FAS Research Computing - Historique des incidents

Holyoke Tier 2 NFS connaît une panne partielle

Status page for the Harvard FAS Research Computing cluster and other resources.

Cluster Utilization (VPN and FASRC login required): Cannon | FASSE


Please scroll down to see details on any Incidents or maintenance notices.
Monthly maintenance occurs on the first Monday of the month (except holidays).

GETTING HELP
Documentation: https://docs.rc.fas.harvard.edu | Account Portal https://portal.rc.fas.harvard.edu
Email: rchelp@rc.fas.harvard.edu | Support Hours

The colors shown in the bars below were chosen to increase visibility for color-blind visitors.
For higher contrast, switch to light mode at the bottom of this page if the background is dark and colors are muted.
Opérationnel

SLURM Scheduler - Cannon - Opérationnel

Cannon Compute Cluster (Holyoke) - Opérationnel

Boston Compute Nodes - Opérationnel

GPU nodes (Holyoke) - Opérationnel

seas_compute - Opérationnel

Opérationnel

SLURM Scheduler - FASSE - Opérationnel

FASSE Compute Cluster (Holyoke) - Opérationnel

Opérationnel

Kempner Cluster CPU - Opérationnel

Kempner Cluster GPU - Opérationnel

Opérationnel

FASSE login nodes - Opérationnel

Opérationnel

Cannon Open OnDemand - Opérationnel

FASSE Open OnDemand - Opérationnel

Panne partielle

Netscratch (Global Scratch) - Opérationnel

Home Directory Storage - Boston - Opérationnel

Tape - (Tier 3) - Opérationnel

Holylabs - Opérationnel

Isilon Storage Holyoke (Tier 1) - Opérationnel

Holystore01 (Tier 0) - Opérationnel

HolyLFS04 (Tier 0) - Opérationnel

HolyLFS05 (Tier 0) - Opérationnel

HolyLFS06 (Tier 0) - Opérationnel

Holyoke Tier 2 NFS - Panne partielle

Holyoke Specialty Storage - Opérationnel

holECS - Opérationnel

Isilon Storage Boston (Tier 1) - Opérationnel

BosLFS02 (Tier 0) - Opérationnel

Boston Tier 2 NFS - Opérationnel

CEPH Storage Boston (Tier 2) - Opérationnel

Boston Specialty Storage - Opérationnel

bosECS - Opérationnel

Samba Cluster - Opérationnel

Globus Data Transfer - Opérationnel

Historique des incidents

juin 2022

Globus.org maintenance Saturday June 18, 9am-10am
  • Terminé
    juin 18, 2022 à 14:00UTC
    Terminé
    juin 18, 2022 à 14:00UTC

    Maintenance has completed successfully

  • Mettre à jour
    juin 18, 2022 à 13:00UTC
    Mettre à jour
    juin 18, 2022 à 13:00UTC

    Maintenance is now in progress

  • En cours
    juin 18, 2022 à 13:00UTC
    En cours
    juin 18, 2022 à 13:00UTC

    Maintenance is now in progress

  • Pas encore commencé
    juin 18, 2022 à 13:00UTC
    Pas encore commencé
    juin 18, 2022 à 13:00UTC

    Globus has informed us that they will be performing maintenance Saturday June 18th 9am-10am

    ``` During the downtime, the following will be impacted:

    • All services in the Globus ecosystem that use Auth, including Flows, Search, and Timer, will be unavailable.
    • Users will be unable to initiate new transfers. Transfers that are inflight when the downtime begins will resume at the last checkpoint when the services are restored at the end of the maintenance period.
    • Users will not be able to log into applications that rely on Globus Auth, including Globus webapp and command line interface.
    • All third party applications and services that rely on Globus Auth will be impacted, and users will not be able to login/authenticate.
    • Users will be unable to initiate new flow runs. Flow runs that attempt to start a new step during the downtime will fail. We recommend that users check the state of their flow runs after services have resumed. ```
CVMFS not available from login nodes
  • Résolu
    UTC
    Résolu

    This issue is currently not fixable on the login nodes. CVMFS can still be used on compute, but not login nodes. We are in contact with OSG and if there is a workaround later we will implement it. As a result, this incident is now closed.

