[ofiwg] completion flags as actually defined by OFI

[Bernard Metzler]

> From: "Hefty, Sean" <sean.hefty at intel.com>
> To: Jason Gunthorpe <jgunthorpe at obsidianresearch.com>
> Cc: "ofiwg at lists.openfabrics.org" <ofiwg at lists.openfabrics.org>
> Date: 04/14/2015 10:18 PM
> Subject: Re: [ofiwg] completion flags  as actually defined by OFI
> Sent by: ofiwg-bounces at lists.openfabrics.org
>
> > > I believe the providers support this guarantee.
> >
> > Including the clean shutdown case?
>
> For FI_TRANSMIT_COMPLETE:
>
> - The sockets and psm providers do not generate a completion until
> the remote side has processed the request and acknowledged the data.
> - Cisco needs to confirm the usnic provider behavior, but it's UD
> anyway.  I believe it adheres to the description given for
> completions on unreliable endpoints.
> -  Verbs does not generate a completion until the data has been
> acked by the remote side, unless I'm remembering it wrong.
>

This is RDMA transport dependent. It might be true for IB but is
definitively not for iWarp.


> It seems reasonable to assume that a message that has been acked
> will complete successfully at the peer.