Dear ROOTers,
I have a 4-node Beowulf-class cluster. The hostnode is named "cluster"
and the other 3 are "node1", "node2" and "node3".
Linux distibution: Mandrake 7.2, gcc version 2.95.3 19991030
ROOT: root 3.00/06
My root is installed in /usr/local/root which is shared among the nodes
via nfs.
I have only 4 lines for my proof.conf.
node cluster image=nfs
node node1 image=nfs
node node2 image=nfs
node node3 image=nfs
I have changed the /etc/services, /etc/inetd.conf and /etc/syslog.conf
as directed in README.PROOF.
When I run ROOT, I got these messages:
*******************************************
* *
* W E L C O M E to R O O T *
* *
* Version 3.00/06 13 March 2001 *
* *
* You are welcome to visit our Web site *
* http://root.cern.ch *
* *
*******************************************
FreeType Engine v1.x used to render TrueType fonts.
Compiled with thread support.
CINT/ROOT C/C++ Interpreter version 5.14.79, Feb 24 2001
Type ? for help. Commands must be C++ statements.
Enclose multiple statements between { }.
root [0] gROOT->Proof("cluster")
Name (cluster:allen): allen
*** Break *** write on a pipe with no one to read it
SysError in <TUnixSystem::UnixSend>: send (Broken pipe)
Error in <TUnixSystem::SendRaw>: cannot send buffer
SysError in <TUnixSystem::UnixRecv>: recv (Broken pipe)
Error in <TUnixSystem::RecvRaw>: cannot receive buffer
Password:
*** Break *** write on a pipe with no one to read it
SysError in <TUnixSystem::UnixSend>: send (Broken pipe)
Error in <TUnixSystem::SendRaw>: cannot send buffer
Error in <TSlave::TSlave>: authentication failed for host cluster
Error in <TProof::Init>: failed to connect to a PROOF master server
root [1]
The proof.log is:
Mar 13 14:54:43 cluster rpc.statd[581]: Caught signal 15, un-registering and exiting.
Please help. I suspect that my proof.conf is wrong.
Thanks in advance.
Allen S. Dahili
Department of Physics
MSU-Iligan Institute of Technology
Iligan City, Philippines
This archive was generated by hypermail 2b29 : Tue Jan 01 2002 - 17:50:39 MET