> Could we somehow also fix or at least catch the issue from librdmacm, e.g. > by checking for uid=0, see the patch below? Probably the patch is not > sufficient, as the event needs to be deleted somehow, is there a way to do > that without further processing it?
Excellent idea! It should be safe to ignore error events where the uid is not set. I want to see if there's a way to handle 'good' events where the uid is not set, possibly by searching for the correct user space id using address information. I'm concerned that discarding such events could result in clients hanging, waiting for some event that never occurs. - Sean
