Bug 1569036

Summary: 4.16.X kernel causes performance problems with videos in kvm
Product: [Fedora] Fedora Reporter: mvharlan <harlan>
Component: kernelAssignee: Kernel Maintainer List <kernel-maint>
Status: CLOSED INSUFFICIENT_DATA QA Contact: Fedora Extras Quality Assurance <extras-qa>
Severity: medium Docs Contact:
Priority: unspecified    
Version: 28CC: airlied, bskeggs, ewk, hdegoede, ichavero, itamar, jarodwilson, jcline, jglisse, john.j5live, jonathan, josef, kernel-maint, linville, mchehab, mjg59, steved
Target Milestone: ---Flags: jforbes: needinfo?
Target Release: ---   
Hardware: x86_64   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: If docs needed, set a value
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: 2018-08-29 15:04:00 UTC Type: Bug
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:
Attachments:
Description Flags
dmesg of the host with working 4.15 kernel
none
dmesg of the guest centos 7.4.1708
none
dmesg (journalctl -k -b -1) of the host with broken kernel 4.16.2 none

Description mvharlan 2018-04-18 14:12:00 UTC 
Description of problem:

Im running Fedora28 beta. When I use kernel 4.16.[12] my kvm (local using spice)
performance playing videos is bad. smplayer starts a video shows a few
frames and freezes after less then a second. Everything is fine with

vmlinuz-4.15.6-200.fc26.x86_64

Version-Release number of selected component (if applicable):

vmlinuz-4.16.2-300.fc28.x86_64

How reproducible:

boot the new kernel: performance is bad
boot the old kernel: performance is ok

Steps to Reproduce:
1. start kvm local
2. play a mp4 video (or other formats) using smplayer
3.

Actual results:

freezes afer a few frames

Expected results:

shows the video

Additional info:

KVM/QEMU Versions:

[root@mbox harlan]# rpm -qa qemu*
qemu-block-curl-2.11.1-2.fc28.x86_64
qemu-block-rbd-2.11.1-2.fc28.x86_64
qemu-block-gluster-2.11.1-2.fc28.x86_64
qemu-common-2.11.1-2.fc28.x86_64
qemu-system-x86-2.11.1-2.fc28.x86_64
qemu-block-nfs-2.11.1-2.fc28.x86_64
qemu-guest-agent-2.11.1-2.fc28.x86_64
qemu-block-dmg-2.11.1-2.fc28.x86_64
qemu-system-x86-core-2.11.1-2.fc28.x86_64
qemu-block-iscsi-2.11.1-2.fc28.x86_64
qemu-block-ssh-2.11.1-2.fc28.x86_64
qemu-img-2.11.1-2.fc28.x86_64
qemu-kvm-2.11.1-2.fc28.x86_64

I have the feeling, it came in with the meltdown/spectre fixes.
Comment 1 Jeremy Cline 2018-04-18 17:55:52 UTC 
Hi,

Thanks for the bug report. Is the host F28, the guest F28, or both? Can you please attach the dmesg logs from the host and guest?
Comment 2 mvharlan 2018-04-19 09:16:38 UTC 
Created attachment 1423948 [details]
dmesg of the host with working 4.15 kernel
Comment 3 mvharlan 2018-04-19 09:21:57 UTC 
Created attachment 1423966 [details]
dmesg of the guest centos 7.4.1708
Comment 4 mvharlan 2018-04-19 09:23:07 UTC 
Created attachment 1423970 [details]
dmesg (journalctl -k -b -1) of the host with broken kernel 4.16.2
Comment 5 Jeremy Cline 2018-04-19 13:38:50 UTC 
There doesn't look to be anything exciting in the logs, so your best bet is to bisect this. https://docs.fedoraproject.org/quick-docs/en-US/kernel/troubleshooting.html#bisecting-the-kernel should get you started if you've not bisected the kernel before. Please let me know if you have any questions. Thanks
Comment 6 Justin M. Forbes 2018-07-23 14:54:35 UTC 
*********** MASS BUG UPDATE **************

We apologize for the inconvenience.  There are a large number of bugs to go through and several of them have gone stale.  Due to this, we are doing a mass bug update across all of the Fedora 28 kernel bugs.

Fedora 28 has now been rebased to 4.17.7-200.fc28.  Please test this kernel update (or newer) and let us know if you issue has been resolved or if it is still present with the newer kernel.

If you experience different issues, please open a new bug report for those.
Comment 7 Justin M. Forbes 2018-08-29 15:04:00 UTC 
*********** MASS BUG UPDATE **************
This bug is being closed with INSUFFICIENT_DATA as there has not been a response in 5 weeks. If you are still experiencing this issue, please reopen and attach the relevant data from the latest kernel you are running and any data that might have been requested previously.