Skip to content
View in the app

A better way to browse. Learn more.

Unraid

A full-screen app on your home screen with push notifications, badges and more.

To install this app on iOS and iPadOS
  1. Tap the Share icon in Safari
  2. Scroll the menu and tap Add to Home Screen.
  3. Tap Add in the top-right corner.
To install this app on Android
  1. Tap the 3-dot menu (⋮) in the top-right corner of the browser.
  2. Tap Add to Home screen or Install app.
  3. Confirm by tapping Install.

NMI lockups with VT-d on HP Proliant DL380 G7

Featured Replies

I have Unraid 6.8.0-rc7 running on my HP Proliant DL380 G7 server. My server has the following setup:
Dual Intel Xeon E5649

72GB DDR3

LSI 9201-8i P20 HBA card

HP SAS expander

512GB NVMe SSD

NVIDIA Quadro P400

 

The BIOS is flashed to the 09/30/2010 version for quieter fans.

 

After a few days of running the system with the BIOS settings reset, I started receiving NMI processor lockups similar to the following message:
 

NMI: IOCK error (debug interrupt?) for reason 61 on CPU 0

Many of the search results for messages like the one above talk about updating the BIOS and setting different kernel flags to address HP's ILO 3 NMI watchdog. I know that HP provides drivers for RedHat for the ILO 3 NMI watchdog, but I haven't seen any for Slackware and I'm not sure how I would go about installing an rpm driver in a non RedHat distribution. I tried flashing the newest BIOS from 2018 and got the same results. I also added the following kernel flags to the Syslinux Configuration, but still got the NMI messages:
 

intremap=off panic_on_unrecovered_nmi=1 unknown_nmi_panic=1 nmi_watchdog=0

According to Slackware's documentation on the nmi_watchdog flag, you should set it to "1" first. If you run "cat /proc/interrupt | grep NMI" and it returns 0, then you should then try setting it to "2" to see if that makes a difference. I've tried both "1" and "2" and neither seem to make a difference. Setting the flag to "0" turns off the watchdog.

 

I was eventually successful though. With some fiddling with CPU settings in the BIOS, I managed to get these messages to disappear when turning off VT-x and VT-d. I suspect that the issue is related to VT-d and not VT-x, but I haven't yet tested with just VT-x enabled. I know that the CPUs are fine because prior to unRAID, I used to run Windows Server 2019 with VMs without issue.

 

Has anyone else seen these errors with VT-x/VT-d? Maybe this is a Linux kernel issue? It would be nice to be able to use both of these CPU features for VMs, but it's not too bad if it doesn't work since I mainly use Docker containers.

Edited by pcmantinker
I missed the SAS expander card in my spec list

  • 1 month later...
  • Author

I just wanted to post a follow up to my original post. I am now running unRAID 6.8.1 and have been successfully running VMs for the past couple of months with VT-d turned off. It seems to be the way HP configured hardware passthrough on this machine and how it interacts with the Linux kernel. This is a strange case, but none of my VMs need hardware passthrough so it's not a big deal.

Archived

This topic is now archived and is closed to further replies.

Account

Navigation

Search

Search

Configure browser push notifications

Chrome (Android)
  1. Tap the lock icon next to the address bar.
  2. Tap Permissions → Notifications.
  3. Adjust your preference.
Chrome (Desktop)
  1. Click the padlock icon in the address bar.
  2. Select Site settings.
  3. Find Notifications and adjust your preference.