allow scraping of docker events

.env.sample

@@ -58,9 +58,6 @@ SECRET_BASIC_AUTH_VERSION=v1
 # COMPOSE_FILE="$COMPOSE_FILE:compose.docker-events.yml"
 
 
-# Monitor physical disks health
-# COMPOSE_FILE="$COMPOSE_FILE:compose.smartctl.yml"
-
 # Monitoring Server
 #
 ## Prometheus

.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
@@ -174,11 +174,3 @@ It is possible to enable the following alerts, by uncommenting the corresponding
 
 - node disk space: `ALERT_NODE_DISK_SPACE_LEFT`
 - node memory usage: `ALERT_NODE_MEMORY_USAGE`
-
-## smart monitoring
-
-To be able monitor hard drive health data, you need to configure
-`smartd` to run on the host system, and also the
-`collect-smartctl-json.sh` script provided here (via cronjob or as
-a `smartd` hook).  This is a limitation on Docker Swarm, which prevents
-the `smartctl_exporter` from running on privileged mode.

abra.sh

@@ -9,7 +9,7 @@ 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 GF_ALERTS_NODE_VERSION=v3
 export CONFIG_ALLOY_VERSION=v3
 
 # migrates secrets from old names to new names by reading values from the

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.service

@@ -1,6 +0,0 @@
-[Unit]
-Description=Collect SMART data
-
-[Service]
-Type=oneshot
-ExecStart=/usr/local/bin/collect-smartctl-json.sh

collect-smartctl-json.sh

@@ -1,61 +0,0 @@
-#! /bin/bash
-# Adapted from https://github.com/prometheus-community/smartctl_exporter/blob/master/collect-smartctl-json.sh
-
-# Data directory to dump smartctl output
-# This directory will be created if it doesn't exist
-data_dir="/var/lib/smartmontools/json"
-
-# The original script used --xall but that doesn't work
-# This matches the command in readSMARTctl()
-smartctl_args="--json --info --health --attributes --tolerance=verypermissive \
---nocheck=standby --format=brief --log=error"
-
-# Ignore this devices
-smartctl_ignore_dev_regex="^(/dev/bus)"
-
-# Determine the json query tool to use
-if command -v jq >/dev/null; then
-	json_tool="jq"
-	json_args="--raw-output"
-elif command -v yq >/dev/null; then
-	json_tool="yq"
-	json_args="--unwrapScalar"
-else
-	echo -e "One of 'yq' or 'jq' is required. Please try again after \
-installing one of them"
-	exit 1
-fi
-
-if [[ ! "${UID}" -eq 0 ]] && ! command -v sudo >/dev/null; then
-	# Not root and sudo doesn't exist
-	echo "sudo does not exist. Please run this as root"
-	exit 1
-fi
-
-SUDO="sudo"
-if [[ "${UID}" -eq 0 ]]; then
-	# Don't use sudo if root
-	SUDO=""
-fi
-
-[[ ! -d "${data_dir}" ]] && mkdir --parents "${data_dir}"
-
-if [[ $# -ne 0 ]]; then
-	devices="${1}"
-else
-	devices="$(smartctl --scan --json | "${json_tool}" "${json_args}" \
-".devices[].name | select(test(\"${smartctl_ignore_dev_regex}\") | not)")"
-  mapfile -t devices <<< "${devices[@]}"
-fi
-
-for device in "${devices[@]}"
-  do
-	echo -n "Collecting data for '${device}'..."
-	# shellcheck disable=SC2086
-	data="$($SUDO smartctl ${smartctl_args} ${device})"
-	# Accommodate a smartmontools pre-7.3 bug
-	data=${data#"  Pending defect count:"}
-	device_name="$(basename "${device}")"
-	echo -e "\tSaving to ${device_name}.json"
-	echo "${data}" > "${data_dir}/${device_name}.json"
-done

collect-smartctl-json.timer

@@ -1,9 +0,0 @@
-[Unit]
-Description=Collect SMART data
-
-[Timer]
-OnCalendar=hourly
-Persistent=true
-
-[Install]
-WantedBy=timers.target

compose.docker-events.yml

@@ -1,7 +1,7 @@
 version: "3.8"
 services:
   docker-events:
-    image: docker:29.9.1-cli
+    image: docker:29.8.1-cli
     command: >
       docker events
       --format '{{json .}}'

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

@@ -1,17 +0,0 @@
----
-version: "3.8"
-services:
-  smartctl:
-    image: "prometheuscommunity/smartctl-exporter:v0.15.0"
-    volumes:
-    - "/var/lib/smartmontools/json:/debug"
-    command:
-    - "--smartctl.fake-data"
-    - "--smartctl.interval=1h"
-    networks:
-    - "proxy"
-    deploy:
-      labels:
-        - "prometheus.io/scrape=true"
-        - "prometheus.io/port=9633"
-        - "prometheus.io/path=/metrics"

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=2.1.0+v1.18.1"
 configs:
   config_alloy:
     template_driver: golang

renovate.json

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