Hello,
I have apalis-imx8 with ixora board. I reset it by ToradexEasyInstaller, and I installed Torizon easy pair last version. Then I used: “Torizon Cloud Application” to pair the device and install the os and apps. All the steps worked until the last steps: Installing os: I chose: Kirkstone-docker imxx8 version, and the demo app: weston-imx8, it always fail, and give me Update fail. I tried about 20 times with different versions of kirkstone-docker, and I reset the board again and reinstalled Torizon easy pair, but it also failed. Previously this happened also, but after about 5 to 10 times I can install the os and apps. Can you please tell me why this happened? What is the solution for this?
Best regards,
Tarek
Hi, I’m the Toradex AI Assistant. The Toradex Support team will follow up with you shortly!
Did you like my answer?
Hello!
When performing OS and application updates on Torizon, several checks are in place to ensure the process runs smoothly. Here’s a breakdown of what happens during these updates:
OS Updates:
- Torizon OS identifies unsuccessful updates and will reboot the system if issues occur. If there are three consecutive unsuccessful boot attempts, the system will automatically roll back to the previous OS version.
Application Updates (e.g., Weston):
- The system sources new container images and uses Docker Compose to stop old containers and start new ones. It checks the exit codes of these operations, where a code of 0 indicates success, and any other code indicates failure.
Synchronous Updates (OS and Application Together):
- The update process begins with a check and download phase that must succeed. The OS installation starts first, followed by the application installation. The system then reboots to finalize both updates. If any step fails, the system will roll back to the previous state.
Troubleshooting Tips:
- Check if the system is rolling back after three boot attempts.
- Ensure both OS and application installations complete successfully before the system reboots.
- Look for any exit codes from the Docker Compose commands to identify potential issues.
For more detailed information, you can refer to the Torizon Updates Technical Overview.
I hope this helps clarify the update process on Torizon. If you have any more questions, feel free to ask!
Best regards,
Toradex AI Assistant
Hello @tarekmhnds,
Can you describe in more detail the following topics:
- Which OS image was initially installed to the device?
- Which exact packages were installed via the Torizon Cloud? In which order?
Best Regards,
Bruno
Hello Bruno,
I reset the board using ToradexEasyInstaller via micro usb, then I installed the last version of Torizon Easy pair 7.xx, after that I paired the device with the cloud, and it gave the device a default name. Then I tried to install Kirkstone-docker-imx8 release versions via Initial update button, like: “kirkstone/apalis-imx8/torizon/torizon-core-docker/release”, with many versions like: “6.2.0+build.2”, “6.3.0+build.4”, … and many others, and I selected: “weston-apalis-imx8” version: 3 from Torizon Demo Apps, but all of them gave: “Update in progress” at the device status, then: “Update failed”. Some times the board rebooted after that, sometimes it did not reboot. I tried this process so many times but it always failed. I delete the device then pair it again, but with the same results. I also tried to reset the board again and started everything again but it also failed.
Best regards,
Tarek
Hello @tarekmhnds,
As you initially installed Torizon 7 to the device, installing kirkstone/apalis-imx8/torizon/torizon-core-docker/release is a downgrade back to Torizon 6.
This is generally not recommended.
Torizon 7 is based on a scarthgap BSP, so installing scarthgap/apalis-imx8/torizon/torizon-docker/release images should work.
Regarding the demo applications, it looks like the latest versions are still version 3, which are intended for Torizon OS 6.
Therefore, to test them out, you could try with Torizon OS 7, but they could not work.
If that is the case, what you can also do is install Torizon OS 6 easy pairing with the Toradex Easy Installer and then try to run the demos from the cloud.
Best Regards,
Bruno
Hello @bruno.tx ,
I have no idea about the Torizon version behind the releases, if its 6 or 7, so how to know this please?
Also I don’t know why I should install Torizon releases (kirkstone or scarthgap) after installing Torizon easy pair version 7? Can I use the board with Toradex extension for VS code after installing Torizon easy pair 7 without installing any release?
I tried the last version of: scarthgap/apalis-imx8/torizon/torizon-docker/release it gave me Update finished and successful, after that the board rebooted and it returned back to the window that have a code to pair the device and a link for the pairing page. If I reboot the device again the same window came back again. At Torizon cloud Devices page it gave me the installed OS Package is: scarthgap/apalis-imx8/torizon/torizon-docker/release and the version is 7.1.0+build.4, but I think the pair is missed and I cannot use the device. Why this happened please?
Best regards,
Tarek
Hello @tarekmhnds,
The versioning as it is displayed now in the Torizon Cloud can be confusing.
We have ongoing discussions on how to improve it.
On the following page you can see our release matrix, which includes the version of the Yocto project used for each release: Release Matrix - Kernel/U-Boot Version | Toradex Developer Center
There is no need to send an OS update to the board to use the Torizon IDE Extension.
You can just install a given version of Torizon OS to the board and follow our guide on how to use the IDE extension:
- If using a Windows PC for development: Install the Build Environment for Torizon | Toradex Developer Center
- If using a Linux PC for development: Install the Build Environment for Torizon | Toradex Developer Center
Also, what do you mean by “the pair is missed and I cannot use the device”?
