[Labs-l] Incident report: partial labs outage 2015-02-17

Andrew Bogott abogott at wikimedia.org
Wed Feb 18 05:41:37 UTC 2015


I've written an incident report about today's labs outage, here:

https://wikitech.wikimedia.org/wiki/Incident_documentation/20150217-LabsOutage

Revisions are welcome!  That page is painfully detailed; I've tried to 
include some information about the nova commands and scripts used to 
diagnose and evacuate, in hopes that other ops may have somewhere to 
start if something like this happens in my absence.

-Andrew




More information about the Labs-l mailing list