First, you should (a) install the ATLAS and scalapak libraries, and make sure these are on each node. Second, you need to install one of the MPI packages (OpenMPI, LAMMPI, MPICH, etc); the run-times need to be on each node, and the compiler libraries and tools need to be on one node. Third, you need to recompile for MPI and ATLAS. I believe linpack uses a configure script in which you tell it to use MPI or something like that. Fourth, for these benchmarks, you should disable Linux's swap; this ensures the linpack doesn't start swapping and killing performance. (Do this with sysctl vm.swappiness=0" and after "=1") (If it runs out of memory, the problem size is too large, and the process fails.)
Next, start out with a simple test to make sure your hpl + mpi setup is working. You'll need a dummy config file like this:
Code:
Our cluster benchmark
My university lab
HPL.out
6
1
400
1
50
1
1
4
3
-1
1 # of panel fact
0
1 # of recursive stopping criterium
2
1 # of panels in recursion
2
1 # of recursive panel fact.
0
1 # of Bcasts
1
1 # of Lookahead depths
0
2
60
0
0
0
8 # alignment of double
It should run to completion and give you some reasonable output (the last number of the output is GFlops). With these Xeon's, your theoretical peak is 3 (nodes) * 4 (CPUs) * 4 (cores) * 3.4 (GHz) * N (Floating point operations / cycle) = 163 * N. (See the Intel spec sheet for your processor to determine N).
Once you have that working, you're ready for tuning the HPL suite: run a series of tests, each with a different configuration. One configuration file does this. The linpack program permutes all possible combinations of parameters within the file, and runs one test on each permutation. A quide to this format can be found here, but here's what I suggest you start with:
Now, this will will take a long time. Make sure you pipe the output with " | tee hpout.dat" to make sure you capture the output and can see it and it gets saved to disk.
After this, look for the top 8 or 16 results, and refine the config file to use only the parameters that produced these results.
NOW you can start performance tuning the cluster. Most critically, you will want to (a) tune the TCP/IP kernel parameters, (b) disable all non-essential Linux processes on all nodes, and (c) tune the switch parameters for the cluster ports -- ie, disable auto-negotiate and maybe tune the messaging queues (some switches use different types of service and have small queues for each one; you want one large queue for all TOS).
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... (0 Replies)
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... (0 Replies)
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... (1 Reply)
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... (6 Replies)
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 . (0 Replies)
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? (2 Replies)
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... (0 Replies)
Discussion started by: NVA
0 Replies
LEARN ABOUT DEBIAN
4s-backend-setup
4S-BACKEND_SETUP(1J) 4store 4S-BACKEND_SETUP(1J)NAME
4s-backend-setup -- Create a new 4store KB
SYNOPSIS
4s-backend-setup kbname [--node node-number] [--cluster cluster-size] [--segments segment-count] kb-name
--node Number of this node in the cluster, values range from 0 to cluster-size - 1. The default is 0.
--cluster
The number of nodes in the cluster. The default is 1.
--segments
The number of segments in the cluster. The default is 2. We recommend one for each CPU core in the cluster as a good
starting point. Higher numbers tend to consume more resources, but may result in increased performance.
NOTES
Once crated with 4s-backend-setup KBs should be started with 4s-backend(1)SEE ALSO 4s-query(1), 4s-size(1), 4s-httpd(1), 4s-backend(1), 4s-delete-model(1)EXAMPLES
$ 4s-backend-setup --node 0 --cluster 1 --segments 4 demo
Creates the indexes for a single-machine KB with four segments, named "demo".
4store May 31, 2019 4store