global c: some user work directories are inaccessible
SIGN-IN

SMP iqaluk.sharcnet.ca

Links System documentation in the SHARCNET Help Wiki

Manufacturer Dell
Operating System CentOS 6
Interconnect NUMA
Total processors/cores 32
Nodes
iqaluk: 1
32 cores
4 sockets x 8 cores per socket
Intel Xeon X7500 @ 2.0 GHz
Type: Compute
Memory: 1024.0 GB
Local storage: None
Total attached storage 10.7 TB
Suitable use

threaded, large-memory
Note: This system is contributed by a research group. Jobs submitted by contributing groups have a higher priority than others. For the policies on the contribution of systems, please refer to Contribution of Computational Assets to SHARCNET.

Software available

PATHSCALE, MODE, GCC, SIESTA, GIT, SPARK, FREEFEM++, NCBIC++TOOLKIT, PYTHON, CMAKE, R, BLAST, ACML, DAR, FFTW, PARI/GP, GAP, OCTAVE, ORCA, NETCDF, UTIL, PETSC_SLEPC, MERCURIAL, GSL, OPENMPI, NCL, OPENJDK, SUBVERSION, PERL, FDTD, GNUPLOT, GMP, GNU , CDF, SAMTOOLS, TINKER, BIOPERL, GDB, BOOST, OPEN64, INTEL, GAUSSIAN, MrBAYES, BINUTILS, BIOSAMTOOLS, QD, VIM, MKL, SPRNG, HDF, MPFR, VALGRIND, MPFUN2015, TEXLIVE, YT, MPC, CHARM++, MPFUN90, PNETCDF, COREUTILS, OPENCV, SUPERLU, IPM, GDL, BIOPERLRUN, ILOGCPLEX, GEANT4, MATLAB, PGI, LLVM, CPAN, LDWRAPPER, ARPACK-NG, EMACS, RUBY, NIX, PROOT, GHC, SYSTEM, AUTODOCKVINA, NINJA

Current system state details Graphs

Recent System Notices

Status Status Notes
Sep 05 2018, 02:53PM
(14 days ago)

please report any problems you notice to help@sharcnet.ca.

Sep 05 2018, 01:30PM
(14 days ago)

There’s been a fibre cut (in London, around 11am) which has killed both links from McMaster to the Sharcnet WAN. As a result, several clusters are unreachable (in general, jobs will hang in this condition, since they won’t be able to do IO to global storage resources.)

This sort of thing is usually fixed fairly soon (hours); we’ll update when we know more.

Jul 17 2018, 02:32PM
(2 months ago)

Unfortunately, there will be yet another power outage this Saturday July 21. We should be able to return Wobbie and Iqaluk to service before Monday.

Jul 05 2018, 07:31PM
(3 months ago)

Iqaluk was returned to service today, but has crashed twice. Logs indicate a problem with Lustre, but don’t suggest the cause.

Please email hahn@sharcnet.ca if you need access – I hope to find the problem within the next day, and restore full access.

Jul 03 2018, 10:57AM
(3 months ago)

A planned building power outage requires shutting down Wobbie, Iqaluk and Cat tonight. Queued jobs will remain queued, but running jobs will be killed.

Systems will be available again in the morning.

Sign-in to get full status history