status.ncsa.illinois.edu


Watch this page in the wiki to subscribe to automatic updates to this status page.

Please do not refer to any NCSA Industry Partners on this page. Please use the iforge nomenclature for all of the *forge infrastructure.

To see older events, see Archive of NCSA Status Home

Report a problem 

Current Status  

StartEndWhat System/Service is affectedWhat is happening?What will be affected?Contact Person

Status

 
1500

TBDAFSWorking on updates to the AFS DB servers.None expected. AFS is served by redundant servers.help@ncsa.illinois.edu

IN PROGRESS

Upcoming Scheduled Maintenance

Listed below in chronological order.

StartEndWhat System/Service is affectedWhat is happening?What will be affected?Contact Person

Status


Previous Outages or Maintenance

StartEndWhat System/Service was affected?What happened?What was affected?

Contact Person

Status

2024-12-04 1700

2024-12-05 0700

NCSA File & Print Servers

Scheduled Windows Server Maintenance

File & Print Shares will be unavailable during maintenance.  Users will be unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing will be unavailable.help@ncsa.illinois.edu

ONGOING

2024-11-18 0930

2024-11-18 11:30

NightingaleSlurm UpdateNew jobs and Slurm commands will fail, existing running jobs will continue to runhelp@ncsa.illinois.edu

COMPLETED

2024-11-13 13002024-11-13 2000

Connectivity

Fiber vendor maintenanceThe fiber provider that provides connectivity to UIUC and Illinois is continuing to troubleshoot issues related to maintenance they performed last night.  Intermittent loss of connectivity may be observed.  help@ncsa.illinois.edu

COMPLETED

2024-11-07 15002024-11-09 1600

radiant.ncsa.illinois.edu

virtual routing was affected during planned rolling updateproject routes were not accessible for periods during the outagehelp@ncsa.illinois.edu

COMPLETED

2024-11-04 12002024-11-04 1234vsphere.ncsa.illinois.eduCritical PatchesThe vsphere.ncsa.illinois.edu web console. VMs should not be affectedhelp@ncsa.illinois.edu

 COMPLETED

2024-10-28 0800

2024-10-28 2300

Core-East

Core-East will be added back to active routing.

The intent is for no service impact. help@ncsa.illinois.edu

COMPLETED

2024-10-23 23:00

2024-10-24 10:30
ncsa-3003 lab

Some systems in NCSA 3003 were unreachable due to DDOS protection because of a host in 3003.

systems connected to the ncsa-3003-agg switch couldn't  be reached or connect to the rest of the NCSA network.help@ncsa.illinois.edu

RESOLVED

2024-10-23 15:20

2024-10-23 19:23
ncsa-3003 lost a lab router

Some systems in NCSA 3003 were unreachable while the router was in a broken state.

systems connected to the ncsa-3003-agg switch couldn't  be reached or connect to the rest of the NCSA network.help@ncsa.illinois.edu

RESOLVED

2024-10-21 0800

2024-10-21 2300

Core-East

Core-East will be replaced.

The intent is for no service impact. help@ncsa.illinois.edu

COMPLETED

2024-10-17 1700

2024-10-18 0700

NCSA File & Print Servers

Scheduled Windows Server Maintenance

File & Print Shares will be unavailable during maintenance.  Users will be unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing will be unavailable.help@ncsa.illinois.edu

COMPLETED

2024-10-14 0900

2024-10-14 2300

Core-East

Removing Core-east from active routing.

The intent is for no service impact. help@ncsa.illinois.edu

COMPLETED

2024-10-11 1220

2024-10-11 1228

NCSA GitLab git.ncsa.illinois.edu

GitLab was updated to latest version.

All GitLab services were unavailable for a few minutes.help@ncsa.illinois.edu

COMPLETED

2024-10-07 0900

2024-10-07 2300

Core-West

The new Core-West being brought fully online from install last week. 

The intent is for no service impact. help@ncsa.illinois.edu

COMPLETED

2024-10-03 5:00pm

2024-10-03 5:35pm

mForge and Nightingale

Replacing faulty npcf-ache-dist switch

Admin access to mForge and all access to Nightingalehelp+neteng@ncsa-illinois.edu

COMPLETED

2024-09-30 0800

2024-09-30 2300

Core-West 

Core-West will be replaced. 

The intent is for no service impact.help@ncsa.illinois.edu

COMPLETED

2024-09-26 10002024-09-26 1023ache-gitgitlab updatesaccess to ache-gitsecurity@ncsa.illinois.edu

COMPLETED

2024-09-24 3:00p

2024-09-24 3:48p

idp.ncsa.illinois.edu

The NCSA IdP was unreachable due to network reconfiguration. The issue was identified and fixed.

Any service which required login via idp.ncsa.illinois.edu .help@ncsa.illinois.edu

FIXED

2024-09-23 12002024-09-23 1300vsphere.ncsa.illinois.eduCritical PatchesThe vsphere.ncsa.illinois.edu web console. VMs should not be affectedhelp@ncsa.illinois.edu

 COMPLETED

2024-09-12 0700

2024-09-12 2100

vForge

scheduled PM

all cluster operations help@ncsa.illinois.edu

COMPLETE

2024-09-12 0800

2024-09-12 1730

Taiga & Granite

Bi-Annual Maintenance 

Taiga and Granite services were upgradedset@ncsa.illinois.edu

COMPLETE

2024-09-10 1600

2024-09-11 1600

ACHE

Users have been erroneously removed from ACHE LDAP Groups 

2400 Update: User access should be restored. ACHE Savannah workflows still be investigated

9-11 1600 Update: Savannah fix has been deployed and workflows should be working

Affected users will be unable to access ACHE/Ngale systemshelp+hipaa@ncsa.illinois.edu

COMPLETE

 
1700

 
0900

Jira

Rollout of new Jira Service Manager ticketing system

Jira will be down starting at 5PM on Friday 6 Sep through 9 AM Monday 9 Sephelp@ncsa.illinois.edu
217-244-0710

COMPLETE

2024-09-04 0700

2024-09-04 1900

NightingaleQuarterly Planned MaintenanceAll Nightingale servers and services were unavailable (other than the ngale-bastion* nodes)help@ncsa.illinois.edu

COMPLETE

2024-09-04 1000

2024-09-04 1100

ACHE-Proxy
Migration to RHEL8Ache proxy will be temporarily unavailable for reinstallsecurity@ncsa.illinois.eduCOMPLETE


2024-08-30 14:30

2024-08-30 15:30

npcf-influxdbMigration to RHEL9 + NVME ServerThe npcf-influxdb server was migrated to new hardware and moved to RHEL 9.4malone12@illinois.edu

COMPLETE

2024-08-26 0930

2024-08-29 1800

NCSA-CWM firewalls

Updating NCSA-CWM Firewalls

fw1 Monday

fw2 Thursday

No outages expectedsecurity@ncsa.illinois.edu

COMPLETE

2024-08-26 0930

2024-08-29 1800

NPCF-CWM firewalls

Updating NPCF-CWM Firewalls

fw1 Monday

fw2 Thursday

No outages expectedsecurity@ncsa.illinois.edu

COMPLETE

2024-08-12 1330

2024-08-22 1300

CA firewalls

Updating the CA firewalls

No outages expectedsecurity@ncsa.illinois.edu

COMPLETE


2024-08-21 1200

2024-08-21 1205

ldap.ncsa.illinois.edu LDAPrestarting service to load new schemaidentity etc. any systems which write to NCSA LDAP tbouvet@illinois.edu

COMPLETE

0700

 

0100

Radiant (and dependent services)

Planned Maintenance

Update of CEPH storage service

Update of OS to Rocky 9

Radiant service and Horizon dashboard
https://radiant.ncsa.illinois.edu

all VM's were stopped for the duration of the event

help@ncsa.illinois.edu

COMPLETE

1530

~2359

Illinois Computes Research Notebooks (ICRN)

Planned maintenance of upstream cloud provider (Radiant)

