FAS Research Computing - Lịch sử thông báo

NOTICES

• GPUTEST and REMOTEVIZ PARTITIONS Due to failed nodes, the gputest partition is down to 2 nodes and the (single node) remoteviz partition is down at the moment. We are working with the vendor to replace hardware, but this is still unresolved and no ETA at this time. Updates and QoS changes on our status page when we have them:https://status.rc.fas.harvard.edu/cl8a94kcf17664hvoj8oksxanx

• GLOBUS PERSONAL CLIENT - UPDATE BY DEC 17 If you are using the Globus Connect Personal client on your machine, please ensure you have updated and are running version 3.2 or greater by December 17th, 2022. You will not be able to use version 3.1 or below after that date. https://docs.globus.org/ca-update-2022/#globusconnectpersonal

• TRAINING New training sessions, including monthly new user training, are available. You can find a list and links to sign up here: https://www.rc.fas.harvard.edu/upcoming-training/

• NERC informs us that they will be performing maintenance on Nov 2nd from 8am-12pm. If you use NERC's services, you can find more information on their status page: https://nerc.instatus.com/

FASRC REGULAR MAINTENANCE

• Network maintenance - HIGH IMPACT POSSIBLE -- Audience: All users -- Impact: Network maintenance will take place during this time and is expected to run the full 4 hours. Work on the firewalls and fibre links will be involved, so impact may be felt across both data centers.

• Samba admin node reboots -- Audience: All users of Samba (desktop) mounts -- Impact: Impact is expected to be transparent or minimal. Active Samba mounts could be affected but only briefly and should recover on their own.

• Globus update -- Audience: All users of Globus -- Impact: Globus may be unavailable for short periods.

• Domain Controller Updates -- Audience: All users -- Impact: Minimal impact is expected.

• Login node and VDI node reboots -- Audience: Anyone logged into a a login node or VDI/OOD node -- Impact: Login and VDI/OOD nodes will be unavailable while updating and rebooting

• Scratch cleanup ( https://docs.rc.fas.harvard.edu/kb/policy-scratch/ ) -- Audience: Cluster users -- Impact: Files older than 90 days will be removed. -- Reminder: Scratch 90-day file retention purging runs occur regularly not just during maintenance periods.

Thanks, FAS Research Computing Department and Service Catalog: https://www.rc.fas.harvard.edu/ Documentation: https://docs.rc.fas.harvard.edu/ Status Page: https://status.rc.fas.harvard.edu/

FIBRE UPDATE As part of the 100Gb link upgrade, networking maintenance will occur at the MGHPCC/Holyoke data center Tuesday Oct 4th, 200 starting at 7PM. They are setting aside a two hour window for this.

Any interruption should be very brief. However, as always the possibility does exist for knock-on issues. We will post any updates here and FASRC staff will be monitoring for any related issues.

FASRC regular monthly maintenance will occur on Monday October 3rd, 2022 from 7am-11am. https://www.rc.fas.harvard.edu/monthly-maintenance IMPORTANT: There are several important notices below.

NETWORK MAINTENANCE TUES 9/27 6pm-8pm

Network maintenance on the MGHPCC/Holyoke fibre links and VPN will take place Tuesday Sept. 27th from 6pm until 8 pm.

• VPN updates will occur during 6pm-7pm VPN connections may drop during this time.
• Maintenance on the fibre links will take place 7pm-8pm. Brief disconnects may occur, especially with login and access nodes.
• See maintenance event: https://status.rc.fas.harvard.edu/cl898lt5b25823hkojo3eslk1x

NOTICES

GPU_TEST and REMOTEVIZ PARTITIONS

Due to failed nodes, the gpu_test partition is down to 2 nodes at the moment. We are working with the vendor to revive these nodes, but no ETA at this time. We are also investigating the root cause for multiple failures.  

• We had already planned to modify the QoS (job limitations) on the gputest partition due to misuse of the partition, but the failures forced us to implement this yesterday.   Going forward, gputest is limited to 1 job per user. That job is limited to a maximum 16 cores, 90GB memory, and 1 GPU.

• Please note: gputest should not be used to avoid the GPU queues and scheduling. See Running Jobs (https://docs.rc.fas.harvard.edu/kb/running-jobs/#Slurmpartitions) for a list of available partitions, including the gpu partition(s).

• The remoteviz node/partition is also down for the same reason. The remoteviz partition is only one node, QoS remains the same.  

Updates on our status page:  https://status.rc.fas.harvard.edu/cl8a94kcf17664hvoj8oksxanx

GLOBUS PERSONAL CLIENT - UPDATE BY DEC 17

• If you are using the Globus Connect Personal client on your machine, please ensure you have updated and are running version 3.2 or greater by December 17th, 2022. You will not be able to use version 3.1 or below after that date. https://docs.globus.org/ca-update-2022/#globusconnectpersonal

TRAINING

• New training sessions, including monthly new user training, are available.   You can find a list and links to sign up here: https://www.rc.fas.harvard.edu/upcoming-training/

REGULAR MAINTENANCE

• Login node and VDI node reboots
  -- Audience: Anyone logged into a a login node or VDI/OOD node
  -- Impact: Login and VDI/OOD nodes will be unavailable while updating and rebooting
   
• Scratch cleanup ( https://docs.rc.fas.harvard.edu/kb/policy-scratch/ )
  -- Audience: Cluster users
  -- Impact: Files older than 90 days will be removed.
  -- Reminder: Scratch 90-day file retention purging runs occur regularly not just during maintenance periods.

Thanks!
FAS Research Computing
https://www.rc.fas.harvard.edu
https://status.rc.fas.harvard.edu

VPN UPDATE This maintenance has been extended to accommodate an VPN update from 6-7PM. The FASRC VPN will deprecate older, less-secure ciphers. VPN connections could drop during this update.

FIBRE UPDATE As part of the 100Gb link upgrade, networking maintenance will occur at the MGHPCC/Holyoke data center Tuesday Sept 27, 200 starting at 7PM. We are setting aside one hour for this but, barring any issues, the updates should not take that long.

Any interruption should be very brief. However, as always the possibility does exist for knock-on issues. We will post any updates here and FASRC staff will be monitoring for any related issues.