grafana: init

Shows powerdraw, temps, uptime, and jellyfin streams

configuration.nix

@@ -47,6 +47,7 @@
     ./services/soulseek.nix
 
     ./services/ups.nix
+    ./services/monitoring.nix
 
     ./services/bitwarden.nix
     ./services/firefox-syncserver.nix

service-configs.nix

@@ -153,6 +153,22 @@ rec {
         port = 8020;
         proto = "tcp";
       };
+      grafana = {
+        port = 3000;
+        proto = "tcp";
+      };
+      prometheus = {
+        port = 9090;
+        proto = "tcp";
+      };
+      prometheus_node = {
+        port = 9100;
+        proto = "tcp";
+      };
+      prometheus_apcupsd = {
+        port = 9162;
+        proto = "tcp";
+      };
     };
   };
 
@@ -266,6 +282,11 @@ rec {
     domain = "firefox-sync.${https.domain}";
   };
 
+  grafana = {
+    dir = services_dir + "/grafana";
+    domain = "grafana.${https.domain}";
+  };
+
   media = {
     moviesDir = torrents_path + "/media/movies";
     tvDir = torrents_path + "/media/tv";

services/monitoring.nix

@@ -0,0 +1,530 @@
+{
+  config,
+  pkgs,
+  service_configs,
+  lib,
+  ...
+}:
+let
+  textfileDir = "/var/lib/prometheus-node-exporter-textfiles";
+
+  promDs = {
+    type = "prometheus";
+    uid = "prometheus";
+  };
+
+  jellyfinCollector = pkgs.writeShellApplication {
+    name = "jellyfin-metrics-collector";
+    runtimeInputs = with pkgs; [
+      curl
+      jq
+    ];
+    text = ''
+      API_KEY=$(cat "$CREDENTIALS_DIRECTORY/jellyfin-api-key")
+      JELLYFIN="http://127.0.0.1:${toString service_configs.ports.private.jellyfin.port}"
+
+      if response=$(curl -sf --max-time 5 "''${JELLYFIN}/Sessions?api_key=''${API_KEY}"); then
+        active_streams=$(echo "$response" | jq '[.[] | select(.NowPlayingItem != null)] | length')
+      else
+        active_streams=0
+      fi
+
+      {
+        echo '# HELP jellyfin_active_streams Number of currently active Jellyfin streams'
+        echo '# TYPE jellyfin_active_streams gauge'
+        echo "jellyfin_active_streams $active_streams"
+      } > "${textfileDir}/jellyfin.prom.$$.tmp"
+      mv "${textfileDir}/jellyfin.prom.$$.tmp" "${textfileDir}/jellyfin.prom"
+    '';
+  };
+
+  dashboard = {
+    editable = true;
+    graphTooltip = 1;
+    schemaVersion = 39;
+    tags = [
+      "system"
+      "monitoring"
+    ];
+    time = {
+      from = "now-6h";
+      to = "now";
+    };
+    timezone = "browser";
+    title = "System Overview";
+    uid = "system-overview";
+
+    panels = [
+      # -- Row 1: UPS --
+      {
+        id = 1;
+        type = "timeseries";
+        title = "UPS Power Draw";
+        gridPos = {
+          h = 8;
+          w = 8;
+          x = 0;
+          y = 0;
+        };
+        datasource = promDs;
+        targets = [
+          {
+            datasource = promDs;
+            expr = "apcupsd_ups_load_percent / 100 * apcupsd_nominal_power_watts";
+            legendFormat = "Power (W)";
+            refId = "A";
+          }
+        ];
+        fieldConfig = {
+          defaults = {
+            unit = "watt";
+            color.mode = "palette-classic";
+            custom = {
+              lineWidth = 2;
+              fillOpacity = 20;
+              spanNulls = true;
+            };
+          };
+          overrides = [ ];
+        };
+      }
+      {
+        id = 7;
+        type = "stat";
+        title = "Energy Usage (24h)";
+        gridPos = {
+          h = 8;
+          w = 4;
+          x = 8;
+          y = 0;
+        };
+        datasource = promDs;
+        targets = [
+          {
+            datasource = promDs;
+            expr = "avg_over_time((apcupsd_ups_load_percent / 100 * apcupsd_nominal_power_watts)[24h:]) * 24 / 1000";
+            legendFormat = "";
+            refId = "A";
+          }
+        ];
+        fieldConfig = {
+          defaults = {
+            unit = "kwatth";
+            decimals = 2;
+            thresholds = {
+              mode = "absolute";
+              steps = [
+                {
+                  color = "green";
+                  value = null;
+                }
+                {
+                  color = "yellow";
+                  value = 5;
+                }
+                {
+                  color = "red";
+                  value = 10;
+                }
+              ];
+            };
+          };
+          overrides = [ ];
+        };
+        options = {
+          reduceOptions = {
+            calcs = [ "lastNotNull" ];
+            fields = "";
+            values = false;
+          };
+          colorMode = "value";
+          graphMode = "none";
+        };
+      }
+      {
+        id = 2;
+        type = "gauge";
+        title = "UPS Load";
+        gridPos = {
+          h = 8;
+          w = 6;
+          x = 12;
+          y = 0;
+        };
