[ofa-general] Non-Signaled RDMA Read (cxgb3)

[Felix Marti]

> -----Original Message-----
> From: general-bounces at lists.openfabrics.org [mailto:general-
> bounces at lists.openfabrics.org] On Behalf Of Roland Dreier
> Sent: Tuesday, July 29, 2008 9:37 AM
> To: Steve Wise
> Cc: Philip Frey1; general at lists.openfabrics.org
> Subject: Re: [ofa-general] Non-Signaled RDMA Read (cxgb3)
> 
>  > Note that I _could_ add code in the driver/lib poll routine to
"eat"
>  > these cqes.  But there is a fundamental problem in that if the CQ
is
>  > armed, then the HW _will_ generate an interrupt in this case.  This
>  > leads to a "false notification" which breaks the semantics of the
>  > notification mechanism.  I'm not sure how bad that is?  To the
>  > application, it would receive a notification, then go poll and get
>  > nothing.
> 
> There's also the issue that these completions take CQ entries... so if
> an app provisions a CQ for some amount of completions and then assumes
> that posting 100 RDMA reads doesn't use any CQ entries, things break.
> 
> Not sure if there is a good way to deal with this quirk really.

Roland, AFAIK, even an unsignaled WR generates a CQE when an error
occurs (and then all subsequent WRs complete in error as well). Doesn't
that imply that the CQ must be sized assuming that _every_ WR can
generate a CQE?
> 
>  - R.
> _______________________________________________
> general mailing list
> general at lists.openfabrics.org
> http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
> 
> To unsubscribe, please visit
http://openib.org/mailman/listinfo/openib-
> general