Hi, I haven't had an issue yet, but the first question would be if you failed the mgr. ;-) The second question is, does the ceph-exporter respond? ceph01:~ # curl http://IP:9926/metrics Does the ceph-exporter log anything? Do you have any custom configs or templates in place? ceph01:~ # ceph config-key get mgr/cephadm/services/prometheus/prometheus.yml Regards, Eugen Zitat von Adam Prycki <aprycki@man.poznan.pl>:

Hello,

I have issue with multiple of our clusters. It doesn't seem to be versions specific and just happens on our clusters which have been running for a while and have been through some version upgrades.

In current cephadm versions prometheus is configured via service discovery from MGR.

Relevant prometheus config looks like this: - job_name: 'ceph-exporter' honor_labels: true http_sd_configs: - url: http://X.X.X.X:8765/sd/prometheus/sd-config?service=ceph-exporter Issue is that mgr doesn't return any hosts. Just an empty array []. Prometheus doesn't scrap ceph-exporter and some of our grafana graphs are empty. :/

Other URLs in this config file work fine and generate valid sd configs.

Has anyone else experienced this? Does anyone know how to fix this?

Best regards Adam Prycki