Menu
▾
▴
bproc-users — General discussion about BProc.
You can subscribe to this list here.
| 2001 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
(25) |
Nov
|
Dec
(22) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2002 |
Jan
(13) |
Feb
(22) |
Mar
(39) |
Apr
(10) |
May
(26) |
Jun
(23) |
Jul
(38) |
Aug
(20) |
Sep
(27) |
Oct
(76) |
Nov
(32) |
Dec
(11) |
| 2003 |
Jan
(8) |
Feb
(23) |
Mar
(12) |
Apr
(39) |
May
(1) |
Jun
(48) |
Jul
(35) |
Aug
(15) |
Sep
(60) |
Oct
(27) |
Nov
(9) |
Dec
(32) |
| 2004 |
Jan
(8) |
Feb
(16) |
Mar
(40) |
Apr
(25) |
May
(12) |
Jun
(33) |
Jul
(49) |
Aug
(39) |
Sep
(26) |
Oct
(47) |
Nov
(26) |
Dec
(36) |
| 2005 |
Jan
(29) |
Feb
(15) |
Mar
(22) |
Apr
(1) |
May
(8) |
Jun
(32) |
Jul
(11) |
Aug
(17) |
Sep
(9) |
Oct
(7) |
Nov
(15) |
Dec
|
|
From: J.A. M. <jam...@ab...> - 2004-02-22 23:50:34
|
Hi all... I have a problem when launcing remote scripts with bpsh. I have a soft that I build with different compilers, and stored like /opt/aleph/bin/tst Shell script /opt/aleph/bin/linux-gcc/tst Binary /opt/aleph/bin/linux-icc/tst Binary /opt/aleph/bin/default -> linux-gcc Deafult build I want to use The script does something like: #!/bin/bash /opt/aleph/bin/default/$(basename $0) Just try this: #!/bin/bash echo $0 The result is: annwn:~> bpsh 0 tst /proc/self/fd/3 Uh ? Something is missing in rfork/rexec to set up properly script names ? TIA -- J.A. Magallon <jamagallon()able!es> \ Software is like sex: werewolf!able!es \ It's better when it's free Mandrake Linux release 10.0 (RC1) for i586 Linux 2.6.3-jam2 (gcc 3.4.0 (Mandrake Linux 10.0 3.4.0-0.2mdk)) |
|
From: Joshua A. <lu...@ln...> - 2004-02-11 00:21:28
|
On Tue, Feb 10, 2004 at 03:58:50PM -0800, Dale Harris wrote: > Well, if you could just make them downloadable somewhere, that'd be > nice, web, ftp, anonymous rsync are all good. ftp.lnxi.com/upload/mpich/ They will be automatically removed this evening at 00:00 MST. > I alreayd have gm-2.0.9 already installed. You didn't have to patch it > in some fashion did you? No, but there are a few patches in there that may make your life easier, like gm-2.0.1-build.patch and gm-2.0.1-build-id.patch that get rid of the build date+time being included in the version. > I'd be happy with mpich..10, but ..11 might be nice someday. ;-) Upgrading should be as easy as slapping in the new tarball and twiddiling the spec file with the new version. The key to this will probably be the new cmtools package. Josh |
|
From: Dale H. <ro...@ma...> - 2004-02-10 23:59:06
|
On Tue, Feb 10, 2004 at 01:43:36PM -0700, Joshua Aune elucidated: > > Yes, I have src.rpms for mpich..10, gm-2.0.9, and an updated cmtools. I > am working with gm-2.0.9 and mpich..10 (don't think moving to ..11 will > be hard though). How would you like them? > > Josh > Well, if you could just make them downloadable somewhere, that'd be nice, web, ftp, anonymous rsync are all good. I alreayd have gm-2.0.9 already installed. You didn't have to patch it in some fashion did you? I'd be happy with mpich..10, but ..11 might be nice someday. ;-) Dale |
|
From: Joshua A. <lu...@ln...> - 2004-02-10 20:43:48
|
On Mon, Feb 09, 2004 at 12:50:43PM -0800, Dale Harris wrote: > > > > If LAM MPI works fine, why not use that one? We mostly use MPICH-GM > > (because of myrinet) on our systems here but I've heard that LAM is > > quite nice from many people. > > Yeah, this is basically the problem I have now, trying to figure out how > to get mpich-gm to work on bproc 3.2.6. I had vain hope of potentially > just applying the patches from cmtools-1.4 to mpich-1.2.5..10-gm and > then use mpirun from cmtool-1.2, but no luck there. > > Anyone have mpich-1.2.5..10-gm working with bproc-3.2.6? Yes, I have src.rpms for mpich..10, gm-2.0.9, and an updated cmtools. I am working with gm-2.0.9 and mpich..10 (don't think moving to ..11 will be hard though). How would you like them? Josh |
|
From: Dale H. <ro...@ma...> - 2004-02-10 03:30:56