Jupyter notebooks for https://jupyter.ncsa.illinois.eduhelp@ncsa.illinois.edu

COMPLETE

2024-08-20 15552024-08-20 1703ICI MetricsThe ICI Metrics server became intermittently unresponsiveAccess to https://metrics.ncsa.illinois.edu and all alerting was interuptedhelp@ncsa.illinois.edu

COMPLETE

2024-08-16 1800

2024-08-17 0700

NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares will be unavailable during maintenance.  Users will be unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing will be unavailable.help@ncsa.illinois.edu

COMPLETE

1600

1730

Illinois Computes Research Notebooks (ICRN)

Network configuration changes

Jupyter notebooks for https://jupyter.ncsa.illinois.edu

help@ncsa.illinois.edu

COMPLETE

2024-08-15 11:452024-08-15 1200DUOsecrets are being rotatedduo.ncsa.illinois.edu will have momentary outage while new keys are updated and service restarted. help+security@ncsa.illinois.edu

COMPLETE

2024-08-14 12002024-08-14 1201LastpassDUO integration is being updatedno issues are expectedhelp+security@ncsa.illinois.edu

COMPLETED


2024-08-12 10002024-08-12 1430Delta-AIShutting down Delta storage rack CDU to connect new Delta-AI storage rack RDX to CDUDelta storage rack RDX  will be switched off, will switch the rack to facility air/air cooling.rantissi@illinois.edu COMPLETE


2024-08-05 0930

2024-08-08

1036

ache-fw

Updating ache fw's

fw1 on Monday

fw2 on Thursday planned

No outages expectedsecurity@ncsa.illinois.eduCOMPLETE


2024-07-31 1800

2024-08-01 0700

NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares will be unavailable during maintenance.  Users will be unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing will be unavailable.help@ncsa.illinois.edu

COMPLETED

2024-07-30 18:30

2024-07-30 21:25

Globus Transfers (All Endpoints)Globus is experienced a nation-wide outage due to service disruptions in AWSGlobus Transfers/Workflowsset@ncsa.illinois.edu

RESOLVED

2024-07-16 07002024-07-16 1700Delta

System updates and networking configuration changes in preparation for DeltaAI fabric and storage linking.

Moving user home directories from Delta local storage to NCSA Harbor storage service.

All Delta systems/servcieshelp@ncsa.illinois.edu

SCHEDULED

 

 

wiki.ncsa.illinois.eduNCSA Wiki will restart daily at 3:30 AMwiki.ncsa.illinois.edu will be inaccessible for a few minutes while the service is restarted.help@ncsa.illinois.edu

RESOLVED

 

Week of  

Granite Tape Archive restores/retrievals. Upgrading the tape library to its new LTO9 tape technologyRestores and retrievals form the tape library. bdickin2@illinois.edu


COMPLETED

2024-07-10 0800

2024-07-10 2000

Illinois Campus ClusterQuarterly MaintenanceScheduler, login and compute nodes. Mounts to ICCP research storage from outside the cluster are unaffected. help@campuscluster.illinois.edu

COMPLETED

0800

1630

Illinois Computes Research Notebooks (ICRN)Quarterly MaintenanceJupyter notebooks for https://jupyter.ncsa.illinois.eduhelp@ncsa.illinois.edu

COMPLETED

2024-07-03 12002024-07-03 1300vsphere.ncsa.illinois.eduCritical PatchesThe vsphere.ncsa.illinois.edu web console. VMs should not be affectedhelp@ncsa.illinois.edu

COMPLETED

2000

0310

cerberus1, cerberus3, some CA systems,  *.security.ncsa.illinois.edunetwork interruptionssome network changes made between 9:45p and 11:15p on 2024-06-28 - waiting to see if that resolves the issues.

Update 03:10 CDT we believe the problem has been isolated and all services recovered, but we continue to monitor
help+security@ncsa.illinois.edu

RESOLVED

2024-06-26 09002024-06-27 1400Ngale BastionsReinstallionEach system will be down, 1 per dayhelp+security@ncsa.illinois.edu

COMPLETED

2024-06-24 09002024-06-25 1400ACHE BastionsReinstallionEach system will be down, 1 per dayhelp+security@ncsa.illinois.edu

COMPLETE

 
0750

 
0845

JiraRan out of licensesNo new tickets could be made, dashboards were unavailable.help@ncsa.illinois.edu

RESOLVED

2024-06-18 18002024-06-19 0700NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares will be unavailable during maintenance.  Users will be unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing will be unavailable.help@ncsa.illinois.edu

COMPLETE


2100

 
2200

wiki.ncsa.illinois.eduNCSA Wiki will be updated to address security concerns.wiki.ncsa.illinois.edu will be inaccessible during the upgradehelp@ncsa.illinois.edu

COMPLETE

2024-06-12 1500

2024-06-12 1600The following websites:
  • midwestbigdatahub.org
  • gladiator.ncsa.uiuc.edu
  • redirect.ncsa.uiuc.edu
  • timelapse.ncsa.illinois.edu
  • woodylants.nres.uiuc.edu
  • www.nationaldataservice.org
  • grid.ncsa.illinois.edu
  • security.ncsa.illinois.edu
Hosts managing these site will be rebootedSites will be inaccessible for a brief periodhelp@ncsa.illinois.edu

COMPLETE

0530

0700

NCSAnet WirelessCampus and NCSA enginners will be making some changes to the NCSAnet wireless.NCSAnet will be periodically unavailable during the maint window.  IllinoisNet will remain available. help+neteng@ncsa.illinois.edu

RESOLVED

2024-06-03 09002024-06-06 1400Cerberus BastionsRe-installationEach system will be down, 1 per dayhelp+security@ncsa.illinois.edu

RESOLVED

2024-05-31 10002024-05-31 1200Networking in 3003ncsa-3003-lr switch stack upgrade  Anything connected to the main switch stack in 3003help+neteng@ncsa-illinois.edu

RESOLVED

1500

1500

Connectivity in 3003network connectivity issues in 3003.
help+neteng@ncsa.illinois.edu


14:04

14:52

NCSA center-wide management firewalls connection to upstream network device was disrupted. Connection has been re-establishedconnectivity to NCSA center-wide management networks in 3003is down / intermittanthelp+security@ncsa.illinois.edu

RESOLVED


2024-05-16
0630
2024-05-17 1530DeltaPlanned MaintenanceFull system outagehelp@ncsa.illinois.eduCOMPLETE


2024-05-17 06002024-05-17 0713NCSA GitLab git.ncsa.illinois.eduGitLab server was updated to new OS.All GitLab services were unavailable.help@ncsa.illinois.edu

COMPLETE

2024-05-15 07002024-05-15 19:00NightingaleQuarterly Planned MaintenanceAll Nightingale servers and services were unavailable (other than the ngale-bastion* nodes)help@ncsa.illinois.edu

COMPLETE

2024-05-14 08002024-05-14 1500RadiantAdding second OpenStack network service node No operational impact is expected but there may be some increased latency in OpenStack network requests as the service rebalances.help@ncsa.illinois.edu

COMPLETE

2024-05-07 1800

2024-05-08 0700

NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares will be unavailable during maintenance.  Users will be unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing will be unavailable.help@ncsa.illinois.edu

COMPLETE

2024-05-03 06002024-05-03 0615NCSA GitLabGitLab was updated to latest version. This was rescheduled from originally scheduled the day before.All GitLab services will be unavailable for a few minutes.help@ncsa.illinois.edu

COMPLETE

10:30

11:00

wiki.ncsa.illinois.eduwiki.ncsa.illinois.edu has slow load time or completely times out (ticketed as SVC-24573)Viewing/Editing Confluence (Wiki) pages.help@ncsa.illinois.edu

RESOLVED

2024-04-25 17:00

2024-04-25 17:45

sslvpn.ncsa.illinois.eduAn update for an active 0day attack was installedvpn connections dropped for users and they had to reconnect.help+neteng@ncsa.illinois.edu

COMPLETE

 
1700


1700

NCSA WikiServer, DB, and Application upgradeswiki.ncsa.illinois.edu will be unavailable during this timehelp@ncsa.illinois.edu

