blob: 50a766e66918e6eefb6b4b11c0c71bff0a5490f0 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
<think>
Okay, so I'm trying to figure out whether this QEMU performance regression bug report falls under 'user-mode' or 'system-mode'. Let's break down the information provided.
The user mentioned they were using QEMU 8.0.4 for qemu-user emulation and it was performing well. Then they upgraded to QEMU 9.0.2, which now includes LSX support. However, performance dropped significantly, even when disabling LSX in the new version. They're using systemd-nspawn and qemu-binfmt for containerized operations.
From what I understand, qemu-user is used for user-mode emulation, which allows running binaries of different architectures without full system virtualization. System-mode would involve emulating an entire system with hardware devices, etc., requiring higher privileges.
Since they're using systemd-nspawn and qemu-binfmt, it sounds like they're setting up a containerized environment where the binary formats are handled by QEMU for user-space emulation. The issue is about performance within this setup after upgrading QEMU versions.
The problem doesn't seem to be related to system-level peripherals or devices but rather how user-mode processes are being emulated. They've tried disabling LSX, which didn't help and even worsened the situation, indicating something else in QEMU 9.0.2 is causing the slowdown.
So putting it all together, this seems like a user-mode issue because it's about binary translation and emulation performance at the user level within containers.
</think>
user
|