Infrastructure News Type: Outage Partial

Affected Infrastructure: registry.access-ci.org

Start Date: March 17, 2025, 1:00 p.m.

End Date: March 17, 2025, 1:30 p.m.

On March 17, 2025, several Enrollment Plugins used by the ACCESS User Registry (https://registry.access-ci.org/) will be updated for compatibility with future versions of COmanage Registry (https://spaces.at.internet2.edu/display/COmanage/Registry+4.4.0+Release+Announcement). Server instances will be restarted during this update which may cause in-progress registrations/logins to fail.

Posted: March 20, 2026

Infrastructure News Type: Outage Full

Affected Infrastructure: faster.tamu.access-ci.org

Start Date: March 10, 2025, 2:00 p.m.

End Date: March 15, 2025, 5:00 p.m.

The FASTER cluster will be unavailable from 9am March 10 to 8pm March 13 for usual OS maintenance, Lustre storage maintenance, and Liqid fabric composability maintenance.

Posted: March 20, 2026

Infrastructure News Type: Outage Partial

Affected Infrastructure: tickets.access-ci.org

Start Date: March 6, 2025, 5:27 p.m.

End Date: March 7, 2025, 7:00 a.m.

This incident affects: Jira Service Management Web, Service Portal, Opsgenie Incident Flow, Opsgenie Alert Flow, Opsgenie Incident Flow, Opsgenie Alert Flow, Jira Service Management Email Requests, Authentication and User Management, Purchasing & Licensing, Signup, Automation for Jira, and Assist. https://jira-service-management.status.atlassian.com/incidents/hjh7ydq8jlj6

Posted: March 20, 2026

Infrastructure News Type: Reconfiguration

Affected Infrastructure: registry.access-ci.org

Start Date: March 4, 2025, 4:00 p.m.

End Date: March 4, 2025, 5:00 p.m.

On March 4, 2025, the ACCESS User Registry (https://registry.access-ci.org/) will be reconfigured to include Kubernetes resource requirements. This will enable ACCESS services to respond to user load and create additional server instances when needed. Server instances will be restarted during this update which may cause in-progress registrations/logins to fail. This update has been deployed to the TEST ACCESS User Registry instance at https://registry-test.access-ci.org/ . For questions or concerns with this update, please contact help@cilogon.org (mailto:help@cilogon.org) or open an ACCESS Help Ticket (https://access-ci.atlassian.net/servicedesk/customer/portal/2/create/30).

Posted: March 20, 2026

Infrastructure News Type: Reconfiguration

Affected Infrastructure: expanse.sdsc.access-ci.org, expanse-gpu.sdsc.access-ci.org, expanse-ps.sdsc.access-ci.org

Start Date: February 24, 2025, 5:00 p.m.

End Date: July 7, 2025, 4:00 p.m.

Dear Expanse User, Starting Feb 24, 2025, two-factor authentication (2FA) will be required on Expanse. To avoid losing access, set up 2FA with Google Authenticator before this date. Instructions are in the Expanse user guide (https://www.sdsc.edu/systems/expanse/user_guide.html) in the system access section. For role accounts needing programmatic access, Science Gateway PIs will be contacted with further details. Other users with automation needs should contact SDSC user support via ticketing before Feb 24, 2025. SDSC User Services Staff

Posted: March 20, 2026

Infrastructure News Type: Degraded

Affected Infrastructure: duo.access-ci.org

Start Date: February 13, 2025, 6:48 p.m.

End Date: February 14, 2025, 1:43 a.m.

DUO has reported issues with phone-call-based authentication on their systems today, leading to some users being locked out for several hours for too many authentication failures. We do NOT recommend that ACCESS users employ phone-call-based authentication, as it is often unreliable, and prone to being abused. We strongly recommend that ACCESS users configure their DUO authentication to use the DUO App on a mobile device, and to use Push authentication. Other authentication methods, including Passkey or token-based authentication are known to work well. For more information about setting up DUO, please consult the documentation at https://guide.duo.com/universal-prompt#add-or-manage-devices.

Posted: March 20, 2026

Infrastructure News Type: Outage Partial

Affected Infrastructure: expanse.sdsc.access-ci.org, expanse-gpu.sdsc.access-ci.org, expanse-ps.sdsc.access-ci.org

Start Date: February 9, 2025, 6:00 a.m.

End Date: February 9, 2025, 6:00 p.m.

Dear Expanse User, We are currently seeing high load on one of the metadata servers of the Expanse Lustre filesystem. This is leading to timeouts on access to some files and directories. We are looking into the problem and will update once it is resolved. SDSC User Services Staff

Posted: March 20, 2026

Infrastructure News Type: Reconfiguration

Affected Infrastructure: registry.access-ci.org

Start Date: February 6, 2025, 2:00 p.m.

End Date: February 6, 2025, 3:00 p.m.

