From a90fb19ed4eff8f74b54b0c095bf1aba5b959fa1 Mon Sep 17 00:00:00 2001
From: mr-forust <vzlomdsisma@gmail.com>
Date: Tue, 29 Sep 2026 14:47:53 +0200
Subject: [PATCH] fix(traefik): size probes for HDD stalls

Single replica is the whole ingress; liveness kills at 2s timeouts took every public service down in a loop. Same stall-sized budgets as postgres/metallb. Applied live via helm (pinned 41.5.0, values from git).
---
 traefik/k8s/traefik-values.yaml | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/traefik/k8s/traefik-values.yaml b/traefik/k8s/traefik-values.yaml
index d4f02af..c5baaf4 100644
--- a/traefik/k8s/traefik-values.yaml
+++ b/traefik/k8s/traefik-values.yaml
@@ -46,6 +46,22 @@ resources:
     cpu: "1000m"
     memory: "1Gi"
 
+# Single replica is the whole ingress: a SIGKILL here takes every public
+# service down. Budgets are sized for HDD stalls on a loaded node, not for a
+# healthy disk — same treatment as immich postgres and metallb speaker.
+readinessProbe:
+  failureThreshold: 6
+  initialDelaySeconds: 10
+  periodSeconds: 10
+  successThreshold: 1
+  timeoutSeconds: 5
+livenessProbe:
+  failureThreshold: 6
+  initialDelaySeconds: 30
+  periodSeconds: 30
+  successThreshold: 1
+  timeoutSeconds: 5
+
 providers:
   kubernetesIngress:
     enabled: true