Hello @ask, I’m currently getting “503 Service Unavailable” errors from ntppool.org and manage.ntppool.org. ntppool-agent also complains about various connectivity problems.
status.ntppool.org says:
“The database cluster is crash looping and/or starting up very slowly after a crash. We’re investigating.”
It’s all better now; with more details at NTP Pool System Status Status - Database trouble (thanks to Claude summarizing the bazillion changes / fixes / investigations).
tl;dr: a Ceph security upgrade done yesterday exposed a bug in a client library used by Mimir and Tempo (observability tools) which made some of the Ceph storage disks fill up and blocked MySQL from doing writes.