|
On Wed, Feb 04, 2004 at 04:36:38PM -0500, Gregory Shakhnarovich elucidated: > > 2) What 2.4.x kernels are supported by this latest version? Ideally we > would like to use 2.4.24 but it looks like 2.4.22 is the latest with a > patch in the Bproc distribution - anybody tried it with 2.4.24? > I have 2.4.x kernels working with bproc 3.2.6 with apparently no problem. You can get the patches from the bproc 3.2.6 for 2.4.22 and fix the rejections, it didn't appear that big of a deal. Or I have a patch against 2.4.24 vanilla here: http://research.amnh.org/users/rodmur/bproc.patch -- Dale Harris ro...@ma... /.-) |
|
From: Dale H. <ro...@ma...> - 2004-02-10 03:14:13
|
On Wed, Oct 08, 2003 at 09:57:03AM -0600, er...@he... elucidated: > > If LAM MPI works fine, why not use that one? We mostly use MPICH-GM > (because of myrinet) on our systems here but I've heard that LAM is > quite nice from many people. > Yeah, this is basically the problem I have now, trying to figure out how to get mpich-gm to work on bproc 3.2.6. I had vain hope of potentially just applying the patches from cmtools-1.4 to mpich-1.2.5..10-gm and then use mpirun from cmtool-1.2, but no luck there. Anyone have mpich-1.2.5..10-gm working with bproc-3.2.6? (Why bproc 3.2.6? I had to jump back to bproc 3.2.6 because there are applications I have that use PVM, and only PVM. PVM doesn't presently work with bproc 4.0.) -- Dale Harris ro...@ma... /.-) |
|
From: Dale H. <ro...@ma...> - 2004-02-10 00:35:29
|
On Wed, Feb 04, 2004 at 04:36:38PM -0500, Gregory Shakhnarovich elucidated: > Hi, > > 1) What is the recommended *stable* (and recent) release of Bproc? is it > 3.2.6, or is some of the 4.0.xpre OK? The same question about beoboot - we > have 1.5 right now, seems that 1.8 is the latest; is it stable? > beoboot 1.5 is the latest that works with bproc 3.2.6, I believe. Newer versions only work with bproc 4.0, due to the big API change. -- Dale Harris ro...@ma... /.-) |
|
From: Daniel G. <dg...@ti...> - 2004-02-04 22:10:09
|
Greg, On Wed, Feb 04, 2004 at 04:36:38PM -0500, Gregory Shakhnarovich wrote: > Hi, > > We have a working cluster with Debian 2.4.20 + Bproc 3.2.5 + Clubmask > 0.5b85 + Maui 3.2.6, and we want to upgrade it. In this context, I'd > appreciate any answers to the following: > > 1) What is the recommended *stable* (and recent) release of Bproc? is it > 3.2.6, or is some of the 4.0.xpre OK? The same question about beoboot - we > have 1.5 right now, seems that 1.8 is the latest; is it stable? Clubmask 0.6b2 does not compile with BProc 4. The API for BProc has changed. I was trying to install Clubmask on a clustermatic 4 cluster, and failed because of it. I got a note from Nic Henke about it, which I will forward to you. > > 2) What 2.4.x kernels are supported by this latest version? Ideally we > would like to use 2.4.24 but it looks like 2.4.22 is the latest with a > patch in the Bproc distribution - anybody tried it with 2.4.24? I am only using whatever is in the clustermatic distributions, either version 3 or 4. > > 3) Although we somehow figured out last time how to install all the stuff > (as evidenced by the working cluster :) we can't for the life of us recall > what exactly is the sequence of operations to create the beoboot image > (for the nodes); i.e., after donwloading and un-taring the directory, what > do we do next? We could't find _any_ docs with the beoboot1.8 release, or > on the Bproc project site. We would appreciate any pointer to docs, or > some help in the form of instructions... Running "beoboot --help" gives you the options. The kernel version should be specified in /etc/beoboot/config, and the list of drivers to include in the ramdisk is specified in /etc/beoboot/config.boot. > > 4) For Clubmask users: what is the recommended version of Bproc that is > stable with Clubmask 0.62 (the latest release)? Again, I believe any version of BProc in the 3.2 series should work. Regards, Daniel -- Dr. Daniel Gruner dg...@ti... Dept. of Chemistry dan...@ut... University of Toronto phone: (416)-978-8689 80 St. George Street fax: (416)-978-5325 Toronto, ON M5S 3H6, Canada finger for PGP public key |
