Page MenuHomePhabricator

wtp2020 - Memory correctable errors -EDAC-
Closed, DuplicatePublic

Description

13:56 EDT < icinga-wm> PROBLEM - Memory correctable errors -EDAC- on wtp2020 is CRITICAL: 16 ge 4

https://grafana.wikimedia.org/dashboard/db/host-overview?orgId=1&var-server=wtp2020&var-datasource=codfw%2520prometheus%252Fops

https://icinga.wikimedia.org/cgi-bin/icinga/extinfo.cgi?type=2&host=wtp2020&service=Memory+correctable+errors+-EDAC-

13:57 < mutante> !log depooled wtp2020 because icinga reported memory errors

[wtp2020:~] $ sudo -i depool
Depooling all services on wtp2020.codfw.wmnet
codfw/parsoid/parsoid/wtp2020.codfw.wmnet: pooled changed yes => no

also see: T183177 rOPUPdab319449718fae9700bd177a43f0e4e5db67e2c T194172