Month: Jan 2011

Planned SEACOM outage – updated

SANREN
We have been notified by TENET that SEACOM have a planned outage due to maintenance on the SMW4 cable system.  The (tentative) date proposed for this maintenance is from the 6th to the the 10th of February.  TENET are trying…
Read More

Sharing resources with Grid technology

hpc, sagrid
The screen capture below is a good example of how ICTS's HPC is contributing towards the research community in South Africa through SAGrid.  Grid technology, in this instance the gLite middleware, allows portions of an HPC cluster to be…
Read More

OpenMPI

hpc, MPI, programming
Installed openmpi 1.4-4 as well as the MPI development suite on the test cluter. Configured host based authentication to obviate the ssh password authentication. Compiled a test case program.  Seeing a 50% speed improvement when splitting the workload over 3…
Read More

Comparative shopping

AWS, hpc
UCT-ICTS offers BL460 dual quad core CPUs with 2.4 GHz Xeon processors.  The blades come with either 16 or 32 GB of RAM, fiber channel HBAs and dual NICs.  Compared to Amazon each CPU gives approximately 2 EC2 compute units. …
Read More

PBS POC upgrade test

hpc, torque
Tested the upgrade path of Torque from 2.5.3 to 3.0.0. Fairly easy, except one needs to remember a few things:
  1. shut down the pbs daemons before starting.
  2. run torque.setup to sort out the symlinks.
  3. restart the maui daemon.
All seems…
Read More

Mount Etna

sagrid
Mount Etna is having another violent eruption.  If the INFN drops off the grid in the near future here is the reason... Mount Etna…
Read More

Top level BDII error

gLite, sagrid
Corrected a config error which was preventing the Wits University site from publishing its details to the core SAGrid services.  Wits is now visible again: …
Read More

HPC cluster fully utilized

hpc
Deployed stats and accounting package to Virtual Box test bed.  Doesn't work so well as Vbox hides various parameters from net-snmp. Another maths user has joined the UCT HPC cluster and started submitting jobs. Currently the cluster CPUs are 100%…
Read More
Menu