I've rebooted mw1272 today around 9:30 UTC, it was marked as down on icinga for the past 12 hours.
It looks like the host had been rebooted several times due to crashes in the past:
- https://wikitech.wikimedia.org/wiki/Server_admin_log/Archive_31
- https://wikitech.wikimedia.org/wiki/Server_admin_log/Archive_34
- https://wikitech.wikimedia.org/wiki/Server_admin_log/Archive_35
A few days before the latest crash, the kernel logged this:
Dec 5 16:30:49 mw1272 kernel: [1519174.005014] BUG: Bad page map in process hhvm pte:a3ae6f845 pmd:8081f1067
A similar issue occurred in October this year: T207983