Add a laconicd Grafana dashboard to monitoring stack (#799)

Part of https://www.notion.so/Monitoring-and-alerting-for-laconicd-86727c3b4dde4dc993d87d6e29f935fe

- Add a laconicd Grafana dashboard
  - Update fixturenet-laconicd script to expose metrics
- Upgrade Grafana version to avoid errors while saving changes made to a dashboard (see [thread](https://community.grafana.com/t/error-cannot-add-property-ishandled-object-is-not-extensible/109268))
-  Add an alert rule for Ajna watcher

Reviewed-on: #799
Co-authored-by: Prathamesh Musale <prathamesh.musale0@gmail.com>
Co-committed-by: Prathamesh Musale <prathamesh.musale0@gmail.com>

stack_orchestrator/data/compose/docker-compose-grafana.yml

@@ -2,7 +2,7 @@ version: "3.7"
 
 services:
   grafana:
-    image: grafana/grafana:10.2.2
+    image: grafana/grafana:10.2.3
     restart: always
     environment:
       GF_SERVER_ROOT_URL: ${GF_SERVER_ROOT_URL}

stack_orchestrator/data/config/fixturenet-laconicd/create-fixturenet.sh

@@ -102,6 +102,17 @@ if [ "$1" == "clean" ] || [ ! -d "$HOME/.laconicd/data/blockstore.db" ]; then
     fi
   fi
 
+  # Enable telemetry (prometheus metrics: http://localhost:1317/metrics?format=prometheus)
+  if [[ "$OSTYPE" == "darwin"* ]]; then
+    sed -i '' 's/enabled = false/enabled = true/g' $HOME/.laconicd/config/app.toml
+    sed -i '' 's/prometheus-retention-time = 0/prometheus-retention-time = 60/g' $HOME/.laconicd/config/app.toml
+    sed -i '' 's/prometheus = false/prometheus = true/g' $HOME/.laconicd/config/config.toml
+  else
+    sed -i 's/enabled = false/enabled = true/g' $HOME/.laconicd/config/app.toml
+    sed -i 's/prometheus-retention-time = 0/prometheus-retention-time = 60/g' $HOME/.laconicd/config/app.toml
+    sed -i 's/prometheus = false/prometheus = true/g' $HOME/.laconicd/config/config.toml
+  fi
+
   # Allocate genesis accounts (cosmos formatted addresses)
   laconicd add-genesis-account $KEY 100000000000000000000000000aphoton --keyring-backend $KEYRING
 

stack_orchestrator/data/config/monitoring/prometheus/prometheus.yml

@@ -65,3 +65,12 @@ scrape_configs:
         target_label: instance
       - target_label: __address__
         replacement: postgres-exporter:9187
+
+  - job_name: laconicd
+    metrics_path: /metrics
+    scrape_interval: 30s
+    static_configs:
+      # Add laconicd REST endpoint target with host and port (1317)
+      # - targets: ['example-host:1317']
+    params:
+      format: ['prometheus']

stack_orchestrator/data/config/monitoring/watcher-alert-rules.yml

@@ -771,3 +771,81 @@ groups:
         annotations:
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
+
+      # Ajna
+      - uid: ajna_diff_external
+        title: ajna_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="ajna", instance="ajna", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="filecoin"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
+        isPaused: false

stack_orchestrator/data/stacks/monitoring/README.md

@@ -4,6 +4,7 @@
 * Comes with the following built-in exporters / dashboards:
   * Chain Head Exporter - for tracking chain heads given external ETH RPC endpoints
   * Watchers dashboard
+  * laconicd dashboard
   * [Prometheus Blackbox](https://grafana.com/grafana/dashboards/7587-prometheus-blackbox-exporter/) - for tracking HTTP endpoints
   * [NodeJS Application Dashboard](https://grafana.com/grafana/dashboards/11159-nodejs-application-dashboard/) - for default NodeJS metrics
   * [PostgreSQL Database](https://grafana.com/grafana/dashboards/9628-postgresql-database/) - for monitoring Postgres dbs
@@ -99,6 +100,7 @@ laconic-so --stack monitoring deploy create --spec-file monitoring-spec.yml --de
       - targets:
         - <HTTP_ENDPOINT_1>
         - <HTTP_ENDPOINT_2>
+        - <LACONICD_GQL_ENDPOINT>
   ```
 
 * Postgres (in-stack exporter):
@@ -116,6 +118,16 @@ laconic-so --stack monitoring deploy create --spec-file monitoring-spec.yml --de
     ```
   * Add database credentials to be used in `auth_modules` in the postgres-exporter config file (`monitoring-deployment/config/monitoring/postgres-exporter.yml`)
 
+* laconicd: update the `laconicd` job with a laconicd node's REST endpoint host and port:
+
+  ```yml
+  ...
+  - job_name: laconicd
+  static_configs:
+    - targets: ['example-host:1317']
+  ...
+  ```
+
 Note: Use `host.docker.internal` as host to access ports on the host machine
 
 ### Grafana Config

stack_orchestrator/data/stacks/monitoring/monitoring-watchers.md

@@ -46,6 +46,11 @@ Add the following scrape configs to prometheus config file (`monitoring-watchers
     static_configs:
       - targets:
         - <AZIMUTH_GATEWAY_GQL_ENDPOINT>
+        - <LACONICD_GQL_ENDPOINT>
+  ...
+  - job_name: laconicd
+  static_configs:
+    - targets: ['LACONICD_REST_HOST:LACONICD_REST_PORT']
   ...
   - job_name: azimuth
     scrape_interval: 10s
@@ -98,6 +103,16 @@ Add the following scrape configs to prometheus config file (`monitoring-watchers
         labels:
           instance: 'merkl_sushiswap'
           chain: 'filecoin'
+
+  - job_name: ajna
+    scrape_interval: 20s
+    metrics_path: /metrics
+    scheme: http
+    static_configs:
+      - targets: ['AJNA_WATCHER_HOST:AJNA_WATCHER_PORT']
+        labels:
+          instance: 'ajna'
+          chain: 'filecoin'
   ```
 
 Add scrape config as done above for any additional watcher to add it to the Watchers dashboard.