cleanup and add alloy

README.md

@@ -0,0 +1,7 @@
+# Host visability 
+I would recommend using [this dashboard](https://grafana.com/grafana/dashboards/1860-node-exporter-full/).
+
+Use `docker compose -f node.yml up` on the devices you are monitoring
+
+Use `docker compose up` for the server that's collecting all the logs.
+

client/alloy-config.alloy

@@ -0,0 +1,15 @@
+local.file_match "caddy" {
+	path_targets = [{"__path__" = "/tmp/app-logs/debug.log"}]
+	sync_period = "5s"
+}
+
+loki.write "remote_loki" {
+	endpoint {
+		url = "http://10.50.50.x/loki/api/v1/push"
+	}
+}
+
+loki.source.file "local_files" {
+	targets 	= local.file_match.caddy.targets
+	forward_to 	= [loki.write.local.loki.reciever]
+}

client/compose.yml

@@ -0,0 +1,20 @@
+services:
+  # monitor the host
+  node_exporter:
+    image: quay.io/prometheus/node-exporter:latest
+    command:
+      - '--path.rootfs=/host'
+    network_mode: host
+    # uses port 9100
+    pid: host
+    restart: unless-stopped
+    volumes:
+      - '/:/host:ro'
+  alloy:
+    image: grafana/alloy:latest
+    ports:
+      - 12345:12345
+    volumes:
+      - ./alloy-config.alloy:/etc/alloy/config.alloy
+      - ./logs:/tmp/app-logs/
+    command: run --server.http.listen-addr=0.0.0.0:12345 --storage.path=/var/lib/alloy/data /etc/alloy/config.alloy

deploy-node.sh

@@ -0,0 +1,3 @@
+wget https://git.oliveratkinson.net/Oliver/linux-node-visability/raw/branch/master/compose-node.yml
+sudo ufw allow from 10.50.50.0/24 to any port 9100
+docker compose -f compose-node.yml up -d

main.py

@@ -1,46 +0,0 @@
-import time
-import board
-import adafruit_dht
-from http.server import BaseHTTPRequestHandler, HTTPServer
-
-sensor = adafruit_dht.DHT22(board.D21)
-
-hostName = "0.0.0.0"
-serverPort = 7070
-
-class MyServer(BaseHTTPRequestHandler):
-    def do_GET(self):
-        try:
-            # Print the values to the serial port
-            temperature_c = sensor.temperature
-            temperature_f = temperature_c * (9 / 5) + 32
-            humidity = sensor.humidity
-            self.send_response(200)
-            self.send_header("Content-type", "text/plain")
-            self.end_headers()
-            self.wfile.write(bytes("# TYPE target_info gauge\n", "utf-8"))
-            self.wfile.write(bytes("humidity{{location=\"beddroom\"}} {}\n".format(humidity), "utf-8"))
-
-            self.wfile.write(bytes("# TYPE temperature gauge\n", "utf-8"))
-            self.wfile.write(bytes("temperature{{location=\"beddroom\"}} {}\n".format(temperature_f), "utf-8"))
-
-        except RuntimeError as error:
-            # Errors happen fairly often, DHT's are hard to read, just keep going
-            self.send_response(500)
-            print(error.args[0])
-        except Exception as error:
-            self.send_response(500)
-            sensor.exit()
-            raise error
-
-if __name__ == "__main__":
-    webServer = HTTPServer((hostName, serverPort), MyServer)
-    print("Server started http://%s:%s" % (hostName, serverPort))
-
-    try:
-        webServer.serve_forever()
-    except KeyboardInterrupt:
-        pass
-
-    webServer.server_close()
-    print("Server stopped.")

prometheus.yaml

@@ -1,9 +0,0 @@
-global:
-  scrape_interval: 15s 
-  query_log_file: /etc/prometheus/query.log
-
-scrape_configs:
-  - job_name: bedroom
-    static_configs:
-      - targets: ['192.168.8.79:7070']
-

server/Caddyfile

@@ -0,0 +1,26 @@
+{
+	admin :2019
+
+	servers :3000 {
+		name grafana
+		metrics
+	}
+
+	servers :3001 {
+		name loki
+		metrics
+	}
+
+	log debug {
+		level debug
+		output file /var/log/caddy/debug.log
+	}
+}
+
+:3000 {
+	reverse_proxy grafana:3000
+}
+
+:3100 {
+	reverse_proxy loki:3100
+}

server/compose.yml

@@ -1,4 +1,20 @@
 services:
+  # r-proxy
+  caddy:
+    image: caddy:latest
+    restart: unless-stopped
+    ports:
+      # HTTP
+      - 80:80
+      - 443:443
+      - '443:443/udp'
+      # Grafana
+      - 3000:3000
+      # Loki
+      - 3100:3100
+    volumes:
+      - ./Caddyfile:/etc/caddy/Caddyfile
+
   # Metrics collector
   prometheus:
     image: prom/prometheus:latest
@@ -8,9 +24,20 @@ services:
       - ./prometheus.yaml:/etc/prometheus/prometheus.yml
       # persist data
       - prometheus_storage:/prometheus
+    depends_on:
+      - caddy
     command: --web.enable-lifecycle --config.file=/etc/prometheus/prometheus.yml
 
-  # log viewer
+  # Logs
+  loki:
+    image: grafana/loki:2.9.2
+    expose:
+    - 3100
+    command: -config.file=/etc/loki/local-config.yaml
+    volumes:
+      - ./loki.yaml:/etc/loki/local-config.yaml
+
+  # Everything viewer
   grafana:
     image: grafana/grafana:latest
     volumes:
@@ -21,8 +48,8 @@ services:
       - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
       - GF_AUTH_DISABLE_LOGIN_FORM=true
       - GF_FEATURE_TOGGLES_ENABLE=traceqlEditor
-    ports:
+    expose:
-      - 3000:3000
+      - 3000
     depends_on:
       - prometheus
 

server/grafana.yaml

@@ -13,3 +13,12 @@ datasources:
   editable: false
   jsonData:
     httpMethod: GET
+- name: Loki
+  type: loki
+  access: proxy 
+  orgId: 1
+  url: http://loki:3100
+  basicAuth: false
+  isDefault: false
+  version: 1
+  editable: false

server/prometheus.yaml

@@ -0,0 +1,15 @@
+global:
+  scrape_interval: 15s 
+  query_log_file: /etc/prometheus/query.log
+
+scrape_configs:
+  - job_name: caddy
+    static_configs:
+      - targets: ['caddy:2019']
+  - job_name: node
+    static_configs:
+      # put a list of all the nodes you are monitoring
+      - targets: ['10.0.0.92:9100']
+  - job_name: prometheus
+    static_configs:
+      - targets: ['localhost:9090']