Compute Nodes Didn't Reboot Properly

dj_thrive · 05-30-2017, 11:15 AM

Good morning. I rebooted my 8 compute nodes in my cluster using

Code:

init 6

, and it appears they didn't come back up. All I see on them is something to the effect of "BUG: soft lockup -CPU#90 stuck for 67s! [migration/0:5]"

Can you tell me what I can do to get them to boot properly? This is my first time rebooting these compute nodes (they are Dell PowerEdge servers).

Thanks for your time!

Nate

Jjanel · 05-31-2017, 04:51 AM

Can you try 'power cycle'? (from web-researching that msg & a LQthread!)

Maybe: add "acpi=off noapic" to the GRUB kernel config line (&maybe: init=/bin/sh)

More info? (what's been updated? more msgs?) Called RH support? Let us know... (Co. still down?) p.s. In hindsight, could you have rebooted just one first?