COMPLETE

2024-04-19 08:00

2024-04-19 09:15

DHCP leases for NCSANet and NCSA wired networkDHCP server stopped renewing IP address leases after a reboot for patchingDHCP lease renewals ceased, causing loss of connectivity for systems that tried to renew during the window. Already established connections were unaffected.help+neteng@ncsa.illinois.edu

COMPLETE

2024-04-17 13:15

2024-04-17 13:16

ache-repo.ncsa.illinois.eduA filesystem is being fsck'ed.The data filesystem will be offline so packages will be unavailable.help+security@ncsa.illinois.edu

COMPLETE

2024-04-16 08:45

2024-04-16 09:15

TaigaRolling Failovers on Taiga's MDT0 applianceAccess to FS was interrupted

set@ncsa.illinois.edu

COMPLETE

2024-04-04 12:35

2024-04-04 16:35

Subset of Taiga native (Lustre) clientsIB Link on tgio11 began failing RDMA traffic causing some I/O interrupt issues on clients leveraging 3 LNET routers.  Access to the file system via these LNET routers is periodically timing out; suspect is bad IB cable.  Confirming with vendor. 

set@ncsa.illinois.edu

MITIGATED

 
0700


0730 

VMware migrationsVMware hosts are migrating to a new license modelAll VM guest machines and all services should remain operational and accessible. No downtimes are expected.

help@ncsa.illinois.edu


COMPLETE

2024-04-03 1800

2024-04-04 0700

NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares will be unavailable during maintenance.  Users will be unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing will be unavailable.help@ncsa.illinois.edu

COMPLETE

2024-04-02 11:00

2024-04-02 11:30

IRST services, including systems run on IRST VMWare clustersmoving to upgraded switches/routers

Systems run by IRST, and any systems on the IRST-run VMWare cluster. Outage is expected to last < 5min.

help+security@ncsa.illinois.edu

COMPLETE



2024-02-28

2024-04-01

SSLVPNSSLVPN will start using CILogon for authentication and DUO integration. Four new profiles have been created (duplicating the existing four) but with the name "cilogon" in the name.  These new profiles will use the new authentication method.   After a few weeks of testing, if no issues are found, we will remove the old profiles on March 20. help+neteng@ncsa.illinois.edu

COMPLETE

 
2330

 
2345

NCSA GitLab,
NCSA Windows File & Print Servers
Web Redirect Server

VMs migrating to a new clusterAffected services will be unavailable for a few minutes.help@ncsa.illinois.edu

COMPLETE

 

 

NPCF WifiTech Services will be replacing the AP at NPCF.

Tech Services will be replacing the Access Points at NPCF.  No user impact is expected.

help+neteng@ncsa.illinois.edu

COMPLETE


2100 hrs


2200 hrs

Jira, Wiki, internal.ncsa.illinois.edu, identity.ncsa.illinois.eduVMs will migrate to a new cluster.Services will be unavailable for a few minutes (<5 mins) while the VM is shutdown and moved.help@ncsa.illinois.edu

COMPLETE

 

 

NCSA WifiTech Services will be replacing the AP at the NCSA building. 

Tech Services will be replacing the Access Points at the NCSA building.  No user impact is expected.

help+neteng@ncsa.illinois.edu

COMPLETE

2024-03-14 0700

2024-03-15  2140

vForge / license serversQuarterly Planned Maintenanceall vForge nodes and services (incl. related license servers/services) will be unavailablehelp@ncsa.illinois.edu

COMPLETE


03/14/2024 080003/15/2024 2125
  • Extended outage due to a problematic upgrade solution. 
  • Vendor engineers involved
Taiga/GraniteSemi-Annual Maintenance

All Taiga & Granite Storage Services

set@ncsa.illinois.edu

COMPLETED

1200

1500

vsphere.ncsa.illinois.edu consoleUpgradeThe vsphere.ncsa.illinois.edu web console. VMs should not be affectedhelp@ncsa.illinois.edu

COMPLETED

2024-03-072024-03-08NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares will be unavailable during maintenance.  Users will be unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing will be unavailable.help@ncsa.illinois.edu

COMPLETED

2024-02-22 06402024-02-22 0648NCSA GitLabGitLab being updated to latest versionAll GitLab services will be unavailable for a few minutes.help@ncsa.illinois.edu

COMPLETED

1500

1600

ACHE vSphere is being upgradedACHE vSphere is being upgraded

ACHE vSphere will not be accessible

help@ncsa.illinois.edu

COMPLETED

1600

 

1630

sslvpn.ncsa.illinois.edussl cert is refreshed

Users may need to manually reconnect if the system drops their session

neteng@ncsa.illinois.edu

COMPLETED

02/08/2024 103002/08/2024 1330NCSA Backbone Network Battery BackupNPCF Network DC Battery Maintenance Network Engineering is taking the battery back-up servicing NPCF networking equipment offline for periodic maintenance. This will be non-service impacting, as all core networking equipment still has two independent power feeds. neteng@ncsa.illinois.edu

COMPLETED

2024-01-29 16002024-02-05UIUC NetworkComplete / partial network outageWhile NCSA network is up and not impacted, much of the UIUC network is currently offline.  This could be affecting a broad range of services such as wireless, facility networks, campus websites, etc.  No current ETA, as engineers are still troubleshooting the problem. neteng@ncsa.illinois.edu

COMPLETED

1730

1830

vCenter Server ApplianceCritical patches are being applied

The vcenter.internal.ncsa.edu site will not be accessible. Operating VMs should not be affected

help@ncsa.illinois.edu

COMPLETED

0800

1400

HOLL-IHOLL-I will enter a shuttered/standby modeAll HOLL-I servers and services will no longer be available after standby mode is activated.help@ncsa.illinois.edu

COMPLETED

2024-01-24 1800

2024-01-25 0700

NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares will be unavailable during maintenance.  Users will be unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing will be unavailable.help@ncsa.illinois.eduCOMPLETED


0900

0915

LastPassyearly audit performed. Users disabled or deleted per policyAccounts that had been disabled for over a year were deleted. Accounts that were unused for a year were disabledhelp+security@ncsa.illinois.edu

COMPLETED


2024-01-22 0900

2024-01-22 1000

idp.ncsa.illinois.eduConfiguration update for sslvpnConfiguration for the NCSA Identity Provider will be updated with login support for sslvpn.ncsa.illinois.edu.help+idp@ncsa.illinois.edu

COMPLETED

1700

1745

Wiki service upgradeUpgrade version to address recently announce security vulnerabilities.

Wiki will be down during upgrade and testing.

help@ncsa.illinois.edu

COMPLETED

  2200

  2330

Jira service upgradeUpgrade version to address recently announce security vulnerabilities.

Jira will be down during upgrade and testing.

help@ncsa.illinois.edu

COMPLETED

2024-01-17 05002024-01-17 0700Wireless connectivity on 2nd, 3rd and 4 floors. Tech Services will be replacing some network components in switches that provide connectivity for wireless. 

Each floor (wireless) will lose connectivity for a few mins while the cards are replaced. 

neteng+help@ncsa.illinois.edu

COMPLETED

2024-01-16 09002024-01-16 23:30Facility UPSSecond attempt, Preventive Maintenance_Replace UPS capacitorsAll systems which are connected to UPS power. During the PM the systems will not lose power but will be unprotected.rantissi@illinois.edu


COMPLETED

2024-01-16 22002024-01-17 0300Waster leak in Node 1 on campus.Node1 ( located on campus) has a water leak that may require full power down to address.  This will take out several devices that provide connectivity to NCSA WAN. No power outage was needed to repair the leakneteng@ncsa.illinois.edu

COMPLETED

2024-01-10 07002024-01-10 12:09NightingaleQuarterly Planned MaintenanceAll Nightingale servers and services were unavailable (other than the ngale-bastion* nodes)help@ncsa.illinois.edu

COMPLETED

2024-01-09 21002024-01-10 0400WifiPerforming a Code upgrade that will affect the Wi-Fi Environment. The majority of the system will be online and functional while individual Access Points will be upgraded. This upgrade is expected to gracefully migrate clients to adjacent access points to minimize any interruption. 

