Intended beaviour of livenessProbe
Hi, we are using Zitadel in production on Kubernetes. We deployed it with Flux using the official helm chart.
Recently, we observed that the livenessProbe always returns "ok" even if Zitadel is not able to connect to its database (and therefore broken).
The readyness probe fails, as we would have expected. Is this behaviour intended?
Environment: self-hosted
Zitadel version: v3.3.6 (3 replicas)
Stack:
* Official helm chart, v8.13.4
* Kubernete v1.33.4
* CNPG 1.27.0 (3 replicas)
Steps to reproduce:
* Make sure that Zitadel can't connect to its database (either by changing the config or deleting the database).
* Deploy a netshoot pod (https://github.com/nicolaka/netshoot#netshoot-with-kubernetes) and execute the following command using the IPs of the Zitadel pods:
curl -ks <pod-ip>:8080/debug/healthz
* Observe that this always returns "ok"
I can understand this behaviour somehow as restarting the pod because of a failed livenessProbe would not solve the problem in this case. But I wouldn't also expect Zitadel to return "ok" on its healthz endpoint if somethings is seriously wrong.
Recently, we observed that the livenessProbe always returns "ok" even if Zitadel is not able to connect to its database (and therefore broken).
The readyness probe fails, as we would have expected. Is this behaviour intended?
Environment: self-hosted
Zitadel version: v3.3.6 (3 replicas)
Stack:
* Official helm chart, v8.13.4
* Kubernete v1.33.4
* CNPG 1.27.0 (3 replicas)
Steps to reproduce:
* Make sure that Zitadel can't connect to its database (either by changing the config or deleting the database).
* Deploy a netshoot pod (https://github.com/nicolaka/netshoot#netshoot-with-kubernetes) and execute the following command using the IPs of the Zitadel pods:
curl -ks <pod-ip>:8080/debug/healthz
* Observe that this always returns "ok"
I can understand this behaviour somehow as restarting the pod because of a failed livenessProbe would not solve the problem in this case. But I wouldn't also expect Zitadel to return "ok" on its healthz endpoint if somethings is seriously wrong.
