Compiling Gromacs 5.0.4 on CentOS 6

Compiling Gromacs has never been easier using the cmake. There are a few assumptions.

  1. Use MKL and Intel Compilers
  2. Use OpenMPI  as the MPI-of-choice. The necessary PATH and LD_LIBRARY_PATH have been placed in .bashrc
  3. We will use SINGLE precision for speed used MDRUN and MPI Flags

Here is my configuration file using Intel Compilers

# tar xfz gromacs-5.0.4.tar.gz
# cd gromacs-5.0.4
# mkdir build
# cd build
# /usr/local/cmake-3.1.3/bin/cmake 
-DCMAKE_INSTALL_PREFIX=/usr/local/gromacs-5.0.4 \
-DGMX_MPI=on \
-DMKL_LIBRARIES="/usr/local/intel/mkl/lib/intel64" \
-DMKL_INCLUDE_DIR="/usr/local/intel/mkl/include" \
# make
# make check
# sudo make install
# source /usr/local/gromacs/bin/GMXRC

Installation Flags

–   -DCMAKE_C_COMPILER=xxx equal to the name of the C99 compiler you
    wish to use (or the environment variable CC)
–   -DCMAKE_CXX_COMPILER=xxx equal to the name of the C++98 compiler you
    wish to use (or the environment variable CXX)
–   -DGMX_MPI=on to build using an MPI wrapper compiler
–   -DGMX_GPU=on to build using nvcc to run with an NVIDIA GPU
–   -DGMX_SIMD=xxx to specify the level of SIMD support of the node on
    which mdrun will run
–   -DGMX_BUILD_MDRUN_ONLY=on to build only the mdrun binary, e.g. for
    compute cluster back-end nodes
–   -DGMX_DOUBLE=on to run GROMACS in double precision (slower, and not
    normally useful)
–   -DCMAKE_PREFIX_PATH=xxx to add a non-standard location for CMake to
    search for libraries
–   -DCMAKE_INSTALL_PREFIX=xxx to install GROMACS to a non-standard
    location (default /usr/local/gromacs)
–   -DBUILD_SHARED_LIBS=off to turn off the building of shared libraries
–   -DGMX_FFT_LIBRARY=xxx to select whether to use fftw, mkl or fftpack
    libraries for FFT support
–   -DCMAKE_BUILD_TYPE=Debug to build GROMACS in debug mode

Joining RHEVM-Manage-Domain tool to join AD Domain

Do note that for Red Hat Enterprise Virtualization you must attach a directory server to the Manager using the Domain Management Tool, engine-manage-domains. This configuration sis for RHEV 3.5
Active Directory
Identity Management (IdM)
Red Hat Directory Server 9 (RHDS 9)

# rhevm-manage-domains add --domain=your_active_directory_domain --user=spmstest --provider=ad

Restart the ovirt-engine

# service ovirt-engine restart

Virtual Machine 3D Support Option is Greyed Out for Windows 2008 and 2012 on VMware

The solution is taken from Enable 3D Support option is greyed out in virtual machine video card settings (2092210) 

Modify the VMX file of the Virtual Machine

1. Take backup of the virtual machines VMX file
2. Open the VMX file, using text editor and add this line in the end

mks.enable3d = TRUE

*You can use the vi to edit the VMX file

3. Check the VMID of the Guest OS you are reloading

# vim-cmd "vmsvc/getallvms"
Vmid        Name .........

4.  Reload the virtual machines configuration file by running this command:

# vim-cmd vmsvc/reload VMID

Enabling Predictive Cache Statistics (PCS) for Data OnTap 8.2p

* node1 is the controller currently primary to the aggregate/vol/LUN.

Step 1: Enable PCS

node1::> node run –node node1
node1::> options flexscale.enable on
node1::>options flexscale.enable
flexscale.enable pcs  you should see this
node1::>options flexscale.pcs_size 330GB  based on 3 x 200GB SSD RAID4

Step 2: Allow the representative workload to run and Run your workload

Step 3: Collect data throughout the process

node1::>stats show -p flexscale-access

NetApp recommends issuing this command through an SSH connection and logging the output throughout the observation period because you want to capture and observe the peak performance of the system and the cache. This output can also be easily imported into spreadsheet software, graphed, and so on.

This process initially provides information on the “cold” state of the emulated cache. That is, no data is in the cache at the start of the test, and the cache is filled as the workload runs. The best time to observe the emulated cache is once it is filled, or “warmed”, as this will be the point when it enters a steady state.
Filling the emulated cache can take a considerable amount of time and depends greatly on the workload.


  1. Introduction to Predictive Cache Statistics
  2. Clustered_Data_ONTAP_82_System_Administration

Relooking at usage of /home directory in Linux

File System in /home can be clustered very quickly nowadays where the amount of data are massive. Residing all the users in one /home directory will cause the administrator to quickly reach the limits of the File System especially if the File System is not a Parallel File System.

One thought is to perhaps using the /home directory to store their user specific files that govern the user environment such as .bashrc .bash_profile .login etc only. All other files such as output, project files etc should not be stored immediately under the /home/user1 files system. Of course no one should be running their computation on the home directory.

If the users is large and you know that the /home directory will be broken further into further hierachy which can be divided into more volume. For example, /home/student/users1 or /home/staff/user2, /home/Department/user3

For more information, do see

NetApp Visual Storage Console (VSC)5.0 Plugin for VCentre 5.5

VSC 5.0 is a major change that includes a new look and seamless integration with the VMware vSphere Web Client. New features in this release include support for the following:

  • The VMware vSphere Web Client
  • VASA Provider for clustered Data ONTAP®
  • SnapVault integration as a backup job option for clustered Data ONTAP
  • Adding a virtual machine or datastore to an existing backup job
  • Numerous bug fixes

VSC 5.0 discontinues support for the following:

  • vCenter 5.1 and earlier
  • VMware Desktop client
  • 32-bit Windows installations
  • mbralign
  • Single File Restore
  • Datastore Remote Replication
  • Flash Accel

To download, see

Documentation, see NetApp Visual Storage Console (VSC) 5.0