Benchmarking a Beowulf Cluster Post: 302315137

Sponsored Content

Special Forums UNIX and Linux Applications High Performance Computing Benchmarking a Beowulf Cluster Post 302315137 by otheus on Monday 11th of May 2009 03:48:18 PM

05-11-2009

Registered User

Quote:

Oh the software was already installed by the university...have been told by the administrator that they are all working properly

Uh-hunh. I wouldn't completely trust that if I were you. Let's take it step-by-step.

Use "type" or "which" or "whence" to find the full path of the linpack executable:
Code:
```
type -a hpl
```
verify this has been compiled dynamically and not statically:
Code:
```
file <hpl path from step 1>
```
You should see something like "Dynamically linked i386 object". As long as you don't see "statically linked binary" proceed to the next step. Otherwise, talk to your system admin and ask him/her very specifically how he/she compiled it.
Next, run
Code:
```
ldd <hpl path from step 1>
```
You should see something like "libopen-rte.so" in the output. If you do not, ask your sysadmin to point you to the correct hpl, the one this is compiled "against" (with) the openMPI runtimes.
The libopen-rte.so should point to the full path of a file. If it does not, again, go to your system administrator and ask him/her for the full LD_LIBRARY_PATH that you should have to run against this hpl program.
The path should be available to you by default on all machines in the cluster. If not, add the LD_LIBRARY_PATH setting into the .bashrc file and include your .bashrc from your .bash_profile (if you're using csh, god help you; if ksh, just change the names to .kshrc and .profile). Now log into the other machine and run the ldd command as above; you should see the line pointing to the full path of the MPI rte library.
Make sure this all works by running:
Code:
```
mpirun -np 8 printenv LD_LIBRARY_PATH
```
You should get 8 instances of the correct LD_LIBRARY_PATH.
Now go back and try getting this to run for exactly 2 processes. (P=2, Q=1, -np 2)
Now modify the machine file so it has two lines in it, one for each hostname, and run it again.
If we're at this point, try again with 8; if it fails, there are some other things to look at and try.

otheus

View Public Profile for otheus

Find all posts by otheus

9 More Discussions You Might Find Interesting

1. UNIX Benchmarks

Server and Workstation benchmarking

This is from my server AMD K6 133MHz 64Mb RAM 4GB HDD (Maxtor - ATA33) 2x10Mb NIC 1Mb Intel Graphic Card BYTE UNIX Benchmarks (Version 3.11) System -- FreeBSD sergiu.tarnita.net 5.0-RELEASE FreeBSD 5.0-RELEASE #2: Thu Mar 17 15:49:16 EET 2005...

2. HP-UX

HP-Unix Hardware benchmarking

Hi everyone, I'm working on one HP-Unix application which we have to port completely onto Windows xp. Before that I have to compare performance of two different machines. My HP-Unix is running on HP-C8000 workstation and windows XP machine is intel Xeon. Now the problem is to evaluate the...

3. High Performance Computing

Building a Solaris Cluster Express cluster in a VirtualBox on OpenSolaris

Provides a description of how to set up a Solaris Cluster Express cluster in a VirtualBox on OpenSolaris. More...

4. High Performance Computing

MySQL Cluster - Designing, Evaluating and Benchmarking (reg. req'd)

Registration is required. In this white paper learn the fundamentals of how to design and select the proper components for a successful MySQL Cluster evaluation. Explore hardware, networking and software requirements. Work through basic functional testing and evaluation best practices. More...

5. High Performance Computing

Tuning HPL.dat for Beowulf Cluster [Linpack]

Hi guys, I am having some issues tuning the HPL.dat file for the Linpack benchmark test across 2 nodes. I am very new to this with minimal Linux experience, however i am trying my luck. The specs for the two nodes are: 3GHZ QX6850 CORE 2 EXTREME (QUAD CORE) 4GB RAM I have been typing these...

6. UNIX for Advanced & Expert Users

Benchmarking a new Solaris, with four different clients

Good morning, for the impatient: I have a new backup-server and need to monitor, what the machine can do, what's the best way of finding that out? I will tell the story right from the beginning, so you have a clue about what's going on: I have a setup of three machines: A new...

7. UNIX for Dummies Questions & Answers

benchmarking application

Where i get a open source benchmark program using pthread library for benchmarking our multicore system for the first stage.I need the source code too for that application ,because in later stage we need to develop our application so that i need to study pthread more. please anybody guide me .

8. UNIX and Linux Applications

Benchmarking and performance analyzing in OS

Is/Are there an/some application/applications , package/packages for benchmarking or system performance measuring which are there for almost all Linux releases and distributions?

9. Solaris

Sun cluster 4.0 - zone cluster failover doubt

Hello experts - I am planning to install a Sun cluster 4.0 zone cluster fail-over. few basic doubts. (1) Where should i install the cluster s/w binaries ?. ( global zone or the container zone where i am planning to install the zone fail-over) (2) Or should i perform the installation on...

LEARN ABOUT OPENSOLARIS

scconf_transp_adap_qfe

scconf_transp_adap_qfe(1M)				  System Administration Commands				scconf_transp_adap_qfe(1M)

NAME

       scconf_transp_adap_qfe - configure the qfe transport adapter

DESCRIPTION

       Note -

	 Beginning  with  the Sun Cluster 3.2 release, Sun Cluster software includes an object-oriented command set. Although Sun Cluster software
	 still supports the original command set, Sun Cluster procedural documentation uses only the object-oriented command set. For more  infor-
	 mation about the object-oriented command set, see the Intro(1CL) man page.

       You can configure qfe Ethernet adapters as cluster transport adapters. These adapters can only be used with transport type dlpi.

       The  qfe Ethernet adapter connects to a transport switch or to another Ethernet adapter on a different node. In either case, the connection
       is made through a transport cable.

       When a transport switch is used and the endpoints of the transport cable are configured by using scconf, scinstall, or other tools, you are
       asked to specify a port name on the transport switch.  You can provide any port name, or accept the default,  as long as the name is unique
       for the switch.

       The default is to set the port name to the node ID hosting  the adapter at the other end of the cable.

       There are no user configurable properties for cluster transport adapters of this type.

SEE ALSO

       Intro(1CL), clinterconnect(1CL), clnode(1CL), scconf(1M), scinstall(1M), qfe(7d)

Sun Cluster 3.2 						    4 May 2006						scconf_transp_adap_qfe(1M)