+        datasource = promDs;
+        targets = [
+          {
+            datasource = promDs;
+            expr = "apcupsd_ups_load_percent";
+            refId = "A";
+          }
+        ];
+        fieldConfig = {
+          defaults = {
+            unit = "percent";
+            min = 0;
+            max = 100;
+            thresholds = {
+              mode = "absolute";
+              steps = [
+                {
+                  color = "green";
+                  value = null;
+                }
+                {
+                  color = "yellow";
+                  value = 70;
+                }
+                {
+                  color = "red";
+                  value = 90;
+                }
+              ];
+            };
+          };
+          overrides = [ ];
+        };
+        options.reduceOptions = {
+          calcs = [ "lastNotNull" ];
+          fields = "";
+          values = false;
+        };
+      }
+      {
+        id = 3;
+        type = "gauge";
+        title = "UPS Battery";
+        gridPos = {
+          h = 8;
+          w = 6;
+          x = 18;
+          y = 0;
+        };
+        datasource = promDs;
+        targets = [
+          {
+            datasource = promDs;
+            expr = "apcupsd_battery_charge_percent";
+            refId = "A";
+          }
+        ];
+        fieldConfig = {
+          defaults = {
+            unit = "percent";
+            min = 0;
+            max = 100;
+            thresholds = {
+              mode = "absolute";
+              steps = [
+                {
+                  color = "red";
+                  value = null;
+                }
+                {
+                  color = "yellow";
+                  value = 20;
+                }
+                {
+                  color = "green";
+                  value = 50;
+                }
+              ];
+            };
+          };
+          overrides = [ ];
+        };
+        options.reduceOptions = {
+          calcs = [ "lastNotNull" ];
+          fields = "";
+          values = false;
+        };
+      }
+
+      # -- Row 2: System --
+      {
+        id = 4;
+        type = "timeseries";
+        title = "CPU Temperature";
+        gridPos = {
+          h = 8;
+          w = 12;
+          x = 0;
+          y = 8;
+        };
+        datasource = promDs;
+        targets = [
+          {
+            datasource = promDs;
+            expr = ''node_hwmon_temp_celsius{chip=~"pci.*"}'';
+            legendFormat = "CPU {{sensor}}";
+            refId = "A";
+          }
+        ];
+        fieldConfig = {
+          defaults = {
+            unit = "celsius";
+            color.mode = "palette-classic";
+            custom = {
+              lineWidth = 2;
+              fillOpacity = 10;
+              spanNulls = true;
+            };
+          };
+          overrides = [ ];
+        };
+      }
+      {
+        id = 5;
+        type = "stat";
+        title = "System Uptime";
+        gridPos = {
+          h = 8;
+          w = 6;
+          x = 12;
+          y = 8;
+        };
+        datasource = promDs;
+        targets = [
+          {
+            datasource = promDs;
+            expr = "time() - node_boot_time_seconds";
+            refId = "A";
+          }
+        ];
+        fieldConfig = {
+          defaults = {
+            unit = "s";
+            thresholds = {
+              mode = "absolute";
+              steps = [
+                {
+                  color = "green";
+                  value = null;
+                }
+              ];
+            };
+          };
+          overrides = [ ];
+        };
+        options = {
+          reduceOptions = {
+            calcs = [ "lastNotNull" ];
+            fields = "";
+            values = false;
+          };
+          colorMode = "value";
+          graphMode = "none";
+        };
+      }
+      {
+        id = 6;
+        type = "stat";
+        title = "Jellyfin Active Streams";
+        gridPos = {
+          h = 8;
+          w = 6;
+          x = 18;
+          y = 8;
+        };
+        datasource = promDs;
+        targets = [
+          {
+            datasource = promDs;
+            expr = "jellyfin_active_streams";
+            refId = "A";
+          }
+        ];
+        fieldConfig = {
+          defaults = {
+            thresholds = {
+              mode = "absolute";
+              steps = [
+                {
+                  color = "green";
+                  value = null;
+                }
+                {
+                  color = "yellow";
+                  value = 3;
+                }
+                {
+                  color = "red";
+                  value = 6;
+                }
+              ];
+            };
+          };
+          overrides = [ ];
