chore: publish 2.3.1+v1.21.3 release

I updated to the latest monitoring-ng version, and got the following error:

```
FATA failed to create config stats_something_gf_alerts_traefik_: Error response from daemon: rpc error: code = InvalidArgument desc = invalid name, only 64 [a-zA-Z0-9-_.] characters allowed, and the start and end character must be [a-zA-Z0-9]
```

It seems that abra.sh is missing an export of a new variable.

Reviewed-on: #57
Reviewed-by: moritz <98+moritz@noreply.git.coopcloud.tech>
Co-authored-by: Linus Gasser <ineiti@gasser.blue>

.env.sample

@@ -75,10 +75,18 @@ SECRET_BASIC_AUTH_VERSION=v1
 #
 # COMPOSE_FILE="$COMPOSE_FILE:compose.loki.yml"
 #
+# LOKI_LOG_LEVEL=warn
+#
 # Set to 0 to disable retention
 # 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
@@ -133,3 +141,15 @@ 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
+
+# Loki ingestion alert will trigger when a host ships fewer than the given number of log entries per second
+#ALERT_LOKI_INGESTION_STALLED=0.01
+
+# Loki write error alert will trigger when log pushes fail at more than the given rate per second
+#ALERT_LOKI_WRITE_ERRORS=0
+
+# Loki WAL disk alert will trigger when the filesystem holding the WAL is above the given number in percent. Loki throttles all writes at 90
+#ALERT_LOKI_WAL_DISK_USAGE=85
+
+# Traefik apdex alert will trigger when the apdex score of a service drops below the given number. Services receiving fewer than 10 requests per 10m are ignored
+#ALERT_TRAEFIK_APDEX=0.5

.gitignore

@@ -1 +1,2 @@
 /.envrc
+*~

README.md

@@ -130,6 +130,18 @@ $ 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:
@@ -174,6 +186,7 @@ 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`
+- traefik apdex: `ALERT_TRAEFIK_APDEX`
 
 ## smart monitoring
 

abra.sh

@@ -5,12 +5,14 @@ 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=v3
+export LOKI_YML_VERSION=v4
 export PROMETHEUS_YML_VERSION=v2
 export MATRIX_ALERTMANAGER_CONFIG_VERSION=v1
 export MATRIX_ALERTMANAGER_ENTRYPOINT_VERSION=v1
-export GF_ALERTS_NODE_VERSION=v3
+export GF_ALERTS_NODE_VERSION=v5
+export GF_ALERTS_LOKI_VERSION=v5
 export CONFIG_ALLOY_VERSION=v3
+export GF_ALERTS_TRAEFIK_VERSION=v1
 
