RHEL Engineering is moving the tracking of its product development work on RHEL 6 through RHEL 9 to Red Hat Jira (issues.redhat.com). If you're a Red Hat customer, please continue to file support cases via the Red Hat customer portal. If you're not, please head to the "RHEL project" in Red Hat Jira and file new tickets here. Individual Bugzilla bugs in the statuses "NEW", "ASSIGNED", and "POST" are being migrated throughout September 2023. Bugs of Red Hat partners with an assigned Engineering Partner Manager (EPM) are migrated in late September as per pre-agreed dates. Bugs against components "kernel", "kernel-rt", and "kpatch" are only migrated if still in "NEW" or "ASSIGNED". If you cannot log in to RH Jira, please consult article #7032570. That failing, please send an e-mail to the RH Jira admins at rh-issues@redhat.com to troubleshoot your issue as a user management inquiry. The email creates a ServiceNow ticket with Red Hat. Individual Bugzilla bugs that are migrated will be moved to status "CLOSED", resolution "MIGRATED", and set with "MigratedToJIRA" in "Keywords". The link to the successor Jira issue will be found under "Links", have a little "two-footprint" icon next to it, and direct you to the "RHEL project" in Red Hat Jira (issue links are of type "https://issues.redhat.com/browse/RHEL-XXXX", where "X" is a digit). This same link will be available in a blue banner at the top of the page informing you that that bug has been migrated.
Bug 1973017 - [virtio-win] [netkvm] Poor network performance with Win2022
Summary: [virtio-win] [netkvm] Poor network performance with Win2022
Keywords:
Status: CLOSED CURRENTRELEASE
Alias: None
Product: Red Hat Enterprise Linux 9
Classification: Red Hat
Component: virtio-win
Version: 9.2
Hardware: Unspecified
OS: Unspecified
high
high
Target Milestone: rc
: 9.2
Assignee: ybendito
QA Contact: Quan Wenli
URL:
Whiteboard:
: 1973016 (view as bug list)
Depends On:
Blocks: 1968315 2057757
TreeView+ depends on / blocked
 
Reported: 2021-06-17 06:06 UTC by Quan Wenli
Modified: 2022-07-26 08:38 UTC (History)
5 users (show)

Fixed In Version:
Doc Type: If docs needed, set a value
Doc Text:
Clone Of:
Environment:
Last Closed: 2022-07-26 08:38:33 UTC
Type: ---
Target Upstream Version:
Embargoed:


Attachments (Terms of Use)

Description Quan Wenli 2021-06-17 06:06:57 UTC
Description of problem:
Compare network performance between 2022 and 2019 with virtio-win-prewhql-0.1-199, we can see two performance issues:

1. For TCP_STREAM tests:

  1.1 TX: there is about 17%-60% performance gap compared with Win2019[1]
  1.2 RX: almost no difference between 2022 and 2019[1]

2. For TCP_RR test, about 30% performance drop compared with Win2019[2]

[1] TCP_STREAM: http://10.73.60.69/results/regression/2021-6-10-network-Win2022/netperf.with_jumbo.host_guest.html

[2] TCP_RR: http://10.73.60.69/results/regression/2021-6-10-network-Win2022/netperf.default.host_guest.html

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

userspace:  qemu-kvm-6.0.50-18.scrmod+el8.5.0+11348+c852f1ac.wrb210609.x86_64
host kernel:  4.18.0-310.el8.x86_64
virtio-win-prewhql: virtio-win-prewhql-0.1-199


How reproducible:


Steps to Reproduce:
1.Boot vm with virtio/vhost like:

