Downloading image from: https://artifacts.toradex.com/artifactory/torizoncore-oe-prerelease-frankfurt/kirkstone-6.x.y/monthly/25//torizon-rt/torizon-core-docker/oedeploy/torizon-core-docker-rt--Tezi_6.8.0-devel-202408+build.25.tar
The download may take some time. Please wait...
The requested image could not be found in the Toradex Artifactory.
Notice that there are TWO dashes between rt and Tezi, but at the toradex artifacts link, this .tar file only has one -
Is this a bug in the way the device tree deploy grabs the .tar name? or is it a typo in the naming? I tried to find out more about how the deploy command determines which .tar file to use to help see why this naming typo is occuring but could not find the answer.
Hi, I’m the Toradex AI Assistant. The Toradex Support team will follow up with you shortly!
Did you like my answer?
Based on the provided context, it seems like there might be an issue with the naming convention used by the torizoncore-builder tool when it tries to locate the image in the Toradex Artifactory. The discrepancy between the expected and actual tarball names could indeed be causing the problem.
Here are a few steps you can take to troubleshoot and potentially resolve this issue:
Verify the Image Name: Double-check the exact name of the tarball in the Toradex Artifactory. Ensure there are no typos or discrepancies in the name.
Check for Updates: Ensure that you are using the latest version of the torizoncore-builder tool. There might have been updates or bug fixes related to this issue.
Manual Download and Deployment:
Download the correct tarball manually from the Toradex Artifactory.
Use the torizoncore-builder tool to deploy the device tree overlay locally instead of relying on the remote download feature.
Report the Issue: If the problem persists, it might be a bug in the torizoncore-builder tool. You can report this issue to Toradex support or on their GitHub repository, providing all the details and the discrepancy in the naming convention.
Workaround: As a temporary workaround, you can manually adjust the naming convention in your local environment to match what the torizoncore-builder tool expects, if feasible.
If none of these steps resolve the issue, it would be best to contact Toradex support directly with all the details, including the exact command you are using and the error message you are receiving. They would be able to provide more specific guidance or a fix for the issue.
Please, also check if these links can help you solve your problem:
Please do not use the dto deploy command. It’s know to have issues and not work with 6.X versions of Torizon OS. It might even be deprecated/removed in the future. On a similar note don’t use the dt checkout command either, as this similarly does not work with 6.X and newer.
Understood! I was following that documentation: Device Tree Overlays on Torizon | Toradex Developer Center.
which has the dto deploy as apart of the process
If it is no longer the desired process then maybe it should be changed! Thank you for your reply
Also, I am not sure if i pulled down a wrong version of the repo, but linux\include\dt-bindings\input\linux-event-codes.h was returning a syntax error:
Error: linux/include/dt-bindings/input/linux-event-codes.h:1.1-3 syntax error
for this line.
…/…/uapi/linux/input-event-codes.h.
fixed by changing it to this: #include “…/…/uapi/linux/input-event-codes.h”
Maybe somehow when you cloned the repo onto your machine it didn’t preserve the symlink? On my system if I clone the repo I can see it’s a symlink and trying to open the file just opens the file the symlink was pointing to.
