At 02:35 PM 4/8/2008, Trond Myklebust wrote:
>The only justification for passing more errors up to the higher layers
>is if they have different error handling requirements.
>The reason why we currently transform more or less everything into
>ENOTCONN is because the two other errors ECONNRESET and ECONNREFUSED
>basically require the same kind of error handling (exit with EIO in the
>"soft" case, and keep retrying in the "hard" case).
>
>So, what kind of RDMA errors are these, and how are we failing to handle
>them correctly today?
Actually, I think I replied to the wrong message - I meant to reply to
the leak, not the error! But yes, the RDMA transport needs to return
the "right" error - I just wish there were a betterlist. At one point I
believe xprtrdma returned EINVAL (because the rdma connection code
returned it to us), and the mount command helpfully printed "internal
error". I.e., it was valid, but not useful.
Tom.