First test kinda working

2026-05-12 11:21:40 -04:00
parent cac6c9ac02
commit d3f09ee062
36 changed files with 3903 additions and 102 deletions
--- a/dashboards/runtime.json
+++ b/dashboards/runtime.json
@@ -0,0 +1,148 @@
+{
+  "title": "quic_ecs_dt — substrate runtime",
+  "uid": "quic-ecs-dt-runtime",
+  "schemaVersion": 39,
+  "version": 1,
+  "timezone": "",
+  "refresh": "5s",
+  "time": { "from": "now-15m", "to": "now" },
+  "tags": ["quic_ecs_dt", "ucami2026", "substrate"],
+  "templating": {
+    "list": [
+      {
+        "name": "datasource",
+        "label": "Data source",
+        "type": "datasource",
+        "query": "prometheus",
+        "current": { "selected": false, "text": "Prometheus", "value": "Prometheus" },
+        "hide": 0
+      }
+    ]
+  },
+  "panels": [
+    {
+      "id": 1,
+      "title": "Tick rate (Hz)",
+      "type": "stat",
+      "gridPos": { "h": 4, "w": 6, "x": 0, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": { "defaults": { "unit": "hertz", "decimals": 1 } },
+      "targets": [
+        { "expr": "substrate_tick_hz", "refId": "A", "legendFormat": "tick_hz" }
+      ]
+    },
+    {
+      "id": 2,
+      "title": "Entities",
+      "type": "stat",
+      "gridPos": { "h": 4, "w": 6, "x": 6, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": { "defaults": { "unit": "short" } },
+      "targets": [
+        { "expr": "substrate_entities", "refId": "A", "legendFormat": "entities" }
+      ]
+    },
+    {
+      "id": 3,
+      "title": "RSS",
+      "type": "stat",
+      "gridPos": { "h": 4, "w": 6, "x": 12, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": { "defaults": { "unit": "bytes", "decimals": 1 } },
+      "targets": [
+        { "expr": "substrate_rss_bytes", "refId": "A", "legendFormat": "rss" }
+      ]
+    },
+    {
+      "id": 4,
+      "title": "T3 — no handler events (cumulative)",
+      "type": "stat",
+      "gridPos": { "h": 4, "w": 6, "x": 18, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": { "defaults": { "unit": "short" } },
+      "targets": [
+        { "expr": "substrate_t3_no_handler_total", "refId": "A", "legendFormat": "no_handler" }
+      ]
+    },
+    {
+      "id": 5,
+      "title": "Per-tier receive rate",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 4 },
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": { "defaults": { "unit": "cps" } },
+      "targets": [
+        {
+          "expr": "rate(substrate_received_total[1m])",
+          "refId": "A",
+          "legendFormat": "received {{tier}}"
+        },
+        {
+          "expr": "rate(substrate_dropped_total[1m])",
+          "refId": "B",
+          "legendFormat": "dropped {{tier}}"
+        }
+      ]
+    },
+    {
+      "id": 6,
+      "title": "Per-tier latency (µs)",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 4 },
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": { "defaults": { "unit": "µs", "decimals": 0 } },
+      "targets": [
+        {
+          "expr": "substrate_latency_us{quantile=\"0.5\"}",
+          "refId": "A",
+          "legendFormat": "p50 {{tier}}"
+        },
+        {
+          "expr": "substrate_latency_us{quantile=\"0.99\"}",
+          "refId": "B",
+          "legendFormat": "p99 {{tier}}"
+        },
+        {
+          "expr": "substrate_latency_us{quantile=\"0.999\"}",
+          "refId": "C",
+          "legendFormat": "p999 {{tier}}"
+        }
+      ]
+    },
+    {
+      "id": 7,
+      "title": "Channel depth (vs. capacity)",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 12 },
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": { "defaults": { "unit": "short" } },
+      "targets": [
+        {
+          "expr": "substrate_channel_depth",
+          "refId": "A",
+          "legendFormat": "depth {{tier}}"
+        },
+        {
+          "expr": "substrate_channel_capacity",
+          "refId": "B",
+          "legendFormat": "capacity {{tier}}"
+        }
+      ]
+    },
+    {
+      "id": 8,
+      "title": "Decode errors (rate)",
+      "type": "timeseries",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 12 },
+      "datasource": { "type": "prometheus", "uid": "${datasource}" },
+      "fieldConfig": { "defaults": { "unit": "cps" } },
+      "targets": [
+        {
+          "expr": "rate(substrate_decode_errors_total[1m])",
+          "refId": "A",
+          "legendFormat": "decode_errors {{tier}}"
+        }
+      ]
+    }
+  ]
+}