|
From: Gregory S. <gr...@ai...> - 2004-02-04 21:37:50
|
Hi, We have a working cluster with Debian 2.4.20 + Bproc 3.2.5 + Clubmask 0.5b85 + Maui 3.2.6, and we want to upgrade it. In this context, I'd appreciate any answers to the following: 1) What is the recommended *stable* (and recent) release of Bproc? is it 3.2.6, or is some of the 4.0.xpre OK? The same question about beoboot - we have 1.5 right now, seems that 1.8 is the latest; is it stable? 2) What 2.4.x kernels are supported by this latest version? Ideally we would like to use 2.4.24 but it looks like 2.4.22 is the latest with a patch in the Bproc distribution - anybody tried it with 2.4.24? 3) Although we somehow figured out last time how to install all the stuff (as evidenced by the working cluster :) we can't for the life of us recall what exactly is the sequence of operations to create the beoboot image (for the nodes); i.e., after donwloading and un-taring the directory, what do we do next? We could't find _any_ docs with the beoboot1.8 release, or on the Bproc project site. We would appreciate any pointer to docs, or some help in the form of instructions... 4) For Clubmask users: what is the recommended version of Bproc that is stable with Clubmask 0.62 (the latest release)? Thanks! -- Greg Shakhnarovich AI Lab, MIT NE43-V611 Cambridge, MA 02139 tel (617) 253-8170 fax (617) 258-6287 |
|
From: Daniel G. <dg...@ti...> - 2004-02-04 08:22:10
|
Hi Nic, Do you have a version of clubmask that works with clustermatic 4 (i.e. BProc 4.0)? I have a cluster that runs that, and would like to install clubmask on it, but it is not working. I managed to build the rpm for supermon on my system, but could not load the supermon_proc module. Also, I could not recompile/rebuild the rpm for clubmask, since the BProc API seems to have changed considerably in going to 4.0. Thanks, Daniel On Mon, Dec 15, 2003 at 04:27:10PM -0500, Nicholas Henke wrote: > Changes since 0.6b1: > ----------------------------------------- > Add support for runtime (clubmask.conf) choice of resource manager subsystem. > The available options now are ganglia and supermon. Support for ganglia3 will be > added once it is released. Ganglia is now the preferred choice, as it is _much_ > more stable. > > add --with-supermon to setup.py to turn on compiling of supermon python module. > It is now off by default, as ganglia is the preferred and default RM subsystem. > ------------------------------------------------------------------------------ > > Name : Clubmask > Version : 0.6 > Release : b2 > Group : Cluster Resource Management and Scheduling > Vendor : Liniac Project, University of Pennsylvania > License : GPL-2 > URL : http://clubmask.sourceforge.net > > What is Clubmask > ------------------------------------------------------------------------------ > Clubmask is a resource manager designed to allow Bproc based clusters > enjoy the full scheduling power and configuration of the Maui HPC > Scheduler. > > Clubmask uses a modified version of the Supermon resource monitoring > software to gather resource information from the cluster nodes. This > information is combined with job submission data and delivered to the > Maui scheduler. Maui issues job control commands back to Clubmask, > which then starts or stops the job scripts using the Bproc environment. > > Clubmask also provides builtin support for a supermon2ganglia translator > that allows a standard Ganlgia web backend to contact supermon and get > XML data that will disply through the Ganglia web interface. > > Clubmask is currently running on around 10 clusters, varying in size > from 8 to 128 nodes, and has been tested up to 5000 jobs. > > > Notes/warnings