Log Request | Search

NSCC Service Status

Scheduled Maintenance [Completed]

2019-06-12 12:45 – ASPIRE 1 maintenance completed and users can log in now

2019-06-11 12:00 – Maintenance works in progress, including update of PBS and Lustre. The next update will be on 12 June 12:00 unless there are any extenuating issues

2019-06-10 12:00 – Maintenance works in progress, including update of PBS and Lustre. The next update will be on 11 June 12:00 unless there are any extenuating issues.

2019-06-09 13:00 – Commencing maintenance works. The next update will be on 10 June 12:00 unless there are any extenuating issues.

2019-06-08 16:00 – Power restored to the data centre.

2019-06-07 20:20 – System shutdown completed. The next update is expected to be on 9 June 13:00 when power is restored to the data centre.

2019-06-07 15:00 – All users logged out, commencing shutdown operations.

ASPIRE 1 Scheduled Maintenance from 7 June to 12 June 2019

The building owners, JTC, have planned the annual power shutdown of the Fusionopolis building on 7 June 2019. As such the ASPIRE 1 system will be affected and will be shut down from 7 June 2019 (Friday), 3:00pm  to 12 June 2019 (Wednesday), 12:00pm.

We are also taking this opportunity to extend the shutdown period to carry out critical works to the data centre and to ASPIRE 1 itself. Please note that this shutdown exercise is longer than usual. Details of the shutdown maintenance can be found below.

IMPORTANT 

In preparation for the power shutdown, please take note of the following dates and times:

1.     2 June 2019 (Sunday), 3pm:

  • All long queues will stop dispatching jobs from the above date and time till the end of the shutdown. This is to ensure jobs do not get terminated during the shutdown period.
  • Jobs which can be completed before the shutdown may still be dispatched manually, subject to the availability of resources.

2.     6 June 2019 (Thursday), 3pm: 

  • Normal queues will stop dispatching jobs.
  • Jobs which can be completed before the shutdown may still be dispatched manually, subject to the availability of resources.

3.     7 June 2019 (Friday), 3pm: 

  • All users will be logged out of the system.
  • All remaining running jobs will be allowed to terminate gracefully before the system shuts down.

4.     10 June 2019 (Monday), 9am

  • ​We will also be upgrading AMS (i.e Allocation Management System)However with this upgrade all jobs that have not been dispatched may be lost. Please check your jobs and resubmit them if required.  

5.     12 June 2019 (Wednesday), 12pm: 

  • ASPIRE 1 system will be brought back online and made available to users.

Shutdown and Maintenance Details –

The following activities will be carried out during the shutdown period from 7 June (Friday), 3pm to 12 June (Wednesday), 12pm:
1. JTC will be carrying out annual maintenance works to the electrical supply of the entire Fusionopolis building as mandated by law
2. NSCC will be replacing all the circuit breakers in the data centre. This is an added safety measure to reduce the likelihood of short circuits in the data centre.
3. NSCC will be upgrading Lustre (i.e the scratch file system) from version 2.07 to version 2.10. The new version of Lustre will address any potential compatibility issues.
4. NSCC will be upgrading the allocation management system (AMS) component of PBS. With this upgrade the occasional qstat or qsub timeout issues encountered should be mitigated. However, all jobs which have not been dispatched may be lost.

NSCC VPN Maintenance Scheduled on 11 May 2019 [Completed]

Please be informed that there will be an urgent maintenance to the NSCC VPN scheduled on 11 May  2019 (Saturday), from 10am to 4pm.

During this period, users logging in via NSCC VPN at https://vpn.nscc.sg may experience intermittent service disruption. Users logging in from A*STAR, NUS, NTU and SUTD will not be affected.

Scheduled Maintenance [Completed]

2018-12-28 12:00 – Inspection of hardware has been completed.

