Created attachment 457110 [details]
I've having some trouble on a new system I'm setting up.
Dmesg errors attached.
Kernels version impacted (at least):
With or without experimental patch, it's the same issue.
Xen Version :
(same issue with xen 4.8)
Kernel config (gentoo-sources 4.8.15) : http://pastebin.com/p0EcHjbu
This is happening when I'm making "huge" I/O (20MB/s with and rsync for example) on a raid 5 RAID stack.
I've to reset system to make it work again.
Reproducible : ALWAYS (making the i/o, it crash in 2-5mins)
Here is configuration :
- 3x Hard Drives running on RAID 5 Software raid created by mdadm
- On top of it, I'm running DRBD for replication over another node (Active/passive cluster)
- On top of it, a BTRFS FileSystem with a few subvolumes
- On top of it, XEN VMs running.
All buit with : gcc (Gentoo 4.9.3 p1.5, pie-0.6.4) 4.9.3
Kernel bug ? Any idea on how to fix it ?
Created attachment 457112 [details]
Don't think is relevant but just in case, emerge --info
I can confirm this bug doesn't exist with a RAID 1 stack instead of the RAID 5...
So what's not clear to me is this a domU or dom0? Is the oops in the kernel or the hypervisor? Does it appear to affect any other domUs if its a domU?
The RAID stack of course is done on dom0.
As the kernel crashes, everything is affected.
Oops visible in the kernel.
In order to reproduce, I can make the I/O even on dom0 or domU, same issue.
Note : issue is happening even if no domU are running.
Is still still an issue on a more recent kernel/xen?