<----


This will more than likely also impact NCSAnet.

neteng+help@ncsa.illinois.edu

COMPLETED

08 Jan 2024 0700

08 Jan 2024 1600

vforgeRadiant upgradeEntire cluster is shut downjlong@ncsa.illinois.eduCOMPLETED


0700

1430

RadiantThe Radiant cluster was be upgraded from OpenStack Wallaby to Yoga.The web dashboard and API endpoints were unavailable; networking for instances may have been intermittent.help@ncsa.illinois.edu

COMPLETED

2024-01-05 04002024-01-19 1200WifiUpgrading the code used for the Authentication on the Wi-Fi system and VPN. There will be an interruption to the IllinoisNet_Guest device registration and the IllinoisNet_Guest self-registration portal; both are expected to be back online before regular business hours. Regular authentication and traffic flow for the Wi-Fi and VPN is not expected to be interrupted.

<----


This will more than likely also impact NCSAnet.

neteng+help@ncsa.illinois.edu

COMPLETED

2023-12-19  04002023-12-19 0800WifiUpgrading the core campus Wi-Fi hardware. There will be an interruption to Campus Wi-Fi (including IllinoisNet, IllinoisNet_Guest, and eduroam), IllinoisNet_Guest device registration, and the IllinoisNet_Guest self-registration portal.

<----


This will more than likely also impact NCSAnet.

neteng+help@ncsa.illinois.edu

COMPLETED

2023-12-13 1800

2023-12-14 0700

NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares will be unavailable during maintenance.  Users will be unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing will be unavailable.help@ncsa.illinois.eduCOMPLETED


  1600

1630

wiki.ncsa.illinois.edu and jira.ncsa.illinois.eduAtlassian has notified us of several critical security vulnerabilities in Confluence and Jira software. A mitigation has been applied to the Jira server and the Confluence server (wiki.ncsa.illinois.edu) will be patched.There will be a brief outage to patch the Confluence server at 1600. The patching is expected to take 15-20 minutes but the entire hour is reserved as a precaution.help@ncsa.illinois.edu

COMPLETED

2023-12-06 09002023-12-06 1700Facility UPSPreventive Maintenance _ Replace UPS capacitors.All systems which are connected to UPS power. During the PM the systems will not lose power but will be unprotected.MO Rantissi

INCOMPLETE

UPS maintenance was halted due to damaged parts.  Putting the UPS back together and rescheduling for a later date.

The UPS is back online.

2023-11-10
0800

2023-11-10
0900

IDDS databasePlanned maintenance: postgresql upgradeNCSA identity, group management, campus cluster user management page, TEM shift report tool, and napshelp+idds@ncsa.illinois.edu

COMPLETED

2023-11-09 0700

2023-11-09 1445 (vForge)

2023-11-09 1630 (license servers)

vForge / license serversQuarterly Planned Maintenanceall vForge nodes and services (incl. related license servers/services) will be unavailablehelp@ncsa.illinois.edu

COMPLETED

2023-11-09 0700

2023-11-09 14:30

vForge / license serversQuarterly Planned Maintenanceall vForge nodes and services (incl. related license servers/services) will be unavailablehelp@ncsa.illinois.edu

COMPLETED

2023-11-08 1200

2023-11-08 1230

RadiantRebuilding rabbitmq serviceDashboard and API services were read-only during this time. help@ncsa.illinois.edu

COMPLETED

2023-11-03

2023-11-07

hub.ncsa.illinois.eduprivate docker registry is down due to volumes in radiant in detaching statehub.ncsa.illinois.edu is not reachable, and images stored are unreachable. Services that have their images local should continue to run, services that want push/pull images will get a 500 error.Rob Kooper 

COMPLETED

1700

1830

Confluence/WikiUpgrade the systemConfluencehelp@ncsa.illinois.edu

COMPLETED

2023-10-31 09:302023-10-31 10:30NCSA OpenSourceupgrade Atlassian productsopensource confluence/jira/bamboo/bitbucket

COMPLETED

 

 

HALFull System PMAll HAL services

POSTPONED


1330

14:30

SSLVPNNew auth method was added to a new login profile, ncsa-vpn-saml-tunnelall. There is now a test profile in place that isn't open to everyone. Please continue to use the profiles you were using before. If you notice and issue please report it. Our testing indicated logins were working as intended. help+neteng@ncsa.illinois.edu

COMPLETE

0900

1700

RadiantOpenStack software updateThe Radiant team will be conducting an OpenStack software update, from Victoria to Wallaby. This is a software stability update and does not include significant features or changes in functionality. The update will be done online and is not expected to impact running instances or system access.help@ncsa.illinois.edu

COMPLETE

  1700

  0700

NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares will be unavailable during maintenance.  Users will be unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing will be unavailable.help@ncsa.illinois.edu

COMPLETE

0930

1100

TaigaOnline, Rolling patch of Taiga serversTaiga File Systemset@ncsa.illinois.edu

COMPLETE

0800

0800

HOLL-ICS-2 Appliance Mode upgradeAll HOLL-I servers and services will be limited to internal testershelp@ncsa.illinois.edu

COMPLETED

0800

0800

HOLL-ICS-2 Appliance Mode hardware installationAll HOLL-I servers and services will be unavailablehelp@ncsa.illinois.edu

COMPLETE

1800

1815

ConfluenceConfig will be applied to increase the period users can be logged in before logged outConfluence will be downhelp@ncsa.illinois.edu

COMPLETE

  1700

  1800

sslvpntesting new auth methodno user impact was observedhelp+neteng@ncsa.illinois.edu

COMPLETE

2023-10-10 08002023-10-10 1000cilogon.orgMoving to new compute infrastructurecilogon.org, demo.cilogon.org, crl.cilogon.orghelp@cilogon.org

COMPLETE

2023-10-09 12152023-10-09 1532TaigaAppliance has unmounted all of its OSTs. Ability to do I/O to Taigaset@ncsa.illinois.edu

COMPLETE

0600

0700

ConfluenceConfluence is being upgradeConfluence will not be available for use

help@ncsa.illinois.edu

COMPLETE

2023-10-04 06002023-10-04 1927DeltaFilesystem and OS patchingAll Delta resources will be unavailable during the maintenance period
including:
+ Delta login nodes - unavailable
+ Delta compute nodes - unavailable
Delta services
+ Open OnDemand - unavailable
+ Delta Globus Online endpoint - unavailable
help@ncsa.illinois.edu

COMPLETE

2023-10-04 09502023-10-04 1000Opensource ConfluencePatching conflueceopensource confluence will be down

COMPLETE

2023-09-27 17002023-09-28 0700NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares were unavailable during maintenance.  Users were unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing was unavailable.help@ncsa.illinois.edu

COMPLETE

2023-09-26 14002023-09-26 1500Wireless NCSA buildingCampus wireless outage.NCSAnet and IllinoisNet users are experiencing connectivity issues.   Tech Services is aware of the problem. help+neteng@ncsa.illinois.edu

COMPLETE

2023-09-28 14332023-09-28 1459cilogon.orgservice outage due to AWS database issuelogins to cilogon.org were failinghelp+cilogon@ncsa.illinois.edu

COMPLETE

2023-09-26 7:30AM2023-09-26 8:00AMLdap Primary  ServerMaintenanceLdap updates will be disabled during maintenanceTimothy Bouvet 

COMPLETE

09/22/2023 8:00am9/22/2023 1:30pmWireless accessNCSANet is not authenticating users and denying connections.Anyone attempting to connect to the wireless NCSANet ID.neteng@ncsa.illinois.edu

COMPLETE

2023-08-292023-09-21 - 1300opensource bitbucketBitbucket is not compatible with the deployed version of git, see https://jira.atlassian.com/browse/BSERV-14390opensource.ncsa.illinois.edu/bitbcket

COMPLETE

2023-Sep-19 - 07452023-Sep-19 - 0750LastPassRekey the LastPass/Duo IntegrationLastPass users that utilize duo may not be able to authenticate until completedJames Eyrich

COMPLETE

2023-Sep-18 - 15112023-Sep-18 - 1749TaigaOutage due to failed MDS failover.Taiga access was unavailable.set@ncsa.illinois.edu

COMPLETE

2023-09-14 07002023-09-14 2015vForge / license serversQuarterly Planned Maintenanceall vForge nodes and services (and related license servers/services) will be unavailablehelp@ncsa.illinois.edu

COMPLETE

2023-09-14-08002023-09-14-2000Taiga & Granite ServicesSemi-Annual Planned MaintenanceAll Taiga and Granite services will be offline 

set@ncsa.illinois.edu

COMPLETE

2023-09-08  06:582023-09-08 09:50disruption to NPCF-DES-CORE, NPCF-CWMGMT-FW1 & 2, MForge VPN

NPCF-CORE-EAST has a DEAD linecard.

