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 1066209 - Libvirt should calculate and pass vectors parameter to qemu command line for multiqueue virtio device
Summary: Libvirt should calculate and pass vectors parameter to qemu command line for ...
Keywords:
Status: CLOSED CURRENTRELEASE
Alias: None
Product: Red Hat Enterprise Linux 7
Classification: Red Hat
Component: libvirt
Version: 7.0
Hardware: Unspecified
OS: Unspecified
unspecified
unspecified
Target Milestone: rc
: ---
Assignee: Michal Privoznik
QA Contact: Virtualization Bugs
URL:
Whiteboard:
Depends On:
Blocks: 1071888
TreeView+ depends on / blocked
 
Reported: 2014-02-18 03:09 UTC by jason wang
Modified: 2014-06-18 01:03 UTC (History)
11 users (show)

Fixed In Version: libvirt-1.1.1-24.el7
Doc Type: Bug Fix
Doc Text:
Clone Of:
: 1071888 (view as bug list)
Environment:
Last Closed: 2014-06-13 09:19:11 UTC
Target Upstream Version:
Embargoed:

Attachments (Terms of Use)

Description jason wang 2014-02-18 03:09:06 UTC 
Description of problem:

Libvirt should calculate the number of msix vectors and pass it to qemu command line for multiqueue virtio-net (maybe scsi). Otherwise the all virtqueue will share a single vector which will damage the performance.

Upstream commit:

commit 4f588a1b465e2b32c78429e8d2f2c010eb11da19
Author:     Michal Privoznik <mprivozn>
AuthorDate: Fri Aug 23 09:48:24 2013 +0200
Commit:     Michal Privoznik <mprivozn>
CommitDate: Thu Jan 9 15:23:57 2014 +0100

    qemuBuildNicDevStr: Set vectors= on Multiqueue
    
    Yet another advice appeared on the Multiqueue wiki page:
    
    http://www.linux-kvm.org/page/Multiqueue#Enable_MQ_feature
    
    We should add vectors=N onto the qemu command line, where
    N = 2 * (number of queues) + 1.

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


How reproducible:


Steps to Reproduce:
1.
2.
3.

Actual results:


Expected results:


Additional info:
Comment 2 Michal Privoznik 2014-02-18 11:00:53 UTC 
Moving to POST:

http://post-office.corp.redhat.com/archives/rhvirt-patches/2014-February/msg00467.html

Moreover, I've build a scratch build to test:

https://brewweb.devel.redhat.com/taskinfo?taskID=7073866
Comment 3 hyao@redhat.com 2014-02-20 07:54:12 UTC 
Reproduced the bug with 
#rpm -qa libvirt
libvirt-1.1.1-23.el7.x86_64
1. Add the following config in domain xml. 
<interface type='network'>
      <mac address='52:54:00:92:d5:ba'/>
      <source network='default'/>
      <target dev='vnet2'/>
      <model type='virtio'/>
      <driver name='vhost' txmode='iothread' ioeventfd='on' event_idx='off' queues='5'/>
      <alias name='net1'/>
      <address type='pci' domain='0x0000' bus='0x00' slot='0x06' function='0x0'/>
    </interface>
2.Start the guest and check the qemu command, vectors=2N+1 is not added. 
#ps aux | grep qemu | grep virtio-net



Test the bug with scratch build: 
#rpm -qa libvirt
libvirt-1.1.1-23.el7multiqueue.x86_64

1. Add the following config in domain xml. 
<interface type='network'>
      <mac address='52:54:00:92:d5:ba'/>
      <source network='default'/>
      <target dev='vnet2'/>
      <model type='virtio'/>
      <driver name='vhost' txmode='iothread' ioeventfd='on' event_idx='off' queues='5'/>
      <alias name='net1'/>
      <address type='pci' domain='0x0000' bus='0x00' slot='0x06' function='0x0'/>
    </interface>
2.Start the guest and check the qemu command, vectors=2N+1 is added. 
#ps aux | grep qemu | grep virtio-net
...-device virtio-net-pci,tx=bh,ioeventfd=on,event_idx=off,mq=on,vectors=11,netdev=hostnet1,id=net1,mac=52:54:00:92:d5:ba,bus=pci.0,addr=0x6 ...
Comment 5 EricLee 2014-02-26 08:34:26 UTC 
Verified pass on libvirt-1.1.1-24.el7, steps as comment #3.
Comment 6 Ludek Smid 2014-06-13 09:19:11 UTC 
This request was resolved in Red Hat Enterprise Linux 7.0.

Contact your manager or support representative in case you have further questions about the request.
Note You need to log in before you can comment on or make changes to this bug.