RE: [rddp] rdmap-03 spec clarification

[Patricio Kaplan <pkaplan at chelsio.com>]

On Fri, 2005-04-15 at 07:33, Barry Reinhold(home) wrote:
> From the conformance testing perspective we send you non-zero values
> in bits 32-63 using the different RDMA operations specified and expect
> the DUT to properly complete the RDMA request. I think this is your
> case 1. 
> 
> I didn’t understand your case 2 – could you reword that case please?
> 

My question has been answered. Thanks.

I was concerned that some conformance test would send a non-zero value
in the Invalidate STag field and expect the receiver to flag an error.

-patricio kaplan
>  
> 
> draft-ietf-rddp-rdmap-03.txt, section 6.1:
> 
>  
> 
> "Bits 32-63; Invalidate STag. However, this field is only valid  for
> Send with Invalidate and Send with Solicited Event and  Invalidate
> Messages (see Figure 4 RDMA Usage of DDP Fields).
> 
>  For Send, Send with Solicited Event, RDMA Read Request, and 
> Terminate, the Invalidate STag field MUST be set to zero on  transmit
> and ignored by the receiver."
> 
>  
> 
> Could someone tell me if "ignored by the receiver" means 
> 
>  
> 
> 1) If it is not zero the receiver MUST NOT generate an error
> 
> 2) The receiver MUST CHECK that the STag is zero but in case it is 
> 
>    it does nothing with it.
> 
>  
> 
> thanks in advance,
> 
>  
> 
> -patricio kaplan
> 
>  
> 
>  
> 
> Barry Reinhold
> 
>  
> 
> reinholds at comcast.net
> 
> (603) 659-2569
> 
> 
>  
> 
> 
> 
> ______________________________________________________________________
> _______________________________________________
> rddp mailing list
> rddp at ietf.org
> https://www1.ietf.org/mailman/listinfo/rddp


_______________________________________________
rddp mailing list
rddp at ietf.org
https://www1.ietf.org/mailman/listinfo/rddp