numactl \
    -m 1  /usr/libexec/qemu-kvm \
    -S  \
    -name 'avocado-vt-vm1'  \
    -sandbox on  \
    -machine q35,memory-backend=mem-machine_mem \
    -device pcie-root-port,id=pcie-root-port-0,multifunction=on,bus=pcie.0,addr=0x1,chassis=1 \
    -device pcie-pci-bridge,id=pcie-pci-bridge-0,addr=0x0,bus=pcie-root-port-0  \
    -nodefaults \
    -device VGA,bus=pcie.0,addr=0x2 \
    -m 4096 \
    -object memory-backend-ram,size=4096M,id=mem-machine_mem  \
    -smp 4,maxcpus=4,cores=2,threads=1,dies=1,sockets=2  \
    -cpu 'Cascadelake-Server-noTSX',hv_time,hv_relaxed,hv_vapic,hv_spinlocks=0xfff,hv_stimer,hv_synic,hv_vpindex,hv_relaxed,hv_spinlocks=0x1fff,hv_vapic,hv_time,hv_frequencies,hv_runtime,hv_tlbflush,hv_reenlightenment,hv_stimer_direct,hv_ipi,+kvm_pv_unhalt \
    -chardev socket,server=on,id=qmp_id_qmpmonitor1,path=/tmp/avocado_63wgacu1/monitor-qmpmonitor1-20210610-033654-ki0n0WVw,wait=off  \
    -mon chardev=qmp_id_qmpmonitor1,mode=control \
    -chardev socket,server=on,id=qmp_id_catch_monitor,path=/tmp/avocado_63wgacu1/monitor-catch_monitor-20210610-033654-ki0n0WVw,wait=off  \
    -mon chardev=qmp_id_catch_monitor,mode=control \
    -device pvpanic,ioport=0x505,id=idVGnkeH \
    -chardev socket,server=on,id=chardev_serial0,path=/tmp/avocado_63wgacu1/serial-serial0-20210610-033654-ki0n0WVw,wait=off \
    -device isa-serial,id=serial0,chardev=chardev_serial0  \
    -chardev socket,id=seabioslog_id_20210610-033654-ki0n0WVw,path=/tmp/avocado_63wgacu1/seabios-20210610-033654-ki0n0WVw,server=on,wait=off \
    -device isa-debugcon,chardev=seabioslog_id_20210610-033654-ki0n0WVw,iobase=0x402 \
    -device pcie-root-port,id=pcie-root-port-1,port=0x1,addr=0x1.0x1,bus=pcie.0,chassis=2 \
    -device qemu-xhci,id=usb1,bus=pcie-root-port-1,addr=0x0 \
    -device usb-tablet,id=usb-tablet1,bus=usb1.0,port=1 \
    -blockdev node-name=file_image1,driver=file,auto-read-only=on,discard=unmap,aio=threads,filename=/root/avocado/data/avocado-vt/vl_avocado-vt-vm1_image1.qcow2,cache.direct=on,cache.no-flush=off \
    -blockdev node-name=drive_image1,driver=qcow2,read-only=off,cache.direct=on,cache.no-flush=off,file=file_image1 \
    -device pcie-root-port,id=pcie-root-port-2,port=0x2,addr=0x1.0x2,bus=pcie.0,chassis=3 \
    -device virtio-blk-pci,id=image1,drive=drive_image1,bootindex=0,write-cache=on,bus=pcie-root-port-2,addr=0x0 \
    -device pcie-root-port,id=pcie-root-port-3,port=0x3,addr=0x1.0x3,bus=pcie.0,chassis=4 \
    -device virtio-net-pci,mac=9a:be:3e:64:42:96,id=id57ApcZ,netdev=idq84UnN,bus=pcie-root-port-3,addr=0x0  \
    -netdev tap,id=idq84UnN,vhost=on,vhostfd=20,fd=16 \
    -device rtl8139,mac=9a:37:37:37:37:7e,id=idpNfodd,netdev=idLwmFfj,bus=pcie-pci-bridge-0,addr=0x1  \
    -netdev tap,id=idLwmFfj,fd=21 \
    -blockdev node-name=file_cd1,driver=file,auto-read-only=on,discard=unmap,aio=threads,filename=/home/kvm_autotest_root/iso/windows/winutils.iso,cache.direct=on,cache.no-flush=off \
    -blockdev node-name=drive_cd1,driver=raw,read-only=on,cache.direct=on,cache.no-flush=off,file=file_cd1 \
    -device ide-cd,id=cd1,drive=drive_cd1,bootindex=1,write-cache=on,bus=ide.0,unit=0  \
    -vnc :0  \
    -rtc base=localtime,clock=host,driftfix=slew  \
    -boot menu=off,order=cdn,once=c,strict=off \
    -enable-kvm \
    -device pcie-root-port,id=pcie_extra_root_port_0,multifunction=on,bus=pcie.0,addr=0x3,chassis=5

2.run netperf-2.6.0 server on guest
3.run "netperf -H 192.168.58.73(guest_ip) -l 67.5 -t TCP_STREAM -- -m 65535" external host.
4.run "netperf -D 1 -H 192.168.58.73 -l 67.5 -t TCP_RR -v 1 -- -r 64,64" on external host.

Actual results:

Win 2022's performance is not worse than Win2016. 

Expected results:

Win 2022's performance is not worse than Win2019. 