 # 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/loki.yml.tmpl

@@ -0,0 +1,191 @@
+apiVersion: 1
+
+# List of alert rule UIDs that should be deleted
+deleteRules:
+  {{ if not (env "ALERT_LOKI_INGESTION_STALLED") }}
+  - orgId: 1
+    uid: coopcloud_loki_ingestion_stalled
+  {{ end }}
+  {{ if not (env "ALERT_LOKI_WRITE_ERRORS") }}
+  - orgId: 1
+    uid: coopcloud_loki_write_errors
+  {{ end }}
+  {{ if not (env "ALERT_LOKI_WAL_DISK_USAGE") }}
+  - orgId: 1
+    uid: coopcloud_loki_wal_disk_usage
+  {{ end }}
+
+groups:
+- orgId: 1
+  name: loki
+  folder: monitoring
+  interval: 5m
+  rules:
+    {{ if (env "ALERT_LOKI_INGESTION_STALLED") }}
+    - uid: coopcloud_loki_ingestion_stalled
+      title: Loki Ingestion Stalled
+      condition: C
+      data:
+        - refId: A
+          relativeTimeRange:
+            from: 1800
+            to: 0
+          datasourceUid: PBFA97CFB590B2093
+          model:
+            editorMode: code
+            expr: sum by (instance) (rate(loki_write_sent_entries_total[15m]))
+            instant: true
+            intervalMs: 1000
+            legendFormat: __auto
+            maxDataPoints: 43200
+            range: false
+            refId: A
+        - refId: C
+          relativeTimeRange:
+            from: 1800
+            to: 0
+          datasourceUid: __expr__
+          model:
+            conditions:
+                - evaluator:
+                    params:
+                        - {{ env "ALERT_LOKI_INGESTION_STALLED" }}
+                    type: lt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                        - C
+                  reducer:
+                    params: []
+                    type: last
+                  type: query
+            datasource:
+                type: __expr__
+                uid: __expr__
+            expression: A
+            intervalMs: 1000
+            maxDataPoints: 43200
+            refId: C
+            type: threshold
+      noDataState: Alerting
+      execErrState: Error
+      for: 15m
+      annotations:
+        description: ""
+        runbook_url: ""
+        summary: Loki received no logs from {{`{{ $labels.instance }}`}} for 15m ({{`{{ printf "%.4f" (index $values "A").Value }}`}} entries/sec, threshold {{ env "ALERT_LOKI_INGESTION_STALLED" }})
+      isPaused: false
+    {{ end }}
+    {{ if (env "ALERT_LOKI_WRITE_ERRORS") }}
+    - uid: coopcloud_loki_write_errors
+      title: Loki Write Errors
+      condition: C
+      data:
+        - refId: A
+          relativeTimeRange:
+            from: 1200
+            to: 0
+          datasourceUid: PBFA97CFB590B2093
+          model:
+            editorMode: code
+            expr: sum by (instance, status_code) (rate(loki_write_request_duration_seconds_count{status_code!~"2.."}[10m]))
+            instant: true
+            intervalMs: 1000
+            legendFormat: __auto
+            maxDataPoints: 43200
+            range: false
+            refId: A
+        - refId: C
+          relativeTimeRange:
+            from: 1200
+            to: 0
+          datasourceUid: __expr__
+          model:
+            conditions:
+                - evaluator:
+                    params:
+                        - {{ env "ALERT_LOKI_WRITE_ERRORS" }}
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                        - C
+                  reducer:
+                    params: []
+                    type: last
+                  type: query
+            datasource:
+                type: __expr__
+                uid: __expr__
+            expression: A
+            intervalMs: 1000
+            maxDataPoints: 43200
+            refId: C
+            type: threshold
+      noDataState: NoData
+      execErrState: Error
+      for: 10m
+      annotations:
+        description: ""
+        runbook_url: ""
+        summary: Loki is rejecting log pushes from {{`{{ $labels.instance }}`}} with HTTP {{`{{ $labels.status_code }}`}} ({{`{{ printf "%.2f" (index $values "A").Value }}`}} failed pushes/sec)
+      isPaused: false
+    {{ end }}
+    {{ if (env "ALERT_LOKI_WAL_DISK_USAGE") }}
+    - uid: coopcloud_loki_wal_disk_usage
+      title: Loki WAL Disk Usage
+      condition: C
+      data:
+        - refId: A
+          relativeTimeRange:
+            from: 600
+            to: 0
+          datasourceUid: PBFA97CFB590B2093
+          model:
+            editorMode: code
+            expr: max by (instance) (loki_ingester_wal_disk_usage_percent * 100)
+            instant: true
+            intervalMs: 1000
+            legendFormat: __auto
+            maxDataPoints: 43200
+            range: false
+            refId: A
+        - refId: C
+          relativeTimeRange:
+            from: 600
+            to: 0
+          datasourceUid: __expr__
+          model:
+            conditions:
+                - evaluator:
+                    params:
+                        - {{ env "ALERT_LOKI_WAL_DISK_USAGE" }}
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params:
+                        - C
+                  reducer:
+                    params: []
+                    type: last
+                  type: query
+            datasource:
+                type: __expr__
+                uid: __expr__
+            expression: A
+            intervalMs: 1000
+            maxDataPoints: 43200
+            refId: C
+            type: threshold
+      noDataState: NoData
+      execErrState: Error
+      for: 10m
+      annotations:
+        description: ""
+        runbook_url: ""
+        summary: Loki WAL disk {{`{{ printf "%.1f" (index $values "A").Value }}`}}% full on {{`{{ $labels.instance }}`}} (threshold {{ env "ALERT_LOKI_WAL_DISK_USAGE" }}%, writes stop at 90%)
+      isPaused: false
+    {{ end }}