Is the device offline or no longer booting?
Best Regards,
Bruno
Hello @bruno.tx ,
Thanks a lot the link was useful to me to know the version of the Yocto project used for each release.
I used the Torezon Easy Pair OS without downloading any other version from the cloud, and it worked fine with the vscode extension.
My question please, why do you have another os versions like: kirkstone or scarthgap at your cloud? What is the benefit of them? Can I work without them using Torizon easy pair only?
the pair is missed and I cannot use the device: I mean that after reboot I got a new code for pairing with Torizon cloud, this usually doesn’t happen. If pairing is Ok, I don’t see this window (with pair code) again. Therefore, I think that the pairing was not successful and using the device to download applications from the cloud will not work, and I need to re-add the device to the cloud. But the device is working and online.
Best Regards,
Tarek
Hello @tarekmhnds,
These different versions of software are the different releases of Torizon OS.
While you may have installed Torizon OS 7.2 on your device, there may be someone else who installed Torizon OS 6.4 and now wants to update to a newer version of Torizon OS 6 or even to Torizon OS 7.
Regardless of the use case, the images that we provide on the Cloud most of the time are not the ones used directly by Torizon users.
Most of the time, there will be some level of customization involved, either through TorizonCore Builder or Yocto.
We would be happy to explain these topics in more details in a Video call where we can show you a bit more of the use cases and features available with Torizon.
If this is something that you would want, please let me know and we will reach out directly via email.
This is unexpected.
However, if the device still shows up as online on the Torizon Cloud, it is still provisioned.
If that is the case, the issue is likely with the application that provides the pairing codes, not with the pairing itself.
Best Regards,
Bruno
Best Regards,
Bruno
Hello @bruno.tx,
Thank you very much for the explanation.
I am currently heavily involved in developing the app and have limited time, but when I am done I will contact you for a video call.
I noticed something new that didn’t happen before after downloading the latest version of Torizon OS, that might explain some of the problem. When I connect to the board applies and set it as default through VS Code Extension, It can’t detect the correct IP for my PC, and it gives me a strange IP which is: 169.254.201.164, and I detected that I need to replace this IP with the correct IP in two places for the program to run correctly on the board via: run-container-torizon-release-arm64, the first place is at the file: .vscode/settings.json, the host_ip setting, the second one is at the board at the file: /etc/docker/daemon.json, the insecure-registries setting. My PC IP is: 192.168.0.50, and the board IP is: 192.168.0.57, and I can ping the board from my PC, and ping my PC from the board. And at any time if I connect to the device and set it as default, the problem returns and the IP becomes: 169.254.201.164. Why does this happen please? My computer’s operating system is Windows 10.
Best regards,
Tarek
Hello @tarekmhnds,
We have seen similar issues in some scenarios in the past.
If you reboot your PC, does the incorrect IP assignment get solved, at least temporarily?
Best Regards,
Bruno
Hello @bruno.tx ,
I rebooted my PC, but the problem of incorrect IP assignment still exists, it set: 169.254.201.164.
Best regards,
Tarek
Hello @tarekmhnds,
Sorry for the delay here.
I will bring this up with the IDE Extension team.
Best Regards,
Bruno
1 Like
1 Like
Hello @tarekmhnds,
Can you try to set the value on your global VSCode configuration to the correct host IP in torizon.overwriteHostIp?
This should override any incorrect config that the extension may reach.
More information can be found here: Workspace - Settings | Toradex Developer Center
Please try to set this value and restart VSCode.
If it does not solve the issue, please let me know.
Best Regards,
Bruno
Hello @bruno.tx ,
I set the setting: "torizon.overwriteHostIp": "192.168.0.50" in the .vscode/settings.json file, but it didn’t work.
The DOCKER commands was like this:
Executing task: DOCKER_HOST=192.168.0.57:2375 LOCAL_REGISTRY=169.254.201.164 DOCKER_LOGIN=169.254.201.164:5002 TAG=v0.0.0 GPU=-imx8 DEBUG_SSH_PORT=2231 DEBUG_PORT1=2232 DEBUG_PORT2=2233 DEBUG_PORT3= docker compose pull test-qt-container with wrong ip for my pc.
Also I have to change the settings: "insecure-registries" at the file: /etc/docker/daemon.json on the Apalis board to my pc ip: "192.168.0.50", and restart the docker daemon on the board.
One of my colleagues is using Python template on Linux Ubuntu and has the same problem.
Best regards,
Tarek
Hello @tarekmhnds,
I apologize again for the delay on this topic.
I think you may have an additional local link between your PC and the board.
Can you send me the output of ip addr show for both the module and your PC?
