FAS Research Computing - Notice history

Login Nodes - Holyoke experiencing major outage

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
https://docs.rc.fas.harvard.edu | https://portal.rc.fas.harvard.edu | Email: rchelp@rc.fas.harvard.edu

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.
Operational

SLURM Scheduler - Cannon - Operational

Cannon Compute Cluster (Holyoke) - Operational

Boston Compute Nodes - Operational

GPU nodes (Holyoke) - Operational

seas_compute - Operational

Operational

SLURM Scheduler - FASSE - Operational

FASSE Compute Cluster (Holyoke) - Operational

Operational

Kempner Cluster CPU - Operational

Kempner Cluster GPU - Operational

Major outage

Login Nodes - Boston - Operational

Login Nodes - Holyoke - Major outage

FASSE login nodes - Operational

Operational

Cannon Open OnDemand/VDI - Operational

FASSE Open OnDemand/VDI - Operational

Operational

Netscratch (Global Scratch) - Operational

Home Directory Storage - Boston - Operational

Tape - (Tier 3) - Operational

Holylabs - Operational

Isilon Storage Holyoke (Tier 1) - Operational

Holystore01 (Tier 0) - Operational

HolyLFS04 (Tier 0) - Operational

HolyLFS05 (Tier 0) - Operational

HolyLFS06 (Tier 0) - Operational

Holyoke Tier 2 NFS (new) - Operational

Holyoke Specialty Storage - Operational

holECS - Operational

Isilon Storage Boston (Tier 1) - Operational

BosLFS02 (Tier 0) - Operational

Boston Tier 2 NFS (new) - Operational

CEPH Storage Boston (Tier 2) - Operational

Boston Specialty Storage - Operational

bosECS - Operational

Samba Cluster - Operational

Globus Data Transfer - Operational

Notice history

Jan 2024

fasselogin nodes down
  • Resolved
    Resolved

    fasselogin machines are back in service

  • Identified
    Identified

    We have identified the underlying issue and are working on fixing the FASSE login nodes. In the meantime, please use FASSE VDI. Updates to come.

  • Investigating
    Investigating

    fasselogin01/02 are currently down. We are investigating this incident.

Ceph instability - Affects Boston VMs (Virtual Machines) and Tier2 Ceph shares
  • Resolved
    Resolved

    The Ceph instability has been resolved. Ceph Tier2 shares, VDI, and VMs should be back to their normal state.

    If your VM, /net/fs-[labname] share, or VDI session is still impacted, please contact rchelp@rc.fas.harvard.edu

  • Identified
    Identified

    The infrastructure behind Tier2 Ceph shares and VMs is unstable.
    This also affects VDI/OOD which relies on virtual machines.

    /net/fs-[labname] shares, new OOD/VDI sessions, and VMs are affected and may will be inaccessible until this is resolved.

    Thanks for your patience.

Ceph instability - Affects Boston VMs (Virtual Machines) and Tier2 Ceph shares
  • Resolved
    Resolved

    The Ceph instability has been resolved. Ceph Tier2 shares, VDI, and VMs should be back to their normal state.

    If your VM, /net/fs-[labname] share, or VDI session is still impacted, please contact rchelp@rc.fas.harvard.edu

  • Identified
    Identified

    The infrastructure behind Tier2 Ceph shares and VMs is unstable.
    This also affects VDI/OOD which relies on virtual machines.

    /net/fs-[labname] shares, new OOD/VDI sessions, and VMs are affected and may will be inaccessible until this is resolved.

    Thanks for your patience.

Coldfront timeout
  • Resolved
    Resolved

    Coldfront is accessible again. Thanks for your patience so that would could investigate further. We've added new logging to have a better view into this should it happen again.

  • Investigating
    Investigating

    Coldfront is currently up but inaccessible. Login attempts will result in a timeout/proxy error.
    We would like time to gather forensics to sort out why this is happening before restarting the service.

    If you need to access Coldfront, please try again later today.

Ceph instability - Affects Boston VMs (Virtual Machines) and Tier2 Ceph shares
  • Resolved
    Resolved

    The Ceph instability has been resolved. Ceph Tier2 shares, VDI, and VMs should be back to their normal state.

