Pronto will be unavailable for most of the day on March 14th beginning around 8 am while we do biannual maintenance. We will send out a notice as soon as it is available again.
The pronto maintenance window will continue tonight (10/27) and into tomorrow (10/28). The physical changes have taken longer than expected, and we're working to restore service as soon as possible. We will send a notice once the cluster is available again.
Pronto will be unavailable for most of the day on October 27th beginning around 8 am while we do biannual maintenance. We will send out a notice as soon as it is available again.
We will be doing maintenance on our virtual server infrastructure on Wednesday August 5th, starting at 8AM. This will require downtime for the virtual servers hosted on this infrastructure.
Pronto (just the login/head node, and not the full cluster) will be down for a couple hours starting at 7AM on July 21st (one week from today). Batch jobs will continue to run uninterrupted, but interactive sessions (srun, tmux, screen) will be terminated.
Services will be down for patching January 9th.
LSS maintenance is complete, and service has been restored. Please email firstname.lastname@example.org with any issues.
We are planning to take down LSS for maintenance on Wed July 17 2019.
During this maintenance window, we will be modifying the LSS networks
to comply with the new Netcom VLAN architecture, and will be applying
Updates are complete & things are back up and running.
Reminder: legion-[1-8] & gpu01 have moved behind pronto, and you'll
need to use slurm on pronto to submit jobs to those servers now.
We will be taking down the ResearchIT servers Wed Mar 20th at 9AM for
some updates & maintenance. We expect to be back up by late afternoon.
The issue with /work has been resolved
We are currently experiencing an issue with one of the lustre servers that composes the /work directories. We are investigating and will post here when we know more.
The issue on condo seems to be resolved, and jobs are running successfully again.
Condo is experiencing intermittent job failures this morning. The HPC team is aware, and looking into the issue.
Condo is operational again
The Condo cluster is currently experiencing an issue, and is being worked on.
They Cyence cluster head-node died last night, and is also in the process of being fixed.
For the past few years, usage of our #bitcom IRC channel has declined and we're now retiring that service. Please contact us through email to email@example.com for all support requests, which will ensure that our full group can respond, and t
# Research IT - Sep '18 Update
## Downtime for patching: Sep 25th
* What: Server downtime
* When: 9/25 9AM-5PM
# Research IT - June '18 Update
## Downtime for Patching June 26th
* What: Server maintenance
* When: 6/26 9AM
* How long: approx 8 hours
The LSS system will experience a brief outage October 17, 2017 at noon for an update in the data center related to connected systems dropping connections. The system will be unavailable during the update, and is expected to be back online in less than an hour.