[openib-general] ib_types.h and Win/Linux consolidation

[Eitan Zahavi]

Hi Sean, Hal, Fab,

I did the obvious diff...
Attached is the results. 

To me most of the differences seem trivial to merge.

Eitan Zahavi
Senior Engineering Director, Software Architect
Mellanox Technologies LTD
Tel:+972-4-9097208
Fax:+972-4-9593245
P.O. Box 586 Yokneam 20692 ISRAEL

> -----Original Message-----
> From: Sean Hefty [mailto:mshefty at ichips.intel.com]
> Sent: Thursday, July 06, 2006 9:32 PM
> To: Eitan Zahavi
> Cc: openib-general at openib.org; openib-windows at openib.org; Erez Cohen
> Subject: Re: [openib-general] ib_types.h and Win/Linux consolidation
> 
> Eitan Zahavi wrote:
> > I have been approached by several people asking for where does one
> > gets a header file defining the IBTA "wire" protocol.
> 
> I'm not sure that it makes sense to try to have a single header file
that defines all wire
> data structures.  For example, I don't think that any module outside
of the IB CM
> cares about the CM wire formats.
> 
> Getting and setting values in wire format is also non-trivial for many
of the structures
> definitions.  The approach used so far has been to pack/unpack the
structures under
> another API, like the sa_query.
> 
> > So the point is clear: If we are missing such a complete IBTA H file
> > and people are actually looking for where the wire protocol is being
> > defined why shouldn't we promote ib_types.h to the main include
directory?
> 
> What wire structures are missing from the include files in
include/rdma?
> 
> - Sean
-------------- next part --------------
A non-text attachment was scrubbed...
Name: ib_types.win2ofed.diff.tgz
Type: application/x-compressed
Size: 34824 bytes
Desc: ib_types.win2ofed.diff.tgz
URL: <http://lists.openfabrics.org/pipermail/general/attachments/20060709/ad041b5e/attachment.bin>