fix: scrape once per hour

.env.sample

@@ -53,10 +53,6 @@ SECRET_BASIC_AUTH_VERSION=v1
 # Not needed if you just want to read local log files — use SYSLOG_FILES instead.
 # SYSLOG=1
 # COMPOSE_FILE="$COMPOSE_FILE:compose.syslog.yml"
-#
-# Scrape Docker-Events via official docker-cli image using docker socket
-# COMPOSE_FILE="$COMPOSE_FILE:compose.docker-events.yml"
-
 
 # Monitor physical disks health
 # COMPOSE_FILE="$COMPOSE_FILE:compose.smartctl.yml"

.gitea/CODEOWNERS

@@ -1 +0,0 @@
-* @coop-cloud/monitoring-ng-maintainers

MAINTENANCE.md

@@ -1,35 +0,0 @@
-# Monitoring NG Recipe Maintenance
-
-All contributions should be made via a pull request. This is to ensure a
-certain quality and consistency, that others can rely on.
-
-## Maintainer Responsibilities
-
-A recipe maintainer has the following responsibilities:
-
-- Respond to pull requests / issues within two weeks
-- Make image security updates within a week
-- Make image major updates every three months
-
-In order to fullfill these responsibilities a recipe maintainer:
-
-- Has to watch the repository (to get notifications)
-- Needs to make sure renovate is configured properly
-
-## Pull Requests
-
-A pull request can be merged if it is approved by at least one maintainer. For
-pull requests opened by a maintainer they need to be approved by another
-maintainer. Even though it is okay to merge a pull request with one approval, it
-is always better if all maintainers looked at the pull request and approved it.
-
-## Become a maintainer
-
-Everyone can apply to be a recipe maintainer:
-1. Watch the repository to always get updates
-2. Simply add your self to the list in the [README.md](./README.md) and open a new pull request with the change.
-3. Once the pull request gets merged you will be added to the
-   [monitoring-ng maintainers
-   team](https://git.coopcloud.tech/org/coop-cloud/teams/monitoring-ng-maintainers).
-4. Join the room
-   [#cc-|-monitoring-ng-maintenance:matrix.org](#cc-|-monitoring-ng-maintenance:matrix.org) and chat to other maintainers.

README.md

@@ -7,7 +7,7 @@ It's based heavily on the [monitoring-lite](https://git.coopcloud.tech/coop-clou
 Metrics and logs are collected by [Grafana Alloy](https://grafana.com/docs/alloy/latest/) and pushed to a central Prometheus/Loki (via `remote_write`/`loki push`). Every `monitoring-ng` instance runs its own Alloy, whether or not it also runs the central stack.
 
 <!-- metadata -->
-- **Maintainer**: [@coop-cloud/monitoring-ng-maintainers](https://git.coopcloud.tech/org/coop-cloud/teams/monitoring-ng-maintainers)
+
 - **Category**: Apps
 - **Status**: 2, beta
 - **Image**: [`grafana/grafana`](https://hub.docker.com/r/grafana/grafana), 4, upstream
@@ -54,14 +54,6 @@ This is what a gathering host pushes into. It also runs its own Alloy, so it mon
 
 ## Additional features
 
-### Scrape docker events
-
-Just uncomment the following line in your .env to collect docker events using
-the official docker-cli image and the docker socket:
-```
-COMPOSE_FILE="$COMPOSE_FILE:compose.docker-events.yml"
-```
-
 ### Discovering metrics from other apps
 
 Alloy auto-discovers and scrapes other Docker Swarm services running on the same host, on the `proxy` network, that opt in via labels. No manual scrape config needed. On the app's `compose.yml`:

abra.sh

@@ -9,8 +9,8 @@ export LOKI_YML_VERSION=v3
 export PROMETHEUS_YML_VERSION=v2
 export MATRIX_ALERTMANAGER_CONFIG_VERSION=v1
 export MATRIX_ALERTMANAGER_ENTRYPOINT_VERSION=v1
-export GF_ALERTS_NODE_VERSION=v4
-export CONFIG_ALLOY_VERSION=v3
+export GF_ALERTS_NODE_VERSION=v3
+export CONFIG_ALLOY_VERSION=v2
 
 # migrates secrets from old names to new names by reading values from the
 # running containers on the server and re-inserting them under the new names.

alerts/node.yml.tmpl

@@ -87,7 +87,7 @@ groups:
           datasourceUid: PBFA97CFB590B2093
           model:
             editorMode: code
-            expr: 100 - ((node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100)
+            expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100
             instant: true
             intervalMs: 1000
             legendFormat: __auto

collect-smartctl-json.sh

@@ -1,6 +1,8 @@
 #! /bin/bash
 # Adapted from https://github.com/prometheus-community/smartctl_exporter/blob/master/collect-smartctl-json.sh
 
