Merge branch 'renovate/grafana-monorepo' of https://git.coopcloud.tech/coop-cloud/monitoring-ng into monitoring.sutty.abyaya.la

Reviewed-on: #24
Reviewed-by: fauno <fauno@sutty.coop.ar>

.env.sample

@@ -79,12 +79,6 @@ SECRET_BASIC_AUTH_VERSION=v1
 # LOKI_RETENTION_PERIOD=744h
 # LOKI_STORAGE_FILESYSTEM=1
 #
-# Opt in to migrating the deprecated boltdb-shipper index store to TSDB, from this date
-# onward (YYYY-MM-DD). MUST be a FUTURE date, e.g. the day after you deploy this: a past
-# or same-day date makes both stores claim that day's data, breaking queries for it.
-# Logs from before this date are still ingested and queried from boltdb-shipper.
-# LOKI_TSDB_FROM_DATE=2026-11-01
-#
 ## S3 Storage
 # LOKI_STORAGE_S3=1
 # LOKI_AWS_ENDPOINT=https://minio.autonomic.zone
@@ -139,3 +133,10 @@ 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

@@ -130,18 +130,6 @@ $ echo '{
 $ systemctl restart docker.service
 ```
 
-### Upgrading: Loki TSDB migration
-
-Loki's index store defaults to `boltdb-shipper`, which is deprecated upstream in favour of
-TSDB. To migrate an existing deployment without losing access to already-ingested logs, set
-`LOKI_TSDB_FROM_DATE` in your `.env` (see `.env.sample`) to a date on or after the day after
-your deploy, then `abra app deploy`. Logs from before that date stay on boltdb-shipper and
-remain queryable as before; only logs from that date onward are indexed with TSDB.
-
-**The date must be in the future when you deploy it, never today or earlier**: both stores share the same
-per-day table, so a past or same-day date makes them collide over that day's data and
-breaks querying it.
-
 ### Setup Push Gateway
 
 1. Enable in the env file by uncommenting the following lines:

abra.sh

@@ -5,12 +5,12 @@ export GF_STACKS_DASH_VERSION=v3
 export GF_TRAEFIK_DASH_VERSION=v3
 export GF_BACKUP_DASH_VERSION=v1
 export GF_CUSTOM_INI_VERSION=v4
-export LOKI_YML_VERSION=v4
+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=v11
 
 # 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

compose.alloy-webui.yml

@@ -14,3 +14,4 @@ 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.grafana.yml

@@ -39,10 +39,11 @@ services:
         - "traefik.enable=true"
         - "traefik.swarm.network=proxy"
         - "traefik.http.services.${STACK_NAME}-grafana.loadbalancer.server.port=3000"
-        - "traefik.http.routers.${STACK_NAME}-grafana.rule=Host(`${GRAFANA_DOMAIN:-$DOMAIN}`)"
+        - "traefik.http.routers.${STACK_NAME}-grafana.rule=Host(`${DOMAIN}`)"
         - "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

@@ -22,7 +22,6 @@ services:
       - STACK_NAME
       - LOKI_STORAGE_FILESYSTEM
       - LOKI_STORAGE_S3
-      - LOKI_TSDB_FROM_DATE
     deploy:
       restart_policy:
         condition: on-failure
@@ -35,6 +34,7 @@ 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

@@ -38,6 +38,7 @@ 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.smartctl.yml

@@ -2,7 +2,7 @@
 version: "3.8"
 services:
   smartctl:
-    image: "prometheuscommunity/smartctl-exporter:v0.15.0"
+    image: "prometheuscommunity/smartctl-exporter:v0.14.0"
     volumes:
     - "/var/lib/smartmontools/json:/debug"
     command:

compose.yml

@@ -53,7 +53,7 @@ services:
         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=2.2.0+v1.18.1"
 configs:
   config_alloy:
     template_driver: golang

loki.yml.tmpl

@@ -56,26 +56,12 @@ schema_config:
       index:
         prefix: index_
         period: 24h
-{{ if env "LOKI_TSDB_FROM_DATE" }}
-    - from: {{ env "LOKI_TSDB_FROM_DATE" }}
-      store: tsdb
-      object_store: filesystem
-      schema: v13
-      index:
-        prefix: index_
-        period: 24h
-{{ end }}
 
 storage_config:
   boltdb_shipper:
     active_index_directory: /loki/boltdb-shipper-active
     cache_location: /loki/boltdb-shipper-cache
     cache_ttl: 24h         # Can be increased for faster performance over longer query periods, uses more disk space
-{{ if env "LOKI_TSDB_FROM_DATE" }}
-  tsdb_shipper:
-    active_index_directory: /loki/tsdb-index
-    cache_location: /loki/tsdb-cache
-{{ end }}
   filesystem:
     directory: /loki/chunks
 {{ end }}
@@ -88,15 +74,6 @@ schema_config:
     index:
       prefix: index_
       period: 24h
-{{ if env "LOKI_TSDB_FROM_DATE" }}
-  - from: {{ env "LOKI_TSDB_FROM_DATE" }}
-    store: tsdb
-    object_store: aws
-    schema: v13
-    index:
-      prefix: index_
-      period: 24h
-{{ end }}
 
 storage_config:
  boltdb_shipper:
@@ -104,11 +81,6 @@ storage_config:
    cache_location: /loki/index_cache
    resync_interval: 5s
    shared_store: aws
-{{ if env "LOKI_TSDB_FROM_DATE" }}
- tsdb_shipper:
-   active_index_directory: /loki/tsdb-index
-   cache_location: /loki/tsdb-cache
-{{ end }}
 
  aws:
    endpoint: {{ env "LOKI_AWS_ENDPOINT" }}
@@ -127,7 +99,7 @@ storage_config:
 
 
 compactor:
-  working_directory: /loki/compactor
+  working_directory: /loki/boltdb-shipper-compactor
   compaction_interval: 10m
   retention_enabled: true
   retention_delete_delay: 2h

release/next

@@ -1 +0,0 @@
-- opt-in migration of Loki's index store from deprecated boltdb-shipper to TSDB via LOKI_TSDB_FROM_DATE