Beowulf I/O Errors
Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.
Robert Sand rsand at d.umn.eduWed Jan 17 04:58:47 PST 2001
- Previous message: Scyld, RedHat 7.0, 6.2 and Athlon's
- Next message: Beowulf I/O Errors
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Hello, I think it is about time that Daniel changed the instructions on the web page. Here are the instructions you'll need to follow. First you'll have to change the /etc/beowulf/fstab file to look like this: /dev/ram3 / ext2 fs_size=65536 0 0 #/dev/hda1 beoboot ext2 defaults 0 0 #/dev/hda2 swap swap defaults 0 0 #/dev/hda3 / ext2 defaults 0 0 #none /proc proc defaults 0 0 #none /dev/pts devpts gid=5,mode=620 0 0 #$MASTER:/home /home nfs defaults 0 0 Then you'll need to boot off of the floppy and do the beofdisk, reboot, beoboot-install. Before you reboot the last time you'll need to edit your fstab file again so it looks similar to this: #/dev/ram3 / ext2 fs_size=65536 0 0 #/dev/hda1 beoboot ext2 defaults 0 0 /dev/hda2 swap swap defaults 0 0 /dev/hda3 / ext2 defaults 0 0 none /proc proc defaults 0 0 none /dev/pts devpts gid=5,mode=620 0 0 $MASTER:/home /home nfs defaults 0 0 Then reboot. I've found that the last node in the cluster always has a problem booting. Just givem it some time and it will finally boot. Matthew Jochum wrote: > > Hello, > Sorry to write directly to you instead of the listserv, but everytime > I post something to the listserv (Beowulf.org) it never gets sent out. > And I have a one question for you(scyle), and the rest of the Beowulf > community. I have other questions, as well, but getting the cluster running > is my priority for now. > > Let me give you ( and if you forward this to beowulf.org ) a run down of > the cluster. I am keeping it small, just to prove that it works. Then > I can build a much larger ( +30 node ) one. > > HomeNode: Dell OptiPlex PII-400 > Node0: Dell PowerEdge2400 Twin 866 Xeon, lots of ram and > disk space. > I have two other nodes, but I want to get this one up first! > > First: > Installation Question, I have followed the slave node setup proceedure, > and the machine will not go to the "up" state automatically. Here is the > proceedure I used to setup the Node > > 1. With a blank Harddrive, boot w/ a boot floppy, move from > unknown to configured node, and click apply. > 2. From /usr/lib/beoboot/bin: > beofdisk -q > beofdisk -w > /usr/sbin/beoboot-install 0 /dev/sda > bpctl -S all -s reboot > > Have I missed anything? When the machine reboots, it is > stuck in the "unavailable" state. > > Thanks, > Matt > > _______________________________________________ > Beowulf mailing list > Beowulf at beowulf.org > http://www.beowulf.org/mailman/listinfo/beowulf -- Robert Sand. mailto:rsand at d.umn.edu US Mail University of Minnesota Duluth 10 University Dr. Information Technology Systems and Services MWAH 176 144 MWAH Duluth, MN 55812 Phone 218-726-6122 fax 218-726-7674 "Walk behind me I may not lead, Walk in front of me I may not follow, Walk beside me and we walk together" UTE Tribal proverb.
- Previous message: Scyld, RedHat 7.0, 6.2 and Athlon's
- Next message: Beowulf I/O Errors
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