on this release: > ------------------------------------------------------------------------------ > Before upgrading, please make sure to save your /etc/clubmask/clubmask.conf > file, as it may get overwritten. > > To use the resource requests, you must be running the latest snapshot of maui. > > > Links > ------------- > Bproc: http://bproc.sourceforge.net > Ganglia: http://ganglia.sourceforge.net > Maui Scheduler: http://www.supercluster.org/maui > Supermon: http://supermon.sourceforge.net > > Nic > -- > Nicholas Henke > Penguin Herder & Linux Cluster System Programmer > Liniac Project - Univ. of Pennsylvania > > > > ------------------------------------------------------- > This SF.net email is sponsored by: SF.net Giveback Program. > Does SourceForge.net help you be more productive? Does it > help you create better code? SHARE THE LOVE, and help us help > YOU! Click Here: http://sourceforge.net/donate/ > _______________________________________________ > BProc-users mailing list > BPr...@li... > https://lists.sourceforge.net/lists/listinfo/bproc-users -- Dr. Daniel Gruner dg...@ti... Dept. of Chemistry dan...@ut... University of Toronto phone: (416)-978-8689 80 St. George Street fax: (416)-978-5325 Toronto, ON M5S 3H6, Canada finger for PGP public key |
|
From: Dale H. <ro...@ma...> - 2004-01-31 00:53:29
|
On Wed, Jan 28, 2004 at 05:51:05PM -0800, Dale Harris elucidated: > > > What is "real_mode_conf"? > Nevermind, I've have long since figured this particularly problem out. Dale |
|
From: Dale H. <ro...@ma...> - 2004-01-30 23:14:50
|
I've gotten my cluster to the point where I can get it is attempting to boot the phase2 kernel (via beoboot). However, I'm getting this error: RARP: 00:30:48:27:A2:B2 -> 192.168.2.10/255.255.255.0 RARP: bproc=2223; mcast=10001; file=/etc/beowulf/boot.img e1000: eth0 NIC Link is Up 100 Mbps Full Duplex recv: /etc/beowulf/boot.imgrecv: /etc/beowulf/boot.imgrecv: /etc/beowulf/boot.img Done monte: kernel setup : 5120 bytes at 0x90000 monte: kernel code : 959555 bytes at 0x100000 Couldn't find symbol real_mode_conf Failed to load kernel image A fatal error has occurred. What is "real_mode_conf"? I'm using bproc 3.2.6 with 2.4.24 kernel. beoboot-lanl.1.2-1, from clustermatic 2, I think. Eventually, I'm trying to get this to boot on myrinet. -- Dale Harris ro...@ma... /.-) |
|
From: <er...@he...> - 2004-01-07 22:34:03
|
On Wed, Jan 07, 2004 at 01:50:02PM -0800, Michael Madore wrote: > Joshua Aune wrote: > > >to > > > > > > > >>node 0 00:90:27:EA:82:92 > >> > >> > > > >I have never tried leaving off the node numbers in 4.x bproc even though > >the comment says that you should be able to. Hopefully one of these > >shots in the dark will help. > > > >Josh > > > > > > > Thanks for the advice. Using 0 explicitly fixed my problem. With CM3 I > didn't need the 0. I just started with no MAC addresses and used > nodeadd to populate the file. Well, that's a new bug then. bummer. - Erik |
|
From: Michael M. <mm...@as...> - 2004-01-07 21:50:07
|
Joshua Aune wrote: >to > > > >>node 0 00:90:27:EA:82:92 >> >> > >I have never tried leaving off the node numbers in 4.x bproc even though >the comment says that you should be able to. Hopefully one of these >shots in the dark will help. > >Josh > > > Thanks for the advice. Using 0 explicitly fixed my problem. With CM3 I didn't need the 0. I just started with no MAC addresses and used nodeadd to populate the file. Mike |
|
From: Joshua A. <lu...@ln...> - 2004-01-07 01:39:39
|
