How to check performance of your HPC cluster?

 
Thread Tools Search this Thread
Special Forums UNIX and Linux Applications High Performance Computing How to check performance of your HPC cluster?
# 1  
Old 05-18-2012
How to check performance of your HPC cluster?

Hello Everybody,

I have few queries :

Do you have any idea how to check the performance of HPC cluster having mpich on top of centos 6.2?
Are there any standard programs (like FFT, graphics rendering etc) to check the performance of mpi cluster with single node and multiple nodes?
Can we check the performance of single core and dual core?
Can we benchmark small cluster of 4 nodes or is benchmarking softwares are only for big clusters?

Thanks..
# 2  
Old 05-19-2012
the standard measuring tool is HPL which solves for a very large multidimensional array. Prepackaged rpms might be found in the Rocks distribution. The answer is yes to each of your other questions
This User Gave Thanks to otheus For This Post:
# 3  
Old 05-20-2012
Thanks for your help Otheus.
Smilie
I am new to the field of HPC. I installed HPCC and HPL. Even I am able run it and get the results. But I am not able to understand it. Also its running for my colete cluster, I also want to run them for my single machine. And now I am not able to tell whether its running on both the cores of my machine or only one process per machine, as I am having core 2 duo machines.
# 4  
Old 05-21-2012
"Understanding" isn't so important. At the end of the results, there is a number labeled "GLOPS". It looks like this:
Code:
WR00L2C2        8192    16     1     1             327.60          1.119e+00

The first column expresses some of the options used in the options (HPL.dat) file. The next two columns express the size in dimensions. The last column -- the one you want -- is the number of Gigaflops measured for that run. It's in scientific notation, meaning:
Code:
1.119 x 10^(00)  = 1.119 GFlops

If the output were 3.42e-01, then you'd have:
Code:
3.42 x 10^(-01) = 0.342 GFlops = 342 MFlops

Do you understand now?

---------- Post updated at 10:02 AM ---------- Previous update was at 09:34 AM ----------

As to how to configure this to run on multiple nodes, you have to (1) configure HPL.dat to run on mxn processors, where m and n are close together; so if you have a cluster containing 12 cores, optimal is normally m=3 and n=4. That's not always the case, but it typically is. (2) You must configure your MPI environment so that it runs on that many processors. How you do #2 depends on your MPICH software and setup. If you have a batch system like PBS or SGE, that further complicates the matter, as you need to queue the job with that number of processors. Sometimes with queuing engines, you can't easily dictate which nodes the job will run on. So if you have 6 nodes each with 4 cores, it might not be possible to say "run this on 3 nodes using all cores on each one". (But normally it's possible to say "run it on 3 nodes using 1 core on each one".)
These 2 Users Gave Thanks to otheus For This Post:
# 5  
Old 05-21-2012
Thanks Otheus for your generous reply.
Its very helpful.Smilie

I configured my system and somehow able to get the results from HPL.
I used one website which says "How do I tune my HPL.dat file?" http: //www.advancedclustering. com/faq/how-do-i-tune-my-hpldat-file.html to create the auto generated HPL.dat file.

The parameters which I used are :
Nodes: 5
Cores per Node: 2
Memory per Node (MB): 2048
Block Size (NB): 128

But I don't know whether the parameters which I used are correct or not.
I built a cluster of 5 PC's and all of them are having intel core 2 duo processors. I don't even know what this block size signifies.

Also, is there a way to chaeck the performance of single PC with respect to its individual core? As I am having Core 2 duo PC, I want to check the performance of this PC while its using single core and on the other hand when it uses both cores.

Thanks.

---------- Post updated at 01:46 PM ---------- Previous update was at 01:30 PM ----------

I have one more query.Smilie
While going through website http ://hpl-calculator.sourceforge.net/
I came across one more parameter Operations Per Cycle, which by default they used 4. I don't understand how to calculate this value. I googled and there are various terms, flops, mips, instructions per cycle, instructions per second and other things. can you tell me how to calculate this value for core 2 duo processor and i7 processor? As now a days multiple cores are there in PCs this per second calculations are for single core or multiple core?

Thanks again...
Login or Register to Ask a Question

Previous Thread | Next Thread

8 More Discussions You Might Find Interesting

1. Solaris

System Check Performance Tuning

Hello Forum, Well I am fairly new to this Solaris os thing. One thing I would like to check for system health and performance. I know the codes like prstat,vmstat,sar,iostat,netstat,prtdiag -v, What else does a want to be sys admin have to look for when checking a solaris box? I know... (3 Replies)
Discussion started by: br1an
3 Replies

2. Red Hat

How to check performance?

Hi, all What would be the a,b,c in troubleshooting slow performance on RH box, I type and it became really slow, what commands or log files to examine. What parameters to check? Thanks all T (2 Replies)
Discussion started by: trento17
2 Replies

3. AIX

How to check if a filesystem is part of a cluster

Hello, - How do I know if a filesystem is part of a cluster? - Or do I have to check if the vg related to the fs is part of a cluster instead? if so, how do I check it? - I would also need to check if there are vxfs type inside aix machines and if there are, how do I know if that type of... (2 Replies)
Discussion started by: asanchez
2 Replies

4. Linux

Cluster check

I am working on a Linux server and want to check the cluster status. I dont know how many server is in cluster and what is the command to check. could you please help me to get the cluster status? (4 Replies)
Discussion started by: anshu ranjan
4 Replies

5. UNIX for Dummies Questions & Answers

How to check if the server is on a Cluster

Hi im connecting to a datacenter remotely. is there a command to know if the server is on a cluster? i want to know the command to use in these OS(hp-ux,solaris,linux) Thanks (6 Replies)
Discussion started by: jinslick25
6 Replies

6. Shell Programming and Scripting

Monitoring script to check if cm cluster is up or not.

hi guys have this little problem, need some help from script gurus. basically I'm running hpux cmviewcl command, cmviewcl command will produce db1pkg up running enabled box1 my script PSV='box1' STAT='up' check_db1pkg() { # assign cmviewcl output... (2 Replies)
Discussion started by: sparcguy
2 Replies

7. Shell Programming and Scripting

how to check all the applications are in cluster using shell script

Hi I have an application running in four different node.The server is tomcat.Each node in each tomcat server.How do i check whether all the nodes are in cluster using shell script. any command to check this would be of great use.:) (2 Replies)
Discussion started by: ahamed
2 Replies

8. Solaris

Performance check without a counterpart

Hi, is it possible to check out the speed limits of a box without a remote peer for netio and stuff? I transferred 1 Terrabyte last night, which is not really much and need to find the bottleneck. The remote server is soon going to retire, yet I need to copy the 8T to the new machine. This... (9 Replies)
Discussion started by: PatrickBaer
9 Replies
Login or Register to Ask a Question