PBS Error: Unable to change the status of compute nodes from down state when using Torque 4.2.5

 I did my installation according to Torque Administration 4.0.2

PBS_Server;LOG_ERROR::get_node_from_str, Node node-c00 is reporting on 
node node-c00.cluster.spms.ntu.edu.sg, 
which pbs_server doesn't know about

The solution is simple. Use the full hostname used by the client nodes and update the $TORQUE_HOME/server_priv/nodes

Restart the pbs_server, pbs_sched, trqauthd services

# service pbs_server restart
# service pbs_sched restart
# service trqauthd restart

Resolving mmremote: Unknown GPFS execution environment when issuing mmdelnode commands

I was issuing a mmdelnode from the NSD node to a client node which are having issues, but somehow I keep getting this error.

[root@nsd1]# mmdelnode -N node-c01

Verifying GPFS is stopped on all affected nodes ...
node-c01-nas:  mmremote: Unknown GPFS execution environment
mmdelnode: Command failed.  Examine previous error messages to determine cause.

If you do a mmgetstate -a on the NSD node, you will get something like this

# mmgetstate -a 
.....
.....
05      node-c01   unknown
.....
.....

The resolution is not too difficult. According to IBM GPFS Administration and Programming References mmdelnode

You have to power down the affected node and do the mmdelnode again. You can see it is successful.

# mmdelnode -N node-c01

Verifying GPFS is stopped on all affected nodes ...
mmdelnode: Command successfully completed
mmdelnode: Propagating the cluster configuration data to all
affected nodes.  This is an asynchronous process.

Do a mmgetstate -a and you will see that the node deletion is successful

Using Intel® C++ Compiler with the Eclipse* IDE on Linux*

There is a very good tutorial on how to use Eclipse IDE with Intel C++ Compilers. Do look at the article by Intel

Using Intel® C++ Compiler with the Eclipse* IDE on Linux*

GPFS Error: Unable to delete Client Node from GPFS Cluster

Today when we were delete a Client GPFS Node, the error received was something like:

 Fri Nov  1 11:55:03 SGT 2013: mmaddnode: Processing node node01
mmaddnode: Node node01 was not added to the cluster.
   The node appears to already belong to a GPFS cluster.
mmaddnode: mmaddnode quitting.  None of the specified nodes are valid.

When we do the command mmlcluster, the node was not in the list. So in other words, we are not able to add or delete the node.

Solution: Just reinstall. But you may have to remove old information

# rm -fr /usr/lpp
# rm -fr /var/mmfs

Reinstall and add the GPFS Node again. For more information, do take a look at  Adding nodes to a GPFS cluster

Compiling and Installing Meep-1.2.1 on CentOS 6 and OpenMPI

Meep (or MEEP) is a free finite-difference time-domain (FDTD) simulation software package developed at MIT to model electromagnetic systems, along with our MPB eigenmode package. The latest official version is 1.2 and can be found at Download Page for Meep

But there is a Lapack linking problem for 1.2 which is explained in Error when compiling Meep-1.2 on CentOS. It is strongly recommended to use the pre-release Meep 1.2.1 found at http://jdj.mit.edu/~stevenj/meep-1.2.1.tar.gz

Before you compile Meep 1.2.1, you need to first compile the libctl library. Compiling the libctl library is quite straightforward.

Step 1-3: For more information do see Compiling and Installing Meep-1.2.1 on CentOS 6 and OpenMPI (linuxcluster.wordpress.com)

Step 4: Compiling meep-1.2.1

# tar -zxvf meep-1.2.1.tar.gz
# cd meep-1.2.1
#  ./configure --prefix=/usr/local/meep-1.2.1 \
--with-libctl=/usr/local/libctl-3.2.1/share/libctl/ \
LDFLAGS=-I/usr/local/libctl-3.2.1/lib \
CPPFLAGS=-I/usr/local/libctl-3.2.1/include \
--with-mpi=/usr/local/openmpi-1.6.5/

References:

1. Undefined reference to `dgetrf_’ error when compiling Meep-1.2 on CentOS
2. crtbegin.o: No such file: No such file or directory Error when compiling Meep-1.2 on CentOS
3. My opinion: Compiling Meep