From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jason Gunthorpe Subject: Re: [RFC] ib_srpt: initial .40-rc1 drivers/infiniband/ulp/srpt merge Date: Thu, 19 May 2011 12:41:13 -0600 Message-ID: <20110519184113.GE12525@obsidianresearch.com> References: <1305682604-21383-1-git-send-email-nab@linux-iscsi.org> <20110518170556.GB2595@obsidianresearch.com> <20110519174420.GD12525@obsidianresearch.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Bart Van Assche Cc: "Nicholas A. Bellinger" , linux-kernel , linux-scsi , linux-rmda , Roland Dreier , Vu Pham , David Dillow , James Bottomley List-Id: linux-rdma@vger.kernel.org On Thu, May 19, 2011 at 08:34:08PM +0200, Bart Van Assche wrote: > My reply applies to your original statement where you were referring > to APM with different destination ports. What you write above is about > APM with identical destination ports and hence does not apply to my > reply. The subnet manager can give an APM result that will switch between ports on the same node, APM handles both switching to a different path with the same end ports, and also switching to a new path using the same end ports. An implementation supporting APM must be ready for both situations - realistically no additional app code is required to support the multiport case since it falls out for free. You'd actually have to actively work to prevent it... This is why in the IB verbs architecture nearly everything is tied to a *device*, not a port. 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