From Clive.Elsum at CSIRO.AU Tue Apr 1 12:42:01 2003 From: Clive.Elsum at CSIRO.AU (Clive Elsum) Date: Tue Nov 9 01:14:27 2010 Subject: [scyld-users] Help with NFS can't get a request slot Message-ID: <200304010144.h311iK6s025714@cce-as.dar.CSIRO.AU> Hi All, I looked through the archives without success. We are running 27bz-8 version of scyld using on eth0 a Realtek card rtl8139D 15 nodes plus the Master. During large file transfers from our server we get nessages nfs: task 273867 can't get a request slot at frequent intervals until finally access to the Master is stopped. I can log in locally and stop the transfer job, and bring eth0 up and all is ok. Are there some settings I can tweak or does this mean the card may be a bit flaky? If so what is a recommended card to use? Thanks in advance for any advice. Clive --------------------------------------------------------------------- Clive Elsum BAppSc, RHCE Systems Engineer - Information Technology Group CSIRO Atmospheric Research PMB 1, Aspendale, Victoria, Australia 3195 Phone : (+61 3) 9239 4509 Fax: (+61 3) 9239 4444 E-mail Clive.Elsum@csiro.au --------------------------------------------------------------------- From info at lifestronics.com Thu Apr 3 11:53:01 2003 From: info at lifestronics.com (info) Date: Tue Nov 9 01:14:27 2010 Subject: [scyld-users] Installation Stalling Message-ID: <002001c2f982$104383c0$6701a8c0@nc.rr.com> Hi, All, I am a newbie to Scyld. I am installing a 4 nodes Scyld Beowulf cluster using the basic version I ordered from Linux central a few days ago. After overcoming a bunch of network cards related issues, I have reach to a point that I successfully install and configure the front-end machine and boot up one of the nodes. I can see the node on beosetup screen and moved it to the central column. However, the state of the node remains "down". When the end node boots, it booted to the point "connecting to 192.168.2.11:1555" and then it got stalled. 192.168.2.11 is the ip address of the front-end machine. It seems to me that for some reason the nodes are not talking with the front-end machine. However I can ping the node (192.168.2.12) from the front-end machine (192.168.2.11) via eth1 card without any problem. I am stacked. Any help will be appreciated. Jeff -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.scyld.com/pipermail/scyld-users/attachments/20030403/8d97f844/attachment.html From Clive.Elsum at csiro.au Fri Apr 11 06:35:01 2003 From: Clive.Elsum at csiro.au (Clive.Elsum@csiro.au) Date: Tue Nov 9 01:14:27 2010 Subject: [scyld-users] ext2 to ext3 Message-ID: Hi, We have kernel 2.2.19-12beosmp with ext2 filesystem. How can this kernel be upgraded to a 2.4 so as we can get to an ext3 filesystem to support our large file greater than 2Gb? Thanks in advance --------------------------------------------------------------------- Clive Elsum BAppSc, RHCE Systems Engineer - Information Technology Group CSIRO Atmospheric Research PMB 1, Aspendale, Victoria, Australia 3195 Phone : (+61 3) 9239 4509 Fax: (+61 3) 9239 4444 E-mail Clive.Elsum@csiro.au --------------------------------------------------------------------- From kjm31 at cu-genome.org Wed Apr 16 16:41:02 2003 From: kjm31 at cu-genome.org (Kristen J. McFadden) Date: Tue Nov 9 01:14:27 2010 Subject: [scyld-users] Customizing Scyld Beowulf Cluster for Perl / Bioinformatics Message-ID: Hi, We have a Scyld Beowulf cluster currently running on 28cz-4 (we are getting -5 soon). We have been running into a lot of problems with users that are trying to run scripts on the child nodes. To start with, what is the best way to run serial (non-MPI) programs? Here is the current issue I'm trying to tackle. Say I have a perl script. (I NFS mount /usr /lib etc. on the child nodes) I want to run this perl script on N nodes with N DIFFERENT arguments. Right now, even when I write up a small file with "mpprun my_program arg1 arg2 | batch now" in 100 lines or something for all different arguments, bbq does NOT properly distribute these programs. It overloads some nodes and behaves essentially unpredictably. Is there any tools or info anyone has about running Perl scripts and the like safely on a Scyld implementation? Thanks, Kristen -------------- next part -------------- An HTML attachment was scrubbed... URL: http://www.scyld.com/pipermail/scyld-users/attachments/20030416/26a9e1cb/attachment.html