Menu
▾
▴
Re: [BProc] Beoboot lanl.1.3 booting problems..
|
From: <er...@he...> - 2002-10-15 15:55:47
|
On Fri, Oct 11, 2002 at 12:51:19AM -0600, Wilton Wong wrote: > Are the 50+ machines that are booting coming up at the same time ? or are they > different speeds ? we are using NForce (yucky) board that come up pretty quick > using PXE, and they come up almost simultaniously.. all of the nodes (well my > current 3 test nodes) are on the same subnet.. same switch... the only real > difference from a default install is that we are starting node numbering from > node 1 rather than 0 ( node 1 = 192.168.21.1.. etc..) and the master node sits > on the end of the subnet 192.168.21.254 Yeah, basically simultaneously. We're using myrinet and they all get mapped at about the same time. When I say 50+ at a time, that's the number that the node_up program says it's going at once. e.g. "Sep 17 13:57:47 xed beoserv: Starting node_up worker for 63 clients. " - Erik > On Thu, 10 Oct 2002, Erik Arjan Hendriks wrote: > > > It works fine for me. I've seen node_up do 50+ nodes at a time on our > > cluster here. The only hidden gotcha that I can think of with vrfork > > is that the nodes need to be able to reach one another w/ IP. So, if > > they're on different subnets, etc. you're going to have some trouble. > > The default route that the boot code puts in is bogus. > > ----[ Wilton William Wong ]--------------------------------------------- > 11060-166 Avenue Ph : 01-780-456-9771 High Performance UNIX > Edmonton, Alberta FAX: 01-780-456-9772 and Linux Solutions > T5X 1Y3, Canada URL: http://www.harddata.com > -------------------------------------------------------[ Hard Data Ltd. ]---- > > > > ------------------------------------------------------- > This sf.net email is sponsored by:ThinkGeek > Welcome to geek heaven. > http://thinkgeek.com/sf > _______________________________________________ > BProc-users mailing list > BPr...@li... > https://lists.sourceforge.net/lists/listinfo/bproc-users |
