-
-
Notifications
You must be signed in to change notification settings - Fork 265
chore: Don't truncate database tables between tests #2572
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
base: main
Are you sure you want to change the base?
Conversation
This PR is stale because it has been open for 30 days with no activity. |
Tip For best results, initiate chat on the files or code changes. 🧩 Analysis chain🏁 Script executed:
Length of output: 344 🏁 Script executed:
Length of output: 550 🏁 Script executed:
Length of output: 9857 🏁 Script executed:
Length of output: 166 🏁 Script executed:
Length of output: 584 🏁 Script executed:
Length of output: 1259 🏁 Script executed:
Length of output: 839 🏁 Script executed:
Length of output: 6713 I've analyzed PR #2572 "Don't truncate database tables between tests" to assess its feasibility. Here's what I found: Merge ConflictsThe PR currently has conflicts with the main branch that need resolution. According to GitHub, the PR is in a CONFLICTING state with 113 changed files. Scope & Complexity
Potential Challenges
Alternative ApproachesYour suggested alternatives seem more targeted and potentially less disruptive:
ConclusionGiven the scope of changes, conflicts, and risk of test interdependency, I believe the PR in its current form would be challenging to complete and maintain. Your alternative approaches, especially the opt-in/opt-out tags, offer a more balanced solution that could achieve performance improvements with less risk. |
Hey! I can rebase this, but there still will be lot of work to do, since the tests don't pass. However, truncating the tables has huge impact on the total test time. Truncate takes c.a. 500ms on my machine, which for 800 test is 400 seconds ~5min. 🤷 |
Yes, we must not use That's why I consider
Exactly. |
No description provided.