2018-12-26 14:00 – 95% of hardware has been inspected and released for use

2018-12-21 12:05 – 75% of hardware has been inspected and released for use

2018-12-20 12:05 – 60% of hardware has been inspected and released for use

2018-12-19 12:05 – 50% of hardware has been inspected and released for use

2018-12-18 12:05 – 45% of hardware has been inspected and released for use

2018-12-17 13:00 – ASPIRE 1 maintenance completed and users can log in now. 40% of hardware has been inspected and released for use

2018-12-16 23:39 – Maintenance of system completed. Hardware inspection is still working in progress

2018-12-16 09:00 – Hardware inspection started

2018-12-14 16:56 – Maintenance of system initiated

2018-12-14 16:23 – System shutdown completed

2018-12-14 15:27 – System shutdown initiated

2018-12-14 15:05 – Log out all users

Maintenance Window: 2018-12-14 (Fri) 15:00 to 2018-12-17 (Mon) 12:00
Services Affected : ASPIRE 1 System maintenance [Completed]

Please take note of the important timelines below that will impact your work:

  • 9 December 2018 (Sunday), 15:00– All long queues will stop dispatching jobs. This is to ensure jobs do not get terminated during the shutdown period. Jobs which can complete before the shutdown may still be dispatched manually, subject to the availability of resources.
  • 13 December 2018 (Thursday), 15:00– Normal queues will stop dispatching jobs. Jobs which can complete before the shutdown may still be dispatched manually, subject to the availability of resources.
  • 14 December 2018 (Friday), 15:00– All users will be logged out of the system. All remaining running jobs will be allowed to terminate gracefully before the system shuts down.
  • 17 December 2018 (Monday), 12:00– the system will be brought online and released to users.

Service Restoration [Completed]

2018-09-26 20:10 – We are pleased to inform you that the ASPIRE 1 system has been brought back online. You may log in to the system. We thank you for your patience and kind understanding.

2018-09-26 16:15 – We are still working in progress to bring up the ASPIRE 1 system.

2018-09-26 12:05 – We are still working in progress to bring up the ASPIRE 1 system.

2018-09-25 12:20 – The chilled water supply has been restored. We are working to bring up ASPIRE 1 system now.

2018-09-24 21:00 – The building management team is still working to restore the chilled water supply. Once it is properly restored, we will begin to power up ASPIRE 1 system.

2018-09-24 10:00 – The building management team is still working to restore the chilled water supply floor by floor. We are expecting further delays as we will only be able to power up the system after our chilled water supply is restored.

2018-09-23 12:35 – The building management team has advised us that the burst water pipe has also affected our power supply. We expect to have our power restored only tomorrow at the earliest.

2018-09-23 06:35 – System shutdown completed

2018-09-23 05:31 – System shutdown initiated

2018-09-23 05:15 – Log in Nodes not available

Service Notification [Completed]

Dear ASPIRE 1 Users, The chilled water pipe in Fusionopolis has burst, and our data centre is affected. Therefore we have shut down the supercomputer and all associated services to prevent it from damage.Unfortunately all running jobs will be lost. Jobs that are still in queue should not be affected though.

We will update you as we have any developments. In the meantime you can refer to https://status.nscc.sg for the latest information.

Please accept our apologies for any inconvenience caused.

Scheduled Maintenance [Completed]

2018-06-08 15:00 – Log out all users

2018-06-08 16:00 – Start: upgrade HCA, OFED

2018-06-08 17:30 – Start: upgrade File System Servers OS

2018-06-08 21:00 – Complete: upgrade HCA, OFED

2018-06-09 09:00 – Start: upgrade NTU/NUS DWDM PacketLight

2018-06-09 09:00 – Start: upgrade Compute Nodes BIOS

2018-06-09 13:50 – Complete: upgrade NTU/NUS DWDM PacketLight

2018-06-10 22:00 – Complete: upgrade Compute Nodes BIOS

2018-06-10 22:00 – Complete: upgrade File System Servers OS

2018-06-10 22:00 – Services Verification

2018-06-11 12:30 – Complete: ASPIRE 1 maintenance and users can log in now

Scheduled Maintenance [Completed]

Maintenance Window: 2018-06-08 (Fri) 15:00 to 2018-06-11 12:00
Services Affected : ASPIRE 1 System maintenance

Please take note of the important timelines below that may impact your work:

  • 2018-06-03 (Sunday), 15:00 – All long queues will stop dispatching jobs. This is to ensure jobs do not get terminated during the maintenance period. Jobs which can complete before the maintenance may still be dispatched manually, subject to the availability of resources.
  • 2018-06-07 (Thursday), 15:00 – Normal queues will stop dispatching jobs.
  • 2018-06-08 (Friday), 15:00 – All users will be logged out of the system. All remaining running jobs will be allowed to terminate gracefully before the system maintenance begins.
  • 2018-06-11 (Monday), 12:00 – System will be brought online and released to users.

Please contact us at [email protected] if you have any questions.


Back to Top