1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
<think>
Alright, I'm trying to classify this bug report for QEMU. The user provided a detailed description, so let me go through it step by step.
First, the issue is with x86 TCG acceleration running on s390x systems when using -smp greater than the host's CPUs. This causes a significant slowdown, around 10 times slower. They mentioned that this affects QEMU 7.2 and is related to a specific patch applied in Debian.
Looking at the possible categories: mistranslation, assembly lowering, device, graphic, socket, network, KVM, boot, vnc, debug, files, permissions, performance, kernel, peripherals, hypervisor, other.
The problem seems to be performance-related because the slowdown is so significant. The user also mentions that this occurs only under certain conditions: when the patch is applied, running x86 on s390x, and when -smp exceeds host CPUs. It doesn't happen with PPC64, which suggests it's specific to the way QEMU handles s390x architecture.
The performance category fits because the issue is about the speed of execution. The user provided timing data showing a 10x increase in runtime for certain test cases. They also linked this to TCG acceleration, which relates to how QEMU translates code for the target architecture.
So, considering all factors, the most appropriate category is 'performance'.
</think>
performance
|