Re: [PATCH v2 5/5] nvme-fc: wait for initial connect attempt to finish

[Sagi Grimberg]

On 21/02/2024 15:24, Daniel Wagner wrote:
> The TCP and RDMA transport are doing a synchronous connects, that is the
> syscal returns with the final result. The operation either fails or
> succeeds. The FC transport offloads the connect attempt to a workqueue
> and thus it's an asynchronous operation.
>
> This async connect feature was introduced to mitigate problems with
> transient connect errors and the task to coordinate retries with
> userspace (nvme-cli).
Maybe it is a better idea to let userspace handle this? the whole async 
connect (and reconnect)
just seems it is causing more issues than solving... I may have missed 
some conversations
about this one...