Relocating affected links to other linecards with open ports while we work with vendor support for a replacement.

redundancy has been lost, access and activity remain normal.

COMPLETE

2023-09-06 09:482023-9-6 10:35NCSA Center Wide Management Networkthe firewall protecting this network is showing offlineCenterwide management networks in NCSA building(John) Walker 

COMPLETE


2023-9-6 09:502023-9-6 10:35The main switch in NCSA 3003In debugging a link problem between NCSA and NPCF the wrong fiber was inadvertently pulledNetworking in and out of 3003 was down for 35 minsneteng@ncsa.illinois.edu

COMPLETE

2023-08-26 23:062023-08-27 01:36CILogonCILogon database replication errorCILogon OAuth/OIDC services unavailablehelp+cilogon@ncsa.illinois.edu

COMPLETE

2023-08-24 13:022023-08-25 14:15TaigaMultiple SAS cable backend failure causing OSTs to go into write protect and unmountAccess to certain OSTs in Taiga

set@ncsa.illinois.edu

COMPLETE

2023-08-16 17002023-08-17 0000NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares were unavailable during maintenance.  Users were unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing was unavailable.help@ncsa.illinois.edu

COMPLETE

2023-08-16 07002023-08-16 1003NightingaleQuarterly Planned MaintenanceAll Nightingale servers and services were unavailable (other than the ngale-bastion* nodes)help@ncsa.illinois.edu

COMPLETE

2023-08-15 04002023-08-15 0500VMWare GatewayVMWare is updating the Gateway OSNo expected effects

help@ncsa.illinois.edu

COMPLETE

2023-08-14 09352023-08-14 2000NCSA VPNDuo implemented new ssl checks that we were not passingUsers couldn't authenticate with DUO to establish new connections to the VPN. Existing VPN sessions remain connected.Matthew Elliott 

COMPLETE

2023-07-27 17002023-07-27 1715HOLL-ILive kernel patchingkernel was updated in response to recent security issue.help@ncsa.illinois.edu

COMPLETE

2023-07-25 09002023-07-25 1630RadiantChanges to the OpenStack network configuration and network service node (increasing MTU on customer networks and adding a new dedicated network server)These changes will impact project/instance networks and cause them to be unreachable for an extended period of time. Expect network timeouts and failure of NFS file system access. Systems may be unreachable for several hours - up to the entire planned time - but we are making every effort to minimize the downtime.

James Glasgow via help@ncsa.illlinois.edu

COMPLETE

2023-07-19 0800

2023-07-19 2000

ICCPICCP Quarterly MaintenanceAll ICCP services

help@campuscluster.illinois.edu

COMPLETE

2023-07-19 08002023-07-19 0900u1carne routerscheduled maintenancemForge, Magnus, and Access will have a brief outage as the routers reboot.

Michael Douglas via neteng@ncsa.illinois.edu

COMPLETE

2023-07-12 17002023-07-12 2130NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares were unavailable during maintenance.  Users were unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing was unavailable.help@ncsa.illinois.edu

COMPLETE

2023-07-07 10002023-07-07 1100NCSA KerberosDeleting out principals that were disabled on 2023-06-07Kerberos authentication should already be disabled for the planned hosts, so there should be zero notable effect. help@ncsa.illinois.edu

COMPLETE

1345

1450

HOLL-ITransitioning CS-2 Execution Mode from Weight Streaming to PipelinedHoll-I CS-2help@ncsa.illinois.edu

COMPLETE

2023-06-30 06002023-06-30 0605NCSA GitLabGitLab was updated to latest versionAll GitLab services was unavailable for a few minutes.help@ncsa.illinois.edu

COMPLETE

2023-06-29 18492023-06-29 2000DeltaMore Power fluctuations due to the severe weather have caused in all NCSA buildings. NCSA staff are working to restore all services to full functionality.Delta Login, Openondemand and Scheduling.help@ncsa.illinois.edu

RESOLVED

2023-06-29 13162023-06-29 1530Most NCSA computer systemsPower fluctuations due to the severe weather have caused multiple system failures in all NCSA buildings. NCSA staff are working to restore all services to full functionality.

Virtually all systems have been impacted to some extent.

Most NCSA compute resources have returned to service.

help@ncsa.illinois.edu

RESOLVED

2023-06-21 18002023-06-21 1900DNS1 / DNS2 BIND security patchesDue to a security issue with BIND, neteng will be rebooting both DNS servers (staggered) starting tonight at 1800.  neteng@ncsa.illinois.edu

COMPLETE

2023-06-15 06002023-06-15 0605NCSA GitLabGitLab updated to use new backup methodAll GitLab services were unavailable for a few minutes.help@ncsa.illinois.edu

COMPLETE

2023-06-14 17002023-06-14 2200NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares were unavailable during maintenance.  Users were unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing was unavailable.help@ncsa.illinois.edu

COMPLETE

2023-06-08 11002023-06-08 1205ICI MetricsMajor Upgrade to Grafana 9.5.x and Unified AlertingAccess to https://metrics.ncsa.illinois.edu and all alerting was pausedmalone12@illinois.edu

COMPLETE

2023-06-07 13002023-06-07 1500NCSA KerberosDisabling Kerberos Host Principals not in DNSKerberos Authentication for hosts may stop working. Please create a ticket if you think your host principal may have been disabled erroneously. help@ncsa.illinois.edu

COMPLETE

2023-05-23 12402023-05-23 1410TaigaFailover events on tgio02I/O to and from Taiga for all services intermittently during this periodset@ncsa.illinois.edu

RESOLVED

2023-05-23 08002023-05-23 1400Granite Tape ArchiveUnplanned Library Maintenance due to component failureRetrieval of data;bdickin2@illinois.edu

RESOLVED

2023-05-18 08002023-05-18 1400Granite Tape ArchiveLibrary Preventative MaintenanceRetrieval of data;bdickin2@illinois.edu

COMPLETE

2023-05-17 07002023-05-17 2125NightingaleQuarterly Planned Maintenance

All Nightingale servers and services were unavailable (other than the ngale-bastion* nodes)

help@ncsa.illinois.edu

COMPLETE

2023-05-17 05302023-05-17 0600Wireless and VoIP (NCSA Building)Router UpgradesWireless, VoIP and anything directly connected to the campus switches will be down, while they upgrade firmware on the router.help+neteng@ncsa.illinois.edu

SCHEDULED

2023-05-16 07002023-05-16 1100HOLL-IQuarterly Planned Maintenanceall HOLL-I nodes and services were unavailablehelp@ncsa.illinois.edu

COMPLETE

2023-05-15 09002023-05-15 1200HOLL-ICS-2 CDU maintenancethe HOLL-I CS-2 was unavailable and there was a reservation in Slurmhelp@ncsa.illinois.edu

COMPLETE

2023-05-12 06002023-05-12 0615NCSA GitLabGitLab was updated to latest versionAll GitLab services was unavailable for a few minutes.help@ncsa.illinois.edu

COMPLETE

2023-05-11 0700

2023-05-11 1900

vForge / license serversQuarterly Planned Maintenance

all vForge nodes and services (and related license servers/services) will be unavailable

help@ncsa.illinois.edu

COMPLETE

2023-May-03 08002023-April-25 0900ACHE FW Cluster Upgrade - SecondaryUpgrading ACHE Firewall member BNo outage expectedeyrich@illinois.edu

