increase grafana healthcheck start_period and reduce error logs

.gitignore

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

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=v5
 export CONFIG_ALLOY_VERSION=v3
 
 # migrates secrets from old names to new names by reading values from the

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")  }}

compose.grafana.yml

@@ -48,7 +48,7 @@ services:
       interval: 5s
       timeout: 10s
       retries: 3
-      start_period: 10s
+      start_period: 300s
 
 configs:
   gf_custom_ini:

compose.prometheus.yml

@@ -28,7 +28,7 @@ services:
       start_period: 30s
     deploy:
       restart_policy:
-        condition: unless-stopped
+        condition: on-failure
       labels:
         - "traefik.enable=true"
         - "traefik.swarm.network=proxy"

compose.yml

@@ -50,7 +50,7 @@ services:
       start_period: 30s
     deploy:
       restart_policy:
-        condition: unless-stopped
+        condition: on-failure
       labels:
         - "backupbot.backup=${ENABLE_BACKUPS:-true}"
         - "coop-cloud.${STACK_NAME}.version=2.3.0+v1.20.1"

release/next

@@ -1 +0,0 @@
-- alloy and prometheus containers restart policy from on-failure to unless-stopped