Additional info:

Comment 1 Quan Wenli 2021-06-17 06:08:59 UTC
*** Bug 1973016 has been marked as a duplicate of this bug. ***

Comment 2 Vadim Rozenfeld 2021-09-20 02:40:23 UTC
Created attachment 1824469 [details]
QPC source checker

Please run this app on your system and post the results.

Thanks,
Vadim.

Comment 15 ybendito 2021-10-17 08:03:30 UTC
Please note that any performance tests must be done with driver verifier turned off for all the drivers, otherwise the performance results are for reference only.
Please add the respective configuration of driver verifier and retest, please refer the results of the comparison in the response.

Comment 19 Qianqian Zhu 2021-11-02 10:35:13 UTC
Hi Wenli,

Would you help test it again with the scratch build here: https://bugzilla.redhat.com/show_bug.cgi?id=1972487#c40? Many thanks.

Regards,
Qianqian

Comment 20 Yvugenfi@redhat.com 2021-11-02 11:52:49 UTC
(In reply to Qianqian Zhu from comment #19)
> Hi Wenli,
> 
> Would you help test it again with the scratch build here:
> https://bugzilla.redhat.com/show_bug.cgi?id=1972487#c40? Many thanks.
> 
> Regards,
> Qianqian

We need comparison to stable release.

Comment 21 Quan Wenli 2021-11-03 04:02:08 UTC
(In reply to Yvugenfi from comment #20)
> (In reply to Qianqian Zhu from comment #19)
> > Hi Wenli,
> > 
> > Would you help test it again with the scratch build here:
> > https://bugzilla.redhat.com/show_bug.cgi?id=1972487#c40? Many thanks.
> > 
> > Regards,
> > Qianqian
> 
> We need comparison to stable release.

In my understanding , we need to compare build 21050 vs 210 version with only Win2022 ?

Comment 22 Yvugenfi@redhat.com 2021-11-03 09:54:10 UTC
(In reply to Quan Wenli from comment #21)
> (In reply to Yvugenfi from comment #20)
> > (In reply to Qianqian Zhu from comment #19)
> > > Hi Wenli,
> > > 
> > > Would you help test it again with the scratch build here:
> > > https://bugzilla.redhat.com/show_bug.cgi?id=1972487#c40? Many thanks.
> > > 
> > > Regards,
> > > Qianqian
> > 
> > We need comparison to stable release.
> 
> In my understanding , we need to compare build 21050 vs 210 version with
> only Win2022 ?

BZ#1972487 is not only for Windows 2022. We would like to see general performance impact, so actually I would prefer to test Windows Server 2019.

Comment 23 Quan Wenli 2021-11-03 10:00:39 UTC
(In reply to Yvugenfi from comment #22)
> (In reply to Quan Wenli from comment #21)
> > (In reply to Yvugenfi from comment #20)
> > > (In reply to Qianqian Zhu from comment #19)
> > > > Hi Wenli,
> > > > 
> > > > Would you help test it again with the scratch build here:
> > > > https://bugzilla.redhat.com/show_bug.cgi?id=1972487#c40? Many thanks.
> > > > 
> > > > Regards,
> > > > Qianqian
> > > 
> > > We need comparison to stable release.
> > 
> > In my understanding , we need to compare build 21050 vs 210 version with
> > only Win2022 ?
> 
> BZ#1972487 is not only for Windows 2022. We would like to see general
> performance impact, so actually I would prefer to test Windows Server 2019.

Ok, what't the base verison, should be 210 or 211 ?

Comment 24 Yvugenfi@redhat.com 2021-11-03 10:06:52 UTC
(In reply to Quan Wenli from comment #23)
> (In reply to Yvugenfi from comment #22)
> > (In reply to Quan Wenli from comment #21)
> > > (In reply to Yvugenfi from comment #20)
> > > > (In reply to Qianqian Zhu from comment #19)
> > > > > Hi Wenli,
> > > > > 
> > > > > Would you help test it again with the scratch build here:
> > > > > https://bugzilla.redhat.com/show_bug.cgi?id=1972487#c40? Many thanks.
> > > > > 
> > > > > Regards,
> > > > > Qianqian
> > > > 
> > > > We need comparison to stable release.
> > > 
> > > In my understanding , we need to compare build 21050 vs 210 version with
> > > only Win2022 ?
> > 
> > BZ#1972487 is not only for Windows 2022. We would like to see general
> > performance impact, so actually I would prefer to test Windows Server 2019.
> 
> Ok, what't the base verison, should be 210 or 211 ?
Let's use 211


Note You need to log in before you can comment on or make changes to this bug.