feat(hub): dashboard + deploy del scraper NATS server-level del cluster unibus

Add the unibus-nats Grafana dashboard and the per-node deploy script for the unibus_exporter NATS-local mode, which surfaces the server-level NATS/JetStream metrics that /healthz cannot (msgs/s, connections, KV bucket msgs, RAFT leader per stream, memory, restarts). - hub/dashboards/unibus-nats.json (uid unibus-nats, datasource victoriametrics): 12 panels — NATS up, connections, msgs/s in, slow consumers, JetStream msgs, nats-server restarts (1h); msgs/s per node (in/out), connections per node, KV bucket msgs per bucket, nats-server memory per node; RAFT leader per stream table, JetStream per node table. Picked up automatically by the existing "fleet" dashboard provider (scans the dashboards path). - hub/deploy_unibus_nats_exporter.sh: deploys unibus_exporter in NATS-local mode on a node. magnus pushes to the local VictoriaMetrics (no auth); homer/datardos push to the public ingest endpoint with basic auth (pass fleet/ingest-pass, never in argv). Installs unibus-exporter-nats.service and probes 8222 to warn if the monitoring endpoint is not yet open. Does NOT restart membershipd or touch the cluster — that is the consolidated 0.11.0 rollout. The scraper code (unibus_exporter NATS-local mode) and the registry parser (parse_nats_monitor_go_infra) ship in their own repos; see report unibus-nats-metrics-clean for the integration order. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-07 21:19:42 +02:00
parent 1803833b50
commit dfd55dc10a
2 changed files with 242 additions and 0 deletions
@@ -0,0 +1,148 @@
+{
+  "uid": "unibus-nats",
+  "title": "unibus — NATS server",
+  "tags": ["fleet", "unibus", "nats", "jetstream"],
+  "timezone": "browser",
+  "schemaVersion": 39,
+  "version": 1,
+  "refresh": "30s",
+  "time": { "from": "now-6h", "to": "now" },
+  "templating": { "list": [] },
+  "panels": [
+    {
+      "id": 1,
+      "type": "stat",
+      "title": "Nodos NATS up",
+      "gridPos": { "h": 4, "w": 4, "x": 0, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "sum(last_over_time(nats_up[2m]))", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "none", "color": { "mode": "fixed", "fixedColor": "green" }, "noValue": "n/d (8222 cerrado)" }, "overrides": [] },
+      "options": { "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, "colorMode": "value", "graphMode": "none", "textMode": "value" }
+    },
+    {
+      "id": 2,
+      "type": "stat",
+      "title": "Conexiones (cluster)",
+      "gridPos": { "h": 4, "w": 4, "x": 4, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "sum(last_over_time(nats_connections[2m]))", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "none", "color": { "mode": "fixed", "fixedColor": "blue" } }, "overrides": [] },
+      "options": { "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, "colorMode": "value", "graphMode": "area", "textMode": "value" }
+    },
+    {
+      "id": 3,
+      "type": "stat",
+      "title": "Msgs/s entrada (cluster)",
+      "gridPos": { "h": 4, "w": 4, "x": 8, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "sum(rate(nats_msgs_in_total[5m]))", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "cps", "color": { "mode": "fixed", "fixedColor": "purple" } }, "overrides": [] },
+      "options": { "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, "colorMode": "value", "graphMode": "area", "textMode": "value" }
+    },
+    {
+      "id": 4,
+      "type": "stat",
+      "title": "Slow consumers",
+      "gridPos": { "h": 4, "w": 4, "x": 12, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "sum(last_over_time(nats_slow_consumers[2m]))", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "none", "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 1 } ] } }, "overrides": [] },
+      "options": { "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, "colorMode": "background", "graphMode": "none", "textMode": "value" }
+    },
+    {
+      "id": 5,
+      "type": "stat",
+      "title": "JetStream msgs (cluster)",
+      "gridPos": { "h": 4, "w": 4, "x": 16, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "sum(last_over_time(nats_jetstream_messages[2m]))", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "none", "color": { "mode": "fixed", "fixedColor": "blue" } }, "overrides": [] },
+      "options": { "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, "colorMode": "value", "graphMode": "none", "textMode": "value" }
+    },
+    {
+      "id": 6,
+      "type": "stat",
+      "title": "Reinicios nats-server (1h)",
+      "gridPos": { "h": 4, "w": 4, "x": 20, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "sum(changes(nats_server_start_seconds[1h]))", "legendFormat": "reinicios", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "none", "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "orange", "value": 1 } ] }, "noValue": "0" }, "overrides": [] },
+      "options": { "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, "colorMode": "background", "graphMode": "none", "textMode": "value" }
+    },
+    {
+      "id": 7,
+      "type": "timeseries",
+      "title": "Mensajes/s por nodo (in / out)",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 4 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [
+        { "refId": "A", "expr": "rate(nats_msgs_in_total[5m])", "legendFormat": "{{node}} · in", "datasource": { "type": "prometheus", "uid": "victoriametrics" } },
+        { "refId": "B", "expr": "rate(nats_msgs_out_total[5m])", "legendFormat": "{{node}} · out", "datasource": { "type": "prometheus", "uid": "victoriametrics" } }
+      ],
+      "fieldConfig": { "defaults": { "unit": "cps", "min": 0, "custom": { "drawStyle": "line", "fillOpacity": 10, "showPoints": "never", "lineWidth": 2 } }, "overrides": [] },
+      "options": { "legend": { "displayMode": "table", "placement": "right", "calcs": ["lastNotNull", "max"] }, "tooltip": { "mode": "multi", "sort": "desc" } }
+    },
+    {
+      "id": 8,
+      "type": "timeseries",
+      "title": "Conexiones por nodo",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 4 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "nats_connections", "legendFormat": "{{node}}", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "none", "min": 0, "custom": { "drawStyle": "line", "fillOpacity": 20, "showPoints": "never", "lineWidth": 2, "lineInterpolation": "stepAfter" } }, "overrides": [] },
+      "options": { "legend": { "displayMode": "table", "placement": "right", "calcs": ["lastNotNull", "max"] }, "tooltip": { "mode": "multi", "sort": "desc" } }
+    },
+    {
+      "id": 9,
+      "type": "timeseries",
+      "title": "KV bucket msgs (por bucket)",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 12 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "max by (bucket) (kv_bucket_msgs)", "legendFormat": "{{bucket}}", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "none", "min": 0, "custom": { "drawStyle": "line", "fillOpacity": 10, "showPoints": "never", "lineWidth": 2, "lineInterpolation": "stepAfter" } }, "overrides": [] },
+      "options": { "legend": { "displayMode": "table", "placement": "right", "calcs": ["lastNotNull"] }, "tooltip": { "mode": "multi", "sort": "desc" } }
+    },
+    {
+      "id": 10,
+      "type": "timeseries",
+      "title": "Memoria nats-server por nodo",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 12 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "nats_mem_bytes", "legendFormat": "{{node}}", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "bytes", "min": 0, "custom": { "drawStyle": "line", "fillOpacity": 10, "showPoints": "never", "lineWidth": 2 } }, "overrides": [] },
+      "options": { "legend": { "displayMode": "table", "placement": "right", "calcs": ["lastNotNull", "max"] }, "tooltip": { "mode": "multi", "sort": "desc" } }
+    },
+    {
+      "id": 11,
+      "type": "table",
+      "title": "Leader RAFT por stream",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 20 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "nats_jetstream_raft_leader == 1", "format": "table", "instant": true, "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "transformations": [
+        { "id": "organize", "options": { "excludeByName": { "Time": true, "instance": true, "__name__": true, "job": true, "Value": true }, "renameByName": { "stream": "Stream", "node": "Leader" }, "indexByName": { "stream": 0, "node": 1 } } }
+      ],
+      "fieldConfig": { "defaults": { "custom": { "align": "left" }, "noValue": "n/d (sin métricas NATS o sin quorum)" }, "overrides": [] },
+      "options": { "showHeader": true }
+    },
+    {
+      "id": 12,
+      "type": "table",
+      "title": "JetStream por nodo",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 20 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [
+        { "refId": "streams", "expr": "last_over_time(nats_jetstream_streams[2m])", "format": "table", "instant": true, "datasource": { "type": "prometheus", "uid": "victoriametrics" } },
+        { "refId": "messages", "expr": "last_over_time(nats_jetstream_messages[2m])", "format": "table", "instant": true, "datasource": { "type": "prometheus", "uid": "victoriametrics" } },
+        { "refId": "bytes", "expr": "last_over_time(nats_jetstream_bytes[2m])", "format": "table", "instant": true, "datasource": { "type": "prometheus", "uid": "victoriametrics" } },
+        { "refId": "subs", "expr": "last_over_time(nats_subscriptions[2m])", "format": "table", "instant": true, "datasource": { "type": "prometheus", "uid": "victoriametrics" } }
+      ],
+      "transformations": [
+        { "id": "joinByField", "options": { "byField": "node", "mode": "outer" } },
+        { "id": "organize", "options": { "excludeByName": { "Time": true, "Time 1": true, "Time 2": true, "Time 3": true, "Time 4": true, "instance": true, "instance 1": true, "instance 2": true, "instance 3": true, "instance 4": true, "__name__": true, "__name__ 1": true, "__name__ 2": true, "__name__ 3": true, "__name__ 4": true, "job": true, "job 1": true, "job 2": true, "job 3": true, "job 4": true }, "renameByName": { "node": "Nodo", "Value #streams": "streams", "Value #messages": "messages", "Value #bytes": "bytes", "Value #subs": "subs" } } }
+      ],
+      "fieldConfig": { "defaults": { "custom": { "align": "center" } }, "overrides": [ { "matcher": { "id": "byName", "options": "bytes" }, "properties": [ { "id": "unit", "value": "bytes" } ] } ] },
+      "options": { "showHeader": true }
+    }
+  ]
+}