Fix telemetry dashboard variables and parameterize gNMI targets

The telemetry dashboards' router/interface variables used a keep|distinct
Flux pattern that returned only one source; switch to schema.tagValues so all
streaming routers and interfaces are listed. Parameterize telegraf.conf gNMI
addresses and credentials via GNMI_ADDRESSES/GNMI_USERNAME/GNMI_PASSWORD so
the telemetry fleet can scale without editing the config.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.env.example

@@ -25,6 +25,13 @@ PSQL_MEM_LIMIT=6g
 PSQL_APP_MEM_LIMIT=4g
 KAFKA_MEM_LIMIT=4g
 
+# gNMI streaming telemetry (telegraf, test profile). GNMI_ADDRESSES is a
+# quoted, comma-separated host:port list — add a router here once gNMI/grpc
+# is enabled on it and the management path is reachable.
+GNMI_ADDRESSES="10.100.0.100:57400", "10.100.0.200:57400"
+GNMI_USERNAME=changeme
+GNMI_PASSWORD=changeme
+
 # ---------------------------------------------------------------------------
 # ExaBGP route injector (test profile)
 # ---------------------------------------------------------------------------

docker-compose.yml

@@ -284,6 +284,11 @@ services:
       - influxdb
     environment:
       - INFLUXDB_TOKEN=openbmp-telemetry-token
+      # gNMI fleet — quoted, comma-separated host:port list. Default = the two
+      # ESXi CORE routers; extend via GNMI_ADDRESSES in .env for more routers.
+      - 'GNMI_ADDRESSES=${GNMI_ADDRESSES:-"10.100.0.100:57400", "10.100.0.200:57400"}'
+      - GNMI_USERNAME=${GNMI_USERNAME:-webui}
+      - GNMI_PASSWORD=${GNMI_PASSWORD:-cisco}
 
   # --- Phase 4: Traffic Generator ---
 

obmp-grafana/dashboards/Telemetry-3001/combined_bmp_telemetry.json

@@ -48,7 +48,7 @@
         "multi": true,
         "name": "router",
         "options": [],
-        "query": "from(bucket: \"telemetry\")\n  |> range(start: -1h)\n  |> filter(fn: (r) => r._measurement == \"interface_counters\")\n  |> keep(columns: [\"source\"])\n  |> distinct(column: \"source\")\n  |> sort()",
+        "query": "import \"influxdata/influxdb/schema\"\nschema.tagValues(bucket: \"telemetry\", tag: \"source\", predicate: (r) => r._measurement == \"interface_counters\", start: -1h)",
         "refresh": 2,
         "regex": "",
         "type": "query"

obmp-grafana/dashboards/Telemetry-3001/interface_errors.json

@@ -48,7 +48,7 @@
         "multi": true,
         "name": "router",
         "options": [],
-        "query": "from(bucket: \"telemetry\")\n  |> range(start: -1h)\n  |> filter(fn: (r) => r._measurement == \"interface_counters\")\n  |> keep(columns: [\"source\"])\n  |> distinct(column: \"source\")\n  |> sort()",
+        "query": "import \"influxdata/influxdb/schema\"\nschema.tagValues(bucket: \"telemetry\", tag: \"source\", predicate: (r) => r._measurement == \"interface_counters\", start: -1h)",
         "refresh": 2,
         "regex": "",
         "type": "query"
@@ -66,7 +66,7 @@
         "multi": true,
         "name": "interface",
         "options": [],
-        "query": "from(bucket: \"telemetry\")\n  |> range(start: -1h)\n  |> filter(fn: (r) => r._measurement == \"interface_counters\")\n  |> filter(fn: (r) => r.source =~ /${router:regex}/)\n  |> keep(columns: [\"name\"])\n  |> distinct(column: \"name\")\n  |> sort()",
+        "query": "import \"influxdata/influxdb/schema\"\nschema.tagValues(bucket: \"telemetry\", tag: \"name\", predicate: (r) => r._measurement == \"interface_counters\" and r.source =~ /${router:regex}/, start: -1h)",
         "refresh": 2,
         "regex": "",
         "type": "query"

obmp-grafana/dashboards/Telemetry-3001/interface_utilization.json

@@ -48,7 +48,7 @@
         "multi": true,
         "name": "router",
         "options": [],
-        "query": "from(bucket: \"telemetry\")\n  |> range(start: -1h)\n  |> filter(fn: (r) => r._measurement == \"interface_counters\")\n  |> keep(columns: [\"source\"])\n  |> distinct(column: \"source\")\n  |> sort()",
+        "query": "import \"influxdata/influxdb/schema\"\nschema.tagValues(bucket: \"telemetry\", tag: \"source\", predicate: (r) => r._measurement == \"interface_counters\", start: -1h)",
         "refresh": 2,
         "regex": "",
         "type": "query"
@@ -66,7 +66,7 @@
         "multi": true,
         "name": "interface",
         "options": [],
-        "query": "from(bucket: \"telemetry\")\n  |> range(start: -1h)\n  |> filter(fn: (r) => r._measurement == \"interface_counters\")\n  |> filter(fn: (r) => r.source =~ /${router:regex}/)\n  |> keep(columns: [\"name\"])\n  |> distinct(column: \"name\")\n  |> sort()",
+        "query": "import \"influxdata/influxdb/schema\"\nschema.tagValues(bucket: \"telemetry\", tag: \"name\", predicate: (r) => r._measurement == \"interface_counters\" and r.source =~ /${router:regex}/, start: -1h)",
         "refresh": 2,
         "regex": "",
         "type": "query"

telegraf/telegraf.conf

@@ -17,15 +17,16 @@
 #                            INPUT PLUGINS                                    #
 ###############################################################################
 
-## CORE routers (directly reachable on port 57400 from host)
+## gNMI targets — driven by environment variables so the telemetry fleet can
-## R9K routers (10.100.0.1-7) are blocked by CML management network filtering
+## scale without editing this file. Set in .env:
+##   GNMI_ADDRESSES — quoted, comma-separated host:port list, e.g.
+##     GNMI_ADDRESSES="10.0.0.1:57400", "10.0.0.2:57400"
+##   GNMI_USERNAME / GNMI_PASSWORD — gNMI credentials (uniform across the fleet)
+## Every target must have gNMI/grpc enabled and be reachable on the gRPC port.
 [[inputs.gnmi]]
-  addresses = [
+  addresses = [ ${GNMI_ADDRESSES} ]
-    "10.100.0.100:57400",
+  username = "${GNMI_USERNAME}"
-    "10.100.0.200:57400"
+  password = "${GNMI_PASSWORD}"
-  ]
-  username = "webui"
-  password = "cisco"
 
   ## No TLS (lab environment)
   enable_tls = false