[openib-general] RDMA write with immediate

[Josh England]

On Thu, 2005-06-23 at 08:56 -0400, Hal Rosenstock wrote:
> On Thu, 2005-06-23 at 08:47, Josh England wrote:
> > Alright, I'm probably being retarded, but just in case:
> > uverbs doesn't seem to work anymore.  Simple pingpong uverbs test gives:
> > 
> > Couldn't get context for mthca0
> > 
> > This is with rev 2685 on 2.6.12.1 under RHEL3.  Fresh rebuild/install of
> > libibverbs, libmthca, and libibcm.  Ports are ACTIVE and ipoib ping
> > works.
> > 
> > # lsmod
> > ib_ucm                 15448  0
> > ib_cm                  33904  1 ib_ucm
> > ib_at                  13704  0
> > ib_uverbs              24088  0
> > ib_ipoib               38920  0
> > ib_sa                  11660  2 ib_at,ib_ipoib
> > ib_mthca               90768  0
> > ib_mad                 38056  3 ib_cm,ib_sa,ib_mthca
> > ib_core                41088  6
> > ib_cm,ib_uverbs,ib_ipoib,ib_sa,ib_mthca,ib_mad
> > 
> > # ll /dev/infiniband
> > crw-r--r--    1 root     root     231, 255 Jun 23 05:31 ucm
> > crw-rw-rw-    1 root     root     231, 128 Jun 23 05:31 uverbs0
> > crw-rw-rw-    1 root     root     231, 129 Jun 23 05:31 uverbs1
> > 
> > 
> > Did I miss something?  I think this is the same environment that was
> > working before.
> 
> Are you sure this is 2685 ? As of 2658, I think uverbs now starts at
> minor 192 rather than 128.

That's probably it.  I'm not using udev for this testing, and had done
mknods by hand more or less.  I'll try the new minor number.

-JE

> 2658
> Modified:
>    gen2/trunk/src/linux-kernel/infiniband/core/uverbs_main.c
> Log:
> Fix order of cleanup in module unload.  Move first minor from 128 to
> 192.

> -- Hal
> 
> > 
> > -JE
> > 
> > On Wed, 2005-06-22 at 19:02 -0700, Roland Dreier wrote:
> > >     Josh> I'm trying to figure out how to do an RDMA write with
> > >     Josh> immediate data.  I've got a regular RDMA write working and
> > >     Josh> tried changing wr.opcode from IBV_WR_RDMA_WRITE to
> > >     Josh> IBV_WR_RDMA_WRITE_WITH_IMM and stuffing a value in
> > >     Josh> wr.imm_data to no avail.  The send fails.
> > > 
> > > This should work, and in fact I tested it a while ago, although it may
> > > have broken in the meantime.
> > > 
> > > When you say that your send fails, what do you mean?  Does
> > > ibv_post_send() return immediately with an error?  Or do you get a
> > > completion for your send request with a failed status?  If so, what is
> > > the status?  Or does the send just never complete and/or never show up
> > > on the remote system?
> > > 
> > >  - R.
> > > 
> > > 
> > 
> > _______________________________________________
> > openib-general mailing list
> > openib-general at openib.org
> > http://openib.org/mailman/listinfo/openib-general
> > 
> > To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
> 
>