On February 6, 2025, the ACCESS User Registry (https://registry.access-ci.org/) will be reconfigured as follows. - The text "Terms and Conditions" will be replaced by "Acceptable Use Policy" throughout the user interface. - The DynamoDB Provisioner will be updated so that SSH pubkeys will have the "comment" field appended to the end of the pubkey. This will emulate the behavior of the LDAP Provisioner. Server instances will be restarted during this update which may cause in-progress registrations/logins to fail. This update has been deployed to the TEST ACCESS User Registry instance at https://registry-test.access-ci.org/ . For questions or concerns with this update, please contact help@cilogon.org (mailto:help@cilogon.org) or open an ACCESS Help Ticket (https://access-ci.atlassian.net/servicedesk/customer/portal/2/create/30).

Posted: March 20, 2026

Infrastructure News Type: Outage Full

Affected Infrastructure: expanse.sdsc.access-ci.org, expanse-gpu.sdsc.access-ci.org

Start Date: February 6, 2025, 5:00 a.m.

End Date: February 6, 2025, 4:00 p.m.

Dear Expanse User, We will be working on the SDSC machine room power infrastructure from 9PM (PT), Feb 5, 2025 to 8AM (PT) Feb 6, 2025. This will impact power to racks 1-8, 16, and 17 of Expanse. We have placed a maintenance reservation on these racks for the duration of the work. This will impact job wait times as we get closer to the maintenance period but the remaining resources of the system will available through the maintenance and logins, filesystem access, and job submissions are not expected to be impacted. Thanks SDSC User Services Staff

Posted: March 20, 2026

Infrastructure News Type: Outage Partial

Affected Infrastructure: expanse.sdsc.access-ci.org, expanse-gpu.sdsc.access-ci.org

Start Date: February 3, 2025, 1:00 a.m.

End Date: February 3, 2025, 5:00 a.m.

Update - the issue was resolved last night around 9PM (PT) Dear Expanse User We had a scheduler issue this evening that unfortunately led to jobs in the queue being lost. We apologize for the inconvenience this will cause as jobs will have to be resubmitted. We are looking into the issue and will update once the scheduler service is restored. Thanks SDSC User Services Staff

Posted: March 20, 2026

Infrastructure News Type: Outage Partial

Affected Infrastructure: expanse.sdsc.access-ci.org, expanse-gpu.sdsc.access-ci.org, expanse-ps.sdsc.access-ci.org

Start Date: January 28, 2025, 5:00 a.m.

End Date: January 28, 2025, 3:00 p.m.

Update: The Lustre MDS issue was resolved this morning and the filesystem access is back to normal. Dear Expanse User We are currently seeing issues with the Expanse Lustre filesystem. This is leading to very slow responses or timeouts on access. We will update once the problem is resolved. SDSC User Services Staff

Posted: March 20, 2026

Infrastructure News Type: Reconfiguration

Affected Infrastructure: identity.access-ci.org

Start Date: January 27, 2025, 8:00 p.m.

End Date: January 27, 2025, 8:30 p.m.

On January 27, 2025, the ACCESS CI Identity Provider (https://idp.access-ci.org/idp/) will be updated to the latest Tomcat version. No downtime is expected.

Posted: March 20, 2026

Infrastructure News Type: Outage Full

Affected Infrastructure: bridges2-em.psc.access-ci.org, bridges2-gpu.psc.access-ci.org, bridges2-rm.psc.access-ci.org, bridges2-ocean.psc.access-ci.org

Start Date: January 27, 2025, 2:00 p.m.

End Date: January 30, 2025, 11:00 p.m.

As announced in August, we are excited to welcome the addition of ten HPE Cray 670 nodes, with eight (8) H100-SXM5-80GB GPUs and 2 TB node memory each, interconnected by a high-performance Infiniband network to the Bridges-2 system. The installation and testing will require an extended maintenance period beginning on Monday, January 27 at 8:00AM Eastern time and running through Thursday, January 30 at 5:00PM Eastern time. During this time, all Bridges-2 nodes, VMs and Filesystems will be unavailable. We thank you for your patience and understanding. As always if you have any questions or problems, please send them to help@psc.edu

Posted: March 20, 2026

Infrastructure News Type: Outage Partial

Affected Infrastructure: registry.access-ci.org

Start Date: January 27, 2025, 2:00 p.m.

End Date: January 27, 2025, 2:30 p.m.

On January 27, 2025, the Email Verification Plugin (https://github.com/cilogon/EmailVerificationEnroller) used by the ACCESS User Registry (https://registry.access-ci.org/) will be updated for compatibility with future versions of COmanage Registry (https://spaces.at.internet2.edu/display/COmanage/Registry+4.4.0+Release+Announcement). Server instances will be restarted during this update which may cause in-progress registrations/logins to fail.

Posted: March 20, 2026

Infrastructure News Type: Outage Partial

Affected Infrastructure: tickets.access-ci.org

Start Date: January 23, 2025, 4:30 p.m.

End Date: January 24, 2025, 1:00 p.m.