    If your VM, /net/fs-[labname] share, or VDI session is still impacted, please contact rchelp@rc.fas.harvard.edu

  • Identified
    Identified

    The infrastructure behind Tier2 Ceph shares and VMs is unstable.
    This also affects VDI/OOD which relies on virtual machines.

    /net/fs-[labname] shares, new OOD/VDI sessions, and VMs are affected and may will be inaccessible until this is resolved.

    Thanks for your patience.

Dec 2023

Ceph instability - Affects Boston VMs (Virtual Machines) and Tier2 Ceph shares
  • Resolved
    Resolved

    The Ceph instability has been resolved. Ceph Tier2 shares, VDI, and VMs should be back to their normal state.

    If your VM, /net/fs-[labname] share, or VDI session is still impacted, please contact rchelp@rc.fas.harvard.edu

  • Identified
    Identified

    The infrastructure behind Tier2 Ceph shares and VMs is unstable.
    This also affects VDI/OOD which relies on virtual machines.

    /net/fs-[labname] shares, new OOD/VDI sessions, and VMs are affected and may will be inaccessible until this is resolved.

    Thanks for your patience.

Ceph instability - Affects Boston VMs (Virtual Machines) and Tier2 Ceph shares
  • Resolved
    Resolved

    The Ceph instability has been resolved. Ceph Tier2 shares, VDI, and VMs should be back to their normal state.

    If your VM, /net/fs-[labname] share, or VDI session is still impacted, please contact rchelp@rc.fas.harvard.edu

  • Identified
    Identified

    The infrastructure behind Tier2 Ceph shares and VMs is unstable.
    This also affects VDI/OOD which relies on virtual machines.

    /net/fs-[labname] shares, new OOD/VDI sessions, and VMs are affected and may will be inaccessible until this is resolved.

    Thanks for your patience.

Loss of power at Holyoke data center
  • Resolved
    Resolved

    Downed nodes are back online. The cluster is now available again.

    Thank you for your patience.

  • Identified
    Identified

    Power was restored to the affected sections and we are bringing the down nodes back up.

  • Investigating
    Investigating

    There has been a loss of street power at MGHPCC, our Holyoke data center due to the windstorm. We are awaiting further details.

    This likely affects most of the Cannon/Kempner compute cluster, and all of the FASSE compute cluster.

    More details as we learn them.

Ceph instability - Affects Boston VMs (Virtual Machines) and Tier2 Ceph shares
  • Resolved
    Resolved

    The Ceph instability has been resolved. Ceph Tier2 shares, VDI, and VMs should be back to their normal state.

    If your VM, /net/fs-[labname] share, or VDI session is still impacted, please contact rchelp@rc.fas.harvard.edu

  • Identified
    Identified

    The infrastructure behind Tier2 Ceph shares and VMs is unstable.
    This also affects VDI/OOD which relies on virtual machines.

    /net/fs-[labname] shares, new OOD/VDI sessions, and VMs are affected and may will be inaccessible until this is resolved.

    Thanks for your patience.

Emergency scheduler update - Security Patch
  • Completed
    December 14, 2023 at 5:00 PM
    Completed
    December 14, 2023 at 5:00 PM

    Maintenance has completed successfully

  • In progress
    December 14, 2023 at 4:00 PM
    In progress
    December 14, 2023 at 4:00 PM

    Maintenance is now in progress

  • Planned
    December 14, 2023 at 4:00 PM
    Planned
    December 14, 2023 at 4:00 PM

    SchedMD has issued a patch for a critical security vulnerability. It is imperative that we apply this patch ASAP. This will require a pause of the cluster for roughly 30-60 minutes at around 11am, after which jobs and the scheduler will continue normal operation.

    A side effect of this is that we will move up to version 23.02.7 with the patch which will fix the IntelMPI and PMI2 issues some users have experienced.