COMPLETE

13:00

16:30

vSphere and hosts on it.VMWare Licensing issues. Was forced to migrate to new vSphere.LDAP, Wordpress Sites, varioushelp@ncsa.illinois.edu

COMPLETE

2023-05-01
1530
2023-05-01
1605
ICI VMwareApply updates to address software issue.
aloftus@ncsa.illinois.edu

COMPLETE

2023-April-26 08002023-April-25 0900ACHE FW Cluster Upgrade - primaryUpgrading ACHE Firewall member ANo outage expectedeyrich@illinois.edu

COMPLETE

2023-April-25 08002023-April-25 0900NPCF CWFM Cluster Upgrade secondaryUpgrading NPCF CW Firewall member BNo outage expectedeyrich@illinois.edu

COMPLETE

 

1700

 

1715

NCSA VPNThe certificate on the NCSA VPN was replaced.Users will be disconnected from the VPN and have to manually reconnect.neteng@ncsa.illinois.edu 

COMPLETE








2023-April-20 08002023-April-20 0900NPCF CWFM Cluster Upgrade primaryUpgrading NPCF CW Firewall member ANo outage expectedeyrich@illinois.eduCOMPLETE


2023-04-19 18002023-04-19 2300NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares were unavailable during maintenance.  Users were be unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing were unavailable.help@ncsa.illinois.edu

COMPLETE

  0800

  2000

DeltaHSN and OS is being updated,The entire system will be offline.kingda@illinois.edu

COMPLETE

04/17/23 090004/17/23 1400Granite Tape ArchiveUpgrades to FSIngest or retrieval of data;bdickin2@illinois.edu

COMPLETE

2023-03-27


2023-04-16NCSA OpenSource BitBucketincompatibility with git, only versions that can be installed are 2.25 or 2.40, and Bitbucket requires version 2.31 - 2.39
https://opensource.ncsa.illinois.edu/bitbucket is down until new version of BitBucket

Rob Kooper 

COMPLETED

2023-04-032023-04-04NCSAnet, IllinoisNet, EDUroamTech Services is deploying a new certificate for all wireless networks.Check #announce on NCSA Slack for more information, including links to download software that will update your wireless profiles. help+neteng@ncsa.illinois.edu

COMPLETE

2023-03-29 12:00 CDT2023-03-29 12:30 CDTPrimary Kerberos serverConfiguration changes to match secondary KDCsPassword changes may have been delayed by ten minutesChristopher Lindsey 

COMPLETE

2023-03-23 08432023-03-23 1030DHCP serving NCSAnet wireless and NCSA office wired wall jacksThe main NCSA DHCP server stopped answering queries and was restartedIf you didn't already have a DHCP lease your system would have been unable to connect to NCSAnet or register on an office wired wall jack.neteng@ncsa.illinois.edu

COMPLETE

2023-03-15 18002023-03-16 2300NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares were unavailable during maintenance.  Users were unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing was unavailable.help@ncsa.illinois.edu

COMPLETE

2023-03-14 11002023-03-14 1150Authentication to vsphere.ncsa.illinois.edu and ache-vcenter will failReplacing SSL certs on Ldap1/2Ldap will be restarted on Ldap1/2tbouvet@illinois.edu

COMPLETE

2023-03-09 0700

2023-03-09 17:20

vForge / license serversQuarterly Planned Maintenance

all nodes and services will be unavailable

help@ncsa.illinois.edu

COMPLETE


03/09/2023 0800

03/09/2023 1713NCSA Taiga & GraniteTaiga Service Node Updates & Granite UpgradeTaiga Public LNET router was upgraded and a second one added; access via public LNET was down from 0800 to 1100.  Globus and NFS services were patched in a rolling/online fashion.  

Granite experienced a short full downtime as we upgraded its software.  
set@ncsa.illinois.edu 

COMPLETE

03/07/2023 8:30am03/07/2023 10:15amDelta HSNThe HSN was dropping nodes and not allowing nodes to reconnectHigh Speed Connectivityhelp@ncsa.illinois.eduCOMPLETE
2023-03-01: 1100

2023-03-01: 1115

Radiant OpenStack ServicesChanges to the OpenStack controller node to address networking performance issues

All OpenStack services were restarted to effect system configuration changes. The work was completed successfully and all services are available again

help@ncsa.illinois.edu

COMPLETE

2023-02-25

2023-02-27 0930

NCSA email A mail loop caused routing and processing problems.Mail routing and delivery was blocked.help@ncsa.illinois.edu

COMPLETE

2023-02-21 0700

2023-02-21 1640

HOLL-IQuarterly Planned Maintenanceall nodes and services will be unavailablehelp@ncsa.illinois.edu

COMPLETE

2023-02-16 ~14:152023-02-16 ~14:25cerberus4mis-configuration caused roughly 50% of connections to be dropped50% of connections in and out droppedhelp+security@ncsa

COMPLETE

2023-02-10 09102023-02-10 0915users.ncsa.illinois.edu web siterestarting the systemno web pages from users.ncsa.illinois.edu will be available help@ncsa.illinois.edu

COMPLETE

02/08/2023 180002/09/2023 0000NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares were unavailable during maintenance.  Users were unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing was unavailable.help@ncsa.illinois.edu

COMPLETE

1215

1230

JiraJira will be restarted to fix stuck notification emails.Jira will unavailable during this time.

Andrew Loftus 

Also posted to #announce (Slack)

COMPLETE

 11:18

15:02

ICCP head node login and golub compute resourcesLost network connectivity for golub infrastructureICCP head node logins (ie cc-login.campuscluster.illinois.edu) and golub compute resources

help@campuscluster.illinois.edu

RESOLVED

1200

1300

JiraJira offline for service restart to fix stuck emails.Jira will unavailable during this time.help@ncsa.illinois.edu

COMPLETED

01/25/2023 0800

01/25/2023 0830

NCSA LDAProlling LDAP restarts of redundant servers to deploy new schema file

Minimal impact for service restarts

COMPLETED

2023-01-19 13102023-01-19 1330JiraJira offline for reboot to fix Boards.Jira will unavailable during this time.help@ncsa.illinois.edu

COMPLETE

  0800

1700

ICCPICCP Quarterly MaintenanceAll ICCP services

help@campuscluster.illinois.edu

RESOLVED

2023-01-13 12002023-01-13 1230JiraJira offline for dashboard fixes.Jira will unavailable during this time.help@ncsa.illinois.edu

COMPLETED

2023-01-12 08002023-01-13 1230JiraMinor issues noticed in Jira likely caused by the upgrade yesterday evening. Gadgets and dashboards are having issues.

RESOLVED

2023-01-11 07002023-01-12 1200NightingaleQuarterly Planned Maintenance

All Nightingale servers and services will be unavailable (other than the ngale-bastion* nodes)

Maintenance has been extended until noon Thu, Jan 12 due to complications with firmware update on the Lustre storage appliance.

help@ncsa.illinois.edu

COMPLETED

2023-01-12 07002023-01-12 0715NCSA VPN Router MigrationThe NCSA VPN was migrated to a different upstream router. Users were briefly disconnected. help+neteng@ncsa.illinois.edu

COMPLETED

  0600

  0615

NCSA GitLabGitLab upgradeAll GitLab services were unavailable for a few minutes while it upgraded to the latest version.

help@ncsa.illinois.edu

COMPLETED

06:40 1/9/20232023-01-11 2100vSphere in 3003One of the storage appliances serving vsphere.ncsa.uiuc.edu started access issues. This has caused issues with 19vms.

crashplan has returned to service

help@ncsa.illinois.eduCOMPLETED


2023-01-11 17302023-01-11 1915Jira Jira software upgradeJira will be unavailable while software upgrades are applied.help@ncsa.illinois.edu

COMPLETED

1/9/2023 6:40am1/11/2023 variousvSphere in 3003One of the storage appliances serving vsphere.ncsa.uiuc.edu had access issues.  Data was moved to different storage for affected VMs.digitalag.ncsa.illinois.edu, gecat, reu.ncsa.illinois.edu, ACIpartnership.org, astro, edream, caiiwp, brainstormhpcd.org, internal-dev, cmdb-dev-kimber7, reu-international.ncsa.illinois.edu, avl-test, mharp - ergo, infews-er.net, ncsa30, bluewaters - 2018-03-05.help@ncsa.illinois.edu

COMPLETED

12/23/2022 6:30pm12/27/2022 1:30pmTaigaSingle OST is failing to re-mount following failoverFile system is unavailableset@ncsa.illinois.edu

COMPLETED

 0530

 0600

Wireless at NCSA building.Router UpgradeTech Services will be upgrading their NCSA building router which will effect wireless at the NCSA building.  Downtime will be estimated at 15 mins. help+neteng@ncsa.illinois.edu

COMPLETED

0800

1200

RadiantSystem maintenance

OpenStack:

  • "Minor system configuration changes will be made to increase system logging and optimize memory usage/allocation across nodes. No noticeable impact to end users is expected."

