorization: Bearer` — IPFabric's REST API does not use bearer auth. |
|
||||||
| `IPFABRIC_SNAPSHOT` | no | `$last` | |
|
| `IPFABRIC_SNAPSHOT` | no | `$last` | |
|
||||||
@@ -66,8 +93,13 @@ re-provision.
|
|||||||
name has no matching series is logged, not silently dropped — the actual
|
name has no matching series is logged, not silently dropped — the actual
|
||||||
fix for a real mismatch belongs in gnmic interface aliasing (#43), not in
|
fix for a real mismatch belongs in gnmic interface aliasing (#43), not in
|
||||||
this script.
|
this script.
|
||||||
7. Writes the dashboard JSON, and provisions it via `POST
|
7. Loads `configs/grafana/dashboard-base.json`, substitutes the real
|
||||||
/api/dashboards/db` if `--provision` is passed.
|
Prometheus datasource UID into its `__DATASOURCE_UID__` placeholders,
|
||||||
|
finds the panel titled `__WEATHERMAP_SLOT__` and splices in the generated
|
||||||
|
weathermap panel content (keeping the slot's `gridPos`/`id`, so the manual
|
||||||
|
layout is never repositioned).
|
||||||
|
8. Writes the merged dashboard JSON to `configs/grafana/weathermap-dashboard.json`,
|
||||||
|
and provisions it via `POST /api/dashboards/db` if `--provision` is passed.
|
||||||
|
|
||||||
## Known gaps
|
## Known gaps
|
||||||
|
|
||||||
|
|||||||
@@ -1,6 +1,14 @@
|
|||||||
#!/usr/bin/env python3
|
#!/usr/bin/env python3
|
||||||
"""Generate a weathermap-ng panel config from IPFabric topology + gnmic/Prometheus
|
"""Generate a weathermap-ng PANEL (only) from IPFabric topology + gnmic/Prometheus
|
||||||
metrics, and optionally provision it into a Grafana dashboard.
|
metrics, merge it into a manually-authored dashboard base, and optionally
|
||||||
|
provision the result into Grafana.
|
||||||
|
|
||||||
|
Scope (see #52): this script knows only about the weathermap panel --
|
||||||
|
targets (node status / link tx / link rx / VXLAN tooltip queries) and
|
||||||
|
options.weathermap (nodes/links/scale/settings). It has no knowledge of the
|
||||||
|
BGP sessions table, ports/interfaces table, or throughput panels -- those
|
||||||
|
live in the manually-authored `configs/grafana/dashboard-base.json` and are
|
||||||
|
not touched by this script.
|
||||||
|
|
||||||
Data sources (see gitea issues #44, #47, #48):
|
Data sources (see gitea issues #44, #47, #48):
|
||||||
- IPFabric REST API: device inventory + connectivity-matrix (topology)
|
- IPFabric REST API: device inventory + connectivity-matrix (topology)
|
||||||
@@ -8,8 +16,13 @@ Data sources (see gitea issues #44, #47, #48):
|
|||||||
values, used both to validate the IPFabric->gnmic interface-name mapping
|
values, used both to validate the IPFabric->gnmic interface-name mapping
|
||||||
and to resolve which VTEPs/VLANs actually have VXLAN data.
|
and to resolve which VTEPs/VLANs actually have VXLAN data.
|
||||||
|
|
||||||
|
Merge: the weathermap panel is generated fresh from live data on every run
|
||||||
|
(no diffing), then spliced into the base dashboard's reserved slot (the panel
|
||||||
|
titled "__WEATHERMAP_SLOT__"), keeping that slot's gridPos so the manually
|
||||||
|
authored layout is never repositioned by the generator. See #52.
|
||||||
|
|
||||||
Usage:
|
Usage:
|
||||||
python3 scripts/generate_weathermap.py [--output PATH] [--provision]
|
python3 scripts/generate_weathermap.py [--base PATH] [--output PATH] [--provision]
|
||||||
|
|
||||||
Environment:
|
Environment:
|
||||||
IPFABRIC_URL e.g. https://ipfabric.example.com
|
IPFABRIC_URL e.g. https://ipfabric.example.com
|
||||||
@@ -396,226 +409,66 @@ def build_weathermap(devices, links, interface_speeds, positions, prometheus_url
|
|||||||
|
|
||||||
|
|
||||||
# --------------------------------------------------------------------------
|
# --------------------------------------------------------------------------
|
||||||
# Grafana provisioning
|
# Weathermap panel (only) -- see #52, scope narrowed from full-dashboard
|
||||||
# --------------------------------------------------------------------------
|
# --------------------------------------------------------------------------
|
||||||
|
|
||||||
def build_templating(datasource_uid):
|
WEATHERMAP_SLOT_TITLE = "__WEATHERMAP_SLOT__"
|
||||||
ds = {"type": "prometheus", "uid": datasource_uid}
|
|
||||||
|
|
||||||
|
def build_weathermap_panel(weathermap, targets, datasource_uid, plugin_id):
|
||||||
|
"""The weathermap panel's own content: type/datasource/targets/options.
