Community CI Meeting Minutes - June 27, 2024

Community CI Meeting Minutes - June 27, 2024

[Patrick Robb]

#####################################################################
Attendees
1. Patrick Robb
2. Paul Szczepanek
3. Luca Vizzarro
4. Nicholas Pratte
5. Aaron Conole
6. Dean Marx
7. Jeremy Spewock
8. Juraj Linkeš
9. Manit Mahajan
10. Tomas Durovec
11. Adam Hassick

#####################################################################
Minutes

=====================================================================
General Announcements
* DPDK Summit in Montreal will be September 24-25:
https://www.dpdk.org/event/dpdk-summit-2024/
   * CFP closes July 21
   * Tech board voted yesterday to allow remote presentations at
Montreal (with lower priority)
   * Luca will make a submission for a remote DTS talk
   * David commented last week stating that there could be a section
for how to setup DTS, run the hello world testsuite
* Nathan Southern set up a call with some folks from AWS next Monday
to discuss testing on cloud infrastructure. Email Nathan if you want
to join this call.
* David indicated there will be a vote over email for a DTS branch for
framework patches

=====================================================================
CI Status

---------------------------------------------------------------------
UNH-IOL Community Lab
* David noted this week that the template engine is out of date
(UNH-IOL fork has some update from the past months). UNH now has a 60
day reminder for aggregation all commits made to our fork and
upstreaming.
* New Servers have arrived at UNH-IOL. Getting these mounted onto our
2nd DPDK Rack, setting up the associated infrastructure etc.
   * Setting up the UPS, tor switch, etc for DPDK rack 2.
* Pending:
   * Pending emails are going out, but the checks are not being
written to the API
   * Emailed Ali - will have to debug with him
   * We only are running this for ABI testing right now, but as soon
as the behavior with the PW API looks good, we can turn this on for
all the other labels (the PR for pending for all testing is ready)
* Depends-on support: Adam has submitted a patchseries to the PW
project which adds the changes to the Django models. Is under review.
   * Github PR: https://github.com/getpatchwork/patchwork/pull/590
   * Has put together the corresponding changes to git-pw (client side)
      * Some overlap between the PW server and git-pw client - the pw
server maintainer is aware of this feature being added for git-pw
which will pair up with the dashboard updates
* SPDK: Submitted a patch fixing a malloc error which affected Fedora
40. This is now merged, so we added Fedora 40 coverage in our lab.
* We increased the retest limit per patchseries to 3 (was previously
1) due to a submitter who needed to retest multiple sets of contexts.

---------------------------------------------------------------------
Intel Lab
* None

---------------------------------------------------------------------
Github Actions
* None, the Robot is running smoothly.
* There was a GitHub outage itself a few weeks ago, but anyone who was
affected would have been able to request a retest.

---------------------------------------------------------------------
Loongarch Lab
* None

=====================================================================
DTS Improvements & Test Development
* Jumboframes testsuite: MTU behavior on different NIC drivers.
   * Within each driver, there are variables set for taking off
ethernet overhead when setting max packet length.
      * MLNX subtracts 18 bytes
      * Intel/Broadcom subtract 26 bytes.
         * But from testing it appears that you can only send packets
with MTU + 22 packets, not 26?
      * These variables are not common across drivers… so basically
MTU as defined by different drivers is not the same
      * When we build scapy packets, the ethernet overhead is 14 bytes
(source mac address, destination mac, error correction), so we can
actually increase the l3 packet above the given MTU and still send
packets
   * Juraj: Important to make sure we are running from the latest
firmware/drivers on each device
   * Firmware driver versions for devices are published per DPDK release
      * Patrick Robbshould set up a 4 month reminder (during beginning
of dpdk release cycle) to update all firmware to whatever was
published as being supported for the release which just came out - use
this version for all testing for the upcoming release
* Mac Filter Testsuite: Submitted, getting reviews on the mailing
list. Nick will respond to Jeremy’s comments today and submit a new
version.
* VLAN Filter: Bugzilla ticket is submitted for the VLAN filtering
bug. David requested some verbose logs, so Dean redid the test and
attached those to the ticket.
* Queue Start/Stop and Dynamic Queue:
   * Show port into exposes a capability for whether you can stop or
start the queue.
* There is another bugzilla ticket out for –max-packet-len. It does
not update the MTU if you are using a kernel driver.
   * https://bugs.dpdk.org/show_bug.cgi?id=1470
   * Need to double check this from the Jumboframes testsuite
* Paul: but essentially we're moving on from vff to l2fwd due to vff
requiring qemu, otherwise all normal, blocklist submitted
   * UNH people need to test blocklist on our hardware
* Luca will be on vacation for the next two weeks
* Juraj will be on vacation next week.
* Capabilities patch: Working on an updated version, it might not be
ready before Juraj goes on vacation next week.
   * Adds the conditional capabilities, for cases where some staging
is needed in order to report the capability. This is the case with
scatter (the capability will only report for some devices if MTU is
increased from the standard size)
   * After the capability setup function runs and then the capability
checked, everything is cleaned up and the previous state restored.
      * For the capability, use a decorated to associate a testpmd
function which will do the pre and post configuration for the
capability check
   * Looking to add support for all the capabilities testpmd exposes
* XLM-RPC server replacement: new version submitted and awaiting reviews
   * Extended usage of kwargs in the new version makes the code a
little more confusing. Right now the arguments are of type any, as
opposed to processing the output via a typed dict.

=====================================================================
Any other business
* Patrick Robbshould check with folks over email whether it would be
okay to reschedule the DTS calls from Wednesdays to Thursdays (same
time as CI calls, on the off weeks)
* Next Meeting: July 11, 2024