Bug 1223426
| Summary: | [NetKVM] Performance degradation with multi-queue | ||
|---|---|---|---|
| Product: | Red Hat Enterprise Linux 7 | Reporter: | Yvugenfi <yvugenfi> |
| Component: | virtio-win | Assignee: | Yvugenfi <yvugenfi> |
| virtio-win sub component: | virtio-win-prewhql | QA Contact: | Virtualization Bugs <virt-bugs> |
| Status: | CLOSED ERRATA | Docs Contact: | |
| Severity: | medium | ||
| Priority: | unspecified | CC: | lmiksik, michen, vrozenfe, wquan, wyu, yvugenfi |
| Version: | 7.3 | ||
| Target Milestone: | rc | ||
| Target Release: | --- | ||
| Hardware: | Unspecified | ||
| OS: | Windows | ||
| Whiteboard: | |||
| Fixed In Version: | Doc Type: | Bug Fix | |
| Doc Text: |
NO_DOCS
|
Story Points: | --- |
| Clone Of: | Environment: | ||
| Last Closed: | 2016-11-04 08:46:28 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: | |||
|
Description
Yvugenfi@redhat.com
2015-05-20 13:34:51 UTC
Hi Yan, Could you tell me what is the detail steps and test tool for reproducing this bug? And what is the virtio-win-prewhql version that cause Performance degradation ? Thanks wyu Hi Wyu, You can use netperf or iperf to test the performance. Run the tools with 32, 64, 128, 256, 512, 1024, 2048, 4096, 8192, 16384, 32768, 65536 packet sizes. In NetKVM code there is even Tests directory with wrapper for netperf, but you don't have to use it - you can use your own script if it is more convenient. https://github.com/YanVugenfirer/kvm-guest-drivers-windows/blob/master/NetKVM/Tests/netperf_wrapper.rb Builds to compare - latest released driver https://brewweb.devel.redhat.com/buildinfo?buildID=467728 (we still don't have MQ in the release) with latest virtio-win-prewhql driver. Best regards, Yan. Hi Yan, compared above two versions on comment#3, there is no obvious degradation and increase with multiqueue, is that OK? Or the performance should be increased with multiqueue? Thanks wyu (In reply to wangyu from comment #7) > Hi Yan, > > compared above two versions on comment#3, there is no obvious degradation > and increase with multiqueue, is that OK? Or the performance should be > increased with multiqueue? > > Thanks > wyu Hi Wyu, With multi-queue when using several streams we should see some performance improvement. With one stream, it should be the same. Best regards, Yan. Since the problem described in this bug report should be resolved in a recent advisory, it has been closed with a resolution of ERRATA. For information on the advisory, and where to find the updated files, follow the link below. If the solution does not work for you, open a new bug report. https://rhn.redhat.com/errata/RHBA-2016-2609.html |