  • Détecté
    UTC
    Détecté

    CVMFS is available from compute nodes, but not from login nodes. This will only impact users who need this filesystem (OpenScienceGrid).

    We will investigate this incident further next week.

Websites & Tools - SPINAL (FAS Informatics) isn't accessible at the moment (automated)
  • Résolu
    UTC
    Résolu

    Websites & Tools - SPINAL (FAS Informatics) is now operational! This update was created by an automated monitoring service.

  • Détecté
    UTC
    Détecté

    Websites & Tools - SPINAL (FAS Informatics) cannot be accessed at the moment. This incident was created by an automated monitoring service.

Portal approval emails
  • Résolu
    UTC
    Résolu

    A problem with the outgoing mail system the Portal uses to send approval and account emails has been found and fixed.

    You may be receiving late notices now. If you receive approval emails and find nothing to approve when following the link, this is why. Apologies for the inconvenience. Additional monitoring is being put into place.

ECS certificate issues
  • Résolu
    UTC
    Résolu

    This issue with the ECS has been resolved.

  • Identifié
    UTC
    Identifié

    We are looking at a certificate issue with bosecs and holyecs. Replacement certs should be available to us shortly.

mai 2022

Websites & Tools - FASRC Documentation (docs.rc) isn't accessible at the moment (automated)
  • Résolu
    UTC
    Résolu

    Websites & Tools - FASRC Documentation (docs.rc) is now operational! This update was created by an automated monitoring service.

  • Détecté
    UTC
    Détecté

    Websites & Tools - FASRC Documentation (docs.rc) cannot be accessed at the moment. This incident was created by an automated monitoring service.

MGHPCC/Holyoke May 2022 power downtime
  • Terminé
    mai 26, 2022 à 15:49UTC
    Terminé
    mai 26, 2022 à 15:49UTC

    Data center maintenance has completed successfully. The cluster and all resources are back in service.

  • En cours
    mai 23, 2022 à 22:00UTC
    En cours
    mai 23, 2022 à 22:00UTC

    Maintenance is now in progress

  • Pas encore commencé
    mai 23, 2022 à 22:00UTC
    Pas encore commencé
    mai 23, 2022 à 22:00UTC

    The annual MGHPCC data center power shutdown will occur from 6pm May 23 - noon May26

    • Power-down of the cluster will begin at 6PM on May 23rd
    • Power will be out that night and through the following day, May 24th
    • Maintenance to FASRC infrastructure will occur on May 25th
    • Power-up ETA and return to service is noon on May 26th

    While this outage impacts all services and resources in the MGHPCC/Holyoke data center, please be aware that this can have a knock-on effect for some Boston services as well.

    LOGIN & VDI Boston and Holyoke login, and VDI will be affected for the duration of the downtime.

    OFFICE HOURS Office hours will not be held on Wednesday May 25th.

    BOSTON DATA CENTER Boston storage may be affected at various times on May 25th. Any additional Boston outages will be noted here.

Websites & Tools - MiniLIMs (FAS Informatics) isn't accessible at the moment (automated)
  • Résolu
    UTC
    Résolu

    Websites & Tools - MiniLIMs (FAS Informatics) is now operational! This update was created by an automated monitoring service.

  • Détecté
    UTC
    Détecté

    Websites & Tools - MiniLIMs (FAS Informatics) cannot be accessed at the moment. This incident was created by an automated monitoring service.

Websites & Tools - SPINAL (FAS Informatics) isn't accessible at the moment (automated)
  • Résolu
    UTC
    Résolu

    Websites & Tools - SPINAL (FAS Informatics) is now operational! This update was created by an automated monitoring service.

  • Détecté
    UTC
    Détecté

    Websites & Tools - SPINAL (FAS Informatics) cannot be accessed at the moment. This incident was created by an automated monitoring service.

