Page MenuHomePhabricator

kafka1012 power supply alerts
Closed, DeclinedPublic

Description

Looks like kafka1012 is still alerting on power supply after T213748: swap a2-eqiad PDU with on-site spare:

kafka1012 IPMI Sensor Status
CRITICAL	2019-02-13 10:53:48	26d 17h 44m 37s	3/3	Sensor Type(s) Temperature, Power_Supply Status: Critical [Status = Critical]

Event Timeline

This sever came from thae a batch of r720's in 2011 and have faulty power modules on the main board. There are several like this. This server and all R720's from that batch need to be decommissioned.