Networking:
  • Swap fiber links to correct issue with security taps: In order to minimize user impact, we will swap one link at a time. User should see no impact however there is a slight possibility of a temporary network outage potentially lasting a few minutes however we currently do not anticipate this happening.
  • Update Ethernet switch firmware: Switch reboots will be done in a rolling fashion and so are not expected to be disruptive to ongoing operations (due to switch/path redundancy).
help@ncsa.illinois.edu

COMPLETED

15 Dec 2022 090015 Dec 2022 0935NCSA KerberosNCSA's Read-Write KDC is being upgradedPassword changes and new accounts are being queued for completion after the upgrade.help@ncsa.illnois.edu

COMPLETED

  0600

  0615

NCSA GitLabGitLab was upgraded to latest versionAll GitLab services was unavailable for a few minutes.

help@ncsa.illinois.edu

COMPLETED

12-01-2022 060012-01-2022 0700NCSA VPNSoftware UpgradesThe appliances hosting the NCSA VPN were patched. Users experienced a brief disconnect as load is failed over between the appliances. The anyconnect client was upgraded at this timeneteng@ncsa.illinois.edu

RESOLVED

1130

1400

NCSA identity password resetsThe password reset process is not completing.Users password resets were queued and then applied when the issue was fixed.  Users who tried to change their password should find there password is now set to the password of their last attempt.help@ncsa.illinois.edu

RESOLVED

 

 

capnjack (license server)Changes to IPTABLESUnknown servers. Licenses affected are IDL, PGI, Intel, MATLAB, Abaqus, Sention LM, Luda, Ansys, CDL, Adaptive, Converge, CFD, RLM Type, rr_ld

meberger@illinois.edu

re: SVCPLAN-1465

COMPLETED

2022-11-16 10422022-11-16 1351CILogonDocker Swarm failureCILogon services were unavailable. See: https://cilogon.statuspage.io/incidents/2blf564965s0help@cilogon.org

RESOLVED

2022-11-15 07002022-11-15 1700HOLL-IQuarterly Planned Maintenanceall nodes and services will be unavailablehelp@ncsa.illinois.edu

COMPLETED

2022-11-10 0700

2022-11-10 1200

vForge / license serversQuarterly Planned Maintenance

all nodes and services will be unavailable

help@ncsa.illinois.edu

COMPLETED

2022-11-10 11:002022-11-10 11:50ASD Vsphere, specifically vm's using the tintri storage appliance.Network connections were upgraded to 25G speed.There was no disruption of service with this work.help@ncsa.illinois.edu

COMPLETED

2022-11-07 09002022-11-07 0958set-analytics.ncsa.illinois.eduPhysical Machine Move from 3003 to NPCFThe SET managed Grafana/InfluxDB instance will be unavailableset@ncsa.illinois.edu

COMPLETED

2022-11-04 19002022-11-04 1930SET TaigaSET  caused a failover of tgio02 and then failed back.  This fixed the mounting issue.Clients with taiga currently mounted may experience slow or stopped IO during the failover.  Failover completed properly and solved the mounting issue.set@ncsa.illinois.edu

COMPLETED

2022-11-03 11322022-11-04 1930Delta

Taiga filesystem (/taiga/ and /projects/) problem on dt-login01 and dt-login02

The issue is limited to dt-login01 and dt-login02. Commands attempting to access /taiga/ or /projects/ on these nodes will hang.

Users are advised to use dt-login03 or the login.delta.ncsa.illinois.edu "round robin" address

UPDATE: dt-login01 and dt-login02 are fully functional again and back in the login.delta.ncsa.illinois.edu DNS "round robin".

help@ncsa.illinois.edu

COMPLETED

2022-11-03 00482022-11-03 0106SET Taigatgio02 and tgio04 failed overOSTs on the two nodes were inaccessible until the reboots were complete. This is a known issue with a vendor patch in progress. set@ncsa.illinois.eduCOMPLETED


2022-11-03 06002022-11-03 0615NCSA GitLabGitLab was upgraded to latest versionAll GitLab services was unavailable for a few minutes.

help@ncsa.illinois.edu

COMPLETED

2022-11-02 17002022-11-02 2000DNS ServicesPatching for out of cycle security updates.DNS1 and DNS2 will be patched and rebooted (staggered) to applied needed updates.help+neteng@ncsa.illinois.edu

COMPLETED

2022-11-01 18002022-11-02 0000NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares were unavailable during maintenance.  Users were unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing was unavailable.help@ncsa.illinois.edu

COMPLETED

0800

0830

idp.ncsa.illinois.eduEnable Duo Universal PromptNCSA Identity Provider will now use Duo Universal Prompthelp+idp@ncsa.illinois.edu

COMPLETED

2022-10-25 08002022-10-25 0900NCSA building 1st Floor Wifi / Security CamerasTech Services is replacing a networking switch on the 1st for of the NCSA building that powers the Access Points on the first floor.This should be a short down time, but the access points will reboot while we migrate cables to the new switch.  help+neteng@ncsa.illinois.edu

COMPLETED

2022-10-19 07:002022-10-20 07:15Some SSH Bastion HostsOut-of-Cycle reboot needed after failed patching.
Will reboot tomorrow at 07:00am
bwbh1.ncsa.illinois.edu
bwbh3.ncsa.illinois.edu
cerberus1.ncsa.illinois.edu
cerberus3.ncsa.illinois.edu
ache-bastion-1.ncsa.illinois.edu
ngale-bastion-1.ncsa.illinois.edu
help+security@ncsa.illinois.edu

COMPLETED

2022-10-18 15:002022-10-18 15:30Radiant instance creation/managementsystem setting changesNo noticeable impactpl@illinois.edu

COMPLETE

2022-10-18 12:002022-10-18 12:05identity, email to NCSA addressessystem updates 1 minute window to cause email delays and identity frontend unavailablecpl@illinois.edu

COMPLETE

2022-10-14 22002022-10-15NCSA office firewall upgradeUpgrading code on the office firewall.Office networks will be offline during this upgrade.help+neteng@ncsa.illinois.edu

COMPLETE

2022-10-13 17002022-10-13 1800SSLVPN MaintenanceThe second member of the HA pair will be put back into service.The second member was added with no outage.help+neteng@ncsa.illinois.edu

COMPLETE

2022-10-12 11:002022-10-12 12:00ASD Vsphere, specifically vm's using the tintri storage appliance.Network connection on tintri storage box were switch to new hardware but their speed was unchanged. Additional work will need to be scheduled to complete the speed increase.This had no service impact.help@ncsa.illinois.edu

INCOMPLETE

2022-10-10 00002022-10-10 1040NCSA VPNThe NCSA VPN had a member of the HA pair fail and licensing didn't fail over. Users were unable to connect to the VPN until the licensing issue was resolved.help+neteng@ncsa.illinois.edu

COMPLETE

2022-10-03 08002022-10-03 0845HOLL-Iinstall security updates and reboot
help@ncsa.illinois.edu

