Quoting r. Roland Dreier <[EMAIL PROTECTED]>: > Subject: Re: [openib-general] [PATCH 1/2] mthca: max_inline_data support > > Thanks... does it make sense to set the max_inline_data value for > kernel QPs but then not support posting inline data?
That will come next (I plan to add that so ULPs can get lower latency). But it seems kernel support is needed even for libibverbs since its the kernel that calculates wqe stride to put in cmd interface. No? > Also should we add some error checking against the HCA's maximum WQE > size? > > - R. And also max sge for memfree. May be a good idea, but seems to apply even without inline data. If you add this I'd prefer that you apply this patch first to avoid merging conflicts. -- MST - Michael S. Tsirkin _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