Slurm security patch causing node unavailability
  • Résolu
    UTC
    Résolu

    The scheduler and node states appear to be stable. Thank you for your patience and understanding.

    Please note that the intermittent deadlock issue is still not resolved, but we are actively monitoring that and intervening as necessary until we receive a solution.

  • Surveillé
    UTC
    Surveillé

    The patch has been deployed and the scheduler restarted. Paused jobs are resuming.

    Any jobs which did not start or were stuck may have been flushed. So please check any pending jobs you might have had.

    Related doc: https://docs.rc.fas.harvard.edu/kb/running-jobs/.

  • Identifié
    UTC
    Identifié

    We have tested the patch on our test cluster before releasing. We are now proceeding to deploy to the cluster. Thanks for your patience.

    UPDATE: jobs suspended, scheduler down for patching, nodes are updating.

  • Détecté
    UTC
    Détecté

    The Slurm emergency security patch introduced a bug which is causing many of our nodes to be set to 'not responding'. The vendor has already identified the issue and issued another patch.

    We are deploying this patch after testing. Jobs will be paused and the scheduler and cluster will be unavailable while deploying the patch. Watch here for updates.

avr. 2022

boslogin04 down
  • Résolu
    UTC
    Résolu

    boslogin04 is back up

  • Identifié
    UTC
    Identifié

    boslogin04 needs to be rebooted in order to address an underlying issue.

Compute nodes not running jobs properly
  • Résolu
    UTC
    Résolu

    Please contact us if you see any lingering node issues.

  • Identifié
    UTC
    Identifié

    From the MGHPCC datacenter outage on 4/12/22, there are some lingering filesystem mount issues for some labs on some nodes. We are actively working on draining and rebooting these nodes to bring them back into service.

A cooling incident at the MGHPCC Datacenter has effected a number of systems
  • Résolu
    UTC
    Résolu

    All cooling, including the water cooling for water-cooled compute nodes, is back online. All partitions are open for jobs. Some compute nodes in various partitions may still require individual attention, so not every compute node is back online, but we will work to bring them all online in the coming hours.

  • Surveillé
    UTC
    Surveillé

    Most storage in Holyoke is back up.

    The Slurm scheduler is back up and accepting jobs. However, most public partitions are down as the water cooling systems for those compute racks require in-person attention. RC staff are already en route to the datacenter to address this.

    The Academic Cluster is back up.

  • Détecté
    UTC
    Détecté

    A cooling failure caused temperatures in the MGHPCC datacenter to exceed the safe range of operation for many systems, causing them to power down to prevent permanent damage.

    The cooling issue has been resolved and we are beginning to power systems back on. Expect outage on various systems until the issue is resolved.

  • Surveillé
    UTC
    Surveillé

    A cooling failure caused temperatures in the MGHPCC datacenter to exceed the safe range of operation for many systems, causing them to power down to prevent permanent damage.

    The cooling issue has been resolved and we are beginning to power systems back on. Expect outage on various systems until the issue is resolved.

Websites & Tools - MiniLIMs (FAS Informatics) isn't accessible at the moment (automated)
  • Résolu
    UTC
    Résolu

    Websites & Tools - MiniLIMs (FAS Informatics) is now operational! This update was created by an automated monitoring service.

  • Détecté
    UTC
    Détecté

    Websites & Tools - MiniLIMs (FAS Informatics) cannot be accessed at the moment. This incident was created by an automated monitoring service.

Websites & Tools - SPINAL (FAS Informatics) isn't accessible at the moment (automated)
  • Résolu
    UTC
    Résolu

    Websites & Tools - SPINAL (FAS Informatics) is now operational! This update was created by an automated monitoring service.

  • Détecté
    UTC
    Détecté

    Websites & Tools - SPINAL (FAS Informatics) cannot be accessed at the moment. This incident was created by an automated monitoring service.

avr. 2022 à juin 2022

Suivant

For issues not shown here, please contact FASRC via
https://portal.rc.fas.harvard.edu or email rchelp@rc.fas.harvard.edu