COMPLETE

2022-09-30 06002022-09-30 0615NCSA GitLabGitLab was upgraded to latest versionAll GitLab services were unavailable for a few minutes.

help@ncsa.illinois.edu

COMPLETE

2022-09-27 11002022-09-28 1700odd numbered bastion hosts (cerberus1, cerberus3, ache-bastion-1, ngale-bastion-1, etc.)puppet code refactoring for SSH configs

More changes were pushed out around 5p on 2022-09-28 and we believe the SSHD config issues are resolved.  You can use the even numbered (cerberus2, cerebrus4) bastions as a work-around if any issues persist.

help+security@ncsa.illinois.eduRESOLVED


2022-09-28 09302022-09-28 1050Jira outgoing emailoutgoing email degradedJira failed to send some/most outgoing email during this time frame.help@ncsa.illinois.edu

RESOLVED

2022-09-24 14452022-09-25 1045GraniteBuilding power outage caused Disk Storage Unit to power cycleAny user operations on the cluster were interrupted and unavailable until resolution.bdickin2@illinois.edu

COMPLETE

2022-09-21 08002022-09-21 0930HOLL-IChange CS-2 execution mode to PipelinedExecution mode of the CS-2 was changed from Weight Streaming to Piplined.help@ncsa.illinois.edu

COMPLETE

2022-09-08 08002022-09-10 1100GraniteGranite Bi-annual Maintenance (now back in service)Any ingest or retrieval to/from the Archivebdickin2@illinois.edu  slack-id: briandi
set@ncsa.illinois.edu 

COMPLETE

2022-09-09 09432022-09-09 1457Jiraoutgoing email degradedJira failed to send some/most outgoing email during this time frame.help@ncsa.illinois.edu

COMPLETE

2022-09-08
0700

2022-09-08 1010: license servers

2022-09-09
0230: vForge

vForge / license serversQuarterly Planned Maintenance

all nodes and services will be unavailable

help@ncsa.illinois.edu

COMPLETE

 

0500

0600

ASD VM services netRouting in the switch stacks is being swiched from NCSA 3003 to NPCFAll systems on the 141.142.192.x network will be unreachable for up to 5 minutes.help@ncsa.illinois.edu

COMPLETE

2022-08-31 18002022-09-01 0700NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares were be unavailable during maintenance.  Users were unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing was unavailable.help@ncsa.illinois.edu

COMPLETE

1730

1830

JiraJira service will be restartedJira will not be availablehelp@ncsa.illinois.edu

COMPLETE

08-24-22 183008-26-22 0800Granite Tape ArchiveFS crash and lockupA few files that were transferred into the archive shortly before the crash needed to be re-transferred.

bdickin2@illinois.edu  slack-id: briandi
set@ncsa.illinois.edu 


COMPLETE

2022-08-17
1200
n/aAll LSST hosts at NCSAServers will be shutoff and retired.All LSST servers and services at NCSA.lsst-admin@ncsa.illinois.edu

COMPLETE

2022-08-17 07002022-08-17 1320NightingaleQuarterly Planned MaintenanceAll Nightingale servers and services will be unavailable (other than the ngale-bastion* nodes)help@ncsa.illinois.edu

COMPLETE

2022-08-16 0700

2022-08-17 1305

HOLL-IQuarterly Planned Maintenance

All HOLL-I servers and services will be unavailable

2022-08-16 1505 - HOLL-I cluster return to service, but CS-2 remains offline for further work; CS-2 expected return to service by 2022-08-17 1000

2022-08-17 1305 - HOLL-I CS-2 is returned to service

help@ncsa.illinois.edu

COMPLETE

2022-08-09 20002022-08-09 2300Office Networks on 2nd FloorCode updates on office network switches.Office ports will be offline as switches reboot. help+neteng@ncsa.illinois.edu

COMPLETE

2022-08-10 20002022-08-10 2300Office Networks on 3rd FloorCode updates on office network switches.Office ports will be offline as switches reboot. help+neteng@ncsa.illinois.edu

COMPLETE

2022-08-11 20002022-08-11 2300Office Networks on 4th FloorCode updates on office network switches.Office ports will be offline as switches reboot. help+neteng@ncsa.illinois.edu

COMPLETE

2022-08-03
0900
2022-08-03
1000
NPCF Center-wide management firewallsSecondary firewall will be upgradedNo impact to services is anticipated.  Traffic will flow normally through the primary firewall as the secondary is upgraded.help+security@ncsa.illinois.edu

COMPLETE

2022-07-27
0940
2022-07-28
15:36
ACHE, Nightingale Several accounts have had their Covered Entity status revokedAffected users/accounts will not be able to access resources that requires Covered Entity enrollment 

help+hippa@ncsa.illinois.edu

RESOLVED

2022-07-27
0900
2022-07-27
1000
NPCF Center-wide management firewallsPrimary firewall will be upgradedNo impact to services is anticipated.  Traffic will be failed over to the secondary firewall, the primary will be updated, and then traffic will be moved back to the primary.help+security@ncsa.illinois.edu

COMPLETE

0900

0915

JiraAdditional LDAP group will be added for exclusion to sync with LDAP users.In theory, nothing.help@ncsa.illinois.edu

COMPLETE

0800

  2000

ICCICC Quarterly MaintenanceAll ICC services

help@campuscluster.illinois.edu

COMPLETE

2022-07-19 07002022-07-19 0900RadiantVictoria UpdateMinimally disruptive, brief interruptions to OpenStack services, such as the Horizon dashboardradiant-admin@ncsa.illinois.edu

COMPLETE

2022-07-14
2345
2022-07-14
2359
WikiThe service will be restarted in order to increase the login timeout.Wiki will be unavailable for about 5 mins while it restarts.

COMPLETE

2022-07-08
1700
2022-07-11
0800
LSST hosts in NCSA 3003Due to a full building power outage at NCSA on Sunday, 10 July, some LSST servers will be unavailable over the weekend. Servers will be shutdown at COB on Friday and returned to service on Monday morning.lsst-dbb-fts1
lsst-dbb-rucio
lsst-demo
lsst-dm-monitor
lsst-int-monitor
lsst-mon-dev
lsst-pup
lsst-test5
lsst-xfer
l1-cl-arctl
l1-cl-fault
l1-cl-header
nts-ccamfwdr1
nts-acamfwdr2
nts-acamfwdr1
lsst-admin@ncsa.illinois.edu

COMPLETE

2022-07-11 08:302-22-07-11 9:30All ITSM (CMDB) VMsAll ITSM VMs are currently down. Ticket has been created to get them brought back up.Production CMDB service (openDCIM) is not availablekimber7@illinois.edu

RESOLVED

2022-07-10 0700

2022-07-10 1430

NCSA building powerBuilding power feed work for multiple campus BuildingsAVL, LSST, ISL and Software standard services were down from Friday afternoon until Monday morning.Daniel Lapine 

COMPLETE

2022-07-8

1600

2022-07-11

0900

cerberus2 and cerberus4Campus is doing work on a common feed that affects multiple buildings, include the NCSA Building. Work is scheduled from 0700-1700, but may finish earlyVM hosts running these 2 bastions will be down for the weekend due to the scheduled power work at NCSAhelp+security@ncsa.illinois.edu

COMPLETE

2022-07-06 17302022-07-06 2030Wiki (wiki.ncsa.illinois.edu)Confluence and MySQL upgradeswiki will be down during the upgrade

COMPLETE

2022-07-05 18002022-07-05 2130NCSA File & Print ServersScheduled Windows Server MaintenanceFile & Print Shares were unavailable during maintenance.  Users were unable to access shares on Fileserver (e.g. home, busnoff, hr, etc.), and printing was unavailable.help@ncsa.illinois.edu

COMPLETE

2022-07-05 1800N/AiForgeend of serviceiForge was removed from service. Operations have moved to the new vForge virtual cluster.help+industry@ncsa.illinois.edu

RESOLVED

Legend:

IN PROGRESS

COMPLETE

RESOLVED

SCHEDULED

MONITORING