AEI (Hannover) issue tracker

2026-09-22

13:12 Atlas Support #3812 (Assigned): move ancient atlas3 and atlas9 to Rack A

In order to hopefully have one or two machines which can scrub disks continuously with easy access to it, please move... Carsten Aulbert

2026-09-18

07:13 Atlas ToDo #3811 (New): Removal of ancient /home

The following users have responded so far:
|_.user|_.server|_.comments|
| Danie Pook-Kolb | work15a:/data/daniel.... Carsten Aulbert

2026-09-17

09:52 Warranty / Broken parts Vendor/megware #3809: g9832: RAM module G0 broken

replaced with DIMM SN 3DB854FC from spare pool Carsten Aulbert

05:27 Warranty / Broken parts Vendor/megware #3809 (Assigned): g9832: RAM module G0 broken

ID Record Type Time GenID(Low) GenID(High) EvMRev Sensor Type Sensor Number EvtDir Type Event Data1 Event Data2 Event... Carsten Aulbert

07:22 Warranty / Broken parts Vendor/misc (out of warranty) #3810 (Resolved): bee57e: Broken disk in store2

wwn-0x5000c500a48dbe8e FAULTED 93 154 0 too many errors
Carsten Aulbert

05:27 Warranty / Broken parts Vendor/megware #3808 (Assigned): g6839 PSU swapped

Carsten Aulbert

2026-08-26

05:45 Warranty / Broken parts Vendor/megware #3793 (Part exchange underway): g9927: GPU#0 broken

Aug 21 15:18:21 g9927 kernel: NVRM: GPU0 _kgspIsHeartbeatTimedOut: Heartbeat timed out, currentTimeMs 619085918 heart... Carsten Aulbert

2026-08-17

11:50 Warranty / Broken parts Vendor/megware #3791 (Part exchange underway): g5439: GPU#2 broken

nvidia-smi --gpu-reset -i 2
The following GPUs could not be reset:
GPU 00000000:0C:00.0: Not Supported
+------... Carsten Aulbert

11:44 Warranty / Broken parts Vendor/misc (out of warranty) #3790 (Assigned): work59b: on board NICs seem to be broken

After the relocation to rack 57 I cannot get any link for any of the two onboard NICs. Thus please take out the addit... Carsten Aulbert

2026-08-15

15:55 Warranty / Broken parts Vendor/megware #3788: g6739: Broken Memory module

This one is for DIMM_P1_J0 Carsten Aulbert