On Tue, Jan 06, 2004 at 02:06:45PM -0800, Michael Madore wrote: > Hi, > > I'm testing out Clustermatic 4 on IA32 and I'm getting the following > message when attempting to boot compute nodes: > > Jan 6 09:53:02 asl87 /usr/sbin/beoserv: RARP: MAC address match but no > netmask match for node 00:90:27:EA:82:92 I have had this problem before, but it was when I had the "interface" and "iprange" net/masks mismatched, you don't seem to have this problem :) Another thought is that maybe eth1 has had it's IP address changed since bpmaster has been started (or kill -HUP'ed)? See my modification to the config file below, it is the only thing that stood out. According to the comment in the config file the way you have it should work... > I never saw this message when I was using CM3, but maybe I have > something configured improperly? I have attached a copy of my config file. > > Thanks > > Mike > > # Sample Clustermatic Configuration file > # > # $Id: config,v 1.14 2003/11/07 21:39:43 mkdist Exp $ > # > # > # Default cluster configuration (uses eth1, and 192.168.1.0/24) > # interface: internal cluster interface (the one connected to the nodes) > # > # iprange: range of IP addresses for nodes. > > interface eth1 192.168.1.1 255.255.255.0 > > # Which nodes in the cluster exist is determined by which node numbers > # have IP addresses assigned to them. The lowest node number is 0. > # Gaps are allowed in node ranges. Nodes may also have more than one > # IP address but an IP can only be assigned to a single node. In the > # following example "0" is the number for the first address. > # Addresses are assigned to nodes sequentially up to and including the > # second address specified. > > iprange 0 192.168.1.10 192.168.1.200 > > > # Library list > # > # This tells beoboot which libraries to put on the node at boot time. > # > # The "librariesfrombinary" lines instruct beoboot to inspect a binary > # and generate a a library list from that. > # > # The "libraries" lines explicitly include libraries. Note that you > # must add the real file to the list - NOT the symlink to the real > # file. Globbing is allowed here. > # > # For both directives: Any file which doesn't exist will be silently > # ignored. Each may be used more than once to add to the list. > > # Example: > librariesfrombinary /bin/sleep /bin/ps /bin/ping # get libc,resolver > libraries /usr/lib/libstdc++* /usr/lib64/libstdc++* # C++ support > libraries /usr/lib/libbproc.so* /usr/lib64/libbproc.so* # BProc, of course. > libraries /lib/libnss_bproc* /lib64/libnss_bproc* # BProc resolver > > # Other possible binaries to run a node. > # librariesfrombinary /sbin/mke2fs > > > # Default location of boot images > bootfile /var/clustermatic/boot.img > > # Here we assign MAC addresses to nodes. Nodes can have multiple MAC > # addresses. Here the optional "0" zero argument states that the address > # should be assigned to node zero. Node lines following that will assign > # addresses to nodes sequentially > # > # The following are some examples: > node 00:90:27:EA:82:92 to > node 0 00:90:27:EA:82:92 I have never tried leaving off the node numbers in 4.x bproc even though the comment says that you should be able to. Hopefully one of these shots in the dark will help. Josh |
|
From: Michael M. <mm...@as...> - 2004-01-06 22:06:49
|
Hi, I'm testing out Clustermatic 4 on IA32 and I'm getting the following message when attempting to boot compute nodes: Jan 6 09:53:02 asl87 /usr/sbin/beoserv: RARP: MAC address match but no netmask match for node 00:90:27:EA:82:92 I never saw this message when I was using CM3, but maybe I have something configured improperly? I have attached a copy of my config file. Thanks Mike |
|
From: Dale H. <ro...@ma...> - 2004-01-06 21:28:48
|
On Tue, Jan 06, 2004 at 08:56:11AM -0800, Dale Harris elucidated: > > After looking at this a little more (and I haven't confirmed this), but > I'm guessing the problem with PVM and bproc is that it checks the > $PVM_RSH to see if it works, in this case bpsh. But bpsh doesn't take Well, Greg Watson had the suggestion of making a shell wrapper for bpsh, and that works for me (/me slaps my head) to strip off the 'n'. However now I seem to be having a permission problems, I cannot run PVM as a regular user, but it works fine as root. -- Dale Harris ro...@ma... /.-) |
|