Best Regards,
Bruno
Hello @bruno.tx ,
This is the output of ip addr show on the Apalis module:
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 65536 qdisc noqueue state UNKNOWN group default qlen 1000
link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
inet 127.0.0.1/8 scope host lo
valid_lft forever preferred_lft forever
inet6 ::1/128 scope host
valid_lft forever preferred_lft forever
2: sit0@NONE: mtu 1480 qdisc noop state DOWN group default qlen 1000
link/sit 0.0.0.0 brd 0.0.0.0
3: ethernet0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP group default qlen 1000
link/ether 00:14:2d:e9:9d:28 brd ff:ff:ff:ff:ff:ff
inet 192.168.0.58/24 brd 192.168.0.255 scope global dynamic noprefixroute ethernet0
valid_lft 24123sec preferred_lft 24123sec
inet6 fe80::4fb3:9fb6:1308:be5a/64 scope link noprefixroute
valid_lft forever preferred_lft forever
4: can0: <NOARP,UP,LOWER_UP,ECHO> mtu 16 qdisc pfifo_fast state UP group default qlen 10
link/can
5: can1: <NOARP,UP,LOWER_UP,ECHO> mtu 16 qdisc pfifo_fast state UP group default qlen 10
link/can
6: mlan0: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc mq state DOWN group default qlen 1000
link/ether 6a:80:e4:75:71:cd brd ff:ff:ff:ff:ff:ff permaddr e8:fb:1c:ce:07:e1
7: uap0: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN group default qlen 1000
link/ether e8:fb:1c:ce:05:e1 brd ff:ff:ff:ff:ff:ff
8: docker0: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc noqueue state DOWN group default
link/ether 02:42:28:d3:13:5d brd ff:ff:ff:ff:ff:ff
inet 172.17.0.1/16 brd 172.17.255.255 scope global docker0
valid_lft forever preferred_lft forever
9: br-fc0bf81bf46d: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc noqueue state DOWN group default
link/ether 02:42:35:84:f8:96 brd ff:ff:ff:ff:ff:ff
inet 172.18.0.1/16 brd 172.18.255.255 scope global br-fc0bf81bf46d
valid_lft forever preferred_lft forever
And this is the output of ip addr show at the vs code / wsl at my PC:
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 65536 qdisc noqueue state UNKNOWN group default qlen 1000
link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
inet 127.0.0.1/8 scope host lo
valid_lft forever preferred_lft forever
inet 10.255.255.254/32 brd 10.255.255.254 scope global lo
valid_lft forever preferred_lft forever
inet6 ::1/128 scope host
valid_lft forever preferred_lft forever
2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP group default qlen 1000
link/ether 00:15:5d:92:ef:ea brd ff:ff:ff:ff:ff:ff
inet 172.30.254.91/20 brd 172.30.255.255 scope global eth0
valid_lft forever preferred_lft forever
inet6 fe80::215:5dff:fe92:efea/64 scope link
valid_lft forever preferred_lft forever
3: docker0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default
link/ether 92:d3:59:8a:2f:6a brd ff:ff:ff:ff:ff:ff
inet 172.17.0.1/16 brd 172.17.255.255 scope global docker0
valid_lft forever preferred_lft forever
inet6 fe80::90d3:59ff:fe8a:2f6a/64 scope link
valid_lft forever preferred_lft forever
8: vethf3545bc@if2: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue master docker0 state UP group default
link/ether 92:e9:6a:b1:89:26 brd ff:ff:ff:ff:ff:ff link-netnsid 0
inet6 fe80::90e9:6aff:feb1:8926/64 scope link
valid_lft forever preferred_lft forever
And this is the output of ipconfig at my Windows PC:
Windows IP Configuration
Wireless LAN adapter Wi-Fi:
Media State . . . . . . . . . . . : Media disconnected
Connection-specific DNS Suffix . :Wireless LAN adapter Yerel Ağ Bağlantısı* 9:
Media State . . . . . . . . . . . : Media disconnected
Connection-specific DNS Suffix . :Wireless LAN adapter Yerel Ağ Bağlantısı* 10:
Media State . . . . . . . . . . . : Media disconnected
Connection-specific DNS Suffix . :Ethernet adapter Ethernet:
Connection-specific DNS Suffix . :
Link-local IPv6 Address . . . . . : fe80::cbb4:fca2:32e:54ce%11
IPv4 Address. . . . . . . . . . . : 192.168.0.50
Subnet Mask . . . . . . . . . . . : 255.255.255.0
Default Gateway . . . . . . . . . : 192.168.0.1Ethernet adapter Bluetooth Ağ Bağlantısı:
Media State . . . . . . . . . . . : Media disconnected
Connection-specific DNS Suffix . :Ethernet adapter vEthernet (WSL (Hyper-V firewall)):
Connection-specific DNS Suffix . :
Link-local IPv6 Address . . . . . : fe80::5a53:9594:a139:4f5b%47
IPv4 Address. . . . . . . . . . . : 172.30.240.1
Subnet Mask . . . . . . . . . . . : 255.255.240.0
Default Gateway . . . . . . . . . :
Best regards,
Tarek
Hello @tarekmhnds,
Can you please confirm if torizon.overwriteHostIp was set on the global settings.json for Visual Studio Code?
If not, can you try doing that. After setting this, the VS Code window needs to be reload and the device reconnected. This will force the update of the fields and the edit of the daemon.json on the device.
Best Regards,
Bruno