Release 23.05

README.md

@@ -110,7 +110,7 @@ stock_fw_scrape_timeout = "5s"
 # maximal number of parallel scrape requests for stock FW devices
 stock_fw_scrape_max_concurrency = 40000
 ```
-### Braiins Farm Monitor Configutation
+### Braiins Farm Proxy Configutation
 Since Braiins Farm Proxy version 23.01, telemetry data are collected in order to be able to track technical issues, errors and future improvements of the application. In case the user doesn't want to send telemetry data to Braiins, he can opt out. Just add to the proxy configuration file following rows:
 
 ```

config/sample.toml

@@ -6,8 +6,6 @@ name = "S1"
 port = 3336
 # Bonus related to devfee
 #slushpool_bos_bonus = "bosBonusUserName"
-# BOS referral code
-#bos_referral_code = "referralCode"
 
 [[target]]
 # Name of this target

docker-compose.yml

@@ -5,7 +5,7 @@ volumes:
   scanner_data: {}
 services:
   farm-proxy:
-    image: braiinssystems/farm-proxy:23.01 # Will be replaced with braiinssystems/farm-proxy:TAG upon public release
+    image: braiinssystems/farm-proxy:23.05 # Will be replaced with braiinssystems/farm-proxy:TAG upon public release
     container_name: farm-proxy
     network_mode: "host"
     volumes:
@@ -21,6 +21,10 @@ services:
         max-size: "100m"
         max-file: "50"
         compress: "true"
+    ulimits:
+      nofile:
+        hard: "1048576"
+        soft: "262144"
   # metrics-exporter is a program, which performs device discovery on the defined network and pulls data from miners running a Stock FW. As a result, those data can be digested by Prometheus and visualized in Grafana dashboard, see dashboard "Farm Dashboard"
   metrics-exporter:
     image: braiinssystems/farm-monitor:23.01
@@ -57,31 +61,8 @@ services:
         compress: "true"
     labels:
       org.label-schema.group: "monitoring"
-      # nodeexporter is a container designed to monitor the host system, more info in https://github.com/prometheus/node_exporter
-      # nodeexporter:
-      #   image: prom/node-exporter:latest
-      #   container_name: nodeexporter
-      #   network_mode: "host"
-      #   volumes:
-      #     - /proc:/host/proc:ro
-      #     - /sys:/host/sys:ro
-      #     - /:/rootfs:ro
-      #   command:
-      #     - '--path.procfs=/host/proc'
-      #     - '--path.rootfs=/rootfs'
-      #     - '--path.sysfs=/host/sys'
-      #     - '--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|host|etc)($$|/)'
-      #   restart: unless-stopped
-      #   logging:
-      #     driver: "json-file"
-      #     options:
-      #       max-size: "10m"
-      #       max-file: "5"
-      #       compress: "true"
-      #   labels:
-      #     org.label-schema.group: "monitoring"
   grafana:
-    image: grafana/grafana:8.4.0
+    image: grafana/grafana:9.5.1
     container_name: grafana
     network_mode: "host"
     depends_on:

