| Summary: | llvmpipe inside VM is ridiculously slow | ||||||
|---|---|---|---|---|---|---|---|
| Product: | [Fedora] Fedora | Reporter: | Julian Sikorski <belegdol> | ||||
| Component: | mesa | Assignee: | Adam Jackson <ajax> | ||||
| Status: | CLOSED DUPLICATE | QA Contact: | Fedora Extras Quality Assurance <extras-qa> | ||||
| Severity: | unspecified | Docs Contact: | |||||
| Priority: | unspecified | ||||||
| Version: | 17 | CC: | ajax, maxamillion, otaylor, samkraju, walters | ||||
| Target Milestone: | --- | ||||||
| Target Release: | --- | ||||||
| Hardware: | Unspecified | ||||||
| OS: | Unspecified | ||||||
| Whiteboard: | |||||||
| Fixed In Version: | Doc Type: | Bug Fix | |||||
| Doc Text: | Story Points: | --- | |||||
| Clone Of: | Environment: | ||||||
| Last Closed: | 2012-03-27 19:10:32 UTC | Type: | --- | ||||
| Regression: | --- | Mount Type: | --- | ||||
| Documentation: | --- | CRM: | |||||
| Verified Versions: | Category: | --- | |||||
| oVirt Team: | --- | RHEL 7.3 requirements from Atomic Host: | |||||
| Cloudforms Team: | --- | Target Upstream Version: | |||||
| Attachments: |
|
||||||
If you ssh into the guest, where is the CPU time being spent? What version of mesa are you using in the guest? Can you try this one and see if it's any better? (It can't possibly be worse) https://admin.fedoraproject.org/updates/mesa-8.0.1-7.fc17 Does dmesg on the host report any problem with kvm? Summing up the IRC session: The new mesa did not help. "top" has shown that time is being spent in gnome-shell process. It eventually turned out that this bug might be a duplicate of bug 787467. *** This bug has been marked as a duplicate of bug 787467 *** |
Created attachment 572434 [details] Xorg.log Description of problem: Since the latest xorg-x11-drv-qxl update the gnome-shell crashes are gone, but the llvmpipe performance is still unusably slow. Opening any new window requires a dozen seconds wait, and gdb initialisation is almost just as slow. My machine has i7-2720M cpu and 4 GB of RAM, and I have assigned 4 virtual cores and 2 GB to the guest. Whenever the wait happens, I can see 100% usage of 1 core on the host's gnome-system-monitor. /var/log/Xorg.0.log on the guest contains some suspicious messages, so I'm attaching it too. Version-Release number of selected component (if applicable): xorg-x11-drv-qxl-0.0.22-0.fc17.x86_64 gnome-shell-3.3.92-1.fc17.x86_64 How reproducible: always Steps to Reproduce: 1. Install F-17 x86_64 guest on a F-16 x86_64 host 2. Boot it 3. Change it to use spice Actual results: Guest is slooooooow Expected results: Guest is snappy and quick Additional info: Feel free to reassign if gnome-shell is not the right component.