alerts/node.yml.tmpl

@@ -71,8 +71,7 @@ groups:
         description: ""
         runbook_url: ""
         summary: Less than {{ env "ALERT_NODE_DISK_SPACE_LEFT" }}% disk space left on {{`{{ $labels.instance }}`}} ({{`{{ (index $values "A").Value }}`}}% left)
-      labels:
-        "": ""
+      labels: {}
       isPaused: false
     {{ end }}
     {{ if (env "ALERT_NODE_MEMORY_USAGE")  }}
@@ -87,7 +86,7 @@ groups:
           datasourceUid: PBFA97CFB590B2093
           model:
             editorMode: code
-            expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100
+            expr: 100 - ((node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100)
             instant: true
             intervalMs: 1000
             legendFormat: __auto

alerts/traefik.yml.tmpl

@@ -0,0 +1,81 @@
+apiVersion: 1
+
+# List of alert rule UIDs that should be deleted
+deleteRules:
+  {{ if not (env "ALERT_TRAEFIK_APDEX") }}
+  - orgId: 1
+    uid: coopcloud_traefik_apdex
+  {{ end }}
+
+groups:
+- orgId: 1
+  name: traefik
+  folder: recipes
+  interval: 5m
+  rules:
+    {{ if (env "ALERT_TRAEFIK_APDEX") }}
+    - uid: coopcloud_traefik_apdex
+      title: Apdex
+      condition: B
+      data:
+        - refId: A
+          relativeTimeRange:
+            from: 600
+            to: 0
+          datasourceUid: PBFA97CFB590B2093
+          model:
+            editorMode: code
+            # apdex = (satisfied + tolerating / 2) / total, which reduces to
+            # (le=0.3 + le=1.2) / 2 / total because the le=1.2 bucket is
+            # cumulative and therefore already contains the satisfied requests.
+            # services with less than 10 requests per 10m are ignored.
+            expr: |-
+              ((sum(rate(traefik_service_request_duration_seconds_bucket{le="0.3",code="200"}[5m])) by (service) +
+               sum(rate(traefik_service_request_duration_seconds_bucket{le="1.2",code="200"}[5m])) by (service)) / 2 /
+               sum(rate(traefik_service_request_duration_seconds_count{code="200"}[5m])) by (service))
+              and on(service)
+              (
+                sum(increase(traefik_service_request_duration_seconds_count{code="200"}[10m])) by (service) >= 10
+              )
+            instant: true
+            intervalMs: 1000
+            legendFormat: __auto
+            maxDataPoints: 43200
+            range: false
+            refId: A
+        - refId: B
+          relativeTimeRange:
+            from: 600
+            to: 0
+          datasourceUid: __expr__
+          model:
+            conditions:
+                - evaluator:
+                    params:
+                        - {{ env "ALERT_TRAEFIK_APDEX" }}
+                    type: lt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+            datasource:
+                type: __expr__
+                uid: __expr__
+            expression: A
+            intervalMs: 1000
+            maxDataPoints: 43200
+            refId: B
+            type: threshold
+      noDataState: OK
+      execErrState: Error
+      for: 10m
+      annotations:
+        description: ""
+        runbook_url: ""
+        summary: Apdex for {{`{{ $labels.service }}`}} is below {{ env "ALERT_TRAEFIK_APDEX" }} (currently at {{`{{ printf "%.2f" (index $values "A").Value }}`}})
+      isPaused: false
+    {{ end }}

compose.grafana.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   grafana:
-    image: grafana/grafana:13.0.6
+    image: grafana/grafana:13.3.0
     volumes:
       - grafana-data:/var/lib/grafana:rw
     secrets:
@@ -24,6 +24,10 @@ services:
         target: /var/lib/grafana/dashboards/backup.json
       - source: gf_alerts_node
         target: /etc/grafana/provisioning/alerting/node.yml
+      - source: gf_alerts_loki
+        target: /etc/grafana/provisioning/alerting/loki.yml
+      - source: gf_alerts_traefik
+        target: /etc/grafana/provisioning/alerting/traefik.yml
     networks:
       - proxy
       - internal
@@ -34,6 +38,10 @@ services:
       - GF_INSTALL_PLUGINS
       - ALERT_NODE_DISK_SPACE_LEFT
       - ALERT_NODE_MEMORY_USAGE
+      - ALERT_LOKI_INGESTION_STALLED
+      - ALERT_LOKI_WRITE_ERRORS
+      - ALERT_LOKI_WAL_DISK_USAGE
+      - ALERT_TRAEFIK_APDEX
     deploy:
       labels:
         - "traefik.enable=true"
@@ -48,7 +56,7 @@ services:
       interval: 5s
       timeout: 10s
       retries: 3
-      start_period: 10s
+      start_period: 300s
 
