From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ira Weiny Subject: Re: how to force opensmd to recalculate all paths? Date: Fri, 19 Feb 2010 09:53:01 -0800 Message-ID: <20100219095301.4fc02e54.weiny2@llnl.gov> References: <20100219114252.4060E3D1821@f53.poczta.interia.pl> <1266600846.22111.199.camel@auk31.llnl.gov> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <1266600846.22111.199.camel-X2zTWyBD0EhliZ7u+bvwcg@public.gmane.org> Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: chu11-i2BcT+NCU+M@public.gmane.org Cc: kovlensky-khu2bkKidpXVItvQsEIGlw@public.gmane.org, linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-Id: linux-rdma@vger.kernel.org On Fri, 19 Feb 2010 09:34:06 -0800 Al Chu wrote: > Hi Kovlensky, > > I'm unsure of what version of Opensm this was added in, but the opensm > console (see opensm manpage for console info), there is a "resweep > [heavy|light]" command. Running "resweep heavy" should do exactly what > you need. Alternately, from the man page. NOTES When opensm receives a HUP signal, it starts a new heavy sweep as if a trap was received or a topology change was found. Ira > > Al > > On Fri, 2010-02-19 at 12:42 +0100, kovlensky-khu2bkKidpXVItvQsEIGlw@public.gmane.org wrote: > > Hi, > > > > My case is simple - opensm does not recalculate paths unless necessary, > > i.e. one of physical links on the way disappears. I just introduced > > significant topology changes and need opensm to take them into > > consideration. New links were added, a lot of them. Is there any way of > > telling opensm to recalculate all paths? At the moment all new links are > > happily ignored and i can find no way of doing that live. > > > > My vendor has bad habit of asking me to add ib link here and there to > > nullify bottleneck identified and, well, while all new paths are up, I can > > find no way of rebalancing paths, so they stay unused. > > > > I'm running OFED-1.3.2-20090119-0501, so all ideas for this version or a > > newer one are welcome. > > > > Regards, > > > > kovlensky > > > > > > ---------------------------------------------------------------------- > > Szybkie i niedrogie... Tylko dla mezczyzn! > > Sprawdz >>> http://**link.interia.pl/f25a7 > > > > -- > > 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 > > > -- > Albert Chu > chu11-i2BcT+NCU+M@public.gmane.org > Computer Scientist > High Performance Systems Division > Lawrence Livermore National Laboratory > > -- > 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 > -- Ira Weiny Math Programmer/Computer Scientist Lawrence Livermore National Lab 925-423-8008 weiny2-i2BcT+NCU+M@public.gmane.org -- 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