This thread over at Cisco Support Community (https://supportforums.cisco.com/discussion/12444221/ucs-blade-ecc-error-alerting) got me thinking of the many headaches suffered from “Correctable ECC Errors”.
I define “Correctable ECC Errors” as memory errors that crash a server, but are not alerted on.
Sending “Shout Out” to Cisco, this is coming between you and customers. A better PR take is needed on this one. DIMM Blacklisting has got the conversation started, but Cisco, you are still seeing this from “Your” point of view and not the customers.
Let’s get in some group counseling and work through this : )