From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jason Gunthorpe Subject: Re: [PATCH 2/3] infiniband-diags: libibnetdisc Allow a DR Path partial fabric query starting at a CA Date: Fri, 22 Jul 2011 16:13:49 -0600 Message-ID: <20110722221349.GT18090@obsidianresearch.com> References: <20110720161655.1ed38052.weiny2@llnl.gov> <20110720233451.GL18090@obsidianresearch.com> <4E297949.2000607@dev.mellanox.co.il> <20110722172945.GP18090@obsidianresearch.com> <20110722150049.ba8e592f.weiny2@llnl.gov> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20110722150049.ba8e592f.weiny2-i2BcT+NCU+M@public.gmane.org> Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Ira Weiny Cc: Hal Rosenstock , "linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org" , Hal Rosenstock List-Id: linux-rdma@vger.kernel.org On Fri, Jul 22, 2011 at 03:00:49PM -0700, Ira Weiny wrote: > I agree it would be nice if one could issue a combined path and "scan through" > any xCA on the fabric. However, I don't think it is allowed, nor correct to > do so. Well, it is explicitly not allowed: 2) If Hop Count is non zero and Hop Pointer is in the range 1 Hop Pointer < Hop Count, this SMI is an intermediate hop in the directed route portion of the path. If the node is not a switch, the SMI shall discard the SMP, otherwise the SMI shall alter the contents of the directed route SMP as follows: > Even if this is considered vague there would be a problem a xCA was allowed. That sort of behavior is explicitly disallowed in other cases, like reading port info. Jason -- 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