From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jason Gunthorpe Subject: Re: [PATCH] Make multicast and path record queue flexible. Date: Tue, 12 Oct 2010 14:47:15 -0600 Message-ID: <20101012204715.GQ24268@obsidianresearch.com> References: <4CAB4D49.9090107@voltaire.com> <20101005162833.GC5967@obsidianresearch.com> <1286900993.31931.4.camel@alst60.voltaire.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Content-Disposition: inline In-Reply-To: <1286900993.31931.4.camel-uOVkuFIEnOODI2cvxHXf6UEOCMrvLtNR@public.gmane.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: ewg-bounces-ZwoEplunGu1OwGhvXhtEPSCwEArCW2h5@public.gmane.org Errors-To: ewg-bounces-ZwoEplunGu1OwGhvXhtEPSCwEArCW2h5@public.gmane.org To: Alekseys Senin Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Moni Shoua , Christoph Lameter , "ewg-ZwoEplunGu1OwGhvXhtEPSCwEArCW2h5@public.gmane.org" List-Id: linux-rdma@vger.kernel.org On Tue, Oct 12, 2010 at 06:29:53PM +0200, Alekseys Senin wrote: > On Tue, 2010-10-05 at 14:12 -0500, Christoph Lameter wrote: > > On Tue, 5 Oct 2010, Jason Gunthorpe wrote: > > > On Tue, Oct 05, 2010 at 06:07:37PM +0200, Aleksey Senin wrote: > > > When using slow SM allow more packets to be buffered before answer > > > comming back. This patch based on idea of Christoph Lameter. > > > > > > http://lists.openfabrics.org/pipermail/general/2009-June/059853.html > > > > IMHO, I think it is better to send multicasts to the broadcast MLID than to > > queue them.. More like ethernet that way. > > I agree. We had similar ideas. However, the kernel does send igmp > reports to the MC address not to 244.0.0.2. We would have to redirect at > the IB layer until multicast via MLID becomes functional. We cannot tell > when that will be the case. > > But what if it will not be available from some reason? How long > should we wait? Do we need implement another queue/counter/timeout? If you follow the scheme I outlined - where traffic to a MGID that doesn't yet have a MLID is routed to the broadcast MLID then you do it until you get a MLID, with periodic retries/refreshes of the SA operation. This is similar to how ethernet works, and is generally harmless. Better to have a working, but suboptimal network, than one that is busted. Jason