Re: [PATCH 05/14] SIWv2: User interface: siw_verbs.h, siw_verbs.c, siw_user.h, siw_ae.c

linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org wrote on 06/17/2011 04:20:35 PM:

On 06/17/2011 09:14 AM, Bernard Metzler wrote:

quoted

Steve,
we currently do not support inline data for kernel clients since
we copy those data into a malloc'd buffer, where kmalloc()
might block. Using an explicit buffer comes from experiments
to allow for larger blocks of inlined data.
I could put the inline data directly into the wqe restricting it
to some 200 bytes or less (dependent on wqe size which
is mainly determined by numer of sge's supported).
would that make sense? maybe it would better reflect the
intended nature of inline data - put some bytes out w/o
doing memory registration...

I assume the intention of SEND_INLINE was precisely to allow putting
the data into the HW WQE to avoid an additional DMA
fetch of small payloads for HW RDMA devices.  For SWIW, this is not
really an issue.

but we have to provide a non-blocking fast path for kernel clients,
which forces me to do the same.

Thanks,
Bernard.

Steve.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html