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 1729442 - ovs kernel throughput running in RHEL-7.7 RC1 is lower than RHEL-7.6
Summary: ovs kernel throughput running in RHEL-7.7 RC1 is lower than RHEL-7.6
Keywords:
Status: CLOSED NOTABUG
Alias: None
Product: Red Hat Enterprise Linux 7
Classification: Red Hat
Component: openvswitch
Version: 7.7
Hardware: Unspecified
OS: Unspecified
medium
medium
Target Milestone: rc
: ---
Assignee: Aaron Conole
QA Contact: Jiying Qiu
URL:
Whiteboard:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2019-07-12 09:50 UTC by Jiying Qiu
Modified: 2019-10-07 10:30 UTC (History)
7 users (show)

Fixed In Version:
Doc Type: If docs needed, set a value
Doc Text:
Clone Of:
Environment:
Last Closed: 2019-10-07 10:30:16 UTC
Target Upstream Version:
Embargoed:


Attachments (Terms of Use)

Description Jiying Qiu 2019-07-12 09:50:17 UTC
Description of problem:
ovs kernel throughput running in RHEL-7.7 is lower than RHEL-7.6

Version-Release number of selected component (if applicable):
openvswitch2.11-2.11.0-12.el7fdp.x86_64.rpm & RHEL-7.7-20190702.0
openvswitch2.11-2.11.0-9.el7fdp.x86_64.rpm & RHEL-7.6

How reproducible:
always

Steps to Reproduce:
1. setup PVP topo, 
2. 1k flows ,ipv4 traffic (xenaL2-3 traffic generator )
3. 

Actual results:
for ovs2.11-9 &RHEL-7.6            got 330197 rx_pps
for ovs2.11-12&RHEL-7.7-20190702.0 got 94382  rx_pps

Expected results:
the performance do not drop

Additional info:

Comment 2 Timothy Redaelli 2019-07-18 08:47:40 UTC
Hi,

can you try to do the performance test with the same ovs version on both rhel 7.6 and 7.7?

Thank you

Comment 3 Jiying Qiu 2019-07-18 09:34:40 UTC
I have submitted jobs, it would take 2+ days to run the whole performance. Will update the results once it finished.

Comment 4 Jiying Qiu 2019-07-22 06:08:43 UTC
                verisons                                      disable_emc                enable_emc 
openvswitch2.11-2.11.0-12.el7fdp&RHEL7.7-RC1                    98902                       64254
openvswitch2.11-2.11.0-12.el7fdp&RHEL7.6                       143340                      301512
openvswitch2.11-2.11.0-9.el7fdp &RHEL7.7-RC1                    90616                       78566
openvswitch2.11-2.11.0-9.el7fdp &RHEL7.6                       330197                       83147

Details can be find in https://docs.google.com/spreadsheets/d/1dE6Iz9RcFDjNLhllWToPOqv4Z2sES4minSzaLC3jmi4/edit?usp=sharing.

Comment 5 Jiying Qiu 2019-07-22 06:46:21 UTC
All these jobs run with RHEL-7.6 guest and testpmd of dpdk-18.11-4.el7_6 version in guest.

Comment 11 Jiying Qiu 2019-08-06 06:46:01 UTC
After donging bisect testing, found Beta-1.1 RHEL-7.7-20190514.2 has a big drop. 
verisons                                                     disable_emc                enable_emc 
openvswitch2.11-2.11.0-12.el7fdp & RHEL-7.7-20190514.0         93630                       298500
openvswitch2.11-2.11.0-12.el7fdp & RHEL-7.7-20190514.2         49190                        49190

Comment 12 Aaron Conole 2019-09-13 20:55:30 UTC
This is a kernel issue - what are the results of the kernel bisect?

Comment 13 Jiying Qiu 2019-09-30 07:29:49 UTC
Have rerun the Beta-1.1 RHEL-7.7-20190514.2 and Beta-1.0 RHEL-7.7-20190514.0
verisons                                                     disable_emc                enable_emc               job url
openvswitch2.11-2.11.0-12.el7fdp & RHEL-7.7-20190514.0         42412                       42412                 https://beaker.engineering.redhat.com/jobs/3815182
openvswitch2.11-2.11.0-12.el7fdp & RHEL-7.7-20190514.2         41658                       37892                 https://beaker.engineering.redhat.com/jobs/3815181 

Both distro are kernel-3.10.0-1048.el7.

will try kernel-3.10.0-1040 "Alpha-1.2" and kernel-3.10.0-1034 "DevelPhaseExit-1.0" .

Comment 14 Jiying Qiu 2019-10-07 10:30:16 UTC
verisons                                                               disable_emc           enable_emc             job url
openvswitch2.11-2.11.0-12.el7fdp & RHEL-7.7-20190514.0                   42412                42412                 https://beaker.engineering.redhat.com/jobs/3815182(qemu2.10) & https://beaker.engineering.redhat.com/jobs/3821690 (qemu2.12)
openvswitch2.11-2.11.0-12.el7fdp & RHEL-7.7-20190514.2                   41658                37892                 https://beaker.engineering.redhat.com/jobs/3815181(qemu2.10) & https://beaker.engineering.redhat.com/jobs/3821689 (qemu2.12)
openvswitch2.11-2.11.0-12.el7fdp & RHEL-7.7-20190612.0(FDP19.D)          42412                43166                 https://beaker.engineering.redhat.com/jobs/3821720
openvswitch2.11-2.11.0-12.el7fdp & RHEL-7.6                              42412                42412                 https://beaker.engineering.redhat.com/jobs/3821719

As FDP19.D and RHEL-7.6 jobs results, I think there are full reasons to say this is not a bug, but a problem of xenaL2-3 traffic generator.


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