Get webhook notifications whenever Pawsey Supercomputing Research Centre creates an incident, updates an incident, resolves an incident or changes a component status.
Completed -
All Pawsey services have been returned to production.
Please e-mail help@pawsey.org.au if you require assistance.
Sep 2, 16:00 AWST
In progress -
Scheduled maintenance is currently in progress. We will provide updates as necessary.
Sep 2, 08:00 AWST
Scheduled -
Maintenance will be carried out on Pawsey systems on Tuesday the 2nd September to apply required patches and updates to improve the systems stability, security, and performance. This maintenance window will also be used to undertake other tasks which require down-time to achieve.
Planned work for this window includes: • Implementation of Firewall-Border re-design (this will affect all network connectivity to all systems at Pawsey, including Acacia, Nimbus, Banksia, Nebula and Setonix). • Setonix will have the latest bug and security fixes applied from SUSE Linux Enterprise Server 15 SP6. • Setonix will have the latest "extended support" versions of HPE Slingshot Host Software and HPE User Services Software applied. • Limits on the gpu partition on Setonix will be updated: max number of concurrent jobs per user will be set to 64 and max number of jobs submitted per user will be set to 1024 for all users. • Limits on the gpu-highmem partition on Setonix will be updated: max number of concurrent jobs per user will be set to 8 and max number of jobs submitted per user will be set to 256 for all users. • Banksia will have a ScoutAM upgrade. • Banksia tape library firmware update. • Patching of visualisation services will be undertaken. • Patching of core Pawsey services will be undertaken.
Aug 25, 16:05 AWST
Completed -
PreEmptive Maintenance has been completed * askap-ingest[01-18] are using HPE hardware based ECC correction / detection * 5 x DIMMs has been replaced in the compute nodes
Aug 26, 09:41 AWST
Scheduled -
Askap Ingest Cluster will undergo ProActive Maintenance * Askap Ingest Compute nodes will switch to HPE hardware based memory error correction / detection vs inline Kernel error correction / detection as with HPE recommendation * Proactive replacement of DIMMs (x5) which could prove problematic in the future
Aug 26, 08:00 AWST