We have been informed of the degraded performance of Jira Work Management, Jira Service Management, and Jira Cloud customers in certain regions. We will provide more details as soon as we have. This incident affects: Jira Service Management Web, Service Portal, Opsgenie Incident Flow, Opsgenie Alert Flow, Opsgenie Incident Flow, Opsgenie Alert Flow, Jira Service Management Email Requests, Authentication and User Management, Purchasing & Licensing, Signup, Automation for Jira, and Assist. https://jira-service-management.status.atlassian.com/incidents/4s58pz6sk3zj This has been resolved

Posted: March 20, 2026

Infrastructure News Type: Degraded

Affected Infrastructure: anvil.purdue.access-ci.org, anvil-gpu.purdue.access-ci.org

Start Date: January 21, 2025, 7:30 p.m.

End Date: January 21, 2025, 8:57 p.m.

Update: As of Tuesday, January 21st, 2025 at 3:57pm EST, this has been resolved and capacity has been restored. The Anvil cluster began experiencing issues with electrical power around 2:30 PM EST. RCAC engineers are working with Purdue electricians to safely restore power. Anvil is operating at reduced capacity while a handful of nodes were shut down as a precaution. If your jobs were running on these please resubmit. If you have any questions, please submit a ticket through ACCESS Help Desk at https://support.access-ci.org/help-ticket. We will provide an update by 5:00 PM.

Posted: March 20, 2026

Infrastructure News Type: Reconfiguration

Affected Infrastructure: anvil.purdue.access-ci.org, anvil-gpu.purdue.access-ci.org

Start Date: January 17, 2025, 2:00 p.m.

End Date: January 17, 2025, 6:00 p.m.

Update: As of 12:00pm EDT. Jan 17, Anvil team has completed maintenance and returned the Open Ondemand service on Anvil cluster back to normal service. Please enjoy the new features on this dashboard and let us know if you notice any bugs or want more features by submitting a ticket through ACCESS Help Desk at https://support.access-ci.org/help-ticket. Update: the maintenance has been postponed to Friday Januany 17, 2025 The Open Ondemand service for Anvil will be unavailable from Friday, January 17 at 9:00am EDT, 2025 to Friday, January 17 at 5:00pm EDT, 2025. During the maintenance, Anvil team will perform a reconfiguration to the Open Ondemand dashboard for Anvil which include a brand new design of the dashboard with new features listed below. What’s New on the dashboard? - Service Unit Balance and Usage: Monitor your allocation usages and remaining balance on Anvil. - Disk Usage: Monitor your storage utilization across Anvil's file systems. - Job Queue: View and manage your running and queued jobs on Anvil. - News Feed: Stay updated with the latest Anvil news and announcements. - Partition Status: Monitor the current state of partitions/queues on Anvil. - My Jobs Page: Re-designed page to show detailed job information for your jobs and jobs in your allocation(s) as well as job management. - Performance Metrics Page: Analyze your job performance and resource utilization patterns over time. What will impact you? - All Slurm jobs on Anvil (including jobs that have already submitted through Open Ondemand before this maintenance) will continue and NOT be impacted. - All functions including login to Open Ondemand will be unavailable during the maintenance. Anvil Open Ondemand service will return to full production by Friday, January 17 at 5:00pm EDT, 2025. Please submit a ticket through ACCESS Help Desk at https://support.access-ci.org/help-ticket (https://support.access-ci.org/help-ticket**) if you have any questions or suggestions.

Posted: March 20, 2026

Infrastructure News Type: Outage Full

Affected Infrastructure: aces.tamu.access-ci.org

Start Date: January 16, 2025, 3:00 p.m.

End Date: January 17, 2025, 2:00 a.m.

The ACES cluster will be unavailable during maintenance from 9am to 8pm CST on Thursday January 16 A reservation is in place to prevent jobs from running past the start time of the maintenance period. After the maintenance has been completed, the maximum permitted time limit for jobs in the cpu queue will be reduced from 7 days to 3 days.

Posted: March 20, 2026

Infrastructure News Type: Outage Partial

Affected Infrastructure: delta.ncsa.access-ci.org

Start Date: January 13, 2025, 2:00 p.m.

End Date: January 13, 2025, 6:00 p.m.

DeltaAI resource users, On Monday, January 13th the DeltaAI compute resource will be unavailable from 8AM to 5PM. During that time all compute nodes will be offline and no jobs will run. During the outage software controlling the High-speed Network will be upgraded and modified to allow the addition of 18 new nodes. There will be no changes to the compute image or other user space software. The DeltaAI logins, storage, scheduler and Openondemand systems will all remain available throughout the outage. Jobs can be submitted during the outage but will not run until the outage ends. The DeltaAI team

Posted: March 20, 2026

Infrastructure News Type: Retirement

Affected Infrastructure: hive.gatech.access-ci.org

Start Date: January 13, 2025, 6:00 a.m.

End Date: Not Specified

Dear ACCESS Community, The Hive Gateway resource at Georgia Tech will enter retirement on January 13th, 2025. The original hardware has reached end-of-life after an additional year of performance post-award and can no longer be supported. The Gateway will remain accessible for existing users, in order to access any data on the system, but it will be impossible to run new jobs. We currently plan to fully turn off Gateway access for ACCESS accounts by March, 2025. Please feel free to reach out if you have any concerns via email at pace-support@oit.gatech.edu. Best, The PACE Team

Posted: March 20, 2026