 configs:
   gf_custom_ini:
@@ -77,6 +85,14 @@ configs:
     template_driver: golang
     name: ${STACK_NAME}_gf_alerts_node_${GF_ALERTS_NODE_VERSION}
     file: alerts/node.yml.tmpl
+  gf_alerts_loki:
+    template_driver: golang
+    name: ${STACK_NAME}_gf_alerts_loki_${GF_ALERTS_LOKI_VERSION}
+    file: alerts/loki.yml.tmpl
+  gf_alerts_traefik:
+    template_driver: golang
+    name: ${STACK_NAME}_gf_alerts_traefik_${GF_ALERTS_TRAEFIK_VERSION}
+    file: alerts/traefik.yml.tmpl
 
 volumes:
   grafana-data:

compose.loki.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   loki:
-    image: grafana/loki:3.7.2
+    image: grafana/loki:3.7.9
     command: -config.file=/etc/loki/local-config.yaml
     networks:
       - proxy
@@ -19,9 +19,17 @@ services:
       - LOKI_AWS_REGION
       - LOKI_BUCKET_NAMES
       - LOKI_RETENTION_PERIOD
+      - LOKI_LOG_LEVEL
       - STACK_NAME
       - LOKI_STORAGE_FILESYSTEM
       - LOKI_STORAGE_S3
+      - LOKI_TSDB_FROM_DATE
+    healthcheck:
+      test: ["CMD", "/usr/bin/loki", "-health"]
+      interval: 10s
+      timeout: 10s
+      retries: 10
+      start_period: 30s
     deploy:
       restart_policy:
         condition: on-failure
@@ -34,6 +42,8 @@ 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"
+        - "prometheus.io/scrape=true"
+        - "prometheus.io/port=3100"
 
 
 configs:

compose.prometheus.yml

@@ -2,7 +2,7 @@ version: '3.8'
 
 services:
   prometheus:
-    image: prom/prometheus:v3.12.0
+    image: prom/prometheus:v3.15.1
     secrets:
       - basic_auth
     volumes:
@@ -28,7 +28,7 @@ services:
       start_period: 30s
     deploy:
       restart_policy:
-        condition: on-failure
+        condition: any
       labels:
         - "traefik.enable=true"
         - "traefik.swarm.network=proxy"

compose.smartctl.yml

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

compose.yml

@@ -3,7 +3,7 @@ version: "3.8"
 
 services:
   app:
-    image: grafana/alloy:v1.18.1
+    image: grafana/alloy:v1.21.3
     hostname: "${DOMAIN}"
     configs:
       - source: config_alloy
@@ -50,10 +50,10 @@ services:
       start_period: 30s
     deploy:
       restart_policy:
-        condition: on-failure
+        condition: any
       labels:
         - "backupbot.backup=${ENABLE_BACKUPS:-true}"
-        - "coop-cloud.${STACK_NAME}.version=2.2.0+v1.18.1"
+        - "coop-cloud.${STACK_NAME}.version=2.3.1+v1.21.3"
 configs:
   config_alloy:
     template_driver: golang

loki.yml.tmpl

@@ -15,7 +15,7 @@ ruler:
 
 server:
   http_listen_port: 3100
-  log_level: warn
+  log_level: {{ or (env "LOKI_LOG_LEVEL") "warn" }}
 
 distributor:
   ring:
@@ -56,12 +56,26 @@ 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 }}
@@ -74,6 +88,15 @@ 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:
@@ -81,6 +104,11 @@ 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" }}
@@ -99,7 +127,7 @@ storage_config:
 
 
 compactor:
-  working_directory: /loki/boltdb-shipper-compactor
+  working_directory: /loki/compactor
   compaction_interval: 10m
   retention_enabled: true
   retention_delete_delay: 2h
@@ -127,4 +155,4 @@ frontend:
 
 table_manager:
   retention_deletes_enabled: false
-  retention_period: 0s
+  retention_period: 0s

release/2.3.0+v1.21.3

@@ -0,0 +1,2 @@
+- opt-in migration of Loki's index store from deprecated boltdb-shipper to TSDB via LOKI_TSDB_FROM_DATE
+- alloy and prometheus containers restart policy from on-failure to any