monitoring/grafana/provisioning/alerting/alerts.yml

@@ -0,0 +1,274 @@
+apiVersion: 1
+groups:
+    - orgId: 1
+      name: invalid-license
+      folder: Alerts
+      interval: 1m
+      rules:
+        - uid: LTLa_oaVz
+          title: Invalid Braiins OS+ Licences
+          condition: Condition
+          data:
+            - refId: A
+              relativeTimeRange:
+                from: 86400
+                to: 0
+              datasourceUid: PABF2E7BD7AE7B0F4
+              model:
+                editorMode: code
+                exemplar: false
+                expr: count(license_state{job="braiinsos-data"} > 1) > 0
+                hide: false
+                instant: false
+                intervalMs: 1000
+                legendFormat: __auto
+                maxDataPoints: 43200
+                range: true
+                refId: A
+            - refId: Number of affected miners
+              relativeTimeRange:
+                from: 86400
+                to: 0
+              datasourceUid: __expr__
+              model:
+                conditions:
+                    - evaluator:
+                        params: []
+                        type: gt
+                      operator:
+                        type: and
+                      query:
+                        params:
+                            - B
+                      reducer:
+                        params: []
+                        type: last
+                      type: query
+                datasource:
+                    type: __expr__
+                    uid: __expr__
+                expression: A
+                hide: false
+                intervalMs: 1000
+                maxDataPoints: 43200
+                reducer: last
+                refId: Number of affected miners
+                type: reduce
+            - refId: Condition
+              relativeTimeRange:
+                from: 86400
+                to: 0
+              datasourceUid: __expr__
+              model:
+                conditions:
+                    - evaluator:
+                        params:
+                            - 0
+                        type: gt
+                      operator:
+                        type: and
+                      query:
+                        params:
+                            - C
+                      reducer:
+                        params: []
+                        type: last
+                      type: query
+                datasource:
+                    type: __expr__
+                    uid: __expr__
+                expression: Number of affected miners
+                hide: false
+                intervalMs: 1000
+                maxDataPoints: 43200
+                refId: Condition
+                type: threshold
+          dashboardUid: syQG2Ha4z
+          panelId: 2
+          noDataState: OK
+          execErrState: Error
+          for: 5m
+          annotations:
+            __dashboardUid__: syQG2Ha4z
+            __panelId__: "2"
+            description: Invalid Licenses
+            summary: Invalid Licenses
+          labels:
+            severity: critical
+            type: license
+          isPaused: false
+        - uid: AhDpvAa4z
+          title: No Braiins OS+ Licences
+          condition: Condition
+          data:
+            - refId: A
+              relativeTimeRange:
+                from: 600
+                to: 0
+              datasourceUid: PABF2E7BD7AE7B0F4
+              model:
+                editorMode: code
+                expr: count(license_state{job="braiinsos-data"} == 0 and license_time_to_restricted_seconds < 55 * 60) > 0
+                hide: false
+                intervalMs: 1000
+                legendFormat: __auto
+                maxDataPoints: 43200
+                range: true
+                refId: A
+            - refId: Number of affected miners
+              relativeTimeRange:
+                from: 600
+                to: 0
+              datasourceUid: __expr__
+              model:
+                conditions:
+                    - evaluator:
+                        params: []
+                        type: gt
+                      operator:
+                        type: and
+                      query:
+                        params:
+                            - B
+                      reducer:
+                        params: []
+                        type: last
+                      type: query
+                datasource:
+                    type: __expr__
+                    uid: __expr__
+                expression: A
+                hide: false
+                intervalMs: 1000
+                maxDataPoints: 43200
+                reducer: last
+                refId: Number of affected miners
+                type: reduce
+            - refId: Condition
+              relativeTimeRange:
+                from: 600
+                to: 0
+              datasourceUid: __expr__
+              model:
+                conditions:
+                    - evaluator:
+                        params:
+                            - 0
+                        type: gt
+                      operator:
+                        type: and
+                      query:
+                        params:
+                            - C
+                      reducer:
+                        params: []
+                        type: last
+                      type: query
+                datasource:
+                    type: __expr__
+                    uid: __expr__
+                expression: Number of affected miners
+                hide: false
+                intervalMs: 1000
+                maxDataPoints: 43200
+                refId: Condition
+                type: threshold
+          dashboardUid: Kzx8BHa4k
+          panelId: 2
+          noDataState: OK
+          execErrState: Error
+          for: 5m
+          annotations:
+            __dashboardUid__: Kzx8BHa4k
+            __panelId__: "2"
+            description: No Braiins OS+ License
+            summary: No Braiins OS+ License
+          labels:
+            severity: warning
+            type: license
+          isPaused: false
+        - uid: GnxL0AaVz
+          title: Soon Expired Braiins OS+ Licences
+          condition: Condition
+          data:
+            - refId: A
+              relativeTimeRange:
+                from: 600
+                to: 0
+              datasourceUid: PABF2E7BD7AE7B0F4
+              model:
+                editorMode: code
+                expr: count(license_state{job="braiinsos-data",label=~"$label"} == 1 and license_time_to_restricted_seconds < 150 * 60) > 0
+                hide: false
+                intervalMs: 1000
+                legendFormat: __auto
+                maxDataPoints: 43200
+                range: true
+                refId: A
+            - refId: Number of affected miners
+              relativeTimeRange:
+                from: 600
+                to: 0
+              datasourceUid: __expr__
+              model:
+                conditions:
+                    - evaluator:
+                        params: []
+                        type: gt
+                      operator:
+                        type: and
+                      query:
+                        params:
+                            - B
+                      reducer:
+                        params: []
+                        type: last
+                      type: query
+                datasource:
+                    type: __expr__
+                    uid: __expr__
+                expression: A
+                hide: false
+                intervalMs: 1000
+                maxDataPoints: 43200
+                reducer: last
+                refId: Number of affected miners
+                type: reduce
+            - refId: Condition
+              relativeTimeRange:
+                from: 600
+                to: 0
+              datasourceUid: __expr__
+              model:
+                conditions:
+                    - evaluator:
+                        params:
+                            - 0
+                        type: gt
+                      operator:
+                        type: and
+                      query:
+                        params:
+                            - C
+                      reducer:
+                        params: []
+                        type: last
+                      type: query
+                datasource:
+                    type: __expr__
+                    uid: __expr__
+                expression: Number of affected miners
+                hide: false
+                intervalMs: 1000
+                maxDataPoints: 43200
+                refId: Condition
+                type: threshold
+          noDataState: OK
+          execErrState: Alerting
+          for: 5m
+          annotations:
+            summary: Soon Expired Braiins OS+ Licences
+          labels:
+            severity: warning
+            type: license
+          isPaused: false

