1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
|
<think>
Okay, so I'm trying to classify this bug report for QEMU. The user mentioned that when they migrate a VM and reboot the guest OS, it sometimes hangs. They provided some commands they used and a strace output of QEMU.
First, I need to understand what's happening here. Migration in QEMU typically refers to live migration, where the VM is moved from one physical host to another without stopping. The user is using `virsh migrate --live` which suggests they're doing this with libvirt as well.
The issue arises when they reboot the guest OS after migration, and sometimes it hangs. So, the problem occurs during or after the live migration process, specifically upon rebooting.
Looking at the strace output, I see several `ppoll` calls returning 0 with a timeout. This might indicate that QEMU is waiting for some events to happen but they're not occurring within the expected time frame. There's also a poll on fd=20 which returns POLLOUT and POLLHUP, suggesting there might be an issue with how I/O is being handled after migration.
Now, considering the possible categories: mistranslation, assembly, other, device, graphic, socket, network, KVM, boot, vnc, debug, files, permissions, performance, kernel, peripherals, hypervisor.
The problem occurs during VM migration and reboot. Since live migration involves network communication between hosts (sending the VM's memory over the network), it's likely related to network handling in QEMU. The hang could be due to some issue with how the network is being set up or re-established after migration, especially when the guest OS reboots.
Another angle is that rebooting the guest might involve certain device resets or reinitializations. If the hypervisor (QEMU) isn't properly handling these after a live migration, it could cause the hang. However, since network issues are often a common problem during migration, I'm leaning towards 'network' as the category.
I don't see any obvious signs pointing to assembly-level issues or performance bottlenecks based on the strace provided. The issue isn't about user-mode translation mistakes, so mistranslation isn't it either.
So, putting it all together, the bug is related to network handling during live migration leading to a hang when the guest reboots.
</think>
network
|