-
Notifications
You must be signed in to change notification settings - Fork 159
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
shutil.copytree fails in local.py run_command #689
Comments
🤖 Hello @adammarples, I'm Dosu, a bot here to help you with your issue while we wait for a human maintainer. I can assist with troubleshooting bugs, answering questions, and guiding you on how to contribute. Please bear with me as I review your issue in detail. I'll get back to you shortly with a more comprehensive response. |
🤖 Hello @adammarples, I'm Dosu, a bot here to assist you while we wait for a human maintainer. I can help troubleshoot bugs, answer questions, and guide you on your journey as a contributor. Don't hesitate to ask if you need anything! Based on the traceback you provided, it seems like the issue is related to a race condition where the A similar issue was reported in the Cosmos repository (#226) and was resolved by running each operation in a temporary directory. This change was introduced in the commit f443493 on April 14, 2023. As for the files with dot prefixes and random suffixes like Regarding your concern about upgrading to the latest version, it's understandable that you're hesitant due to the issue you encountered before (#642). However, it's worth noting that software updates not only introduce new features but also include bug fixes and performance improvements. Therefore, it's generally recommended to keep your software up-to-date. If you decide to upgrade, make sure to test the new version in a controlled environment before deploying it to production. If you encounter any issues, don't hesitate to report them. The Cosmos community is always here to help. If you decide not to upgrade, you could try to implement a similar solution to the one used to fix issue #226. This would involve modifying the I hope this helps! Let me know if you have any other questions. Sources
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research. Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant. If you want to continue the conversation, start your reply with @dosu-bot. |
@adammarples is there any particular reason why you're using I just replied to your comment on #642, I'm sorry, I missed it before. |
@tatiana the reason I'm not updating from 0.7.3 to latest is because the signature for DbtTaskGroup has changed and it would involve some new coding and testing. In my tests in upgrading to the latest version I have run into issues #642 #693 #694 which has made it impossible for me to use the select methods that I need in this case |
Hi, @adammarples, I'm helping the Cosmos team manage their backlog and am marking this issue as stale. From what I understand, you reported an issue involving a failure to copy certain files when the Could you please confirm if this issue is still relevant to the latest version of the Cosmos repository? If it is, please let the Cosmos team know by commenting on the issue. Otherwise, feel free to close the issue yourself, or the issue will be automatically closed in 7 days. Thank you for your understanding and cooperation. |
astronomer-cosmos==0.7.3
I periodically get failures like this when running a simple
dbt run --models
on a local operator.In this instance it is failing to copy a test documentation file called my_test.md but it happens with model files and others too.
The issue is that run_command calls shutil.copytree to copy the contents of the project directory. This fails when it says that a source file doesn't exist. This is odd for two reasons.
shutil.copytree shouldn't be attempting to move files which don't exist, which means that the files are being modified while it is running. I think it has something to do with this Possible race condition with multiple DbtTaskGroups starting at the same time. #226 because I do have two task groups chained together.
The files have dot prefixes and random suffixes like
.my_test.md.EDIhpJ
which suggest that they are tempfiles or partial files.I suspect that the answer will be to upgrade to the latest version but I am hesitant to do so because last time I ran into this issue #642
Would very much appreciate a hint on what is happening and maybe I could fix it.
The text was updated successfully, but these errors were encountered: