LuxProvide Outage History

LuxProvide is up right now

LuxProvide had 4 outages in the last 2 years totaling 447h 47m of downtime, averaging 0.2 incidents per month.

There were 4 LuxProvide outages since September 7, 2026 totaling 447h 47m of downtime. Each is summarised below. Incident details, duration, and resolution information.

Source: status.lxp.lu

Minor October 2, 2026

Lustre tier1 error

Detected by Pingoru
Oct 02, 2026, 10:50 PM UTC
Resolved
Oct 03, 2026, 12:11 PM UTC
Duration
13h 20m
Affected: Tier 1 - Scratch
Timeline · 3 updates
  1. investigating Oct 02, 2026, 10:50 PM UTC

    Status: Investigating Dear MeluXina users, Some users may experience a 'No space left on device' error on the lustre tier1 (scratch) filesystem. The issue is due to a single Lustre OST being out of space, and should only occur when trying to grow an existing file residing on the affected OST. The issue is being investigated for a solution by migrating files to a different OST. For any questions, please contact our Service Desk. Thank you for your understanding The LuxProvide team Affected components Tier 1 - Scratch (Degraded performance)

  2. identified Oct 03, 2026, 01:36 AM UTC

    Status: Identified The issue has been identified and is related to Lustre file striping. A file migration is in progress, which will move a few TIB of data around, which will take a bit of time. Affected components Tier 1 - Scratch (Degraded performance)

  3. resolved Oct 03, 2026, 12:11 PM UTC

    Status: Resolved Dear MeluXina user, The Lustre issue which affected a single OST on the tier1 (scratch) filesystem has been resolved. The impact of this was limited to cases where a file stored on the affected OST was growing. New file creation or reading data was not impacted. For any questions, please contact our Service Desk. Thank you for your understanding The LuxProvide team Affected components Tier 1 - Scratch (Operational)

Read the full incident report →

Minor September 30, 2026

Network Connectivity Issue

Detected by Pingoru
Sep 30, 2026, 12:59 PM UTC
Resolved
Oct 15, 2026, 09:37 AM UTC
Duration
14d 20h
Affected: ISPsLogin NodesEFP Login NodesWorkload Manager
Timeline · 4 updates
  1. investigating Sep 30, 2026, 12:59 PM UTC

    Status: Investigating Dear MeluXina users, We are currently facing some internet connectivity issue. The issue is being investigated. Thank you for your understanding The LuxProvide team Affected components ISPs (Partial outage)

  2. investigating Sep 30, 2026, 03:16 PM UTC

    Status: Investigating A firewall module failure triggered 3 incidents in a row. • Public Connectivity issue (14:47-14:59) • Internal communication to the Workload manager (slurm) failure (16h06-16h20) • Internal communication to the Workload manager (slurm) failure (16h32-16h46) All services are now operational again. Issue is still being investigated with the vendor support. For any questions, please contact our Service Desk. Thank you for your understanding, The LuxProvide team Affected components Statistics (insights.lxp.lu) (Operational) MeluXina Slurm REST API (slurm-api.lxp.lu) (Operational) ISPs (Operational) Workload Manager (Operational) MeluXina S3 Data Transfer (s3.lxp.lu) (Operational) Service Desk (servicedesk.lxp.lu) (Operational) MeluXina SPE Open OnDemand (portal.lxp.lu) (Operational) EFP Login Nodes (Operational) MeluXina Open OnDemand (portal.lxp.lu) (Operational) Documentation (docs.lxp.lu) (Operational) Login Nodes (Operational)

  3. monitoring Sep 30, 2026, 05:08 PM UTC

    Status: Monitoring Issue is being monitored and awaiting feedback from vendor. Affected components MeluXina Slurm REST API (slurm-api.lxp.lu) (Operational) Documentation (docs.lxp.lu) (Operational) ISPs (Operational) Login Nodes (Operational) Workload Manager (Operational) MeluXina SPE Open OnDemand (portal.lxp.lu) (Operational) MeluXina Open OnDemand (portal.lxp.lu) (Operational) MeluXina S3 Data Transfer (s3.lxp.lu) (Operational) Service Desk (servicedesk.lxp.lu) (Operational) EFP Login Nodes (Operational) Statistics (insights.lxp.lu) (Operational)

  4. resolved Oct 15, 2026, 09:37 AM UTC

    Status: Resolved A maintenance has been planed on October 26th to resolve the issue. Affected components MeluXina Slurm REST API (slurm-api.lxp.lu) (Operational) MeluXina Open OnDemand (portal.lxp.lu) (Operational) Documentation (docs.lxp.lu) (Operational) ISPs (Operational) Login Nodes (Operational) MeluXina S3 Data Transfer (s3.lxp.lu) (Operational) MeluXina SPE Open OnDemand (portal.lxp.lu) (Operational) EFP Login Nodes (Operational) Statistics (insights.lxp.lu) (Operational) Workload Manager (Operational) Service Desk (servicedesk.lxp.lu) (Operational)

Read the full incident report →

Minor September 14, 2026

Login nodes unreachable

Detected by Pingoru
Sep 14, 2026, 12:00 PM UTC
Resolved
Sep 14, 2026, 12:00 PM UTC
Duration
–
Timeline · 1 update
  1. resolved Sep 14, 2026, 12:00 PM UTC

    Status: Resolved Dear MeluXina users, Earlier today, the standard (non-EFP) login nodes experienced a service disruption between 14:00 and 14:30 CEST (14 September). An SSH connectivity issue prevented new sessions from being established. Already-established sessions were not affected, and there was no impact on currently running MeluXina jobs. The root cause is still under investigation. For any questions, please contact our Service Desk. Thank you for your understanding. The LuxProvide team

Read the full incident report →

Minor September 7, 2026

MeluXina Rack power loss

Detected by Pingoru
Sep 07, 2026, 10:44 AM UTC
Resolved
Sep 10, 2026, 04:33 PM UTC
Duration
3d 5h
Affected: CPU Compute Partition Service
Timeline · 4 updates
  1. investigating Sep 07, 2026, 10:44 AM UTC

    Status: Investigating Dear MeluXina users, During some maintenance work in the datacenter, Rack01 (CPU nodes) lost power. This power loss induced reboot of 96 CPU compute nodes. The issue is currently being investigated. For any questions, please contact our Service Desk. Thank you for your understanding The LuxProvide team Affected components CPU Compute Partition Service (Partial outage)

  2. investigating Sep 07, 2026, 04:38 PM UTC

    Status: Investigating CPU rack01 is partially operational. 24 CPU nodes remains unavailable, management hardware will be replaced in the coming days. Affected components CPU Compute Partition Service (Partial outage)

  3. investigating Sep 10, 2026, 07:16 AM UTC

    Status: Investigating Management switch failing will be replaced today (Thursday, September 10 2026). Rack01 was reserved for the duration of the maintenance to avoid impacts on user jobs. Affected components CPU Compute Partition Service (Partial outage)

  4. resolved Sep 10, 2026, 04:33 PM UTC

    Status: Resolved Management switch has been replaced. CPU Rack01 fully is now operational again. Affected components CPU Compute Partition Service (Operational)

Read the full incident report →