Current System Load

The plot below shows the status of the CPU nodes on the current Cirrus service for the past day (note: the Cirrus GPU nodes are not included in this plot).

A description of each of the status types is provided below the plot.

Cirrus Node Status graph

Note: the long running reservation visible in the plot corresponds to the short QoS which is used to support small, short jobs with fast turnaround time.

Known Issues

We are experiening a heavy load on the metadata server. Our systems team are investigating but we suspect this is due to user(s) performing many I/O operations. We apologise for the inconvenience this is causing users.

Service Alerts

No current service alerts

Recently Resolved Service Alerts

This table lists resolved service alerts from the past 30 days. A full list of historical resolved service alerts is available.

Status Type Start End Scope User Impact Reason
Resolved Service alert 2022-09-12 07:00 2022-09-14 14:30 Login nodes, compute nodes Access to solid state storage (/scratch) is now available from login nodes, CPUs and GPUs nodes. Software modules are now available and are loaded from lustre (/work). The RPOOL solid state storage has an error on one of the NVMe devices
Resolved Issue 2021-07-01 09:00 2022-09-13 00:00 Object Store (WoS) The WoS has been removed from service. We are working with the hardware vendor to restore the WoS to service again.

Service Calendar and Maintenance

Maintenance Sessions:Quarter 2 2022 (1st April - 30th June 2022)

No scheduled maintenance

Maintenance Logs for previous periods

Previous maintenance logs

Module Updates

Module Update following Cirrus Upgrade March 2022

Description Reason Advice
Default git loaded at login is 2.35.1 There should be no adverse consequences for git users 2.21 will still be available as a non-default version
Updated mpt Updated The HPE MPI implementation (MPT) has been updated to mpt/2.25. The previous version mpt/2.22 is no longer available. Applications may require recompilation
Updated nvidia/cub/1.8.0 Updated Please use nvidia/nvhpc/22.2, which contains cub 
Updated nvidia/cuda-11.2 Updated Please use nvidia/nvhpc/22.2, which contains cuda 11.6
Updated nvidia/cudnn/8.2.1-cuda-11.2 Updated Please use nvidia/cudnn/8.2.1-cuda-11.6
Updated nvidia/nvhpc Updated nvidia/mathlibs-11.2 superseded by nvidia/nvhpc/22.2, which contains mathlibs cuda 11.6
Updated nvidia/nvhpc-nompi Updated nvidia/mathlibs-11.2 superseded by nvidia/nvhpc/22.2, which contains mathlibs cuda 11.6
Remove anaconda/python2 Outdated Use anaconda/python3-2021.11 for python3
Remove anaconda/python3-5.1.0 Outdated Use anaconda/python3-2021.11 for python3
Remove epcc/deprecated-software Outdated Deprecated with extreme prejudice
Remove hdf5parallel/1.10.6-intel18-mpt222 Outdated Please use new HDF5 module built against MPT 2.25
Remove hdf5parallel/1.10.6-intel19-mpt222 Outdated Please use new HDF5 module built against MPT 2.25
Remove hdf5parallel/1.10.6-gcc6-mpt222 Outdated Please use new HDF5 module built against MPT 2.25
Remove htop/2.2.0 Outdated Please use htop/3.1.2
Remove htop/3.0.0 Outdated Please use htop/3.1.2
Remove namd/2.12 Outdated Please use Superseded by namd/2.14
Remove netcdf-parallel/4.7.4-intel18-mpt222 Outdated Depends on hdf5parallel/1.10.6-intel18-mpt222 being removed. To be replaced with proposed new NetCDF module built against MPT 2.25
Remove openfoam/v1712 Outdated Versions 2006 and 8.0 are centrally available
Remove openfoam/v1912 Outdated Versions 2006 and 8.0 are centrally available
Remove fftw/3.3.8-intel19-mpt220 Outdated Please use the new build against MPT 2.25
Remove fftw/3.3.8-intel19-multiprecision Outdated Please use the new build against MPT 2.25
Remove fftw/3.3.8-intel19-mpt220-multiprecision Outdated Please use the new build against MPT 2.25
Remove fftw/3.3.8-gcc8-ompi4 Outdated Please use the new build against MPT 2.25
Remove spack/2020 Outdated Update to install location has broken Spack rpaths, scripts, modules, etc.
Remove strace/2.2.0 Outdated Use default strace/5.8
Remove WRF/em_real Not used Not required

At Risk Maintenance Sessions

There is an ‘At-Risk’ Session provisionally booked every Wednesday from 1000 - 1200. A user mailing will be sent if any work is going to take place which may impact users.

Service Calendar

We maintain a calendar for the Cirrus service that lists upcoming events (such as training courses and maintenance sessions):

We keep maintenance downtime to a minimum on the service but do occaisionally need to perform essential work on the system. Maintenance sessions are used to ensure that:

Additional maintenance sessions can be scheduled for major hardware or software updates; major upgrades to facility plant and infrastructure; acceptance testing following major service upgrades and statutory electrical testing.