rdc@fri - Zgodovina obvestil

Vsi sistemi delujejo brez napak

Docs - Deluje

100% - razpoložljivost
feb. 2025 · 100.0%mar. · 100.0%apr. · 100.0%

Previous page

Next page

feb. 2025
mar. 2025
apr. 2025
98% - razpoložljivost

Login - Deluje

100% - razpoložljivost
feb. 2025 · 100.0%mar. · 99.98%apr. · 100.0%

Previous page

Next page

feb. 2025
mar. 2025
apr. 2025

Storage - Deluje

100% - razpoložljivost
feb. 2025 · 100.0%mar. · 100.0%apr. · 100.0%

Previous page

Next page

feb. 2025
mar. 2025
apr. 2025

Compute - Deluje

95% - razpoložljivost
feb. 2025 · 98.90%mar. · 91.60%apr. · 95.07%

Previous page

Next page

feb. 2025
mar. 2025
apr. 2025

Zgodovina obvestil

Ogled trenutnega stanja

apr. 2025

APR30
Regular maintenance
ZaključenoVzdrževanje144 ur
  • Posodobitev
    maj 06, 2025 ob 20:59:12UTC
    Posodobitev
    maj 06, 2025 ob 20:59:12UTC

    Maintenance has completed successfully. We performed the full set of updates & upgrades on all cluster nodes. The storage cluster has also undergone the full set of updates & upgrades.

    Most of the cluster is operational and ready to accept jobs. One node is currently kept in maintenance mode due to HW issues that require physical maintenance, it should resume operation in the next few days.

  • Zaključeno
    maj 06, 2025 ob 20:00:00UTC
    Zaključeno
    maj 06, 2025 ob 20:00:00UTC
    Vzdrževanje je uspešno zaključeno
  • V teku
    april 30, 2025 ob 20:00:01UTC
    V teku
    april 30, 2025 ob 20:00:01UTC
    Vzdrževanje je v teku
  • Načrtovano
    april 30, 2025 ob 20:00:00UTC
    Načrtovano
    april 30, 2025 ob 20:00:00UTC
    We are planning for a scheduled maintenance during that time.
Login is down
OdpravljenoVečji izpad delovanja
  • Odpravljeno
    UTC
    Odpravljeno
  • Raziskovanje
    UTC
    Raziskovanje
Cluster outage
OdpravljenoVečji izpad delovanja172 ur 39 minut
  • Odpravljeno
    UTC
    Odpravljeno
    This incident has been resolved.
  • Raziskovanje
    UTC
    Raziskovanje

    Cluster cannot be accessed at the moment. This incident was created by an automated monitoring service.

RDC cooling malfunction
OdpravljenoVečji izpad delovanja306 ur 20 minut
  • Odpravljeno
    UTC
    Odpravljeno

    The RDC cooling was partially fixed, we're bringing the cluster back to production. We'll be monitoring the status. During the week the remaining RDC cooling issues will be resolved.

    We appreciate your patience

  • Napaka odkrita
    UTC
    Napaka odkrita

    The RDC cooling is experiencing malfunction. As a preventative measure we're forced to shutdown the cluster; all jobs will be canceled.

    We appreciate your patience.

  • Spremljanje
    UTC
    Spremljanje

    The RDC cooling was fixed, we're currently bringing the cluster back to life, performing the scheduled FRIDA maintenance, and monitoring the status.

  • Napaka odkrita
    UTC
    Napaka odkrita

    The RDC cooling is experiencing malfunction. As a preventative measure we're forced to shutdown the cluster; all jobs will be canceled. While working to fix the issue we'll also perform the scheduled FRIDA maintenance to keep the downtime at minimum.

    We appreciate your patience.

mar. 2025

Jobs reporting BadConstraints
OdpravljenoVečji izpad delovanja2 uri 57 minut
  • Odpravljeno
    UTC
    Odpravljeno
    This incident has been resolved.
  • Raziskovanje
    UTC
    Raziskovanje
    We are currently investigating this incident.
Login is down
OdpravljenoVečji izpad delovanja4 minute
  • Odpravljeno
    UTC
    Odpravljeno
  • Raziskovanje
    UTC
    Raziskovanje
Login is down
OdpravljenoVečji izpad delovanja4 minute
  • Odpravljeno
    UTC
    Odpravljeno
  • Raziskovanje
    UTC
    Raziskovanje
Cluster nodes are reporting invalid state
OdpravljenoDelni izpad delovanja1 ura 53 minut
  • Odpravljeno
    UTC
    Odpravljeno
    This incident has been resolved.
  • Raziskovanje
    UTC
    Raziskovanje

    We are currently investigating the incident.

feb. 2025

FEB28
Storage upgrade
ZaključenoVzdrževanje344 ur 57 minut
  • Zaključeno
    marec 14, 2025 ob 22:57:00UTC
    Zaključeno
    marec 14, 2025 ob 22:57:00UTC

    Maintenance on FRIDA has completed successfully.

    The key aspects of the cluster that have been updated are a new shared storage system based on the Weka Data Platform, and upgrade of Teleport to version v17. Install the latest v17.X version of the Teleport client (https://goteleport.com/download) before connecting.

    In the upcoming weeks we will progressively increase storage space (mostly lab/group/project space) even further. For higher performance we advise you to move your lab/group/project related data to the corresponding shared folder.

    We appreciate your patience.

  • Posodobitev
    marec 09, 2025 ob 22:04:52UTC
    Posodobitev
    marec 09, 2025 ob 22:04:52UTC

    Due to the complexity of the storage deploy procedure associated with the heterogeneous nature of our environment we are extending the maintenance window.

    We appreciate your patience.

  • V teku
    februar 28, 2025 ob 14:00:01UTC
    V teku
    februar 28, 2025 ob 14:00:01UTC
    Vzdrževanje je v teku
  • Načrtovano
    februar 28, 2025 ob 14:00:00UTC
    Načrtovano
    februar 28, 2025 ob 14:00:00UTC

    We are planning a major maintenance on FRIDA. During this time the cluster will be unavailable. A maintenance reservation is already in place. The cluster will continue processing jobs that are scheduled to finish before the maintenance start time, other jobs will wait in queue. As this is a major maintenance waiting jobs may be cancelled. You can list the active reservations by issuing the following command

    scontrol show reservations

FEB12
Storage upgrade
ZaključenoVzdrževanje8 ur 44 minut
  • Zaključeno
    februar 12, 2025 ob 22:44:06UTC
    Zaključeno
    februar 12, 2025 ob 22:44:06UTC

    The scheduled maintenance has been postponed due to a delay in the delivery of essential network infrastructure. We will provide an updated schedule once the required components are received and ready for installation.

  • V teku
    februar 12, 2025 ob 14:00:01UTC
    V teku
    februar 12, 2025 ob 14:00:01UTC
    Vzdrževanje je v teku
  • Načrtovano
    februar 12, 2025 ob 14:00:00UTC
    Načrtovano
    februar 12, 2025 ob 14:00:00UTC

    We are planning a major maintenance on FRIDA. During this time the cluster will be unavailable. A maintenance reservation is already in place. The cluster will continue processing jobs that are scheduled to finish before the maintenance start time, other jobs will wait in queue. As this is a major maintenance waiting jobs may be cancelled. You can list the active reservations by issuing the following command

    scontrol show reservations

Prejšnja

feb. 2025 do apr. 2025

Naprej