chore: publish 2.2.0+v1.18.1 release

another one! closes #15

again, the compose-snippet was generated using Claude, but verified and tested manually.
Thought of using a socket-proxy just as traefik does, but since alloy has socket access anyways and the official docker image should be as safe as it gets, I think this should be alright.

## Loki log preview
![grafik.png](/attachments/013605e9-9abc-47ef-8cb9-c118fbaec3b5)

Reviewed-on: #32
Reviewed-by: moritz <98+moritz@noreply.git.coopcloud.tech>
Co-authored-by: Simon <s.thiessen@local-it.org>

.env.sample

@@ -53,6 +53,10 @@ 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"
+
 
 # Monitoring Server
 #
@@ -126,10 +130,3 @@ SECRET_BASIC_AUTH_VERSION=v1
 
 # Node memory usage alert will trigger when memory usage is above the given number in percent
 #ALERT_NODE_MEMORY_USAGE=85
-
-# Tell Traefik to keep access logs (could be very verbose). See Access
-# logs on Traefik recipe.
-#ALLOY_ACCESS_LOGS=true
-#PROMETHEUS_ACCESS_LOGS=true
-#LOKI_ACCESS_LOGS=true
-#GRAFANA_ACCESS_LOGS=true

README.md

@@ -54,6 +54,14 @@ 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

@@ -10,7 +10,7 @@ export PROMETHEUS_YML_VERSION=v2
 export MATRIX_ALERTMANAGER_CONFIG_VERSION=v1
 export MATRIX_ALERTMANAGER_ENTRYPOINT_VERSION=v1
 export GF_ALERTS_NODE_VERSION=v3
-export CONFIG_ALLOY_VERSION=v2
+export CONFIG_ALLOY_VERSION=v3
 
 # 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.

compose.alloy-webui.yml

@@ -14,4 +14,3 @@ services:
         - "traefik.http.routers.${STACK_NAME}-alloy.tls=true"
         - "traefik.http.routers.${STACK_NAME}-alloy.tls.certresolver=${LETS_ENCRYPT_ENV}"
         - "traefik.http.routers.${STACK_NAME}-alloy.middlewares=basicauth@file"
-        - "traefik.http.routers.${STACK_NAME}-alloy.observability.accesslogs=${ALLOY_ACCESS_LOGS:-false}"

compose.docker-events.yml

@@ -0,0 +1,20 @@
+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

@@ -43,7 +43,6 @@ services:
         - "traefik.http.routers.${STACK_NAME}-grafana.entrypoints=web-secure"
         - "traefik.http.routers.${STACK_NAME}-grafana.tls=true"
         - "traefik.http.routers.${STACK_NAME}-grafana.tls.certresolver=${LETS_ENCRYPT_ENV}"
-        - "traefik.http.routers.${STACK_NAME}-grafana.observability.accesslogs=${GRAFANA_ACCESS_LOGS:-false}"
     healthcheck:
       test: "wget -q http://localhost:3000/healthz -O/dev/null"
       interval: 5s

compose.loki.yml

@@ -34,7 +34,6 @@ services:
         - "traefik.http.routers.${STACK_NAME}-loki.tls=true"
         - "traefik.http.routers.${STACK_NAME}-loki.tls.certresolver=${LETS_ENCRYPT_ENV}"
         - "traefik.http.routers.${STACK_NAME}-loki.middlewares=basicauth@file"
-        - "traefik.http.routers.${STACK_NAME}-loki.observability.accesslogs=${LOKI_ACCESS_LOGS:-false}"
 
 
 configs:

compose.prometheus.yml

@@ -38,7 +38,6 @@ services:
         - "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"
-        - "traefik.http.routers.${STACK_NAME}-prometheus.observability.accesslogs=${PROMETHEUS_ACCESS_LOGS:-false}"
 
 configs:
   prometheus_yml:

compose.yml

@@ -53,7 +53,7 @@ services:
         condition: on-failure
       labels:
         - "backupbot.backup=${ENABLE_BACKUPS:-true}"
-        - "coop-cloud.${STACK_NAME}.version=2.0.0+v1.18.1"
+        - "coop-cloud.${STACK_NAME}.version=2.2.0+v1.18.1"
 configs:
   config_alloy:
     template_driver: golang

config.alloy.tmpl

@@ -52,7 +52,32 @@ 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" {
@@ -290,7 +315,35 @@ 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

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

release/2.2.0+v1.18.1

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