Francisco Sedano
Francisco Sedano
Hello @gunpuz @ddelange and others, On my use case, I have long-running jobs (~1 hour) and each pod can only handle 1 of them. In this scenario, killing the wrong...
@ovidiupl Thanks for the hint -- Could you share some example of that approach? Stuck with the same problem as you, but not being successful with that approach either. In...
@pierDipi as discussed in Kubecon -- This is my main use case, so I'd like to work on solving this issue.
Before working on this, I think we should fix an underlying issue being discussed here: https://github.com/knative/serving/issues/13075 Because of this, the premise "as it requires the HTTP connection to stay open...
@mroberts91 before working on this I want to handle the regular UX described here: https://github.com/knative/serving/issues/13075 (which is impacting my use case) Would that also help you? Or do you need...
On this aspect, I'd like to understand the best practices to deploy models in production. The proposed change here would break our model, which is as follows. We might be...
@artursouza @yaron2 can we see the logs of the test? I think if you just crash and restart, app will be up again when the reminder is sent, so bug...
@artursouza @yaron2 were you able to verify with the delay I mentioned? Do you need any further detail?
Thanks @artursouza -- Still can't repro? If that's the case I'll point to my code.