diff options
Diffstat (limited to 'results/classifier/zero-shot/118/TCG/693')
| -rw-r--r-- | results/classifier/zero-shot/118/TCG/693 | 70 |
1 files changed, 70 insertions, 0 deletions
diff --git a/results/classifier/zero-shot/118/TCG/693 b/results/classifier/zero-shot/118/TCG/693 new file mode 100644 index 00000000..6f1c124b --- /dev/null +++ b/results/classifier/zero-shot/118/TCG/693 @@ -0,0 +1,70 @@ +TCG: 0.933 +graphic: 0.891 +performance: 0.851 +virtual: 0.721 +boot: 0.627 +device: 0.626 +hypervisor: 0.573 +architecture: 0.518 +semantic: 0.507 +i386: 0.357 +x86: 0.311 +debug: 0.273 +network: 0.243 +PID: 0.232 +permissions: 0.214 +ppc: 0.212 +mistranslation: 0.182 +vnc: 0.171 +risc-v: 0.165 +kernel: 0.130 +user-level: 0.123 +arm: 0.115 +register: 0.105 +peripherals: 0.104 +socket: 0.101 +VMM: 0.039 +assembly: 0.024 +files: 0.011 +KVM: 0.006 +-------------------- +virtual: 0.987 +TCG: 0.873 +performance: 0.843 +hypervisor: 0.800 +x86: 0.411 +kernel: 0.069 +debug: 0.033 +VMM: 0.016 +device: 0.016 +PID: 0.013 +register: 0.010 +i386: 0.010 +boot: 0.008 +files: 0.008 +ppc: 0.007 +arm: 0.004 +user-level: 0.004 +assembly: 0.003 +socket: 0.003 +KVM: 0.002 +risc-v: 0.001 +network: 0.001 +semantic: 0.001 +architecture: 0.001 +vnc: 0.001 +graphic: 0.001 +permissions: 0.001 +peripherals: 0.001 +mistranslation: 0.000 + +Qemu increased memory usage with TCG +Description of problem: +The issue is that instances that are supposed to use only a small amount of memory (like 256MB) suddenly use a much higher amount of RSS when running the accel=tcg, around 512MB in the above example. This was not happening with qemu-4.2 (on Ubuntu 20.04). This is also not happening when using accel=kvm instead. The issue has been first noticed on Debian 11 (Bullseye) with the versions above, but it is happening in the same way on Centos 8 Stream, Ubuntu 21.10 and a pre-release version of Ubuntu 22.04. It also also seen when testing with qemu-6.1 built from source. +Steps to reproduce: +1. Deploy devstack (https://opendev.org/openstack/devstack) with VIRT_TYPE=qemu on a VM +2. Start an instance with cirros image and a flavor allocating 256MB +3. Do a ps and see a RSS size of about 512MB being used after the instance has finished booting +4. Expected result (seen with qemu-4.2 or VIRT_TYPE=kvm): RSS stays < 256MB +Additional information: +I can try to find a smaller commandline for manual reproduction if needed. The above sample is generated by OpenStack Nova via libvirt. |