Sponsored Content
Special Forums UNIX and Linux Applications High Performance Computing Python code runs on login node but not on cluster Post 302985382 by devinmgibson on Tuesday 8th of November 2016 05:29:10 PM
Old 11-08-2016
Python code runs on login node but not on cluster

I work for one of my professors and we are trying to run SU2 in parallel on a cluster owned by the university that uses slurm for its workload manager. The problem we are running into is that when we ssh into the cluster and run the command:

Code:
parallel_computation.py -f SU2.cfg

on an assigned node by slurm (using sbatch), the code hangs and wont run. The weird thing about this is if we run the same command on the login node, it works just fine. Do any of you know what could possibly be the problem?

Here is some additional information:
- We talked with the IT guy in charge of the cluster and he doesn't have enough background to know what is going on.
- On some of our output files we would get the escape key [!0134h, when we changed the terminal settings to get rid of the escape key the code behavior was consistent as above.
- We can run SU2_CFD "config file", the code in serial, on both the login node and the cluster just fine
- We have tried running an interactive session on a node (using srun), no change in behavior

Any thoughts would be appreciated! We really want to be able to run the code in-house instead of outsource.


Moderator's Comments:
Mod Comment Please use CODE tags as required by forum rules!

Last edited by RudiC; 11-09-2016 at 04:07 AM.. Reason: Added CODE tags.
 

10 More Discussions You Might Find Interesting

1. Shell Programming and Scripting

The other node name of a SUN cluster

Hello, Under ksh I have to run a script on one of the nodes of a Solaris 8 cluster which at some time must execute a command on the alternate node: # rsh <name> "command" I have to implement this script on all the clusters of my company (a lot of...). Fortunately, the names of the two nodes... (11 Replies)
Discussion started by: heartwork
11 Replies

2. HP-UX

Node can't join cluster

Need help guys! when running cmrunnode batch i'm getting this error cmrunnode : Waiting for cluster to... (1 Reply)
Discussion started by: Tris
1 Replies

3. HP-UX

MC/SG Fail to join cluster node

Hi, Please advise me whereas I have two node cluster server configured with MC/SG. Application and DB are running on Node 1, while Node 2 is standby. All the volume group devices are part of cluster environment. There is only one package running at node 1. Node 2 is having the problem to... (1 Reply)
Discussion started by: rauphelhunter
1 Replies

4. High Performance Computing

Removed crashed node from Solaris Cluster 3.0

All- I am new to these forums so please excuse me if this post is in the wrong place. I had a node crash in a 4 node cluster and mgmt has determined this node will not be part of the cluster when rebuilt. I am researching how to remove it from the cluster information on the other 3 nodes and... (2 Replies)
Discussion started by: bluescreen
2 Replies

5. High Performance Computing

Setting up 2 node cluster using solaris 10

hi, i am trying to setup a 2 node cluster environment. following is what i have; 1. 2 x sun ultra60 - 450MHz procs, 1GB RAM, 9GB HDD, solaris 10 2. 2 x HBA cards 3. 2 x Connection leads to connect ultra60 with D1000 4. 1 x D1000 storage box. 5. 3 x 9GB HDD + 2 x 36GB HDD first of all,... (1 Reply)
Discussion started by: solman17
1 Replies

6. Solaris

Active Sun cluster node?

I now the logical name and Virtual IP of the cluster. How can I find the active sun cluster node without having root access? (3 Replies)
Discussion started by: sreeniatbp
3 Replies

7. HP-UX

Identify cluster active node

Hello, Is there any way to identify the active node in a HP-UX cluster without root privileges? (3 Replies)
Discussion started by: psimoes79
3 Replies

8. Solaris

How to remove single node cluster

Hi Gurus, I am very new to clustering and for test i have created a single node cluster, now i want to remove the system from cluster. Did some googling however as a newbee in cluster unable to co related the info. Please help Thanks (1 Reply)
Discussion started by: kumarmani
1 Replies

9. Solaris

SVM metaset on 2 node Solaris cluster storage replicated to non-clustered Solaris node

Hi, Is it possible to have a Solaris cluster of 2 nodes at SITE-A using SVM and creating metaset using say 2 LUNs (on SAN). Then replicating these 2 LUNs to remote site SITE-B via storage based replication and then using these LUNs by importing them as a metaset on a server at SITE-B which is... (0 Replies)
Discussion started by: dn2011
0 Replies

10. AIX

Cluster node not starting

Setting up HACMP 6.1 on a two node cluster. The other node works fine and can start properly on STABLE state (VGs varied, FS mounted, Service IP aliased). However, the other node is always stuck on ST_JOINING state. Its taking forever and you can't stop the cluster as well or recover from script... (2 Replies)
Discussion started by: depam
2 Replies
scversions(1M)						  System Administration Commands					    scversions(1M)

NAME
scversions - Sun Cluster version management SYNOPSIS
scversions [-c] 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. The scversions command commits the cluster to a new level of functionality after a rolling-upgrade to new Sun Cluster software. With no arguments, the scversions command prints a message indicating whether a commitment is needed. OPERANDS
The following operands are supported: -c Commit the set of nodes that are currently active members of the cluster to the highest possible level of functionality. When you upgrade a node (either through upgrade to a new release of the product or by application of a patch) and boot it back into the cluster, some of the internal protocols on that node might have to run at lower versions in order to cooperate cor- rectly with other nodes in the cluster. When the cluster is in this state, some administrative actions might be disabled and some new functionality introduced in the upgrade might be unavailable. When you run this command once from any node after all nodes are upgraded, the cluster switches to the highest versions of internal protocols possible. Assuming that all nodes have the same Sun Cluster software installed at that time, all new func- tionality becomes available and any administrative restrictions are removed. If a node that has not been upgraded is an active member of the cluster at the time you run the -c option to scversions, the command has no effect because the cluster is already running at the highest possible level of functionality. If a node has not been upgraded and is not an active member of the cluster when you run the -c option to scversions (for exam- ple, if that node is down for maintenance), the internal protocols of the cluster are upgraded to the highest possible ver- sions. You might have to upgrade the node that was not an active member of the cluster to enable it to rejoin the cluster. EXIT STATUS
0 Success non-zero Failure ATTRIBUTES
See attributes(5) for descriptions of the following attributes: +-----------------------------+-----------------------------+ | ATTRIBUTE TYPE | ATTRIBUTE VALUE | +-----------------------------+-----------------------------+ |Availability |SUNWsczu | +-----------------------------+-----------------------------+ |Interface Stability |Evolving | +-----------------------------+-----------------------------+ SEE ALSO
scinstall(1M) Sun Cluster 3.2 17 Aug 2007 scversions(1M)
All times are GMT -4. The time now is 09:48 AM.
Unix & Linux Forums Content Copyright 1993-2022. All Rights Reserved.
Privacy Policy