|
||||||
|
Deliberately has no gridPos/id/title of its own -- those come from
|
||||||
|
whatever slot it's merged into (see merge_weathermap_into_base)."""
|
||||||
return {
|
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,
|
|
||||||
# Management0 excluded -- gNMI telemetry traffic on the OOB
|
|
||||||
# port otherwise swamps fabric traffic and skews in/out
|
|
||||||
# wildly asymmetric, see #51.
|
|
||||||
"expr": 'sum by (site) (rate(interfaces_interface_state_counters_in_octets{site=~"$site", interface!~"Management.*"}[5m]) * 8)',
|
|
||||||
"legendFormat": "{{site}} in",
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"refId": "B",
|
|
||||||
"datasource": ds,
|
|
||||||
# negated so in/out render as a signed graph (in above zero, out below)
|
|
||||||
"expr": '-sum by (site) (rate(interfaces_interface_state_counters_out_octets{site=~"$site", interface!~"Management.*"}[5m]) * 8)',
|
|
||||||
"legendFormat": "{{site}} out",
|
|
||||||
},
|
|
||||||
],
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
def build_dashboard(weathermap, targets, dashboard_uid, datasource_uid, plugin_id):
|
|
||||||
weathermap_panel = {
|
|
||||||
"id": 1,
|
|
||||||
"type": plugin_id,
|
"type": plugin_id,
|
||||||
"title": "Fabric Weathermap",
|
|
||||||
"gridPos": {"h": 24, "w": 24, "x": 0, "y": 0},
|
|
||||||
"datasource": {"type": "prometheus", "uid": datasource_uid},
|
"datasource": {"type": "prometheus", "uid": datasource_uid},
|
||||||
"targets": [dict(t, datasource={"type": "prometheus", "uid": datasource_uid}) for t in targets],
|
"targets": [dict(t, datasource={"type": "prometheus", "uid": datasource_uid}) for t in targets],
|
||||||
"options": {"weathermap": weathermap},
|
"options": {"weathermap": weathermap},
|
||||||
}
|
}
|
||||||
return {
|
|
||||||
"dashboard": {
|
|
||||||
"uid": dashboard_uid,
|
# --------------------------------------------------------------------------
|
||||||
"title": "EVPN/VXLAN Fabric Weathermap",
|
# Manual base dashboard + merge (see #52)
|
||||||
"tags": ["evpn", "vxlan", "weathermap", "auto-generated"],
|
# --------------------------------------------------------------------------
|
||||||
"timezone": "browser",
|
|
||||||
"schemaVersion": 39,
|
def load_base_dashboard(path):
|
||||||
"version": 0,
|
with open(path) as f:
|
||||||
"templating": build_templating(datasource_uid),
|
return json.load(f)
|
||||||
"panels": [
|
|
||||||
weathermap_panel,
|
|
||||||
build_bgp_table_panel(2, datasource_uid, 24),
|
def substitute_placeholders(obj, replacements):
|
||||||
build_ports_table_panel(3, datasource_uid, 24),
|
"""Recursively replace exact-match string placeholders (e.g. the
|
||||||
build_throughput_panel(4, datasource_uid, 34),
|
datasource UID token) anywhere in the manually-authored base JSON."""
|
||||||
],
|
if isinstance(obj, dict):
|
||||||
},
|
return {k: substitute_placeholders(v, replacements) for k, v in obj.items()}
|
||||||
"overwrite": True,
|
if isinstance(obj, list):
|
||||||
}
|
return [substitute_placeholders(v, replacements) for v in obj]
|
||||||
|
if isinstance(obj, str) and obj in replacements:
|
||||||
|
return replacements[obj]
|
||||||
|
return obj
|
||||||
|
|
||||||
|
|
||||||
|
def merge_weathermap_into_base(base_dashboard, weathermap_panel, dashboard_uid):
|
||||||
|
"""Splice the freshly generated weathermap panel into the base
|
||||||
|
dashboard's reserved slot (matched by title), keeping the slot's
|
||||||
|
gridPos/id -- layout stays manual, the generator never repositions it."""
