[openib-general] nfsrdma release 7 issues,

[Tom Tucker]

22 is EINVAL. I believe the only way to get this on an RDMA connection
is when there is an error in the RPCRDMA header. The completing WR is
just a flush that resulted from shutting the connection down.


On Wed, 2006-12-13 at 17:09 -0500, James Lentini wrote:
> 
> On Tue, 12 Dec 2006, Vu Pham wrote:
> 
> > > > 2.  While some clients run I/Os, one idle client try to access the mount
> > > > point ie. *ls* and get I/O input error. I see these error messages on
> > > > server log
> 
> Was there anything in the log before this point? I'd expect to see a 
> message started with "svcrdma: failed to post SQ..."
> 
> > > > Dec 12 13:58:29 ibd202 kernel: nfsd: terminating on error 22
> > > > Dec 12 13:58:29 ibd202 kernel: svcrdma: bad WR completion
> > > > Dec 12 13:58:29 ibd202 kernel:  ctxt=ffff810242130800, count=1 on
> > > > xprt=ffff8102431c0400, rqstp=ffff8102414cdc00, status=5
> > > > ...
> > > > Dec 12 14:04:29 ibd202 kernel: ib_mthca 0000:08:00.0: CQ entry for unknown
> > > > QP 2e0408