    Thanks for your understanding and patience.
    FAS Research Computing

Nov 2023

Ceph instability - Affects Boston VMs (Virtual Machines) and Tier2 Ceph shares
  • Resolved
    Resolved

    The Ceph instability has been resolved. Ceph Tier2 shares, VDI, and VMs should be back to their normal state.

    If your VM, /net/fs-[labname] share, or VDI session is still impacted, please contact rchelp@rc.fas.harvard.edu

  • Identified
    Identified

    The infrastructure behind Tier2 Ceph shares and VMs is unstable.
    This also affects VDI/OOD which relies on virtual machines.

    /net/fs-[labname] shares, new OOD/VDI sessions, and VMs are affected and may will be inaccessible until this is resolved.

    Thanks for your patience.

Ceph instability - Affects Boston VMs (Virtual Machines) and Tier2 Ceph shares
  • Resolved
    Resolved

    The Ceph instability has been resolved. Caeph Tier2 shares, VDI, and VMs should be back to their normal state.

    If your VM, /net/fs-[labname] share, or VDI session is still impacted, please contact rchelp@rc.fas.harvard.edu

  • Identified
    Identified

    The infrastructure behind Tier2 Ceph shares and VMs is unstable.
    This also affects VDI/OOD which relies on virtual machines.

    /net/fs-[labname] shares, new OOD/VDI sessions, and VMs are affected and may will be inaccessible until this is resolved.

    Thanks for your patience.

Partial Cannon outage
  • Resolved
    Resolved

    Cooling and power have been restored to the affected racks. The compute nodes have been resumed in Slurm and are now accepting jobs again.

    This incident has been resolved.

  • Identified
    Identified

    We have identified the partitions that are impacted due to loss of cooling in holy7c[02-12] compute nodes. Some of these partitions are fully down, others are partially down.

    blackhole
    blackholepriority davies desai hucecascade
    hucecascadepriority
    huttenhower
    janson
    jansoncascade joonholee lukin seascompute
    shared
    tambe
    test
    vishwanath
    whipple

    Please submit to other partitions in order to run jobs.

    The spart command will show you all partitions you have access to, and our Running Jobs page provides a list of publicly available partitions for all cluster users. Please see our docs page for other helpful Slurm commands.

    The Holyoke MGHPCC data center is working to restore cooling, and FASRC staff are onsite to assist. No ETA.

  • Investigating
    Investigating

    Compute nodes in holy7c[02-12] have experienced a power loss and are currently down. GPUs are not impacted at this time.

    The 'shared' partition is significantly impacted. Other public partitions and lab-owned partitions may be down or running at reduced capacity. Jobs are still being accepted/running, but may need to wait longer in the queue due to fewer resources being available.

    We are in contact with the Holyoke MGHPCC data center to investigate further. Updates to come. No ETA at this time.

Ceph instability - Affects Boston VMs (Virtual Machines) and Tier2 Ceph shares
  • Resolved
    Resolved

    The Ceph instability has been resolved. Caeph Tier2 shares, VDI, and VMs should be back to their normal state.

    If your VM, /net/fs-[labname] share, or VDI session is still impacted, please contact rchelp@rc.fas.harvard.edu

  • Identified
    Identified

    The infrastructure behind Tier2 Ceph shares and VMs is unstable.
    This also affects VDI/OOD which relies on virtual machines.

    /net/fs-[labname] shares, new OOD/VDI sessions, and VMs are affected and may will be inaccessible until this is resolved.

    Thanks for your patience.

Ceph instability - Affects Boston VMs (Virtual Machines) and Tier2 Ceph shares
  • Resolved
    Resolved

    The Ceph instability has been resolved. Caeph Tier2 shares, VDI, and VMs should be back to their normal state.

    If your VM, /net/fs-[labname] share, or VDI session is still impacted, please contact rchelp@rc.fas.harvard.edu

  • Identified
    Identified

    The infrastructure behind Tier2 Ceph shares and VMs is unstable.
    This also affects VDI/OOD which relies on virtual machines.

    /net/fs-[labname] shares, new OOD/VDI sessions, and VMs are affected and may will be inaccessible until this is resolved.

    Thanks for your patience.

Nov 2023 to Jan 2024

Next

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