1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
<think>
Okay, let me try to classify this bug report for QEMU. The user mentioned a problem during virtual disk live migration where VMs experience severe stuttering and CPU soft lockups. They included a link to a kernel bug report, which I can't access, but from the description, it seems related to high disk latency leading to system hangs.
Looking at the symptoms: the syslog shows a soft lockup on CPU#1 for 22 seconds. Soft lockups typically happen when a CPU is stuck in a long loop without yielding, often due to I/O waits. The iotest output shows some requests taking an unusually long time (like 22.5 seconds), which could be causing the system to hang.
Since this occurs during live migration, it's likely related to how data is being transferred or handled between storage systems. QEMU handles block I/O and storage migration, so any issues here might cause such lockups.
Possible areas to look into: Maybe there's a bug in how QEMU handles certain disk operations during migration, leading to long waits that trigger the watchdog. Alternatively, it could be a problem with the underlying storage or network causing delays, but since it's specific to live migration and linked to a kernel issue, I'm leaning towards a QEMU-related bug.
The classification options are: block I/O, device model, execution, guest agent, net I/O, or other. Since this is about disk operations during migration, which involves block I/O handling in QEMU, the most appropriate category would be 'block I/O'.
</think>
**Classification: Block I/O**
The bug report describes issues occurring during virtual disk live migration, where high disk latency leads to CPU soft lockups. This points to problems in how QEMU handles block I/O operations during storage transfers, making the 'block I/O' classification appropriate.
|