docs: Update deploy docs and adds prometheus basic auth back

README.md

@@ -18,32 +18,18 @@ It's based heavily on the [monitoring-lite](https://git.coopcloud.tech/coop-clou
 
 <!-- endmetadata -->
 
-## Setup a Metrics Gathering
+## Setup Metrics Gathering
 
 Where gathering.org is the node you want to gather metrics from.
 
 1. Configure DNS
-  - monitoring.gathering.org
   - cadvisor.monitoring.gathering.org
   - node.monitoring.gathering.org
-1. Configure Traefik to use BasicAuth
-  * `abra app config traefik.gathering.org`
-  uncomment
-  ```
-  # BASIC_AUTH
-  COMPOSE_FILE="$COMPOSE_FILE:compose.basicauth.yml"
-  BASIC_AUTH=1
-  SECRET_USERSFILE_VERSION=v1
-  ```
-  - Generate userslist with httpasswd hashed password
-    `abra app secret insert traefik.gathering.org usersfile v1 'admin:<hashed-secret>'`
-    make sure there is no whitespace in between `admin:<hashed-secret>`, it seems to break stuff...
-  - `abra app deploy -f traefik`
-1. `abra app new monitoring-ng`
-1. `abra app config monitoring.gathering.org`
-   for gathering only the main `compose.yml` is needed, nothing more.
-1. `abra app deploy monitoring.gathering.org`
-1. check that endpoints are up and basic-auth works
+2. [Configure Traefik to use BasicAuth](https://git.coopcloud.tech/coop-cloud/traefik#configuring-wildcard-ssl-using-dns)
+3. `abra app new monitoring-ng`
+4. `abra app config monitoring.gathering.org` (for gathering only the main `compose.yml` is needed, nothing more.)
+5. `abra app deploy monitoring.gathering.org`
+6. check that endpoints are up and basic-auth works
   - cadvisor.monitoring.gathering.org
   - node.monitoring.gathering.org
 
@@ -56,16 +42,13 @@ In case you have no traefik running on the machine, you can expose the ports dir
 
 ## Setup Metrics Browser
 
+This builds upon [Setup Metrics Gathering](#setup-metrics-grathering) so make sure you did that first.
 
 1. Configure DNS
    - monitoring.example.org
-   - prometheus.monitoring.example.org
-   - loki.monitoring.example.org
 2. Setup monitoring stack
-   - `abra app new monitoring-ng`
-   - `abra app config monitoring.example.org`
-      Uncomment all the stuff
-   - `abra app secret insert monitoring.example.org basic_auth v1 <secret>`
+   - `abra app config monitoring.example.org` Uncomment prometheus, loki and grafana
+   - `abra app secret insert monitoring.example.org basic_auth v1 <password>`
       this needs the plaintext traefik basic-auth secret, not the hashed one!
    - `abra app secret ls monitoring.example.org`
    - `abra app deploy monitoring.example.org`

compose.prometheus.yml

@@ -30,6 +30,7 @@ services:
         - "traefik.http.routers.${STACK_NAME}-prometheus.entrypoints=web-secure"
         - "traefik.http.routers.${STACK_NAME}-prometheus.tls=true"
         - "traefik.http.routers.${STACK_NAME}-prometheus.tls.certresolver=${LETS_ENCRYPT_ENV}"
+        - "traefik.http.routers.${STACK_NAME}-prometheus.middlewares=basicauth@file"
 
 configs:
   prometheus_yml:

grafana-alerts.json.tmpl

@@ -68,76 +68,50 @@
           "condition": "B",
           "data": [
             {
+              "refId": "A",
+              "relativeTimeRange": { "from": 600, "to": 0 },
+              "datasourceUid": "PBFA97CFB590B2093",
+              "model": {
+                "disableTextWrap": false,
+                "editorMode": "builder",
+                "expr": "rate(backup[24h])",
+                "fullMetaSearch": false,
+                "includeNullMetadata": true,
+                "instant": true,
+                "intervalMs": 1000,
+                "legendFormat": "__auto",
+                "maxDataPoints": 43200,
+                "range": false,
                 "refId": "A",
-                "relativeTimeRange": {
-                    "from": 28800,
-                    "to": 0
-                },
-                "datasourceUid": "PBFA97CFB590B2093",
-                "model": {
-                    "disableTextWrap": false,
-                    "editorMode": "code",
-                    "expr": "rate(backup[25h]) == 0",
-                    "fullMetaSearch": false,
-                    "includeNullMetadata": true,
-                    "instant": true,
-                    "intervalMs": 1000,
-                    "legendFormat": "__auto",
-                    "maxDataPoints": 43200,
-                    "range": false,
-                    "refId": "A",
-                    "useBackend": false
-                }
+                "useBackend": false
+              }
             },
             {
+              "refId": "B",
+              "relativeTimeRange": { "from": 600, "to": 0 },
+              "datasourceUid": "__expr__",
+              "model": {
+                "conditions": [
+                  {
+                    "evaluator": { "params": [0, 0], "type": "within_range" },
+                    "operator": { "type": "and" },
+                    "query": { "params": ["C"] },
+                    "reducer": { "params": [], "type": "last" },
+                    "type": "query"
+                  }
+                ],
+                "datasource": { "type": "__expr__", "uid": "__expr__" },
+                "expression": "A",
+                "intervalMs": 1000,
+                "maxDataPoints": 43200,
                 "refId": "B",
-                "relativeTimeRange": {
-                    "from": 28800,
-                    "to": 0
-                },
-                "datasourceUid": "__expr__",
-                "model": {
-                    "conditions": [
-                        {
-                            "evaluator": {
-                                "params": [
-                                    -1,
-                                    0
-                                ],
-                                "type": "gt"
-                            },
-                            "operator": {
-                                "type": "and"
-                            },
-                            "query": {
-                                "params": []
-                            },
-                            "reducer": {
-                                "params": [],
-                                "type": "avg"
-                            },
-                            "type": "query"
-                        }
-                    ],
-                    "datasource": {
-                        "name": "Expression",
-                        "type": "__expr__",
-                        "uid": "__expr__"
-                    },
-                    "expression": "A",
-                    "hide": false,
-                    "intervalMs": 1000,
-                    "maxDataPoints": 43200,
-                    "refId": "B",
-                    "type": "threshold"
-                }
+                "type": "threshold"
+              }
             }
           ],
           "noDataState": "NoData",
           "execErrState": "Error",
           "for": "5m",
-          "annotations": {},
-          "labels": {},
           "isPaused": false
         },
         {{ end }}
@@ -214,9 +188,9 @@
             ],
             "noDataState": "NoData",
             "execErrState": "Error",
-            "for": "60m",
+            "for": "20m",
             "annotations": {
-                "summary": "Backup did not finish within 60 minutes"
+                "summary": "Backup did not finish within 20 minutes"
             },
             "labels": {},
             "isPaused": false