Network Volume and copying data between pods.
Hey folks,
I've had a pod with 3 GPUs and 1TB under /workspace mounted (not a network volume).
All my GPUs are gone without me stopping the pod (ID: jlqfqkgo7sd8h5).
1) It wasn't a spot instance, it was an on-demand one. Why would that happen?
2) I can't allocate more GPU to the existing pod, so I'm forced to create a new one.
3) I've created a network volume that I would like to attach to the old pod, so I can copy my files into it and use it in new pod.
4) How to attach network volume to an old / previously started pod?
5) If it's not possible to attach network volume to an already started pod, what's the easiest way to transfer 1TB of data between pods?
1 Reply
You can't attach a network volume to an existing pod, it can only be done when you deploy the pod.
You can use runpodctl, croc, scp etc to transfer the data.