+script_dir=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+
 # Data directory to dump smartctl output
 # This directory will be created if it doesn't exist
 data_dir="/var/lib/smartmontools/json"
@@ -55,6 +57,12 @@ for device in "${devices[@]}"
 	data="$($SUDO smartctl ${smartctl_args} ${device})"
 	# Accommodate a smartmontools pre-7.3 bug
 	data=${data#"  Pending defect count:"}
+	type="$(echo "${data}" | "${json_tool}" "${json_args}" '.device.type')"
+	family="$(echo "${data}" | "${json_tool}" "${json_args}" \
+'select(.model_family != null) | .model_family | sub(" |/" ; "_" ; "g")
+ | sub("\"|\\(|\\)" ; "" ; "g")')"
+	model="$(echo "${data}" | "${json_tool}" "${json_args}" \
+'.model_name | sub(" |/" ; "_" ; "g") | sub("\"|\\(|\\)" ; "" ; "g")')"
 	device_name="$(basename "${device}")"
 	echo -e "\tSaving to ${device_name}.json"
 	echo "${data}" > "${data_dir}/${device_name}.json"

compose.docker-events.yml

@@ -1,20 +0,0 @@
-version: "3.8"
-services:
-  docker-events:
-    image: docker:29.8.1-cli
-    command: >
-      docker events
-      --format '{{json .}}'
-      --filter type=container
-      --filter event=start
-      --filter event=die
-      --filter event=kill
-      --filter event=oom
-      --filter event=restart
-      --filter event=stop
-      --filter event=health_status
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock:ro
-    deploy:
-      restart_policy:
-        condition: on-failure

compose.grafana.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   grafana:
-    image: grafana/grafana:13.2.3
+    image: grafana/grafana:13.0.6
     volumes:
       - grafana-data:/var/lib/grafana:rw
     secrets:

compose.prometheus.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   prometheus:
-    image: prom/prometheus:v3.15.0
+    image: prom/prometheus:v3.12.0
     secrets:
       - basic_auth
     volumes:

compose.smartctl.yml

@@ -2,8 +2,9 @@
 version: "3.8"
 services:
   smartctl:
-    image: "prometheuscommunity/smartctl-exporter:v0.15.0"
+    image: "prometheuscommunity/smartctl-exporter:v0.14.0"
     volumes:
+    - "/dev:/dev"
     - "/var/lib/smartmontools/json:/debug"
     command:
     - "--smartctl.fake-data"

compose.yml

@@ -3,7 +3,7 @@ version: "3.8"
 
 services:
   app:
-    image: grafana/alloy:v1.20.1
+    image: grafana/alloy:v1.18.1
     hostname: "${DOMAIN}"
     configs:
       - source: config_alloy
@@ -46,14 +46,14 @@ services:
       test: ["CMD", "bash", "-c", "exec 3<>/dev/tcp/localhost/12345 && printf 'GET /-/ready HTTP/1.0\r\nHost: localhost\r\n\r\n' >&3 && head -1 <&3 | grep -q 200"]
       interval: 5s
       timeout: 10s
-      retries: 10
-      start_period: 30s
+      retries: 3
+      start_period: 10s
     deploy:
       restart_policy:
         condition: on-failure
       labels:
         - "backupbot.backup=${ENABLE_BACKUPS:-true}"
-        - "coop-cloud.${STACK_NAME}.version=2.3.0+v1.20.1"
+        - "coop-cloud.${STACK_NAME}.version=2.0.0+v1.18.1"
 configs:
   config_alloy:
     template_driver: golang

config.alloy.tmpl

@@ -52,32 +52,7 @@ prometheus.scrape "default" {
     prometheus.exporter.cadvisor.docker.targets,
   )
 
-  forward_to = [prometheus.relabel.container_meta.receiver]
-}
-
-prometheus.relabel "container_meta" {
   forward_to = [prometheus.remote_write.prometheus.receiver]
-
-  // remove sha tail: nginx:1.31.1@sha256:608a... -> nginx:1.31.1
-  rule {
-    source_labels = ["image"]
-    regex         = "([^@]+)@sha256:.*"
-    target_label  = "image"
-    replacement   = "$1"
-  }
-  // split image in name and tag
-  rule {
-    source_labels = ["image"]
-    regex         = "(.+):[^:/]+"
-    target_label  = "image_name"
-    replacement   = "$1"
-  }
-  rule {
-    source_labels = ["image"]
-    regex         = ".+:([^:/]+)"
-    target_label  = "image_tag"
-    replacement   = "$1"
-  }
 }
 
 prometheus.remote_write "prometheus" {
@@ -315,35 +290,7 @@ loki.source.docker "docker" {
 loki.source.journal "journal" {
   path = "/rootfs/var/log/journal"
   labels = { job = "{{ env "DOMAIN" }}" }
-  relabel_rules = loki.relabel.journal.rules
-  forward_to = [loki.process.journal.receiver]
-}
-
-loki.relabel "journal" {
-  forward_to = []
-
-  rule {
-    source_labels = ["__journal__systemd_unit"]
-    target_label  = "unit"
-  }
-  rule {
-    source_labels = ["__journal_syslog_identifier"]
-    target_label  = "ident"
-  }
-  rule {
-    source_labels = ["__journal_priority_keyword"]
-    target_label  = "priority"
-  }
-}
-
-// drop network db stats (15-20% of kernel logs)
-loki.process "journal" {
   forward_to = [loki.write.loki.receiver]
-
-  stage.drop {
-    expression          = ".*NetworkDB stats.*"
-    drop_counter_reason = "networkdb_stats"
-  }
 }
 {{ end }}
 

release/2.1.0+v1.18.1

@@ -1 +0,0 @@
-alloy: split image label in "image_name" and "image_tag", relabel journald logs and drop NetworkDB stats

release/2.2.0+v1.18.1

@@ -1 +0,0 @@
-allow scraping of docker events via new compose.docker-events.yml

renovate.json

@@ -1,6 +0,0 @@
-{
-  "$schema": "https://docs.renovatebot.com/renovate-schema.json",
-  "extends": [
-    "config:recommended"
-  ]
-}