|
||||||
|
dashboard = dict(base_dashboard)
|
||||||
|
dashboard["uid"] = dashboard_uid
|
||||||
|
panels = []
|
||||||
|
found = False
|
||||||
|
for panel in dashboard.get("panels", []):
|
||||||
|
if panel.get("title") == WEATHERMAP_SLOT_TITLE:
|
||||||
|
found = True
|
||||||
|
merged = dict(panel)
|
||||||
|
merged.update(weathermap_panel)
|
||||||
|
merged["title"] = "Fabric Weathermap"
|
||||||
|
panels.append(merged)
|
||||||
|
else:
|
||||||
|
panels.append(panel)
|
||||||
|
if not found:
|
||||||
|
sys.exit(f"Base dashboard has no panel titled {WEATHERMAP_SLOT_TITLE!r} -- nowhere to merge the weathermap panel")
|
||||||
|
dashboard["panels"] = panels
|
||||||
|
return dashboard
|
||||||
|
|
||||||
|
|
||||||
def provision_to_grafana(grafana_url, api_token, dashboard_payload):
|
def provision_to_grafana(grafana_url, api_token, dashboard_payload):
|
||||||
@@ -636,10 +489,12 @@ def provision_to_grafana(grafana_url, api_token, dashboard_payload):
|
|||||||
|
|
||||||
def main():
|
def main():
|
||||||
parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
|
parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
|
||||||
|
parser.add_argument("--base", default="configs/grafana/dashboard-base.json",
|
||||||
|
help="manually-authored dashboard base JSON (everything but the weathermap panel)")
|
||||||
parser.add_argument("--output", default="configs/grafana/weathermap-dashboard.json",
|
parser.add_argument("--output", default="configs/grafana/weathermap-dashboard.json",
|
||||||
help="where to write the generated dashboard-as-code JSON")
|
help="where to write the merged dashboard-as-code JSON (build artifact)")
|
||||||
parser.add_argument("--provision", action="store_true",
|
parser.add_argument("--provision", action="store_true",
|
||||||
help="also POST the dashboard to the Grafana API (requires GRAFANA_* env vars)")
|
help="also POST the merged dashboard to the Grafana API (requires GRAFANA_* env vars)")
|
||||||
args = parser.parse_args()
|
args = parser.parse_args()
|
||||||
|
|
||||||
ipfabric_url = env("IPFABRIC_URL", required=True)
|
ipfabric_url = env("IPFABRIC_URL", required=True)
|
||||||
@@ -674,13 +529,20 @@ def main():
|
|||||||
dashboard_uid = env("GRAFANA_DASHBOARD_UID", "evpn-vxlan-fabric-weathermap")
|
dashboard_uid = env("GRAFANA_DASHBOARD_UID", "evpn-vxlan-fabric-weathermap")
|
||||||
datasource_uid = env("GRAFANA_DATASOURCE_UID", "PROMETHEUS_DATASOURCE_UID_PLACEHOLDER")
|
datasource_uid = env("GRAFANA_DATASOURCE_UID", "PROMETHEUS_DATASOURCE_UID_PLACEHOLDER")
|
||||||
plugin_id = env("GRAFANA_WEATHERMAP_PLUGIN_ID", "tamirsuliman-weathermap-panel")
|
plugin_id = env("GRAFANA_WEATHERMAP_PLUGIN_ID", "tamirsuliman-weathermap-panel")
|
||||||
dashboard_payload = build_dashboard(weathermap, targets, dashboard_uid, datasource_uid, plugin_id)
|
weathermap_panel = build_weathermap_panel(weathermap, targets, datasource_uid, plugin_id)
|
||||||
|
|
||||||
|
print(f"Loading manual dashboard base ({args.base})...")
|
||||||
|
base_dashboard = load_base_dashboard(args.base)
|
||||||
|
base_dashboard = substitute_placeholders(base_dashboard, {"__DATASOURCE_UID__": datasource_uid})
|
||||||
|
dashboard = merge_weathermap_into_base(base_dashboard, weathermap_panel, dashboard_uid)
|
||||||
|
dashboard_payload = {"dashboard": dashboard, "overwrite": True}
|
||||||
|
|
||||||
os.makedirs(os.path.dirname(args.output) or ".", exist_ok=True)
|
os.makedirs(os.path.dirname(args.output) or ".", exist_ok=True)
|
||||||
with open(args.output, "w") as f:
|
with open(args.output, "w") as f:
|
||||||
json.dump(dashboard_payload, f, indent=2)
|
json.dump(dashboard_payload, f, indent=2)
|
||||||
f.write("\n")
|
f.write("\n")
|
||||||
print(f"Wrote {args.output} ({len(weathermap['nodes'])} nodes, {len(weathermap['links'])} links)")
|
print(f"Wrote {args.output} ({len(weathermap['nodes'])} nodes, {len(weathermap['links'])} links, "
|
||||||
|
f"{len(dashboard['panels'])} panels total)")
|
||||||
|
|
||||||
if args.provision:
|
if args.provision:
|
||||||
grafana_url = env("GRAFANA_URL", required=True)
|
grafana_url = env("GRAFANA_URL", required=True)
|
||||||
|
|||||||
Reference in New Issue
Block a user