From: Greg Banks Subject: Re: [PATCH 000 of 11] knfsd: NUMAisation Date: Tue, 25 Jul 2006 19:03:57 +1000 Message-ID: <1153818237.21040.160.camel@hole.melbourne.sgi.com> References: <1153805274.21040.38.camel@hole.melbourne.sgi.com> <17605.50325.842862.8823@cse.unsw.edu.au> <17605.53272.237011.603771@cse.unsw.edu.au> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Cc: Linux NFS Mailing List Return-path: Received: from sc8-sf-mx1-b.sourceforge.net ([10.3.1.91] helo=mail.sourceforge.net) by sc8-sf-list2-new.sourceforge.net with esmtp (Exim 4.43) id 1G5Ipi-0005u2-9e for nfs@lists.sourceforge.net; Tue, 25 Jul 2006 02:04:06 -0700 Received: from omx2-ext.sgi.com ([192.48.171.19] helo=omx2.sgi.com) by mail.sourceforge.net with esmtp (Exim 4.44) id 1G5Iph-0005C6-EH for nfs@lists.sourceforge.net; Tue, 25 Jul 2006 02:04:06 -0700 To: Neil Brown In-Reply-To: <17605.53272.237011.603771@cse.unsw.edu.au> List-Id: "Discussion of NFS under Linux development, interoperability, and testing." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: nfs-bounces@lists.sourceforge.net Errors-To: nfs-bounces@lists.sourceforge.net On Tue, 2006-07-25 at 18:02, Neil Brown wrote: > On Tuesday July 25, neilb@suse.de wrote: > > > > Thanks. I now have all those patches applied. > > > > I'll post the interesting revisions in a little while. > > You can see them all at > http://cgi.cse.unsw.edu.au/~neilb/patches/linux-devel/2.6/2006-07-25-07/ > > The following patch removes some of the #if's. > Do you agree with it? Yep. > > struct svc_pool_map svc_pool_map = { .mode = -1, .init = 0 }; > @@ -54,7 +53,6 @@ svc_pool_map_init(void) > * Detect best pool mapping mode heuristically. > */ > m->mode = 0; /* default: one global pool */ > -#ifdef CONFIG_NUMA > if (num_online_nodes() > 1) { > /* > * Actually have multiple NUMA nodes, > @@ -73,14 +71,6 @@ svc_pool_map_init(void) > m->mode = 1; > } > } > -#else > - if (num_online_cpus() > 1) { > - /* > - * Plain SMP with multiple CPUs online. > - */ > - m->mode = 1; > - } > -#endif > } This hunk actually changes the logic slightly, but not detrimentally (the threshold for using mode `1' is changed from 1 to 2 cpus in the !NUMA case). It shouldn't matter. The rest looks fine. Greg. -- Greg Banks, R&D Software Engineer, SGI Australian Software Group. I don't speak for SGI. ------------------------------------------------------------------------- Take Surveys. Earn Cash. Influence the Future of IT Join SourceForge.net's Techsay panel and you'll get the chance to share your opinions on IT & business topics through brief surveys -- and earn cash http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV _______________________________________________ NFS maillist - NFS@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/nfs