+        };
+        options = {
+          reduceOptions = {
+            calcs = [ "lastNotNull" ];
+            fields = "";
+            values = false;
+          };
+          colorMode = "value";
+          graphMode = "area";
+        };
+      }
+    ];
+  };
+in
+{
+  imports = [
+    (lib.serviceMountWithZpool "grafana" service_configs.zpool_ssds [
+      service_configs.grafana.dir
+    ])
+    (lib.serviceFilePerms "grafana" [
+      "Z ${service_configs.grafana.dir} 0700 grafana grafana"
+    ])
+    (lib.serviceMountWithZpool "prometheus" service_configs.zpool_ssds [
+      "/var/lib/prometheus"
+    ])
+    (lib.serviceFilePerms "prometheus" [
+      "Z /var/lib/prometheus 0700 prometheus prometheus"
+    ])
+  ];
+
+  # -- Prometheus --
+  services.prometheus = {
+    enable = true;
+    port = service_configs.ports.private.prometheus.port;
+    listenAddress = "127.0.0.1";
+    stateDir = "prometheus";
+    retentionTime = "90d";
+
+    exporters = {
+      node = {
+        enable = true;
+        port = service_configs.ports.private.prometheus_node.port;
+        listenAddress = "127.0.0.1";
+        enabledCollectors = [
+          "hwmon"
+          "systemd"
+          "textfile"
+        ];
+        extraFlags = [
+          "--collector.textfile.directory=${textfileDir}"
+        ];
+      };
+
+      apcupsd = {
+        enable = true;
+        port = service_configs.ports.private.prometheus_apcupsd.port;
+        listenAddress = "127.0.0.1";
+        apcupsdAddress = "127.0.0.1:3551";
+      };
+    };
+
+    scrapeConfigs = [
+      {
+        job_name = "prometheus";
+        static_configs = [
+          { targets = [ "127.0.0.1:${toString service_configs.ports.private.prometheus.port}" ]; }
+        ];
+      }
+      {
+        job_name = "node";
+        static_configs = [
+          { targets = [ "127.0.0.1:${toString service_configs.ports.private.prometheus_node.port}" ]; }
+        ];
+      }
+      {
+        job_name = "apcupsd";
+        static_configs = [
+          { targets = [ "127.0.0.1:${toString service_configs.ports.private.prometheus_apcupsd.port}" ]; }
+        ];
+      }
+    ];
+  };
+
+  # -- Grafana --
+  services.grafana = {
+    enable = true;
+    dataDir = service_configs.grafana.dir;
+
+    settings = {
+      server = {
+        http_addr = "127.0.0.1";
+        http_port = service_configs.ports.private.grafana.port;
+        domain = service_configs.grafana.domain;
+        root_url = "https://${service_configs.grafana.domain}";
+      };
+
+      # Caddy handles auth -- disable Grafana login entirely
+      "auth.anonymous" = {
+        enabled = true;
+        org_role = "Admin";
+      };
+      "auth.basic".enabled = false;
+      "auth".disable_login_form = true;
+
+      analytics.reporting_enabled = false;
+    };
+
+    provision = {
+      datasources.settings = {
+        apiVersion = 1;
+        datasources = [
+          {
+            name = "Prometheus";
+            type = "prometheus";
+            url = "http://127.0.0.1:${toString service_configs.ports.private.prometheus.port}";
+            access = "proxy";
+            isDefault = true;
+            editable = false;
+            uid = "prometheus";
+          }
+        ];
+      };
+
+      dashboards.settings.providers = [
+        {
+          name = "system";
+          type = "file";
+          options.path = "/etc/grafana-dashboards";
+          disableDeletion = true;
+          updateIntervalSeconds = 60;
+        }
+      ];
+    };
+  };
+
+  # Provision dashboard JSON
+  environment.etc."grafana-dashboards/system-overview.json" = {
+    text = builtins.toJSON dashboard;
+    mode = "0444";
+  };
+
+  # Caddy reverse proxy with auth
+  services.caddy.virtualHosts."${service_configs.grafana.domain}".extraConfig = ''
+    import ${config.age.secrets.caddy_auth.path}
+    reverse_proxy :${builtins.toString service_configs.ports.private.grafana.port}
+  '';
+
+  # -- Jellyfin metrics collector --
+  # Queries the Jellyfin API for active streams and writes a .prom file
+  # for the node_exporter textfile collector.
+  systemd.services.jellyfin-metrics-collector = {
+    description = "Collect Jellyfin metrics for Prometheus";
+    after = [ "network.target" ];
+    serviceConfig = {
+      Type = "oneshot";
+      ExecStart = lib.getExe jellyfinCollector;
+      LoadCredential = "jellyfin-api-key:${config.age.secrets.jellyfin-api-key.path}";
+    };
+  };
+
+  systemd.timers.jellyfin-metrics-collector = {
+    wantedBy = [ "timers.target" ];
+    timerConfig = {
+      OnCalendar = "*:*:0/30";
+      RandomizedDelaySec = "5s";
+    };
+  };
+
+  # Ensure textfile collector directory exists (tmpfs root -- recreated on boot)
+  systemd.tmpfiles.rules = [
+    "d ${textfileDir} 0755 root root -"
+  ];
+}