-
Notifications
You must be signed in to change notification settings - Fork 84
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
Stage large numbers of jobs without affecting performance #3646
Comments
Notes from meeting 7/2/21: 1K workers and 100K staged jobs: what is the shape of a solution that could make sense? Todo: Make a doc outlining the solution and how that would differ from the current implementation, inefficiencies in current implementation, etc. For example: maybe doing everything in memory is better than updating the database over and over again |
Look at Jane's doc, other scheduling solutions |
@adiprerepa : take a look at bundle_manager.py, Jane's docs to understand what was done in the past. |
Note: we want to look at timings of different bundle manager stages, Jane looked at timings earlier, see her doc |
benchmark on dev |
Allow a user to stage as many jobs as they want without affecting performance (goal: 100K)
The text was updated successfully, but these errors were encountered: