From: Patrick Robb <probb@iol.unh.edu>
To: ci@dpdk.org
Cc: dev <dev@dpdk.org>
Subject: Community CI Meeting Minutes - September 4, 2025
Date: Tue, 16 Sep 2025 09:47:30 -0400 [thread overview]
Message-ID: <CAJvnSUBYCQmnHQwWWgZsnqooTVyo7UMPtMsbm4jSa6ErJG7X6g@mail.gmail.com> (raw)
[-- Attachment #1: Type: text/plain, Size: 4796 bytes --]
#####################################################################
September 4, 2025
Attendees
1. Patrick Robb
2. Aaron Conole
3. Andrew Bailey
4. Luca Vizzarro
#####################################################################
Minutes
=====================================================================
General Announcements
* Tech board discussed 32 bit testing yesterday:
* Will continue to do this for 1-2 years more. Tech board will discuss
again in 6 months.
* Patrick will collect the unit testing results for an x86_64 system
running with the cross compiled 32 bit unit tests
=====================================================================
CI Status
---------------------------------------------------------------------
AWS Lab
* Running fine
---------------------------------------------------------------------
UNH-IOL Community Lab
* DTS: We threw in 100 dry run testruns and looked at all the results to
get a better understanding, and:
* Scatter (drop rx packets rarely)
* Vlan (rarely error trying to add a vlan)
* Going to change from DTS testcase Error - > failure on patchwork to
DTS Error -> no result submitted to patchwork and UNH guys get an email
saying go look at the testrun
* Packet_capture
* Rarely fail on RX packet does not match TX
* UNH team to remove these from CI temporarily and check their packet
matching scheme for an implementation issue
* Maintenance
* We were doing some system migrations recently which have been
successful but required some overnight downtime on 2 nights.
* Will require 1 more night of downtime to move 1 more service (the
community lab dashboard) off of an old system
* Ajit Khaparde helped us update our broadcom driver/firmware update
procedure
---------------------------------------------------------------------
Intel Lab
* None
* Now that the mbuf_fast_free testcase in DTS is submitted, we need to CC
those guys in. (they recently disabled the mbuf_fast_free testcase in
legacy DTS)
---------------------------------------------------------------------
Github Actions Robot
* Automated PR for AI code review: https://github.com/ovsrobot/dpdk/pulls
* DPDK project is moving ahead with this
* Example: https://github.com/ovsrobot/dpdk/pull/1
* There might be some rate limiting issue or similar - Aaron is debugging
* The other benefit is there could be other services that operate
according to the GH pull request model, and now that we have this staged it
would be easy to start integration those services too
---------------------------------------------------------------------
Loongson Lab
* David did merge the dpdk-web patch this morning which updates the recheck
support blurb indicating the new loongson support
=====================================================================
DTS Improvements & Test Development
* Arg and return type type hints
* This was merged with Luca’s fixup suggestion
* File Artifacts:
* V2 is submitted
* Corrects the issue with there being duplicate testsuite log files and
testcase log files which overlapped with testsuite log files
* Pcaps were previously not being correctly placed (they were all just
dumped into the top level output dir) so they are now being put in the
testsuite specific folders
* DTS API Series:
* It is an incremental approach
* First, Paul is dealing with testpmd shell
* Virtio testing: Dean is working on a virtio forwarding testsuite to start
* Contains virtio testing testcases both with the backend vhost in
–no-pci mode and also others that have the backend vhost forward packets
from physical NICs
* Mbuf_fast_free
* There are some opportunities to improve offload configuration parsing
and classifying queue offloads vs port offloads. We have a rejected series
from last year that was also adding tx_offload support to DTS and we can
pull some ideas from it:
https://patchwork.dpdk.org/project/dpdk/patch/20240903194642.24458-4-jspewock@iol.unh.edu/
* Single_core_forwarding
* Must now enable mbuf_fast_free explicitly in the testcase because
Morten has a series in which change the default from enabled to disabled
and if it’s disabled, forwarding is like -20% MPPS
* Otherwise, Patrick has worked on some Luca’s comments and remaining
work is minimal
*
https://patchwork.dpdk.org/project/dpdk/patch/20250828123758.20451-1-abailey@iol.unh.edu/
* We need to refactor the bound_for_kernel logic
=====================================================================
Any other business
* Next Meeting is Sep 18, 2025
* We will be getting Sourcery reviews for the DTS patches going forward:
https://github.com/ovsrobot/dpdk/pull/2
[-- Attachment #2: Type: text/html, Size: 5422 bytes --]
reply other threads:[~2025-09-16 13:54 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAJvnSUBYCQmnHQwWWgZsnqooTVyo7UMPtMsbm4jSa6ErJG7X6g@mail.gmail.com \
--to=probb@iol.unh.edu \
--cc=ci@dpdk.org \
--cc=dev@dpdk.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).