blob: 35ec1b30c5b1106ac5ed9ea7e661243df8c41978 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
<think>
Alright, so I need to classify this bug report into one of the given categories. Let me read through it carefully.
The user is reporting an issue where the hypervisor hangs when running VMs with CirrOS or Ubuntu 12.04 using QEMU-2.0 and libvirtd 1.2.2. They mentioned that the network interface is attached to a PCI virtual function (SR-IOV). The problem occurs with both Mellanox and Intel NICs.
They've tested different combinations: when using QEMU 1.5/libvirtd 1.1.1, there's no issue. But with QEMU 2.0/libvirtd 1.2.2, only CirrOS and Ubuntu 12.04 guests cause the hang. CentOS 6.4 and Ubuntu 13.10 work fine. The problematic kernels are around 3.2.y.
Looking at the categories: Mistranslation is about user-mode assembly issues. Assembly lowering is similar but might not fit here. 'Other' is a catch-all, but perhaps there's a more specific category.
The issue involves hypervisor and QEMU, so 'hypervisor' seems relevant. The problem occurs during VM launch, possibly related to the network setup or device assignment since SR-IOV is involved. It affects certain guest OSes with particular kernels, which might relate to how they handle virtual functions or network drivers.
Considering that it's a hypervisor issue when using specific QEMU versions and guest OS combinations, especially related to networking (SR-IOV), the most fitting category is 'hypervisor'.
</think>
hypervisor
|