From: Dale H. <ro...@ma...> - 2004-01-06 16:56:12
|
On Thu, Dec 18, 2003 at 08:23:48PM +0100, Thomas Eckert elucidated: > > Hi, > > I have the same problem -- /etc/nsswitch.conf reads: > hosts: files bproc dns > and /etc/hosts does not contain something nasty. > > Unfortunately downgrading beonss is not possible (I guess) due to /bpfs > related changes? > > With bproc 3.2.5 and beonss 1.0.12 (or 1.0.20) node-resolving was possible > with "nX" and ".X" (verified as I was not sure anymore) but with 4.0.0pre3 and > beonss cm1.1 only "nX" seems to be possible (X=-1 ... <max-node-number>). > > Thomas > After looking at this a little more (and I haven't confirmed this), but I'm guessing the problem with PVM and bproc is that it checks the $PVM_RSH to see if it works, in this case bpsh. But bpsh doesn't take node id's of the from "n#", it takes just "#", but gethostbyname() wants "n#". So I'm guessing we are in a bit of catch 22. It'd be nice if bpsh would support the "n#" naming convention. Cause I can ping names like "n1" in my cluster just fine, and gethostbyname() returns the correct information. -- Dale Harris ro...@ma... /.-) |
|
From: <er...@he...> - 2003-12-26 18:42:07
|
On Fri, Dec 19, 2003 at 03:11:58PM -0500, gor...@ph... wrote: > Haven't seen anyone post this one yet: bproc 3.2.5 on kernel 2.4.21 > > Dec 15 17:04:58 pangu bpmaster: FATAL: assoc_find: invalid pid 0 This is bad. Are there any other messages related to this? Do you have any idea what caused it? Is there any chance that the front end was out of memory or that a fork failed for some other reason? I'm guessing that this has to do with some fork error path because of the next message. > Dec 15 17:04:59 pangu kernel: bproc: ghost: unhandled error case: > add_ghost flailed!!! > Dec 15 17:04:59 pangu last message repeated 23 times This is probably a race with ghosts forking and the master daemon dying because of the previous error. - Erik |
|
From: <gor...@ph...> - 2003-12-19 20:13:16
|
Haven't seen anyone post this one yet: bproc 3.2.5 on kernel 2.4.21 Dec 15 17:04:58 pangu bpmaster: FATAL: assoc_find: invalid pid 0 Dec 15 17:04:59 pangu kernel: bproc: ghost: unhandled error case: add_ghost flailed!!! Dec 15 17:04:59 pangu last message repeated 23 times Only happened once so far. |
|
From: Dale H. <ro...@ma...> - 2003-12-18 20:43:09
|
On Thu, Dec 18, 2003 at 08:23:48PM +0100, Thomas Eckert elucidated: > > With bproc 3.2.5 and beonss 1.0.12 (or 1.0.20) node-resolving was possible > with "nX" and ".X" (verified as I was not sure anymore) but with 4.0.0pre3 and > beonss cm1.1 only "nX" seems to be possible (X=-1 ... <max-node-number>). > > Thomas > > So has the dot form of node id resolution been deprecated in bproc 4.0? Or was this something just overlooked? Basically I'm wondering if we need to patch pvm or bproc? -- Dale Harris ro...@ma... /.-) |
|
From: Dale H. <ro...@ma...> - 2003-12-18 19:28:06
|
On Thu, Dec 18, 2003 at 02:05:49PM -0500, steven james elucidated: > Greetings, > > Do you have beonss installed and configured in /etc/nsswitch.conf? > > G'day, > sjames > Yeah. beonss-cm1.1 in /etc/nsswitch.conf hosts: files bproc dns Dale |
|
From: Thomas E. <eck...@gm...> - 2003-12-18 19:23:59
|
Hi, I have the same problem -- /etc/nsswitch.conf reads: hosts: files bproc dns and /etc/hosts does not contain something nasty. Unfortunately downgrading beonss is not possible (I guess) due to /bpfs related changes? With bproc 3.2.5 and beonss 1.0.12 (or 1.0.20) node-resolving was possible with "nX" and ".X" (verified as I was not sure anymore) but with 4.0.0pre3 and beonss cm1.1 only "nX" seems to be possible (X=-1 ... <max-node-number>). Thomas On Thu, 18 Dec 2003, steven james wrote: > Greetings, > > Do you have beonss installed and configured in /etc/nsswitch.conf? > > G'day, > sjames > > > -------------------------steven james, director of research, linux labs > ... ........ ..... .... 