You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Working with only Argo itself, is there any possible or solution to let argo-server of Argo on one cluster, and workflow-controller of Argo to create/watch step pods on the other cluster?
Motivation
We're building a specific CI/CD based on Argo, for some performance testing or test cases involving GPU nodes scenarios, the step pods should be running on the same remote cluster with the testbed pods. And we want to minimize the changes upon the remote clusters.
The text was updated successfully, but these errors were encountered:
@alexec Thanks for your reply! So it's kinda design problem.
Is it hard/complicated to adjust Argo Workflow Controller for this purpose? Or it's nearly impossible to make such a change since it's the root of Argo and its design.
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
Summary
We want to figure out best/simplest practice to run steps on remote cluster.
Already read through and tried the admiraltyio/multicluster-scheduler solution, however it's kinda complicated and overwhelming for our scenarios:
Working with only Argo itself, is there any possible or solution to let
argo-server
of Argo on one cluster, andworkflow-controller
of Argo to create/watch step pods on the other cluster?Motivation
We're building a specific CI/CD based on Argo, for some performance testing or test cases involving GPU nodes scenarios, the step pods should be running on the same remote cluster with the testbed pods. And we want to minimize the changes upon the remote clusters.
The text was updated successfully, but these errors were encountered: