FAS Research Computing - All Cluster nodes down or draining – Details zu Vorfällen

Alle Systeme betriebsbereit

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.

All Cluster nodes down or draining

Gelöst
Betriebsbereit
Aufgetreten am vor mehr als 2 JahrenDauerte 1 Stunde 37 Minuten

Betroffen

Cannon Cluster

Betriebsbereit aus 7:18 PM zu 8:56 PM

SLURM Scheduler - Cannon

Betriebsbereit aus 7:18 PM zu 8:56 PM

Cannon Compute Cluster (Holyoke)

Betriebsbereit aus 7:18 PM zu 8:56 PM

Boston Compute Nodes

Betriebsbereit aus 7:18 PM zu 8:56 PM

GPU nodes (Holyoke)

Betriebsbereit aus 7:18 PM zu 8:56 PM

FASSE Cluster

Betriebsbereit aus 7:18 PM zu 8:56 PM

Aktualisierung
  • Gelöst
    UTC
    Gelöst

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

  • Identifizierung
    UTC
    Identifizierung

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

  • Überwachung
    UTC
    Überwachung

    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.

  • Update
    UTC
    Update

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

  • Identifizierung
    UTC
    Identifizierung

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

  • Analyse
    UTC
    Analyse

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