230 peachtree st nw ste 2701 > the original linux labs atlanta.ga.us 30303 > -since 1995 http://www.linuxlabs.com > office 404.577.7747 fax 404.577.7743 > ----------------------------------------------------------------------- > > > On Thu, 18 Dec 2003, Dale Harris wrote: > > > > > Hi, > > > > Trying to get pvm 3.4.4 working on bproc 4.0.0pre3-1. Having a problem > > where I cannot start the pvmd. > > > > [pvmd pid7301] 12/18 13:59:50 master_config() .-1: can't gethostbyname > > [pvmd pid7301] 12/18 13:59:50 pvmbailout(0) > > > > > > I assume that the ".-1" is the master node, but I don't know why it > > should be trying a DNS lookup on that. I'm going by the directions > > in Readme.Beoscyld in PVM 3.4.4. So my PVM_ARCH is BEOSCYLD. > > > > -- > > Dale Harris > > ro...@ma... > > /.-) > > > > > > ------------------------------------------------------- > > This SF.net email is sponsored by: IBM Linux Tutorials. > > Become an expert in LINUX or just sharpen your skills. Sign up for IBM's > > Free Linux Tutorials. Learn everything from the bash shell to sys admin. > > Click now! http://ads.osdn.com/?ad_id=1278&alloc_id=3371&op=click > > _______________________________________________ > > BProc-users mailing list > > BPr...@li... > > https://lists.sourceforge.net/lists/listinfo/bproc-users > > > > > ------------------------------------------------------- > This SF.net email is sponsored by: IBM Linux Tutorials. > Become an expert in LINUX or just sharpen your skills. Sign up for IBM's > Free Linux Tutorials. Learn everything from the bash shell to sys admin. > Click now! http://ads.osdn.com/?ad_id=1278&alloc_id=3371&op=click > _______________________________________________ > BProc-users mailing list > BPr...@li... > https://lists.sourceforge.net/lists/listinfo/bproc-users > > -- /home/tom/bin/sig: line 10: /usr/bin/fortune: No such file or directory |
|
From: steven j. <py...@li...> - 2003-12-18 19:06:38
|
Greetings, Do you have beonss installed and configured in /etc/nsswitch.conf? G'day, sjames -------------------------steven james, director of research, linux labs ... ........ ..... .... 230 peachtree st nw ste 2701 the original linux labs atlanta.ga.us 30303 -since 1995 http://www.linuxlabs.com office 404.577.7747 fax 404.577.7743 ----------------------------------------------------------------------- On Thu, 18 Dec 2003, Dale Harris wrote: > > Hi, > > Trying to get pvm 3.4.4 working on bproc 4.0.0pre3-1. Having a problem > where I cannot start the pvmd. > > [pvmd pid7301] 12/18 13:59:50 master_config() .-1: can't gethostbyname > [pvmd pid7301] 12/18 13:59:50 pvmbailout(0) > > > I assume that the ".-1" is the master node, but I don't know why it > should be trying a DNS lookup on that. I'm going by the directions > in Readme.Beoscyld in PVM 3.4.4. So my PVM_ARCH is BEOSCYLD. > > -- > Dale Harris > ro...@ma... > /.-) > > > ------------------------------------------------------- > This SF.net email is sponsored by: IBM Linux Tutorials. > Become an expert in LINUX or just sharpen your skills. Sign up for IBM's > Free Linux Tutorials. Learn everything from the bash shell to sys admin. > Click now! http://ads.osdn.com/?ad_id=1278&alloc_id=3371&op=click > _______________________________________________ > BProc-users mailing list > BPr...@li... > https://lists.sourceforge.net/lists/listinfo/bproc-users > |
|
From: Dale H. <ro...@ma...> - 2003-12-18 19:00:45
|
Hi, Trying to get pvm 3.4.4 working on bproc 4.0.0pre3-1. Having a problem where I cannot start the pvmd. [pvmd pid7301] 12/18 13:59:50 master_config() .-1: can't gethostbyname [pvmd pid7301] 12/18 13:59:50 pvmbailout(0) I assume that the ".-1" is the master node, but I don't know why it should be trying a DNS lookup on that. I'm going by the directions in Readme.Beoscyld in PVM 3.4.4. So my PVM_ARCH is BEOSCYLD. -- Dale Harris ro...@ma... /.-) |
1488 messages has been excluded from this view by a project administrator.
