Outage in AgResearch eRI
long GPFS waiters on login-0 and some compute nodes
Resolved MinorIncident Report
We have an unkillable defunct process on login-0, and associated long GPFS waiters. A restart of GPFS on login-0 will be required to clear this situation. This is scheduled for 1200hrs tomorrow, Thursday 12th June. All processes on login-0 using the GPFS filesystems will likely die. Slurm jobs will remain unaffected.
Should the impact increase today we will bring the restart forward. Should the restart not clear the waiters, a full reboot of login-0 will be required.
Trusted by 1,000+ teams
Never miss outages in third-party dependencies
Stop finding out about outages from your users. Monitor 6,320+ cloud services and get alerted the second something breaks.
Latest Updates ( sorted recent to last )
RESOLVED
11 months ago - at 06/12/2025 04:21AM
This incident has been resolved.
MONITORING
11 months ago - at 06/12/2025 12:11AM
A fix has been implemented and we are monitoring the results.
IDENTIFIED
11 months ago - at 06/12/2025 12:11AM
GPFS has been restarted on login-0 and the associated waiters have been cleared. However new waiters appeared overnight on login-1, and these have not cleared. A new status page will be raised for this.
IDENTIFIED
11 months ago - at 06/11/2025 01:07AM
We have an unkillable defunct process on login-0, and associated long GPFS waiters. A restart of GPFS on login-0 will be required to clear this situation. This is scheduled for 1200hrs tomorrow, Thursday 12th June. All processes on login-0 using the GPFS filesystems will likely die. Slurm jobs will remain unaffected.
Should the impact increase today we will bring the restart forward. Should the restart not clear the waiters, a full reboot of login-0 will be required.
Latest AgResearch eRI outages
Slow Access to Data on S: Datasets on ERI for several Users - 2 months ago
Windows clients hanging when accessing dataseta - 3 months ago
compute-[1-4] nodes affected by a GPFS long waiter - 4 months ago
No Internet connectivity from compute nodes - 4 months ago
Research Developer Cloud Dashboard and API Issue - 4 months ago
Never miss outages in third-party dependencies
With IsDown, you can monitor all your critical services' official status pages from one centralized dashboard and receive instant alerts the moment an outage is detected. Say goodbye to constantly checking multiple sites for updates and stay ahead of outages with IsDown.
Start free trialNo credit card required · Cancel anytime · 6320 services available
Integrations with
