blob: 75d611f7a4e0bf8898ed9df89a457c52ff83637c (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
<think>
Okay, so I need to classify this bug report. Let me read it carefully.
The user is having trouble with KVM freezing after live migration between two hosts with different CPU types: AMD Opteron 4234 and 4184. They mention that migrating from B (Opteron 4184) to A (Opteron 4234) works fine, but the reverse causes KVM to freeze. Symptoms include VNC still showing output, but no input possible, and CPU usage stuck at 100% on one core.
Looking at the provided command line, it's a standard QEMU/KVM setup with various devices: virtio-blk-pci, virtio-net-pci, etc. The user has tried different CPU types without success.
The bug report points to an email from 2014 where someone else had the same issue. The QEMU version is 2.5.1.1.
Now, considering the categories: possible issues include mistranslation, assembly lowering, device-related problems, etc. Since this involves KVM freezing during live migration between different CPU types, it's likely a problem with how the hypervisor handles CPUs or migrations. The issue seems to be specific to certain CPU transitions, which might relate to device handling or CPU compatibility in QEMU/KVM.
The most fitting category here is "hypervisor" because it directly relates to KVM functionality during live migration and involves CPU compatibility issues between hosts.
</think>
hypervisor
|