Motherboard
B450 Steel Legend ASRock (P4.20 08/03/2021)
CPU
4 × AMD Athlon 300GE with Radeon Vega Graphics AES
Disk Model
Samsung Flash Drive 64.2GB
System type
linux
Kernel
5.10.0-hiveos #83
Drivers A 20.40 (5.11.1001)
N 470.86
8GB ram
OS version 0.6-213@220222
I am facing the following problem. After running gminer for some time 2-3 days sometimes 1day
I got those kernel erros in log.
Mar 2 23:19:57 RR2-6 kernel: [399545.561379][T18073] [drm:amdgpu_cs_ioctl [amdgpu]] ERROR amdgpu_vm_validate_pt_bos() failed.
Mar 2 23:19:57 RR2-6 kernel: [399545.561502][T18266] [drm:amdgpu_gem_va_ioctl [amdgpu]] ERROR Couldn’t update BO_VA (1)
Mar 2 23:19:57 RR2-6 kernel: [399545.561568][T18192] [drm:amdgpu_cs_ioctl [amdgpu]] ERROR amdgpu_vm_validate_pt_bos() failed.
Mar 2 23:19:57 RR2-6 kernel: [399545.561628][T18192] [drm:amdgpu_cs_ioctl [amdgpu]] ERROR Failed to process the buffer list 1!
Mar 2 23:19:57 RR2-6 kernel: [399545.561781][T18073] [drm:amdgpu_cs_ioctl [amdgpu]] ERROR Failed to process the buffer list 1!
Mar 2 23:19:57 RR2-6 kernel: [399545.561936][T18192] Huh VM_FAULT_OOM leaked out to the #PF handler. Retrying PF
Mar 2 23:19:57 RR2-6 kernel: [399545.562120][T18266] [drm:amdgpu_gem_va_ioctl [amdgpu]] ERROR Couldn’t update BO_VA (1)
Mar 2 23:19:57 RR2-6 kernel: [399545.562140][T18073] Huh VM_FAULT_OOM leaked out to the #PF handler. Retrying PF
Mar 2 23:19:57 RR2-6 kernel: [399545.562387][T18192] Huh VM_FAULT_OOM leaked out to the #PF handler. Retrying PF
Mar 2 23:19:57 RR2-6 kernel: [399545.562743][T19036] [drm:amdgpu_cs_ioctl [amdgpu]] ERROR amdgpu_vm_validate_pt_bos() failed.
Mar 2 23:19:57 RR2-6 kernel: [399545.562925][T19036] [drm:amdgpu_cs_ioctl [amdgpu]] ERROR Failed to process the buffer list 1!
I got those error on 3 rigs, all with the same cards rx 6600 , powercolor hellhound - non xt , 20 pcs in total
After those errors happen, 1-2 cards from a rig does not work anymore, they consume 17w, gminers shows 29.3mh/s which is not real.
Where should i search the problem?