monitoring/grafana/provisioning/alerting/contact-points.yml

@@ -0,0 +1,21 @@
+apiVersion: 1
+# more info here https://grafana.com/docs/grafana/latest/alerting/set-up/provision-alerting-resources/file-provisioning/
+contactPoints:
+  - orgId: 1
+    # in the file ./monitoring/grafana/provisioning/grafana.ini you need to define your [smtp] to be able to get email alerts
+    name: Email
+    receivers:
+      - uid: HNEU8Ta4zz
+        type: email
+        settings:
+          addresses: your_name@your_domain.cz
+          singleEmail: false
+        disableResolveMessage: true
+      # to be able to use Telegram, it is needed to generate BOT token. Here you can read how to do it https://medium.com/geekculture/generate-telegram-token-for-bot-api-d26faf9bf064
+      - uid: mOVzlTaVk
+        type: telegram
+        settings:
+          bottoken: "token" #Telegram bottoken in ""
+          chatid: "chat_id" #Telegram bottoken in ""
+          disable_notification: false
+        disableResolveMessage: true

monitoring/grafana/provisioning/alerting/mute-timings.yml

@@ -0,0 +1,17 @@
+apiVersion: 1
+
+# A mute timing is a recurring interval of time when no new notifications for a policy are generated or sent.
+# Use them to prevent alerts from firing a specific and reoccurring period, for example, a regular maintenance period.
+# Read more at https://grafana.com/docs/grafana/latest/alerting/manage-notifications/mute-timings/
+
+# To allow mute timings, uncomment time_intervals section with prepared simple config. User can modify it to meet his needs.
+# Read more about time interval at at https://prometheus.io/docs/alerting/latest/configuration/#time_interval-0
+muteTimes:
+  - orgId: 1
+    name: mti_1
+    #time_intervals:
+    #  - times:
+    #      - start_time: '09:00'
+    #        end_time: '17:00'
+    #    weekdays: ['monday:friday']
+

monitoring/grafana/provisioning/alerting/policy.yml

@@ -0,0 +1,11 @@
+apiVersion: 1
+
+policies:
+  - orgId: 1
+    receiver: Email
+    group_by: ['grafana_folder','alertname']
+    object_matchers:
+      - ['type', '=', 'license']
+    group_wait: 1m
+    group_interval: 5m
+    repeat_interval: 1h