FAS Research Computing - Observați istoricul

Toate sistemele operaționale

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.
Operațional

SLURM Scheduler - Cannon - Operațional

Cannon Compute Cluster (Holyoke) - Operațional

Boston Compute Nodes - Operațional

GPU nodes (Holyoke) - Operațional

seas_compute - Operațional

Operațional

SLURM Scheduler - FASSE - Operațional

FASSE Compute Cluster (Holyoke) - Operațional

Operațional

Kempner Cluster CPU - Operațional

Kempner Cluster GPU - Operațional

Operațional

FASSE login nodes - Operațional

Operațional

Cannon Open OnDemand - Operațional

FASSE Open OnDemand - Operațional

Operațional

Netscratch (Global Scratch) - Operațional

Home Directory Storage - Boston - Operațional

Tape - (Tier 3) - Operațional

Holylabs - Operațional

Isilon Storage Holyoke (Tier 1) - Operațional

Holystore01 (Tier 0) - Operațional

HolyLFS04 (Tier 0) - Operațional

HolyLFS05 (Tier 0) - Operațional

HolyLFS06 (Tier 0) - Operațional

Holyoke Tier 2 NFS (new) - Operațional

Holyoke Specialty Storage - Operațional

holECS - Operațional

Isilon Storage Boston (Tier 1) - Operațional

BosLFS02 (Tier 0) - Operațional

Boston Tier 2 NFS (new) - Operațional

CEPH Storage Boston (Tier 2) - Operațional

Boston Specialty Storage - Operațional

bosECS - Operațional

Samba Cluster - Operațional

Globus Data Transfer - Operațional

Observați istoricul

feb 2024

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

    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

  • Identificat
    UTC
    Identificat

    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.

holyscratch01 performance
  • Rezolvat
    UTC
    Rezolvat

    This incident has been resolved.

  • În curs de investigare
    UTC
    În curs de investigare

    holyscratch01 is experiencing high load. Performance may be delayed.

    OOD is also affected as a result of this.

    We are currently investigating this incident.

All Cluster nodes down or draining
  • Rezolvat
    UTC
    Rezolvat

    Clusters are back in production status. We will continue to monitor for any aberrant behavior, but this incident has been resolved.

  • Identificat
    UTC
    Identificat

    I spoke too soon, partial recovery, I'll update here when we are sure everything is back in production, apologies.

  • În curs de monitorizare
    UTC
    În curs de monitorizare

    All cannon nodes are back in service and slurm is resuming jobs, fasse is coming back up as well, we will monitor the situation, but anticipate a return to full normal operations shortly.

  • Actualizare
    UTC
    Actualizare

    The nodes are coming back into normal service, we anticipate this to be fairly quick

  • Identificat
    UTC
    Identificat

    slurm is operational, jobs are idled and should resume as normal

  • În curs de investigare
    UTC
    În curs de investigare

    We are currently investigating this incident. We will update here as we can

BOSLFS02 Instability
  • Rezolvat
    UTC
    Rezolvat
    This incident has been resolved.
  • În curs de investigare
    UTC
    În curs de investigare

    Boslfs02 (/n/boslfs02) is currently experiencing instability.

    We are working on the issue and will update this incident as the situation progresses.

boslffs instability
  • Rezolvat
    UTC
    Rezolvat
    This incident has been resolved.
  • Identificat
    UTC
    Identificat

    We are working on a fix for this incident.

ian 2024

fasselogin nodes down
  • Rezolvat
    UTC
    Rezolvat

    fasselogin machines are back in service

  • Identificat
    UTC
    Identificat

    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.

  • În curs de investigare
    UTC
    În curs de investigare

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

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

    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

  • Identificat
    UTC
    Identificat

    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
  • Rezolvat
    UTC
    Rezolvat

    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

  • Identificat
    UTC
    Identificat

    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
  • Rezolvat
    UTC
    Rezolvat

    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.

  • În curs de investigare
    UTC
    În curs de investigare

    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
  • Rezolvat
    UTC
    Rezolvat

    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

  • Identificat
    UTC
    Identificat

    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
  • Rezolvat
    UTC
    Rezolvat

    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

  • Identificat
    UTC
    Identificat

    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
  • Rezolvat
    UTC
    Rezolvat

    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

  • Identificat
    UTC
    Identificat

    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
  • Rezolvat
    UTC
    Rezolvat

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

    Thank you for your patience.

  • Identificat
    UTC
    Identificat

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

  • În curs de investigare
    UTC
    În curs de investigare

    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
  • Rezolvat
    UTC
    Rezolvat

    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

  • Identificat
    UTC
    Identificat

    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
  • Finalizat
    decembrie 14, 2023 la 17:00UTC
    Finalizat
    decembrie 14, 2023 la 17:00UTC

    Maintenance has completed successfully

  • În curs
    decembrie 14, 2023 la 16:00UTC
    În curs
    decembrie 14, 2023 la 16:00UTC

    Maintenance is now in progress

  • Plănuit
    decembrie 14, 2023 la 16:00UTC
    Plănuit
    decembrie 14, 2023 la 16:00UTC

    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

dec 2023 către feb 2024

Următorul

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